{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "metadata": {},
   "outputs": [],
   "source": [
    "## =======================================================\n",
    "## IMPORTING\n",
    "## =======================================================\n",
    "import os\n",
    "def get_data_from_files(path):\n",
    "    directory = os.listdir(path)\n",
    "    results = []\n",
    "    for file in directory:\n",
    "        f=open(path+file)\n",
    "        results.append(f.read())\n",
    "        f.close()\n",
    "    return results\n",
    "\n",
    "## =======================================================\n",
    "## TOKENIZING\n",
    "## =======================================================\n",
    "from nltk.tokenize import word_tokenize, sent_tokenize\n",
    "def get_tokens(sentence):\n",
    "    tokens = word_tokenize(sentence)\n",
    "    clean_tokens = [word.lower() for word in tokens if word.isalpha()]\n",
    "    return clean_tokens\n",
    "\n",
    "def get_sentence_tokens(review):\n",
    "    return sent_tokenize(review)\n",
    "\n",
    "## =======================================================\n",
    "## REMOVING STOPWORDS\n",
    "## =======================================================\n",
    "from nltk.corpus import stopwords\n",
    "stop_words = set(stopwords.words(\"english\"))\n",
    "def remove_stopwords(sentence):\n",
    "    filtered_text = []\n",
    "    for word in sentence:\n",
    "        if word not in stop_words:\n",
    "            filtered_text.append(word)\n",
    "    return filtered_text\n",
    "\n",
    "## =======================================================\n",
    "## FREQUENCY DISTRIBUTIONS\n",
    "## =======================================================\n",
    "from nltk.probability import FreqDist\n",
    "def get_most_common(tokens):\n",
    "    fdist = FreqDist(tokens)\n",
    "    return fdist.most_common(12)\n",
    "\n",
    "def get_most_common(tokens):\n",
    "    fdist = FreqDist(tokens)\n",
    "    return fdist.most_common(12)\n",
    "\n",
    "def get_fdist(tokens):\n",
    "    return (FreqDist(tokens))\n",
    "\n",
    "## =======================================================\n",
    "## SENTIMENT ANALYSIS\n",
    "## =======================================================\n",
    "from nltk.sentiment import SentimentAnalyzer\n",
    "from nltk.sentiment.util import *\n",
    "from nltk.sentiment.vader import SentimentIntensityAnalyzer\n",
    "sid = SentimentIntensityAnalyzer()\n",
    "\n",
    "def get_vader_score(review):\n",
    "    return sid.polarity_scores(review)\n",
    "\n",
    "def separate_vader_score(vader_score, key):\n",
    "    return vader_score[key]\n",
    "\n",
    "## =======================================================\n",
    "## SUMMARIZER\n",
    "## =======================================================\n",
    "def get_weighted_freq_dist(review, freq_dist):\n",
    "    max_freq = max(freq_dist.values())\n",
    "    for word in freq_dist.keys():\n",
    "        freq_dist[word] = (freq_dist[word]/max_freq)\n",
    "    return freq_dist\n",
    "\n",
    "def get_sentence_score(review, freq_dist):\n",
    "    sentence_scores = {}\n",
    "    for sent in review:\n",
    "        for word in nltk.word_tokenize(sent.lower()):\n",
    "            if word in freq_dist.keys():\n",
    "                if len(sent.split(' ')) < 30:\n",
    "                    if sent not in sentence_scores.keys():\n",
    "                        sentence_scores[sent] = freq_dist[word]\n",
    "                    else:\n",
    "                        sentence_scores[sent] += freq_dist[word]\n",
    "    return sentence_scores\n",
    "\n",
    "def get_summary_sentences(sentence_scores):\n",
    "    sorted_sentences = sorted(sentence_scores.items(), key=lambda kv: kv[1], reverse=True)\n",
    "    return ''.join(sent[0] for sent in sorted_sentences[:5])\n",
    "\n",
    "def get_freq_words(freq_dist):\n",
    "    sorted_words = sorted(freq_dist.items(), key=lambda kv: kv[1], reverse=True)\n",
    "    return ' '.join(word[0] for word in sorted_words[:50])\n",
    "\n",
    "\n",
    "def clean_rogue_characters(string):\n",
    "    exclude = ['\\\\',\"\\'\",'\"']\n",
    "    string = ''.join(string.split('\\\\n'))\n",
    "    string = ''.join(ch for ch in string if ch not in exclude)\n",
    "    return string\n",
    "\n",
    "\n",
    "import re\n",
    "def clean_rogue_characters_2(string):\n",
    "    return re.sub('[^0-9a-zA-Z.]+', ' ', string)\n",
    "\n",
    "\n",
    "def most_freq_words(freq_dist):\n",
    "    return freq_dist.most_common(100)\n",
    "\n",
    "def pruner(review):\n",
    "    clean_review = ' '.join([word.lower() for word in review.split() if len(word) > 3])\n",
    "    return clean_review\n",
    "\n",
    "def pruner_v2(review):\n",
    "    clean_review = ' '.join([word.lower() for word in review.split() if len(word) > 3 and word not in stop_words])\n",
    "    \n",
    "    return clean_review\n",
    "\n",
    "def get_bow_from_column(df, column):\n",
    "    all_column_data = ' '.join(df[column].tolist())\n",
    "    all_column_fd = Counter(all_column_data.split())\n",
    "    return all_column_fd\n",
    "\n",
    "def get_common_words(num):\n",
    "    most_common_neg = [word[0] for word in big_bow_n.most_common(num)]\n",
    "    most_common_pos = [word[0] for word in big_bow_p.most_common(num)]\n",
    "    in_both = np.intersect1d(most_common_neg, most_common_pos)\n",
    "    neg_notpos = np.setdiff1d(most_common_neg, most_common_pos)\n",
    "    pos_notneg = np.setdiff1d(most_common_pos, most_common_neg)\n",
    "    return [len(in_both), len(neg_notpos), len(pos_notneg), len(in_both)/num, in_both, neg_notpos, pos_notneg]\n",
    "\n",
    "def get_only_polarized(tokens, common_words):\n",
    "    return [token for token in tokens if token not in common_words[4]] # 70"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "metadata": {},
   "outputs": [],
   "source": [
    "# pos = get_data_from_files('../hw4_lie_false/')\n",
    "data = get_data_from_files('AmazonPhotoTextCorpus/')\n",
    "\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "df = pd.DataFrame(data)\n",
    "all_df = df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "metadata": {},
   "outputs": [],
   "source": [
    "all_df['tokens'] = all_df.apply(lambda x: get_tokens(x[0]), axis=1)\n",
    "all_df['num_tokens'] = all_df.apply(lambda x: len(x['tokens']), axis=1)\n",
    "\n",
    "all_df = all_df.drop(all_df[all_df.num_tokens < 1].index)\n",
    "\n",
    "all_df['sentences'] = all_df.apply(lambda x: get_sentence_tokens(x[0]), axis=1)\n",
    "all_df['num_sentences'] = all_df.apply(lambda x: len(x['sentences']), axis=1)\n",
    "\n",
    "all_df['no_sw'] = all_df.apply(lambda x: remove_stopwords(x['tokens']),axis=1)\n",
    "all_df['freq_dist'] = all_df.apply(lambda x: get_fdist(x['no_sw']),axis=1)\n",
    "\n",
    "all_df['weighted_freq_dist'] = all_df.apply(lambda x: get_weighted_freq_dist(x['sentences'], x['freq_dist']),axis=1)\n",
    "all_df['sentence_scores'] = all_df.apply(lambda x: get_sentence_score(x['sentences'], x['freq_dist']),axis=1)\n",
    "all_df['summary_sentences'] = all_df.apply(lambda x: get_summary_sentences(x['sentence_scores']), axis=1)\n",
    "\n",
    "all_df['clean'] = all_df.apply(lambda x: clean_rogue_characters(x[0]), axis=1)\n",
    "all_df['clean_v2'] = all_df.apply(lambda x: clean_rogue_characters_2(x[0]), axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "metadata": {},
   "outputs": [],
   "source": [
    "clean_df = pd.DataFrame(all_df['clean_v2'].tolist())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "metadata": {},
   "outputs": [],
   "source": [
    "all_df = clean_df.copy()\n",
    "all_df['tokens'] = all_df.apply(lambda x: get_tokens(x[0]), axis=1)\n",
    "all_df['num_tokens'] = all_df.apply(lambda x: len(x['tokens']), axis=1)\n",
    "\n",
    "all_df = all_df.drop(all_df[all_df.num_tokens < 1].index)\n",
    "\n",
    "all_df['sentences'] = all_df.apply(lambda x: get_sentence_tokens(x[0]), axis=1)\n",
    "all_df['num_sentences'] = all_df.apply(lambda x: len(x['sentences']), axis=1)\n",
    "\n",
    "all_df['no_sw'] = all_df.apply(lambda x: remove_stopwords(x['tokens']),axis=1)\n",
    "all_df['freq_dist'] = all_df.apply(lambda x: get_fdist(x['no_sw']),axis=1)\n",
    "\n",
    "all_df['weighted_freq_dist'] = all_df.apply(lambda x: get_weighted_freq_dist(x['sentences'], x['freq_dist']),axis=1)\n",
    "all_df['sentence_scores'] = all_df.apply(lambda x: get_sentence_score(x['sentences'], x['freq_dist']),axis=1)\n",
    "all_df['summary_sentences'] = all_df.apply(lambda x: get_summary_sentences(x['sentence_scores']), axis=1)\n",
    "\n",
    "all_df['clean'] = all_df.apply(lambda x: clean_rogue_characters(x[0]), axis=1)\n",
    "all_df['clean_v2'] = all_df.apply(lambda x: clean_rogue_characters_2(x[0]), axis=1)\n",
    "\n",
    "all_df['FREQ'] = all_df.apply(lambda x: most_freq_words(x['freq_dist']), axis=1)\n",
    "all_df['pruned'] = all_df.apply(lambda x: pruner(x[0]), axis=1)\n",
    "\n",
    "\n",
    "all_df['pruned_nosw'] = all_df.apply(lambda x: pruner_v2(x[0]), axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "      <th>tokens</th>\n",
       "      <th>num_tokens</th>\n",
       "      <th>sentences</th>\n",
       "      <th>num_sentences</th>\n",
       "      <th>no_sw</th>\n",
       "      <th>freq_dist</th>\n",
       "      <th>weighted_freq_dist</th>\n",
       "      <th>sentence_scores</th>\n",
       "      <th>summary_sentences</th>\n",
       "      <th>clean</th>\n",
       "      <th>clean_v2</th>\n",
       "      <th>FREQ</th>\n",
       "      <th>pruned</th>\n",
       "      <th>pruned_nosw</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>iS 11 23 1 Q Search If shine a white LED ligh...</td>\n",
       "      <td>[is, q, search, if, shine, a, white, led, ligh...</td>\n",
       "      <td>135</td>\n",
       "      <td>[ iS 11 23 1 Q Search If shine a white LED lig...</td>\n",
       "      <td>2</td>\n",
       "      <td>[q, search, shine, white, led, light, prism, w...</td>\n",
       "      <td>{'q': 0.25, 'search': 0.25, 'shine': 0.75, 'wh...</td>\n",
       "      <td>{'q': 0.25, 'search': 0.25, 'shine': 0.75, 'wh...</td>\n",
       "      <td>{'r theemotionmac 140 1 Share r Serendipity u ...</td>\n",
       "      <td>r theemotionmac 140 1 Share r Serendipity u se...</td>\n",
       "      <td>iS 11 23 1 Q Search If shine a white LED ligh...</td>\n",
       "      <td>iS 11 23 1 Q Search If shine a white LED ligh...</td>\n",
       "      <td>[(r, 1.0), (shine, 0.75), (see, 0.75), (line, ...</td>\n",
       "      <td>search shine white light through prism would s...</td>\n",
       "      <td>search shine white light prism would spectrum ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>6 51 . 0 forums.nexusmods.com ee BrettM fosaym...</td>\n",
       "      <td>[ee, brettm, fosaym, apr, stealth, archery, wo...</td>\n",
       "      <td>340</td>\n",
       "      <td>[6 51 ., 0 forums.nexusmods.com ee BrettM fosa...</td>\n",
       "      <td>16</td>\n",
       "      <td>[ee, brettm, fosaym, apr, stealth, archery, wo...</td>\n",
       "      <td>{'ee': 0.25, 'brettm': 0.25, 'fosaym': 0.25, '...</td>\n",
       "      <td>{'ee': 0.25, 'brettm': 0.25, 'fosaym': 0.25, '...</td>\n",
       "      <td>{'0 forums.nexusmods.com ee BrettM fosaym 617 ...</td>\n",
       "      <td>You should be far enough away from the first f...</td>\n",
       "      <td>6 51 . 0 forums.nexusmods.com ee BrettM fosaym...</td>\n",
       "      <td>6 51 . 0 forums.nexusmods.com ee BrettM fosaym...</td>\n",
       "      <td>[(sneak, 1.0), (one, 1.0), (get, 1.0), (bow, 1...</td>\n",
       "      <td>forums.nexusmods.com brettm fosaym 2012 stealt...</td>\n",
       "      <td>forums.nexusmods.com brettm fosaym 2012 stealt...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>6 52 al Se forums.nexusmods.com 17 Apr 2012 St...</td>\n",
       "      <td>[al, se, apr, stealth, archery, works, great, ...</td>\n",
       "      <td>345</td>\n",
       "      <td>[6 52 al Se forums.nexusmods.com 17 Apr 2012 S...</td>\n",
       "      <td>15</td>\n",
       "      <td>[al, se, apr, stealth, archery, works, great, ...</td>\n",
       "      <td>{'al': 0.25, 'se': 0.25, 'apr': 0.25, 'stealth...</td>\n",
       "      <td>{'al': 0.25, 'se': 0.25, 'apr': 0.25, 'stealth...</td>\n",
       "      <td>{'6 52 al Se forums.nexusmods.com 17 Apr 2012 ...</td>\n",
       "      <td>You should be far enough away from the first f...</td>\n",
       "      <td>6 52 al Se forums.nexusmods.com 17 Apr 2012 St...</td>\n",
       "      <td>6 52 al Se forums.nexusmods.com 17 Apr 2012 St...</td>\n",
       "      <td>[(sneak, 1.0), (one, 1.0), (get, 1.0), (bow, 1...</td>\n",
       "      <td>forums.nexusmods.com 2012 stealth archery work...</td>\n",
       "      <td>forums.nexusmods.com 2012 stealth archery work...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>4 06 aw Fe spokesman.com 4 ILULL. LL 1S SUUULI...</td>\n",
       "      <td>[aw, fe, ilull, ll, suuuliiis, aalllu, culilal...</td>\n",
       "      <td>121</td>\n",
       "      <td>[4 06 aw Fe spokesman.com 4 ILULL., LL 1S SUUU...</td>\n",
       "      <td>10</td>\n",
       "      <td>[aw, fe, ilull, suuuliiis, aalllu, culilallis,...</td>\n",
       "      <td>{'aw': 0.3333333333333333, 'fe': 0.33333333333...</td>\n",
       "      <td>{'aw': 0.3333333333333333, 'fe': 0.33333333333...</td>\n",
       "      <td>{'4 06 aw Fe spokesman.com 4 ILULL.': 1.0, 'LL...</td>\n",
       "      <td>Listerine contains herbal oils that fight fung...</td>\n",
       "      <td>4 06 aw Fe spokesman.com 4 ILULL. LL 1S SUUULI...</td>\n",
       "      <td>4 06 aw Fe spokesman.com 4 ILULL. LL 1S SUUULI...</td>\n",
       "      <td>[(fungus, 1.0), (antifungal, 0.666666666666666...</td>\n",
       "      <td>spokesman.com ilull. suuuliiis aalllu culilall...</td>\n",
       "      <td>spokesman.com ilull. suuuliiis aalllu culilall...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>Parents do not own their children. No one owns...</td>\n",
       "      <td>[parents, do, not, own, their, children, no, o...</td>\n",
       "      <td>315</td>\n",
       "      <td>[Parents do not own their children., No one ow...</td>\n",
       "      <td>14</td>\n",
       "      <td>[parents, children, one, owns, anything, loan,...</td>\n",
       "      <td>{'parents': 0.7142857142857143, 'children': 0....</td>\n",
       "      <td>{'parents': 0.7142857142857143, 'children': 0....</td>\n",
       "      <td>{'Parents do not own their children.': 0.78571...</td>\n",
       "      <td>Kids are not carbon copies of parents adoptive...</td>\n",
       "      <td>Parents do not own their children. No one owns...</td>\n",
       "      <td>Parents do not own their children. No one owns...</td>\n",
       "      <td>[(kids, 1.0), (parents, 0.7142857142857143), (...</td>\n",
       "      <td>parents their children. owns anything just loa...</td>\n",
       "      <td>parents children. owns anything loan duration ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5</td>\n",
       "      <td>o changed shampoos cut out dairy litres of wat...</td>\n",
       "      <td>[o, changed, shampoos, cut, out, dairy, litres...</td>\n",
       "      <td>236</td>\n",
       "      <td>[o changed shampoos cut out dairy litres of wa...</td>\n",
       "      <td>12</td>\n",
       "      <td>[changed, shampoos, cut, dairy, litres, water,...</td>\n",
       "      <td>{'changed': 0.2, 'shampoos': 0.2, 'cut': 0.4, ...</td>\n",
       "      <td>{'changed': 0.2, 'shampoos': 0.2, 'cut': 0.4, ...</td>\n",
       "      <td>{'o changed shampoos cut out dairy litres of w...</td>\n",
       "      <td>So searched about antiseptics agents on MRSA a...</td>\n",
       "      <td>o changed shampoos cut out dairy litres of wat...</td>\n",
       "      <td>o changed shampoos cut out dairy litres of wat...</td>\n",
       "      <td>[(mrsa, 1.0), (folliculitis, 0.8), (like, 0.6)...</td>\n",
       "      <td>changed shampoos dairy litres water fast food ...</td>\n",
       "      <td>changed shampoos dairy litres water fast food ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6</td>\n",
       "      <td>WEIS 2P 40p o2ua8 yp i deyiaao SpJ0M Jo 3eq su...</td>\n",
       "      <td>[weis, yp, i, deyiaao, jo, suunseayy, z, e, ae...</td>\n",
       "      <td>183</td>\n",
       "      <td>[WEIS 2P 40p o2ua8 yp i deyiaao SpJ0M Jo 3eq s...</td>\n",
       "      <td>1</td>\n",
       "      <td>[weis, yp, deyiaao, jo, suunseayy, z, e, aeazz...</td>\n",
       "      <td>{'weis': 0.2, 'yp': 0.2, 'deyiaao': 0.2, 'jo':...</td>\n",
       "      <td>{'weis': 0.2, 'yp': 0.2, 'deyiaao': 0.2, 'jo':...</td>\n",
       "      <td>{}</td>\n",
       "      <td></td>\n",
       "      <td>WEIS 2P 40p o2ua8 yp i deyiaao SpJ0M Jo 3eq su...</td>\n",
       "      <td>WEIS 2P 40p o2ua8 yp i deyiaao SpJ0M Jo 3eq su...</td>\n",
       "      <td>[(aq, 1.0), (jo, 0.8), (z, 0.6), (du, 0.6), (t...</td>\n",
       "      <td>weis o2ua8 deyiaao spj0m suunseayy aeazze yoty...</td>\n",
       "      <td>weis o2ua8 deyiaao spj0m suunseayy aeazze yoty...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7</td>\n",
       "      <td>casispie hugealienpie thechubbynerd just showe...</td>\n",
       "      <td>[casispie, hugealienpie, thechubbynerd, just, ...</td>\n",
       "      <td>70</td>\n",
       "      <td>[casispie hugealienpie thechubbynerd just show...</td>\n",
       "      <td>7</td>\n",
       "      <td>[casispie, hugealienpie, thechubbynerd, shower...</td>\n",
       "      <td>{'casispie': 0.5, 'hugealienpie': 0.5, 'thechu...</td>\n",
       "      <td>{'casispie': 0.5, 'hugealienpie': 0.5, 'thechu...</td>\n",
       "      <td>{'casispie hugealienpie thechubbynerd just sho...</td>\n",
       "      <td>casispie hugealienpie thechubbynerd just showe...</td>\n",
       "      <td>casispie hugealienpie thechubbynerd just showe...</td>\n",
       "      <td>casispie hugealienpie thechubbynerd just showe...</td>\n",
       "      <td>[(language, 1.0), (kind, 1.0), (casispie, 0.5)...</td>\n",
       "      <td>casispie hugealienpie thechubbynerd just showe...</td>\n",
       "      <td>casispie hugealienpie thechubbynerd shower tho...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>8</td>\n",
       "      <td>527k J 173k it Share Oo elfmere 16h Why do you...</td>\n",
       "      <td>[j, it, share, oo, elfmere, why, do, you, work...</td>\n",
       "      <td>241</td>\n",
       "      <td>[527k J 173k it Share Oo elfmere 16h Why do yo...</td>\n",
       "      <td>11</td>\n",
       "      <td>[j, share, oo, elfmere, work, factory, honors,...</td>\n",
       "      <td>{'j': 0.5, 'share': 0.25, 'oo': 0.25, 'elfmere...</td>\n",
       "      <td>{'j': 0.5, 'share': 0.25, 'oo': 0.25, 'elfmere...</td>\n",
       "      <td>{'distinctly recall a coworker of mine who wor...</td>\n",
       "      <td>asked him one time vy what he was doing workin...</td>\n",
       "      <td>527k J 173k it Share Oo elfmere 16h Why do you...</td>\n",
       "      <td>527k J 173k it Share Oo elfmere 16h Why do you...</td>\n",
       "      <td>[(one, 1.0), (working, 1.0), (home, 0.75), (de...</td>\n",
       "      <td>527k 173k share elfmere work factory when have...</td>\n",
       "      <td>527k 173k share elfmere work factory honors de...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>9</td>\n",
       "      <td>6 55 at google.com h Google strange women lyin...</td>\n",
       "      <td>[at, h, google, strange, women, lying, in, pon...</td>\n",
       "      <td>50</td>\n",
       "      <td>[6 55 at google.com h Google strange women lyi...</td>\n",
       "      <td>2</td>\n",
       "      <td>[h, google, strange, women, lying, ponds, dist...</td>\n",
       "      <td>{'h': 0.25, 'google': 0.25, 'strange': 1.0, 'w...</td>\n",
       "      <td>{'h': 0.25, 'google': 0.25, 'strange': 1.0, 'w...</td>\n",
       "      <td>{'In Pon Etsy Redbubble Turtles STRANGE WOMEN ...</td>\n",
       "      <td>In Pon Etsy Redbubble Turtles STRANGE WOMEN AA...</td>\n",
       "      <td>6 55 at google.com h Google strange women lyin...</td>\n",
       "      <td>6 55 at google.com h Google strange women lyin...</td>\n",
       "      <td>[(strange, 1.0), (women, 1.0), (lying, 0.75), ...</td>\n",
       "      <td>google.com google strange women lying ponds di...</td>\n",
       "      <td>google.com google strange women lying ponds di...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>10</td>\n",
       "      <td>1 51 Mail glassdoor.com as GitHub Policy Detai...</td>\n",
       "      <td>[mail, as, github, policy, details, we, encour...</td>\n",
       "      <td>126</td>\n",
       "      <td>[1 51 Mail glassdoor.com as GitHub Policy Deta...</td>\n",
       "      <td>6</td>\n",
       "      <td>[mail, github, policy, details, encourage, hub...</td>\n",
       "      <td>{'mail': 0.2, 'github': 0.4, 'policy': 0.2, 'd...</td>\n",
       "      <td>{'mail': 0.2, 'github': 0.4, 'policy': 0.2, 'd...</td>\n",
       "      <td>{'1 51 Mail glassdoor.com as GitHub Policy Det...</td>\n",
       "      <td>1 51 Mail glassdoor.com as GitHub Policy Detai...</td>\n",
       "      <td>1 51 Mail glassdoor.com as GitHub Policy Detai...</td>\n",
       "      <td>1 51 Mail glassdoor.com as GitHub Policy Detai...</td>\n",
       "      <td>[(manager, 1.0), (work, 0.6), (github, 0.4), (...</td>\n",
       "      <td>mail glassdoor.com github policy details encou...</td>\n",
       "      <td>mail glassdoor.com github policy details encou...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>11</td>\n",
       "      <td>fantasywriters u SlinkySlang 3h Writing advic...</td>\n",
       "      <td>[fantasywriters, u, slinkyslang, writing, advi...</td>\n",
       "      <td>172</td>\n",
       "      <td>[ fantasywriters u SlinkySlang 3h Writing advi...</td>\n",
       "      <td>11</td>\n",
       "      <td>[fantasywriters, u, slinkyslang, writing, advi...</td>\n",
       "      <td>{'fantasywriters': 0.2, 'u': 0.2, 'slinkyslang...</td>\n",
       "      <td>{'fantasywriters': 0.2, 'u': 0.2, 'slinkyslang...</td>\n",
       "      <td>{' fantasywriters u SlinkySlang 3h Writing adv...</td>\n",
       "      <td>For the sake of your self esteem your sanity a...</td>\n",
       "      <td>fantasywriters u SlinkySlang 3h Writing advic...</td>\n",
       "      <td>fantasywriters u SlinkySlang 3h Writing advic...</td>\n",
       "      <td>[(first, 1.0), (draft, 0.6), (stop, 0.6), (wri...</td>\n",
       "      <td>fantasywriters slinkyslang writing advice...fr...</td>\n",
       "      <td>fantasywriters slinkyslang writing advice...fr...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>12</td>\n",
       "      <td>10 21 wil Mail jobs.capitalgroup.com Responsib...</td>\n",
       "      <td>[wil, mail, responsibilities, work, in, a, tea...</td>\n",
       "      <td>204</td>\n",
       "      <td>[10 21 wil Mail jobs.capitalgroup.com Responsi...</td>\n",
       "      <td>5</td>\n",
       "      <td>[wil, mail, responsibilities, work, team, anal...</td>\n",
       "      <td>{'wil': 0.125, 'mail': 0.125, 'responsibilitie...</td>\n",
       "      <td>{'wil': 0.125, 'mail': 0.125, 'responsibilitie...</td>\n",
       "      <td>{'Proven analytical and problem solving skills...</td>\n",
       "      <td>Proven analytical and problem solving skills w...</td>\n",
       "      <td>10 21 wil Mail jobs.capitalgroup.com Responsib...</td>\n",
       "      <td>10 21 wil Mail jobs.capitalgroup.com Responsib...</td>\n",
       "      <td>[(research, 1.0), (portfolio, 0.5), (asset, 0....</td>\n",
       "      <td>mail jobs.capitalgroup.com responsibilities wo...</td>\n",
       "      <td>mail jobs.capitalgroup.com responsibilities wo...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>13</td>\n",
       "      <td>177k 3.9k it Share Oo GalacticPingvin 3h lemla...</td>\n",
       "      <td>[it, share, oo, galacticpingvin, lemlang, atli...</td>\n",
       "      <td>158</td>\n",
       "      <td>[177k 3.9k it Share Oo GalacticPingvin 3h leml...</td>\n",
       "      <td>10</td>\n",
       "      <td>[share, oo, galacticpingvin, lemlang, atlienk,...</td>\n",
       "      <td>{'share': 0.3333333333333333, 'oo': 0.33333333...</td>\n",
       "      <td>{'share': 0.3333333333333333, 'oo': 0.33333333...</td>\n",
       "      <td>{'177k 3.9k it Share Oo GalacticPingvin 3h lem...</td>\n",
       "      <td>Her husband at the time basically spent a few ...</td>\n",
       "      <td>177k 3.9k it Share Oo GalacticPingvin 3h lemla...</td>\n",
       "      <td>177k 3.9k it Share Oo GalacticPingvin 3h lemla...</td>\n",
       "      <td>[(marriage, 1.0), (time, 0.6666666666666666), ...</td>\n",
       "      <td>177k 3.9k share galacticpingvin lemlang atlien...</td>\n",
       "      <td>177k 3.9k share galacticpingvin lemlang atlien...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>14</td>\n",
       "      <td>a. Ricky Montgomery am upset with my parents f...</td>\n",
       "      <td>[ricky, montgomery, am, upset, with, my, paren...</td>\n",
       "      <td>33</td>\n",
       "      <td>[a. Ricky Montgomery am upset with my parents ...</td>\n",
       "      <td>2</td>\n",
       "      <td>[ricky, montgomery, upset, parents, making, ex...</td>\n",
       "      <td>{'ricky': 1.0, 'montgomery': 1.0, 'upset': 1.0...</td>\n",
       "      <td>{'ricky': 1.0, 'montgomery': 1.0, 'upset': 1.0...</td>\n",
       "      <td>{'a. Ricky Montgomery am upset with my parents...</td>\n",
       "      <td>u just decided to make a person one day who s ...</td>\n",
       "      <td>a. Ricky Montgomery am upset with my parents f...</td>\n",
       "      <td>a. Ricky Montgomery am upset with my parents f...</td>\n",
       "      <td>[(ricky, 1.0), (montgomery, 1.0), (upset, 1.0)...</td>\n",
       "      <td>ricky montgomery upset with parents making exi...</td>\n",
       "      <td>ricky montgomery upset parents making exist. d...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>15</td>\n",
       "      <td>ig nyx5 i prefer guys who make small dick joke...</td>\n",
       "      <td>[ig, i, prefer, guys, who, make, small, dick, ...</td>\n",
       "      <td>39</td>\n",
       "      <td>[ig nyx5 i prefer guys who make small dick jok...</td>\n",
       "      <td>1</td>\n",
       "      <td>[ig, prefer, guys, make, small, dick, jokes, g...</td>\n",
       "      <td>{'ig': 0.3333333333333333, 'prefer': 0.3333333...</td>\n",
       "      <td>{'ig': 0.3333333333333333, 'prefer': 0.3333333...</td>\n",
       "      <td>{}</td>\n",
       "      <td></td>\n",
       "      <td>ig nyx5 i prefer guys who make small dick joke...</td>\n",
       "      <td>ig nyx5 i prefer guys who make small dick joke...</td>\n",
       "      <td>[(dick, 1.0), (guys, 0.6666666666666666), (mak...</td>\n",
       "      <td>nyx5 prefer guys make small dick jokes about t...</td>\n",
       "      <td>nyx5 prefer guys make small dick jokes guys ma...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>16</td>\n",
       "      <td>427 27 it Share Oo mrtrouble22 4h Believer i r...</td>\n",
       "      <td>[it, share, oo, believer, i, read, one, story,...</td>\n",
       "      <td>166</td>\n",
       "      <td>[427 27 it Share Oo mrtrouble22 4h Believer i ...</td>\n",
       "      <td>10</td>\n",
       "      <td>[share, oo, believer, read, one, story, woman,...</td>\n",
       "      <td>{'share': 0.5, 'oo': 0.5, 'believer': 0.5, 're...</td>\n",
       "      <td>{'share': 0.5, 'oo': 0.5, 'believer': 0.5, 're...</td>\n",
       "      <td>{'427 27 it Share Oo mrtrouble22 4h Believer i...</td>\n",
       "      <td>427 27 it Share Oo mrtrouble22 4h Believer i r...</td>\n",
       "      <td>427 27 it Share Oo mrtrouble22 4h Believer i r...</td>\n",
       "      <td>427 27 it Share Oo mrtrouble22 4h Believer i r...</td>\n",
       "      <td>[(bigfoot, 1.0), (greys, 1.0), (long, 1.0), (s...</td>\n",
       "      <td>share mrtrouble22 believer read story where wo...</td>\n",
       "      <td>share mrtrouble22 believer read story woman gr...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>17</td>\n",
       "      <td>6 52 al Se forums.nexusmods.com 4 as Soon as y...</td>\n",
       "      <td>[al, se, as, soon, as, you, dismount, and, use...</td>\n",
       "      <td>301</td>\n",
       "      <td>[6 52 al Se forums.nexusmods.com 4 as Soon as ...</td>\n",
       "      <td>14</td>\n",
       "      <td>[al, se, soon, dismount, use, key, wait, tor, ...</td>\n",
       "      <td>{'al': 0.2, 'se': 0.2, 'soon': 0.2, 'dismount'...</td>\n",
       "      <td>{'al': 0.2, 'se': 0.2, 'soon': 0.2, 'dismount'...</td>\n",
       "      <td>{'6 52 al Se forums.nexusmods.com 4 as Soon as...</td>\n",
       "      <td>like using Shock damage Stamina damage enchant...</td>\n",
       "      <td>6 52 al Se forums.nexusmods.com 4 as Soon as y...</td>\n",
       "      <td>6 52 al Se forums.nexusmods.com 4 as Soon as y...</td>\n",
       "      <td>[(damage, 1.0), (bow, 0.8), (arrows, 0.8), (be...</td>\n",
       "      <td>forums.nexusmods.com soon dismount wait dark. ...</td>\n",
       "      <td>forums.nexusmods.com soon dismount wait dark. ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>18</td>\n",
       "      <td>11 54 a eG sciencedaily.com The medical commun...</td>\n",
       "      <td>[a, eg, the, medical, community, used, to, thi...</td>\n",
       "      <td>273</td>\n",
       "      <td>[11 54 a eG sciencedaily.com The medical commu...</td>\n",
       "      <td>10</td>\n",
       "      <td>[eg, medical, community, used, think, obesity,...</td>\n",
       "      <td>{'eg': 0.14285714285714285, 'medical': 0.14285...</td>\n",
       "      <td>{'eg': 0.14285714285714285, 'medical': 0.14285...</td>\n",
       "      <td>{'11 54 a eG sciencedaily.com The medical comm...</td>\n",
       "      <td>Obesity is increasing at 2.3 rate each year am...</td>\n",
       "      <td>11 54 a eG sciencedaily.com The medical commun...</td>\n",
       "      <td>11 54 a eG sciencedaily.com The medical commun...</td>\n",
       "      <td>[(obesity, 1.0), (also, 0.42857142857142855), ...</td>\n",
       "      <td>sciencedaily.com medical community used think ...</td>\n",
       "      <td>sciencedaily.com medical community used think ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>19</td>\n",
       "      <td>lore 54352452524 deactivated201 you can reple...</td>\n",
       "      <td>[lore, you, can, replenish, your, health, by, ...</td>\n",
       "      <td>67</td>\n",
       "      <td>[ lore 54352452524 deactivated201 you can repl...</td>\n",
       "      <td>1</td>\n",
       "      <td>[lore, replenish, health, drinking, water, bre...</td>\n",
       "      <td>{'lore': 0.5, 'replenish': 0.5, 'health': 1.0,...</td>\n",
       "      <td>{'lore': 0.5, 'replenish': 0.5, 'health': 1.0,...</td>\n",
       "      <td>{}</td>\n",
       "      <td></td>\n",
       "      <td>lore 54352452524 deactivated201 you can reple...</td>\n",
       "      <td>lore 54352452524 deactivated201 you can reple...</td>\n",
       "      <td>[(health, 1.0), (breathing, 1.0), (fresh, 1.0)...</td>\n",
       "      <td>lore 54352452524 deactivated201 replenish your...</td>\n",
       "      <td>lore 54352452524 deactivated201 replenish heal...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>20</td>\n",
       "      <td>4128 8 it Share We Datadevourer 3h Recently st...</td>\n",
       "      <td>[it, share, we, datadevourer, recently, starte...</td>\n",
       "      <td>240</td>\n",
       "      <td>[4128 8 it Share We Datadevourer 3h Recently s...</td>\n",
       "      <td>10</td>\n",
       "      <td>[share, datadevourer, recently, started, using...</td>\n",
       "      <td>{'share': 0.125, 'datadevourer': 0.125, 'recen...</td>\n",
       "      <td>{'share': 0.125, 'datadevourer': 0.125, 'recen...</td>\n",
       "      <td>{'4128 8 it Share We Datadevourer 3h Recently ...</td>\n",
       "      <td>However it s not at all good to rely on others...</td>\n",
       "      <td>4128 8 it Share We Datadevourer 3h Recently st...</td>\n",
       "      <td>4128 8 it Share We Datadevourer 3h Recently st...</td>\n",
       "      <td>[(time, 1.0), (try, 0.5), (sometimes, 0.375), ...</td>\n",
       "      <td>4128 share datadevourer recently started using...</td>\n",
       "      <td>4128 share datadevourer recently started using...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>21</td>\n",
       "      <td>53.2k 176k it Share o PyroSnakel41 13h Become...</td>\n",
       "      <td>[it, share, o, become, a, politician, and, rai...</td>\n",
       "      <td>165</td>\n",
       "      <td>[ 53.2k 176k it Share o PyroSnakel41 13h Becom...</td>\n",
       "      <td>8</td>\n",
       "      <td>[share, become, politician, raise, pay, creati...</td>\n",
       "      <td>{'share': 0.25, 'become': 0.25, 'politician': ...</td>\n",
       "      <td>{'share': 0.25, 'become': 0.25, 'politician': ...</td>\n",
       "      <td>{' 53.2k 176k it Share o PyroSnakel41 13h Beco...</td>\n",
       "      <td>o 9 14k owningmclovin 10h Most of the federal ...</td>\n",
       "      <td>53.2k 176k it Share o PyroSnakel41 13h Become...</td>\n",
       "      <td>53.2k 176k it Share o PyroSnakel41 13h Become...</td>\n",
       "      <td>[(rich, 1.0), (raise, 0.75), (would, 0.75), (p...</td>\n",
       "      <td>53.2k 176k share pyrosnakel41 become politicia...</td>\n",
       "      <td>53.2k 176k share pyrosnakel41 become politicia...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>22</td>\n",
       "      <td>r nosurf u fibonacciseries 9d Turning on the G...</td>\n",
       "      <td>[r, nosurf, u, fibonacciseries, turning, on, t...</td>\n",
       "      <td>203</td>\n",
       "      <td>[r nosurf u fibonacciseries 9d Turning on the ...</td>\n",
       "      <td>10</td>\n",
       "      <td>[r, nosurf, u, fibonacciseries, turning, greys...</td>\n",
       "      <td>{'r': 0.125, 'nosurf': 0.125, 'u': 0.125, 'fib...</td>\n",
       "      <td>{'r': 0.125, 'nosurf': 0.125, 'u': 0.125, 'fib...</td>\n",
       "      <td>{'r nosurf u fibonacciseries 9d Turning on the...</td>\n",
       "      <td>r nosurf u fibonacciseries 9d Turning on the G...</td>\n",
       "      <td>r nosurf u fibonacciseries 9d Turning on the G...</td>\n",
       "      <td>r nosurf u fibonacciseries 9d Turning on the G...</td>\n",
       "      <td>[(phone, 1.0), (attractive, 0.5), (filter, 0.3...</td>\n",
       "      <td>nosurf fibonacciseries turning greyscale filte...</td>\n",
       "      <td>nosurf fibonacciseries turning greyscale filte...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>23</td>\n",
       "      <td>Vote J 10 it Share Oo it2051229 36m In the be...</td>\n",
       "      <td>[vote, j, it, share, oo, in, the, beginning, t...</td>\n",
       "      <td>220</td>\n",
       "      <td>[ Vote J 10 it Share Oo it2051229 36m In the b...</td>\n",
       "      <td>12</td>\n",
       "      <td>[vote, j, share, oo, beginning, thing, compute...</td>\n",
       "      <td>{'vote': 0.3333333333333333, 'j': 0.3333333333...</td>\n",
       "      <td>{'vote': 0.3333333333333333, 'j': 0.3333333333...</td>\n",
       "      <td>{' Vote J 10 it Share Oo it2051229 36m In the ...</td>\n",
       "      <td>Rey 24 binjamin2 36m Computer science is heave...</td>\n",
       "      <td>Vote J 10 it Share Oo it2051229 36m In the be...</td>\n",
       "      <td>Vote J 10 it Share Oo it2051229 36m In the be...</td>\n",
       "      <td>[(take, 1.0), (efficiently, 1.0), (computers, ...</td>\n",
       "      <td>vote share it2051229 beginning there such thin...</td>\n",
       "      <td>vote share it2051229 beginning thing computer ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>24</td>\n",
       "      <td>4 50 Q Search News Home Popular 20k J 15 it Sh...</td>\n",
       "      <td>[q, search, news, home, popular, j, it, share,...</td>\n",
       "      <td>55</td>\n",
       "      <td>[4 50 Q Search News Home Popular 20k J 15 it S...</td>\n",
       "      <td>2</td>\n",
       "      <td>[q, search, news, home, popular, j, share, r, ...</td>\n",
       "      <td>{'q': 0.5, 'search': 0.5, 'news': 0.5, 'home':...</td>\n",
       "      <td>{'q': 0.5, 'search': 0.5, 'news': 0.5, 'home':...</td>\n",
       "      <td>{'4 50 Q Search News Home Popular 20k J 15 it ...</td>\n",
       "      <td>4 50 Q Search News Home Popular 20k J 15 it Sh...</td>\n",
       "      <td>4 50 Q Search News Home Popular 20k J 15 it Sh...</td>\n",
       "      <td>4 50 Q Search News Home Popular 20k J 15 it Sh...</td>\n",
       "      <td>[(share, 1.0), (r, 1.0), (u, 1.0), (bullet, 1....</td>\n",
       "      <td>search news home popular share basicbulletjour...</td>\n",
       "      <td>search news home popular share basicbulletjour...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>25</td>\n",
       "      <td>e205 16 it Share o iseemath 18h think you ll f...</td>\n",
       "      <td>[it, share, o, iseemath, think, you, ll, find,...</td>\n",
       "      <td>177</td>\n",
       "      <td>[e205 16 it Share o iseemath 18h think you ll ...</td>\n",
       "      <td>9</td>\n",
       "      <td>[share, iseemath, think, find, princeton, comp...</td>\n",
       "      <td>{'share': 0.25, 'iseemath': 0.25, 'think': 0.2...</td>\n",
       "      <td>{'share': 0.25, 'iseemath': 0.25, 'think': 0.2...</td>\n",
       "      <td>{'e205 16 it Share o iseemath 18h think you ll...</td>\n",
       "      <td>Reply Vote J AddemF 5h I ve been researching s...</td>\n",
       "      <td>e205 16 it Share o iseemath 18h think you ll f...</td>\n",
       "      <td>e205 16 it Share o iseemath 18h think you ll f...</td>\n",
       "      <td>[(mathematics, 1.0), (j, 0.75), (find, 0.5), (...</td>\n",
       "      <td>e205 share iseemath think find princeton compa...</td>\n",
       "      <td>e205 share iseemath think find princeton compa...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>26</td>\n",
       "      <td>124k J 49k it Share Oo Go 234 15 MORE REPLIES...</td>\n",
       "      <td>[j, it, share, oo, go, more, replies, honchomi...</td>\n",
       "      <td>100</td>\n",
       "      <td>[ 124k J 49k it Share Oo Go 234 15 MORE REPLIE...</td>\n",
       "      <td>6</td>\n",
       "      <td>[j, share, oo, go, replies, honchominerva, cj,...</td>\n",
       "      <td>{'j': 0.5, 'share': 0.25, 'oo': 0.25, 'go': 0....</td>\n",
       "      <td>{'j': 0.5, 'share': 0.25, 'oo': 0.25, 'go': 0....</td>\n",
       "      <td>{'Bing Crosby single handedly managed to creat...</td>\n",
       "      <td>Bing Crosby single handedly managed to create ...</td>\n",
       "      <td>124k J 49k it Share Oo Go 234 15 MORE REPLIES...</td>\n",
       "      <td>124k J 49k it Share Oo Go 234 15 MORE REPLIES...</td>\n",
       "      <td>[(honchominerva, 1.0), (bing, 1.0), (crosby, 1...</td>\n",
       "      <td>124k share more replies honchominerva moki hon...</td>\n",
       "      <td>124k share more replies honchominerva moki hon...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>27</td>\n",
       "      <td>124k J 49k it Share Oo 10 MORE REPLIES sudden...</td>\n",
       "      <td>[j, it, share, oo, more, replies, suddenly, sa...</td>\n",
       "      <td>110</td>\n",
       "      <td>[ 124k J 49k it Share Oo 10 MORE REPLIES sudde...</td>\n",
       "      <td>7</td>\n",
       "      <td>[j, share, oo, replies, suddenly, satire, augu...</td>\n",
       "      <td>{'j': 0.3333333333333333, 'share': 0.333333333...</td>\n",
       "      <td>{'j': 0.3333333333333333, 'share': 0.333333333...</td>\n",
       "      <td>{'To date it is the strongest candidate for an...</td>\n",
       "      <td>The Wow signal was detected on August 16 1977 ...</td>\n",
       "      <td>124k J 49k it Share Oo 10 MORE REPLIES sudden...</td>\n",
       "      <td>124k J 49k it Share Oo 10 MORE REPLIES sudden...</td>\n",
       "      <td>[(replies, 1.0), (august, 1.0), (radio, 1.0), ...</td>\n",
       "      <td>124k share more replies suddenly satire august...</td>\n",
       "      <td>124k share more replies suddenly satire august...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>28</td>\n",
       "      <td>2 07 al a 2 Messages Back Front Back NV I m no...</td>\n",
       "      <td>[al, a, messages, back, front, back, nv, i, m,...</td>\n",
       "      <td>160</td>\n",
       "      <td>[2 07 al a 2 Messages Back Front Back NV I m n...</td>\n",
       "      <td>7</td>\n",
       "      <td>[al, messages, back, front, back, nv, home, ri...</td>\n",
       "      <td>{'al': 0.25, 'messages': 0.25, 'back': 1.0, 'f...</td>\n",
       "      <td>{'al': 0.25, 'messages': 0.25, 'back': 1.0, 'f...</td>\n",
       "      <td>{'read that and her other interview book.': 1....</td>\n",
       "      <td>promise to come back and extend the list when ...</td>\n",
       "      <td>2 07 al a 2 Messages Back Front Back NV I m no...</td>\n",
       "      <td>2 07 al a 2 Messages Back Front Back NV I m no...</td>\n",
       "      <td>[(back, 1.0), (recommend, 0.75), (problems, 0....</td>\n",
       "      <td>messages back front back home right going give...</td>\n",
       "      <td>messages back front back home right going give...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>29</td>\n",
       "      <td>527k J 173k it Share Oo Q Reply 56k H insertca...</td>\n",
       "      <td>[j, it, share, oo, q, reply, h, insertcaffeine...</td>\n",
       "      <td>161</td>\n",
       "      <td>[527k J 173k it Share Oo Q Reply 56k H insertc...</td>\n",
       "      <td>10</td>\n",
       "      <td>[j, share, oo, q, reply, h, insertcaffeine, qu...</td>\n",
       "      <td>{'j': 0.6666666666666666, 'share': 0.333333333...</td>\n",
       "      <td>{'j': 0.6666666666666666, 'share': 0.333333333...</td>\n",
       "      <td>{'527k J 173k it Share Oo Q Reply 56k H insert...</td>\n",
       "      <td>Go 9 16 4 3 MORE REPLIES 75 MORE REPLIES imk 1...</td>\n",
       "      <td>527k J 173k it Share Oo Q Reply 56k H insertca...</td>\n",
       "      <td>527k J 173k it Share Oo Q Reply 56k H insertca...</td>\n",
       "      <td>[(asked, 1.0), (j, 0.6666666666666666), (reply...</td>\n",
       "      <td>527k 173k share reply insertcaffeine questions...</td>\n",
       "      <td>527k 173k share reply insertcaffeine questions...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>30</td>\n",
       "      <td>124k J 49k it Share Oo 2 MORE REPLIES 1 MORE ...</td>\n",
       "      <td>[j, it, share, oo, more, replies, more, reply,...</td>\n",
       "      <td>156</td>\n",
       "      <td>[ 124k J 49k it Share Oo 2 MORE REPLIES 1 MORE...</td>\n",
       "      <td>8</td>\n",
       "      <td>[j, share, oo, replies, reply, replies, honcho...</td>\n",
       "      <td>{'j': 0.5, 'share': 0.25, 'oo': 0.25, 'replies...</td>\n",
       "      <td>{'j': 0.5, 'share': 0.25, 'oo': 0.25, 'replies...</td>\n",
       "      <td>{'The particularly interesting part is that it...</td>\n",
       "      <td>Over the past 200 years numerous chess masters...</td>\n",
       "      <td>124k J 49k it Share Oo 2 MORE REPLIES 1 MORE ...</td>\n",
       "      <td>124k J 49k it Share Oo 2 MORE REPLIES 1 MORE ...</td>\n",
       "      <td>[(alphazero, 1.0), (chess, 1.0), (j, 0.5), (re...</td>\n",
       "      <td>124k share more replies more reply more replie...</td>\n",
       "      <td>124k share more replies more reply more replie...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>31</td>\n",
       "      <td>f r stopdrinking u creaturefeaturel6 10h 689 d...</td>\n",
       "      <td>[f, r, stopdrinking, u, days, a, very, sad, te...</td>\n",
       "      <td>244</td>\n",
       "      <td>[f r stopdrinking u creaturefeaturel6 10h 689 ...</td>\n",
       "      <td>19</td>\n",
       "      <td>[f, r, stopdrinking, u, days, sad, text, messa...</td>\n",
       "      <td>{'f': 0.3333333333333333, 'r': 0.3333333333333...</td>\n",
       "      <td>{'f': 0.3333333333333333, 'r': 0.3333333333333...</td>\n",
       "      <td>{'f r stopdrinking u creaturefeaturel6 10h 689...</td>\n",
       "      <td>You looked like you were going to pass out in ...</td>\n",
       "      <td>f r stopdrinking u creaturefeaturel6 10h 689 d...</td>\n",
       "      <td>f r stopdrinking u creaturefeaturel6 10h 689 d...</td>\n",
       "      <td>[(feel, 1.0), (like, 1.0), (sad, 0.66666666666...</td>\n",
       "      <td>stopdrinking creaturefeaturel6 days very text ...</td>\n",
       "      <td>stopdrinking creaturefeaturel6 days text messa...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>32</td>\n",
       "      <td>6 51 al Se forums.nexusmods.com 4 ToniPrufrock...</td>\n",
       "      <td>[al, se, toniprufrock, apr, so, was, getting, ...</td>\n",
       "      <td>255</td>\n",
       "      <td>[6 51 al Se forums.nexusmods.com 4 ToniPrufroc...</td>\n",
       "      <td>12</td>\n",
       "      <td>[al, se, toniprufrock, apr, getting, little, b...</td>\n",
       "      <td>{'al': 0.3333333333333333, 'se': 0.33333333333...</td>\n",
       "      <td>{'al': 0.3333333333333333, 'se': 0.33333333333...</td>\n",
       "      <td>{'Not exactly the most dignified way to go.': ...</td>\n",
       "      <td>faced 2 dragons from the offset outside each o...</td>\n",
       "      <td>6 51 al Se forums.nexusmods.com 4 ToniPrufrock...</td>\n",
       "      <td>6 51 al Se forums.nexusmods.com 4 ToniPrufrock...</td>\n",
       "      <td>[(go, 1.0), (dragons, 1.0), (getting, 0.666666...</td>\n",
       "      <td>forums.nexusmods.com toniprufrock 2012 getting...</td>\n",
       "      <td>forums.nexusmods.com toniprufrock 2012 getting...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>33</td>\n",
       "      <td>12 40 1 Fe ice comftort ae iY wsyusuallyjread ...</td>\n",
       "      <td>[fe, ice, comftort, ae, iy, wsyusuallyjread, a...</td>\n",
       "      <td>31</td>\n",
       "      <td>[12 40 1 Fe ice comftort ae iY wsyusuallyjread...</td>\n",
       "      <td>4</td>\n",
       "      <td>[fe, ice, comftort, ae, iy, wsyusuallyjread, c...</td>\n",
       "      <td>{'fe': 0.5, 'ice': 0.5, 'comftort': 0.5, 'ae':...</td>\n",
       "      <td>{'fe': 0.5, 'ice': 0.5, 'comftort': 0.5, 'ae':...</td>\n",
       "      <td>{'12 40 1 Fe ice comftort ae iY wsyusuallyjrea...</td>\n",
       "      <td>12 40 1 Fe ice comftort ae iY wsyusuallyjread ...</td>\n",
       "      <td>12 40 1 Fe ice comftort ae iY wsyusuallyjread ...</td>\n",
       "      <td>12 40 1 Fe ice comftort ae iY wsyusuallyjread ...</td>\n",
       "      <td>[(images, 1.0), (fe, 0.5), (ice, 0.5), (comfto...</td>\n",
       "      <td>comftort wsyusuallyjread chapter book lightsjo...</td>\n",
       "      <td>comftort wsyusuallyjread chapter book lightsjo...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>34</td>\n",
       "      <td>8 00 wl LTE google.com hy It was October 28 19...</td>\n",
       "      <td>[wl, lte, hy, it, was, october, his, third, bi...</td>\n",
       "      <td>125</td>\n",
       "      <td>[8 00 wl LTE google.com hy It was October 28 1...</td>\n",
       "      <td>6</td>\n",
       "      <td>[wl, lte, hy, october, third, birthday, phoeni...</td>\n",
       "      <td>{'wl': 0.3333333333333333, 'lte': 0.3333333333...</td>\n",
       "      <td>{'wl': 0.3333333333333333, 'lte': 0.3333333333...</td>\n",
       "      <td>{'8 00 wl LTE google.com hy It was October 28 ...</td>\n",
       "      <td>8 00 wl LTE google.com hy It was October 28 19...</td>\n",
       "      <td>8 00 wl LTE google.com hy It was October 28 19...</td>\n",
       "      <td>8 00 wl LTE google.com hy It was October 28 19...</td>\n",
       "      <td>[(phoenix, 1.0), (venezuela, 1.0), (parents, 1...</td>\n",
       "      <td>google.com october 1977 third birthday phoenix...</td>\n",
       "      <td>google.com october 1977 third birthday phoenix...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>35</td>\n",
       "      <td>86k 3.5k it Share Oo MrBOOMbabdtlc 7h flinty d...</td>\n",
       "      <td>[it, share, oo, mrboombabdtlc, flinty, day, of...</td>\n",
       "      <td>145</td>\n",
       "      <td>[86k 3.5k it Share Oo MrBOOMbabdtlc 7h flinty ...</td>\n",
       "      <td>8</td>\n",
       "      <td>[share, oo, mrboombabdtlc, flinty, day, lovesm...</td>\n",
       "      <td>{'share': 0.3333333333333333, 'oo': 0.33333333...</td>\n",
       "      <td>{'share': 0.3333333333333333, 'oo': 0.33333333...</td>\n",
       "      <td>{'86k 3.5k it Share Oo MrBOOMbabdtlc 7h flinty...</td>\n",
       "      <td>Go 9 2k y Mudders Milk Man 3h Fun fact Bryan A...</td>\n",
       "      <td>86k 3.5k it Share Oo MrBOOMbabdtlc 7h flinty d...</td>\n",
       "      <td>86k 3.5k it Share Oo MrBOOMbabdtlc 7h flinty d...</td>\n",
       "      <td>[(porch, 1.0), (adams, 1.0), (forever, 0.66666...</td>\n",
       "      <td>3.5k share mrboombabdtlc flinty lovesmesomered...</td>\n",
       "      <td>3.5k share mrboombabdtlc flinty lovesmesomered...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>36</td>\n",
       "      <td>21k J 2.1k it Share Oo Ww DOO VYUNINIENISO WwW...</td>\n",
       "      <td>[j, it, share, oo, ww, doo, vyuninieniso, www,...</td>\n",
       "      <td>94</td>\n",
       "      <td>[21k J 2.1k it Share Oo Ww DOO VYUNINIENISO Ww...</td>\n",
       "      <td>7</td>\n",
       "      <td>[j, share, oo, ww, doo, vyuninieniso, www, fuc...</td>\n",
       "      <td>{'j': 0.25, 'share': 0.25, 'oo': 0.25, 'ww': 0...</td>\n",
       "      <td>{'j': 0.25, 'share': 0.25, 'oo': 0.25, 'ww': 0...</td>\n",
       "      <td>{'21k J 2.1k it Share Oo Ww DOO VYUNINIENISO W...</td>\n",
       "      <td>21k J 2.1k it Share Oo Ww DOO VYUNINIENISO WwW...</td>\n",
       "      <td>21k J 2.1k it Share Oo Ww DOO VYUNINIENISO WwW...</td>\n",
       "      <td>21k J 2.1k it Share Oo Ww DOO VYUNINIENISO WwW...</td>\n",
       "      <td>[(nerves, 1.0), (skydiving, 0.5), (super, 0.5)...</td>\n",
       "      <td>2.1k share vyuninieniso fuckin mate happy8day ...</td>\n",
       "      <td>2.1k share vyuninieniso fuckin mate happy8day ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>37</td>\n",
       "      <td>4 147k J 314 it Share Oo mikevago 4h One of my...</td>\n",
       "      <td>[j, it, share, oo, mikevago, one, of, my, favo...</td>\n",
       "      <td>179</td>\n",
       "      <td>[4 147k J 314 it Share Oo mikevago 4h One of m...</td>\n",
       "      <td>9</td>\n",
       "      <td>[j, share, oo, mikevago, one, favorite, things...</td>\n",
       "      <td>{'j': 0.25, 'share': 0.25, 'oo': 0.25, 'mikeva...</td>\n",
       "      <td>{'j': 0.25, 'share': 0.25, 'oo': 0.25, 'mikeva...</td>\n",
       "      <td>{'ie.': 0.25, 'the selfish short sighted schem...</td>\n",
       "      <td>Back in the day the stern cardigan wearing pip...</td>\n",
       "      <td>4 147k J 314 it Share Oo mikevago 4h One of my...</td>\n",
       "      <td>4 147k J 314 it Share Oo mikevago 4h One of my...</td>\n",
       "      <td>[(dad, 1.0), (deep, 0.75), (one, 0.5), (shows,...</td>\n",
       "      <td>147k share mikevago favorite things about both...</td>\n",
       "      <td>147k share mikevago favorite things shows ralp...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>38</td>\n",
       "      <td>631 4 59 it Share Oo PublicFigurex 28d It s fr...</td>\n",
       "      <td>[it, share, oo, publicfigurex, it, s, fried, r...</td>\n",
       "      <td>214</td>\n",
       "      <td>[631 4 59 it Share Oo PublicFigurex 28d It s f...</td>\n",
       "      <td>15</td>\n",
       "      <td>[share, oo, publicfigurex, fried, rice, kinda,...</td>\n",
       "      <td>{'share': 0.16666666666666666, 'oo': 0.1666666...</td>\n",
       "      <td>{'share': 0.16666666666666666, 'oo': 0.1666666...</td>\n",
       "      <td>{'631 4 59 it Share Oo PublicFigurex 28d It s ...</td>\n",
       "      <td>Get the mushrooms in there and toss in some so...</td>\n",
       "      <td>631 4 59 it Share Oo PublicFigurex 28d It s fr...</td>\n",
       "      <td>631 4 59 it Share Oo PublicFigurex 28d It s fr...</td>\n",
       "      <td>[(sauce, 1.0), (toss, 0.8333333333333334), (ch...</td>\n",
       "      <td>share publicfigurex fried rice. kinda chicken ...</td>\n",
       "      <td>share publicfigurex fried rice. kinda chicken ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>39</td>\n",
       "      <td>r EatCheapAndHealthy u chickentender1995 12h B...</td>\n",
       "      <td>[r, eatcheapandhealthy, u, best, tips, have, f...</td>\n",
       "      <td>229</td>\n",
       "      <td>[r EatCheapAndHealthy u chickentender1995 12h ...</td>\n",
       "      <td>14</td>\n",
       "      <td>[r, eatcheapandhealthy, u, best, tips, eating,...</td>\n",
       "      <td>{'r': 0.25, 'eatcheapandhealthy': 0.25, 'u': 0...</td>\n",
       "      <td>{'r': 0.25, 'eatcheapandhealthy': 0.25, 'u': 0...</td>\n",
       "      <td>{'r EatCheapAndHealthy u chickentender1995 12h...</td>\n",
       "      <td>All the veggies coincidentally came from last ...</td>\n",
       "      <td>r EatCheapAndHealthy u chickentender1995 12h B...</td>\n",
       "      <td>r EatCheapAndHealthy u chickentender1995 12h B...</td>\n",
       "      <td>[(food, 1.0), (one, 0.75), (month, 0.75), (che...</td>\n",
       "      <td>eatcheapandhealthy chickentender1995 best tips...</td>\n",
       "      <td>eatcheapandhealthy chickentender1995 best tips...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>40</td>\n",
       "      <td>423 M6 it Share Oo specific or more detailed w...</td>\n",
       "      <td>[it, share, oo, specific, or, more, detailed, ...</td>\n",
       "      <td>195</td>\n",
       "      <td>[423 M6 it Share Oo specific or more detailed ...</td>\n",
       "      <td>9</td>\n",
       "      <td>[share, oo, specific, detailed, probably, talk...</td>\n",
       "      <td>{'share': 0.2, 'oo': 0.4, 'specific': 0.2, 'de...</td>\n",
       "      <td>{'share': 0.2, 'oo': 0.4, 'specific': 0.2, 'de...</td>\n",
       "      <td>{'The fact that it is difficult and a lot of i...</td>\n",
       "      <td>oO 9 F Vote rookhunter 22d It s a feature of d...</td>\n",
       "      <td>423 M6 it Share Oo specific or more detailed w...</td>\n",
       "      <td>423 M6 it Share Oo specific or more detailed w...</td>\n",
       "      <td>[(hunt, 1.0), (would, 0.6), (solved, 0.6), (oo...</td>\n",
       "      <td>share specific more detailed probably wouldn t...</td>\n",
       "      <td>share specific detailed probably talking never...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>41</td>\n",
       "      <td>9 01 li LTE 4 Clock Q Search ED SJ o Atwater V...</td>\n",
       "      <td>[li, lte, clock, q, search, ed, sj, o, atwater...</td>\n",
       "      <td>200</td>\n",
       "      <td>[9 01 li LTE 4 Clock Q Search ED SJ o Atwater ...</td>\n",
       "      <td>13</td>\n",
       "      <td>[li, lte, clock, q, search, ed, sj, atwater, v...</td>\n",
       "      <td>{'li': 0.16666666666666666, 'lte': 0.166666666...</td>\n",
       "      <td>{'li': 0.16666666666666666, 'lte': 0.166666666...</td>\n",
       "      <td>{'If you know me you know that make most of my...</td>\n",
       "      <td>have a good printing company because they adop...</td>\n",
       "      <td>9 01 li LTE 4 Clock Q Search ED SJ o Atwater V...</td>\n",
       "      <td>9 01 li LTE 4 Clock Q Search ED SJ o Atwater V...</td>\n",
       "      <td>[(dog, 1.0), (good, 0.6666666666666666), (adop...</td>\n",
       "      <td>clock search atwater village topics neighborho...</td>\n",
       "      <td>clock search atwater village topics neighborho...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>42</td>\n",
       "      <td>What is the most a dollar has ever gotten you ...</td>\n",
       "      <td>[what, is, the, most, a, dollar, has, ever, go...</td>\n",
       "      <td>203</td>\n",
       "      <td>[What is the most a dollar has ever gotten you...</td>\n",
       "      <td>16</td>\n",
       "      <td>[dollar, ever, gotten, eeae, tldr, wife, three...</td>\n",
       "      <td>{'dollar': 1.0, 'ever': 0.2, 'gotten': 0.2, 'e...</td>\n",
       "      <td>{'dollar': 1.0, 'ever': 0.2, 'gotten': 0.2, 'e...</td>\n",
       "      <td>{'What is the most a dollar has ever gotten yo...</td>\n",
       "      <td>What is the most a dollar has ever gotten you ...</td>\n",
       "      <td>What is the most a dollar has ever gotten you ...</td>\n",
       "      <td>What is the most a dollar has ever gotten you ...</td>\n",
       "      <td>[(dollar, 1.0), (back, 0.8), (three, 0.4), (st...</td>\n",
       "      <td>what most dollar ever gotten eeae tldr wife th...</td>\n",
       "      <td>what dollar ever gotten eeae tldr wife three b...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>43</td>\n",
       "      <td>2 48 at O Ali Ho 8 Today 10 40 AM Recommendati...</td>\n",
       "      <td>[at, o, ali, ho, today, am, recommendations, a...</td>\n",
       "      <td>102</td>\n",
       "      <td>[2 48 at O Ali Ho 8 Today 10 40 AM Recommendat...</td>\n",
       "      <td>5</td>\n",
       "      <td>[ali, ho, today, recommendations, ask, recomme...</td>\n",
       "      <td>{'ali': 1.0, 'ho': 0.25, 'today': 0.5, 'recomm...</td>\n",
       "      <td>{'ali': 1.0, 'ho': 0.25, 'today': 0.5, 'recomm...</td>\n",
       "      <td>{'Overall you have d well.': 0.5, 'A grade of ...</td>\n",
       "      <td>This is GOOD GR We dazzled her eo c ocA grade ...</td>\n",
       "      <td>2 48 at O Ali Ho 8 Today 10 40 AM Recommendati...</td>\n",
       "      <td>2 48 at O Ali Ho 8 Today 10 40 AM Recommendati...</td>\n",
       "      <td>[(ali, 1.0), (data, 0.75), (today, 0.5), (prof...</td>\n",
       "      <td>today recommendations recommended received giv...</td>\n",
       "      <td>today recommendations recommended received giv...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>44</td>\n",
       "      <td>27k 6.2k it Share Oo Empurpledprose 18h wrote ...</td>\n",
       "      <td>[it, share, oo, empurpledprose, wrote, this, e...</td>\n",
       "      <td>193</td>\n",
       "      <td>[27k 6.2k it Share Oo Empurpledprose 18h wrote...</td>\n",
       "      <td>9</td>\n",
       "      <td>[share, oo, empurpledprose, wrote, elsewhere, ...</td>\n",
       "      <td>{'share': 0.3333333333333333, 'oo': 0.33333333...</td>\n",
       "      <td>{'share': 0.3333333333333333, 'oo': 0.33333333...</td>\n",
       "      <td>{'Earth.': 0.6666666666666666, 'This incredibl...</td>\n",
       "      <td>Oh and didja know Arsenic is extremely water s...</td>\n",
       "      <td>27k 6.2k it Share Oo Empurpledprose 18h wrote ...</td>\n",
       "      <td>27k 6.2k it Share Oo Empurpledprose 18h wrote ...</td>\n",
       "      <td>[(enough, 1.0), (yellowknife, 0.66666666666666...</td>\n",
       "      <td>6.2k share empurpledprose wrote this elsewhere...</td>\n",
       "      <td>6.2k share empurpledprose wrote elsewhere thin...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>45</td>\n",
       "      <td>6 52 wi Fe 4 forums.nexusmods.com best arrows ...</td>\n",
       "      <td>[wi, fe, best, arrows, that, a, merchant, will...</td>\n",
       "      <td>268</td>\n",
       "      <td>[6 52 wi Fe 4 forums.nexusmods.com best arrows...</td>\n",
       "      <td>16</td>\n",
       "      <td>[wi, fe, best, arrows, merchant, offer, charac...</td>\n",
       "      <td>{'wi': 0.14285714285714285, 'fe': 0.1428571428...</td>\n",
       "      <td>{'wi': 0.14285714285714285, 'fe': 0.1428571428...</td>\n",
       "      <td>{'6 52 wi Fe 4 forums.nexusmods.com best arrow...</td>\n",
       "      <td>like using Shock damage Stamina damage enchant...</td>\n",
       "      <td>6 52 wi Fe 4 forums.nexusmods.com best arrows ...</td>\n",
       "      <td>6 52 wi Fe 4 forums.nexusmods.com best arrows ...</td>\n",
       "      <td>[(damage, 1.0), (arrows, 0.5714285714285714), ...</td>\n",
       "      <td>forums.nexusmods.com best arrows that merchant...</td>\n",
       "      <td>forums.nexusmods.com best arrows merchant offe...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>46</td>\n",
       "      <td>4128 8 it Share We UMNKINg ADOUL It ana e naQ ...</td>\n",
       "      <td>[it, share, we, umnking, adoul, it, ana, e, na...</td>\n",
       "      <td>211</td>\n",
       "      <td>[4128 8 it Share We UMNKINg ADOUL It ana e naQ...</td>\n",
       "      <td>8</td>\n",
       "      <td>[share, umnking, adoul, ana, e, naq, waslin, i...</td>\n",
       "      <td>{'share': 0.25, 'umnking': 0.25, 'adoul': 0.25...</td>\n",
       "      <td>{'share': 0.25, 'umnking': 0.25, 'adoul': 0.25...</td>\n",
       "      <td>{'4128 8 it Share We UMNKINg ADOUL It ana e na...</td>\n",
       "      <td>it ll help you keep track of what you break as...</td>\n",
       "      <td>4128 8 it Share We UMNKINg ADOUL It ana e naQ ...</td>\n",
       "      <td>4128 8 it Share We UMNKINg ADOUL It ana e naQ ...</td>\n",
       "      <td>[(make, 1.0), (problem, 0.75), (time, 0.5), (t...</td>\n",
       "      <td>4128 share umnking adoul waslin spiral into pr...</td>\n",
       "      <td>4128 share umnking adoul waslin spiral problem...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>47</td>\n",
       "      <td>124k J 49k it Share Oo 5 MORE REPLIES HonchoM...</td>\n",
       "      <td>[j, it, share, oo, more, replies, honchominerv...</td>\n",
       "      <td>155</td>\n",
       "      <td>[ 124k J 49k it Share Oo 5 MORE REPLIES Honcho...</td>\n",
       "      <td>8</td>\n",
       "      <td>[j, share, oo, replies, honchominerva, honchom...</td>\n",
       "      <td>{'j': 0.5, 'share': 0.25, 'oo': 0.25, 'replies...</td>\n",
       "      <td>{'j': 0.5, 'share': 0.25, 'oo': 0.25, 'replies...</td>\n",
       "      <td>{'The particularly interesting part is that it...</td>\n",
       "      <td>Over the past 200 years numerous chess masters...</td>\n",
       "      <td>124k J 49k it Share Oo 5 MORE REPLIES HonchoM...</td>\n",
       "      <td>124k J 49k it Share Oo 5 MORE REPLIES HonchoM...</td>\n",
       "      <td>[(alphazero, 1.0), (chess, 1.0), (replies, 0.7...</td>\n",
       "      <td>124k share more replies honchominerva honchomi...</td>\n",
       "      <td>124k share more replies honchominerva honchomi...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>48</td>\n",
       "      <td>Being a pet owner is like being a sugar daddy....</td>\n",
       "      <td>[being, a, pet, owner, is, like, being, a, sug...</td>\n",
       "      <td>89</td>\n",
       "      <td>[Being a pet owner is like being a sugar daddy...</td>\n",
       "      <td>5</td>\n",
       "      <td>[pet, owner, like, sugar, daddy, waste, money,...</td>\n",
       "      <td>{'pet': 0.5, 'owner': 0.5, 'like': 0.5, 'sugar...</td>\n",
       "      <td>{'pet': 0.5, 'owner': 0.5, 'like': 0.5, 'sugar...</td>\n",
       "      <td>{'Being a pet owner is like being a sugar dadd...</td>\n",
       "      <td>You waste all of your money on keeping them ha...</td>\n",
       "      <td>Being a pet owner is like being a sugar daddy....</td>\n",
       "      <td>Being a pet owner is like being a sugar daddy....</td>\n",
       "      <td>[(jack, 1.0), (pet, 0.5), (owner, 0.5), (like,...</td>\n",
       "      <td>being owner like being sugar daddy. waste your...</td>\n",
       "      <td>being owner like sugar daddy. waste money keep...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>49</td>\n",
       "      <td>Dana Schwartz DanaSchwartzzz BELLE There goes ...</td>\n",
       "      <td>[dana, schwartz, danaschwartzzz, belle, there,...</td>\n",
       "      <td>25</td>\n",
       "      <td>[Dana Schwartz DanaSchwartzzz BELLE There goes...</td>\n",
       "      <td>1</td>\n",
       "      <td>[dana, schwartz, danaschwartzzz, belle, goes, ...</td>\n",
       "      <td>{'dana': 0.5, 'schwartz': 0.5, 'danaschwartzzz...</td>\n",
       "      <td>{'dana': 0.5, 'schwartz': 0.5, 'danaschwartzzz...</td>\n",
       "      <td>{}</td>\n",
       "      <td></td>\n",
       "      <td>Dana Schwartz DanaSchwartzzz BELLE There goes ...</td>\n",
       "      <td>Dana Schwartz DanaSchwartzzz BELLE There goes ...</td>\n",
       "      <td>[(belle, 1.0), (goes, 1.0), (baker, 1.0), (dan...</td>\n",
       "      <td>dana schwartz danaschwartzzz belle there goes ...</td>\n",
       "      <td>dana schwartz danaschwartzzz belle there goes ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>50</td>\n",
       "      <td>7 42 all All inboxes N Parker from Interview C...</td>\n",
       "      <td>[all, all, inboxes, n, parker, from, interview...</td>\n",
       "      <td>159</td>\n",
       "      <td>[7 42 all All inboxes N Parker from Interview ...</td>\n",
       "      <td>6</td>\n",
       "      <td>[inboxes, n, parker, interview, cake, yesthisi...</td>\n",
       "      <td>{'inboxes': 0.2, 'n': 0.4, 'parker': 0.2, 'int...</td>\n",
       "      <td>{'inboxes': 0.2, 'n': 0.4, 'parker': 0.2, 'int...</td>\n",
       "      <td>{'So instead of storing each of those characte...</td>\n",
       "      <td>So instead of storing each of those characters...</td>\n",
       "      <td>7 42 all All inboxes N Parker from Interview C...</td>\n",
       "      <td>7 42 all All inboxes N Parker from Interview C...</td>\n",
       "      <td>[(stack, 1.0), (problem, 0.8), (week, 0.8), (i...</td>\n",
       "      <td>inboxes parker from interview cake 00pm yesthi...</td>\n",
       "      <td>inboxes parker interview cake 00pm yesthisiske...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>51</td>\n",
       "      <td>stupid bumps are that painful pus filled kinda...</td>\n",
       "      <td>[stupid, bumps, are, that, painful, pus, fille...</td>\n",
       "      <td>236</td>\n",
       "      <td>[stupid bumps are that painful pus filled kind...</td>\n",
       "      <td>13</td>\n",
       "      <td>[stupid, bumps, painful, pus, filled, kinda, l...</td>\n",
       "      <td>{'stupid': 0.2, 'bumps': 0.2, 'painful': 0.2, ...</td>\n",
       "      <td>{'stupid': 0.2, 'bumps': 0.2, 'painful': 0.2, ...</td>\n",
       "      <td>{'stupid bumps are that painful pus filled kin...</td>\n",
       "      <td>So searched about antiseptics agents on MRSA a...</td>\n",
       "      <td>stupid bumps are that painful pus filled kinda...</td>\n",
       "      <td>stupid bumps are that painful pus filled kinda...</td>\n",
       "      <td>[(mrsa, 1.0), (like, 0.6), (folliculitis, 0.6)...</td>\n",
       "      <td>stupid bumps that painful filled kinda like ac...</td>\n",
       "      <td>stupid bumps painful filled kinda like acne ye...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>52</td>\n",
       "      <td>spokesman.com 4 A. Jock itch is normally caus...</td>\n",
       "      <td>[jock, itch, is, normally, caused, by, a, fung...</td>\n",
       "      <td>107</td>\n",
       "      <td>[ spokesman.com 4 A. Jock itch is normally cau...</td>\n",
       "      <td>8</td>\n",
       "      <td>[jock, itch, normally, caused, fungal, infecti...</td>\n",
       "      <td>{'jock': 0.6666666666666666, 'itch': 0.6666666...</td>\n",
       "      <td>{'jock': 0.6666666666666666, 'itch': 0.6666666...</td>\n",
       "      <td>{' spokesman.com 4 A. Jock itch is normally ca...</td>\n",
       "      <td>You may want to alternate it with other OTC an...</td>\n",
       "      <td>spokesman.com 4 A. Jock itch is normally caus...</td>\n",
       "      <td>spokesman.com 4 A. Jock itch is normally caus...</td>\n",
       "      <td>[(contains, 1.0), (antifungal, 1.0), (jock, 0....</td>\n",
       "      <td>spokesman.com jock itch normally caused fungal...</td>\n",
       "      <td>spokesman.com jock itch normally caused fungal...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>53</td>\n",
       "      <td>10 21 Mail ef jobs.capitalgroup.com Date Oct 1...</td>\n",
       "      <td>[mail, ef, date, oct, location, los, angeles, ...</td>\n",
       "      <td>182</td>\n",
       "      <td>[10 21 Mail ef jobs.capitalgroup.com Date Oct ...</td>\n",
       "      <td>5</td>\n",
       "      <td>[mail, ef, date, oct, location, los, angeles, ...</td>\n",
       "      <td>{'mail': 0.125, 'ef': 0.125, 'date': 0.25, 'oc...</td>\n",
       "      <td>{'mail': 0.125, 'ef': 0.125, 'date': 0.25, 'oc...</td>\n",
       "      <td>{'All investment group associates are expected...</td>\n",
       "      <td>A hallmark of Capital s philosophy is an overr...</td>\n",
       "      <td>10 21 Mail ef jobs.capitalgroup.com Date Oct 1...</td>\n",
       "      <td>10 21 Mail ef jobs.capitalgroup.com Date Oct 1...</td>\n",
       "      <td>[(capital, 1.0), (group, 0.875), (solutions, 0...</td>\n",
       "      <td>mail jobs.capitalgroup.com date 2019 location ...</td>\n",
       "      <td>mail jobs.capitalgroup.com date 2019 location ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>54</td>\n",
       "      <td>47g Mo it Share Oo VULTESIUPIILVIAVII CII Step...</td>\n",
       "      <td>[mo, it, share, oo, vultesiupiilviavii, cii, s...</td>\n",
       "      <td>234</td>\n",
       "      <td>[47g Mo it Share Oo VULTESIUPIILVIAVII CII Ste...</td>\n",
       "      <td>11</td>\n",
       "      <td>[mo, share, oo, vultesiupiilviavii, cii, steph...</td>\n",
       "      <td>{'mo': 0.25, 'share': 0.25, 'oo': 0.25, 'vulte...</td>\n",
       "      <td>{'mo': 0.25, 'share': 0.25, 'oo': 0.25, 'vulte...</td>\n",
       "      <td>{'47g Mo it Share Oo VULTESIUPIILVIAVII CII St...</td>\n",
       "      <td>took Stephen Grider s modern react redux 2019 ...</td>\n",
       "      <td>47g Mo it Share Oo VULTESIUPIILVIAVII CII Step...</td>\n",
       "      <td>47g Mo it Share Oo VULTESIUPIILVIAVII CII Step...</td>\n",
       "      <td>[(react, 1.0), (took, 0.75), (way, 0.75), (end...</td>\n",
       "      <td>share vultesiupiilviavii stephen grider been p...</td>\n",
       "      <td>share vultesiupiilviavii stephen grider profes...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>55</td>\n",
       "      <td>a couple of scenes later when Mr. Robot is wea...</td>\n",
       "      <td>[a, couple, of, scenes, later, when, mr, robot...</td>\n",
       "      <td>241</td>\n",
       "      <td>[a couple of scenes later when Mr., Robot is w...</td>\n",
       "      <td>10</td>\n",
       "      <td>[couple, scenes, later, mr, robot, wearing, sc...</td>\n",
       "      <td>{'couple': 0.2, 'scenes': 0.2, 'later': 0.2, '...</td>\n",
       "      <td>{'couple': 0.2, 'scenes': 0.2, 'later': 0.2, '...</td>\n",
       "      <td>{'a couple of scenes later when Mr.': 0.8, 'Ro...</td>\n",
       "      <td>TL DR You re not elliot you re the alter think...</td>\n",
       "      <td>a couple of scenes later when Mr. Robot is wea...</td>\n",
       "      <td>a couple of scenes later when Mr. Robot is wea...</td>\n",
       "      <td>[(think, 1.0), (actually, 0.8), (elliot, 0.6),...</td>\n",
       "      <td>couple scenes later when robot wearing scarf p...</td>\n",
       "      <td>couple scenes later robot wearing scarf protec...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>56</td>\n",
       "      <td>27k 6.2k it Share Oo Tell Rachel said Hi. o 9 ...</td>\n",
       "      <td>[it, share, oo, tell, rachel, said, hi, o, mor...</td>\n",
       "      <td>153</td>\n",
       "      <td>[27k 6.2k it Share Oo Tell Rachel said Hi., o ...</td>\n",
       "      <td>9</td>\n",
       "      <td>[share, oo, tell, rachel, said, hi, replies, r...</td>\n",
       "      <td>{'share': 0.3333333333333333, 'oo': 0.33333333...</td>\n",
       "      <td>{'share': 0.3333333333333333, 'oo': 0.33333333...</td>\n",
       "      <td>{'27k 6.2k it Share Oo Tell Rachel said Hi.': ...</td>\n",
       "      <td>Oh and didja know Arsenic is extremely water s...</td>\n",
       "      <td>27k 6.2k it Share Oo Tell Rachel said Hi. o 9 ...</td>\n",
       "      <td>27k 6.2k it Share Oo Tell Rachel said Hi. o 9 ...</td>\n",
       "      <td>[(enough, 1.0), (replies, 0.6666666666666666),...</td>\n",
       "      <td>6.2k share tell rachel said 3324 more replies ...</td>\n",
       "      <td>6.2k share tell rachel said 3324 more replies ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>57</td>\n",
       "      <td>10 01 WF 4 google.com Google deacon fallout 4 ...</td>\n",
       "      <td>[wf, google, deacon, fallout, voice, actor, x,...</td>\n",
       "      <td>48</td>\n",
       "      <td>[10 01 WF 4 google.com Google deacon fallout 4...</td>\n",
       "      <td>2</td>\n",
       "      <td>[wf, google, deacon, fallout, voice, actor, x,...</td>\n",
       "      <td>{'wf': 0.25, 'google': 0.25, 'deacon': 0.5, 'f...</td>\n",
       "      <td>{'wf': 0.25, 'google': 0.25, 'deacon': 0.5, 'f...</td>\n",
       "      <td>{'Fandom fallout wiki Ryan Al... Ryan Alosio F...</td>\n",
       "      <td>Fandom fallout wiki Ryan Al... Ryan Alosio Fal...</td>\n",
       "      <td>10 01 WF 4 google.com Google deacon fallout 4 ...</td>\n",
       "      <td>10 01 WF 4 google.com Google deacon fallout 4 ...</td>\n",
       "      <td>[(fallout, 1.0), (ryan, 1.0), (alosio, 0.75), ...</td>\n",
       "      <td>google.com google deacon fallout voice actor n...</td>\n",
       "      <td>google.com google deacon fallout voice actor n...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                    0  \\\n",
       "0    iS 11 23 1 Q Search If shine a white LED ligh...   \n",
       "1   6 51 . 0 forums.nexusmods.com ee BrettM fosaym...   \n",
       "2   6 52 al Se forums.nexusmods.com 17 Apr 2012 St...   \n",
       "3   4 06 aw Fe spokesman.com 4 ILULL. LL 1S SUUULI...   \n",
       "4   Parents do not own their children. No one owns...   \n",
       "5   o changed shampoos cut out dairy litres of wat...   \n",
       "6   WEIS 2P 40p o2ua8 yp i deyiaao SpJ0M Jo 3eq su...   \n",
       "7   casispie hugealienpie thechubbynerd just showe...   \n",
       "8   527k J 173k it Share Oo elfmere 16h Why do you...   \n",
       "9   6 55 at google.com h Google strange women lyin...   \n",
       "10  1 51 Mail glassdoor.com as GitHub Policy Detai...   \n",
       "11   fantasywriters u SlinkySlang 3h Writing advic...   \n",
       "12  10 21 wil Mail jobs.capitalgroup.com Responsib...   \n",
       "13  177k 3.9k it Share Oo GalacticPingvin 3h lemla...   \n",
       "14  a. Ricky Montgomery am upset with my parents f...   \n",
       "15  ig nyx5 i prefer guys who make small dick joke...   \n",
       "16  427 27 it Share Oo mrtrouble22 4h Believer i r...   \n",
       "17  6 52 al Se forums.nexusmods.com 4 as Soon as y...   \n",
       "18  11 54 a eG sciencedaily.com The medical commun...   \n",
       "19   lore 54352452524 deactivated201 you can reple...   \n",
       "20  4128 8 it Share We Datadevourer 3h Recently st...   \n",
       "21   53.2k 176k it Share o PyroSnakel41 13h Become...   \n",
       "22  r nosurf u fibonacciseries 9d Turning on the G...   \n",
       "23   Vote J 10 it Share Oo it2051229 36m In the be...   \n",
       "24  4 50 Q Search News Home Popular 20k J 15 it Sh...   \n",
       "25  e205 16 it Share o iseemath 18h think you ll f...   \n",
       "26   124k J 49k it Share Oo Go 234 15 MORE REPLIES...   \n",
       "27   124k J 49k it Share Oo 10 MORE REPLIES sudden...   \n",
       "28  2 07 al a 2 Messages Back Front Back NV I m no...   \n",
       "29  527k J 173k it Share Oo Q Reply 56k H insertca...   \n",
       "30   124k J 49k it Share Oo 2 MORE REPLIES 1 MORE ...   \n",
       "31  f r stopdrinking u creaturefeaturel6 10h 689 d...   \n",
       "32  6 51 al Se forums.nexusmods.com 4 ToniPrufrock...   \n",
       "33  12 40 1 Fe ice comftort ae iY wsyusuallyjread ...   \n",
       "34  8 00 wl LTE google.com hy It was October 28 19...   \n",
       "35  86k 3.5k it Share Oo MrBOOMbabdtlc 7h flinty d...   \n",
       "36  21k J 2.1k it Share Oo Ww DOO VYUNINIENISO WwW...   \n",
       "37  4 147k J 314 it Share Oo mikevago 4h One of my...   \n",
       "38  631 4 59 it Share Oo PublicFigurex 28d It s fr...   \n",
       "39  r EatCheapAndHealthy u chickentender1995 12h B...   \n",
       "40  423 M6 it Share Oo specific or more detailed w...   \n",
       "41  9 01 li LTE 4 Clock Q Search ED SJ o Atwater V...   \n",
       "42  What is the most a dollar has ever gotten you ...   \n",
       "43  2 48 at O Ali Ho 8 Today 10 40 AM Recommendati...   \n",
       "44  27k 6.2k it Share Oo Empurpledprose 18h wrote ...   \n",
       "45  6 52 wi Fe 4 forums.nexusmods.com best arrows ...   \n",
       "46  4128 8 it Share We UMNKINg ADOUL It ana e naQ ...   \n",
       "47   124k J 49k it Share Oo 5 MORE REPLIES HonchoM...   \n",
       "48  Being a pet owner is like being a sugar daddy....   \n",
       "49  Dana Schwartz DanaSchwartzzz BELLE There goes ...   \n",
       "50  7 42 all All inboxes N Parker from Interview C...   \n",
       "51  stupid bumps are that painful pus filled kinda...   \n",
       "52   spokesman.com 4 A. Jock itch is normally caus...   \n",
       "53  10 21 Mail ef jobs.capitalgroup.com Date Oct 1...   \n",
       "54  47g Mo it Share Oo VULTESIUPIILVIAVII CII Step...   \n",
       "55  a couple of scenes later when Mr. Robot is wea...   \n",
       "56  27k 6.2k it Share Oo Tell Rachel said Hi. o 9 ...   \n",
       "57  10 01 WF 4 google.com Google deacon fallout 4 ...   \n",
       "\n",
       "                                               tokens  num_tokens  \\\n",
       "0   [is, q, search, if, shine, a, white, led, ligh...         135   \n",
       "1   [ee, brettm, fosaym, apr, stealth, archery, wo...         340   \n",
       "2   [al, se, apr, stealth, archery, works, great, ...         345   \n",
       "3   [aw, fe, ilull, ll, suuuliiis, aalllu, culilal...         121   \n",
       "4   [parents, do, not, own, their, children, no, o...         315   \n",
       "5   [o, changed, shampoos, cut, out, dairy, litres...         236   \n",
       "6   [weis, yp, i, deyiaao, jo, suunseayy, z, e, ae...         183   \n",
       "7   [casispie, hugealienpie, thechubbynerd, just, ...          70   \n",
       "8   [j, it, share, oo, elfmere, why, do, you, work...         241   \n",
       "9   [at, h, google, strange, women, lying, in, pon...          50   \n",
       "10  [mail, as, github, policy, details, we, encour...         126   \n",
       "11  [fantasywriters, u, slinkyslang, writing, advi...         172   \n",
       "12  [wil, mail, responsibilities, work, in, a, tea...         204   \n",
       "13  [it, share, oo, galacticpingvin, lemlang, atli...         158   \n",
       "14  [ricky, montgomery, am, upset, with, my, paren...          33   \n",
       "15  [ig, i, prefer, guys, who, make, small, dick, ...          39   \n",
       "16  [it, share, oo, believer, i, read, one, story,...         166   \n",
       "17  [al, se, as, soon, as, you, dismount, and, use...         301   \n",
       "18  [a, eg, the, medical, community, used, to, thi...         273   \n",
       "19  [lore, you, can, replenish, your, health, by, ...          67   \n",
       "20  [it, share, we, datadevourer, recently, starte...         240   \n",
       "21  [it, share, o, become, a, politician, and, rai...         165   \n",
       "22  [r, nosurf, u, fibonacciseries, turning, on, t...         203   \n",
       "23  [vote, j, it, share, oo, in, the, beginning, t...         220   \n",
       "24  [q, search, news, home, popular, j, it, share,...          55   \n",
       "25  [it, share, o, iseemath, think, you, ll, find,...         177   \n",
       "26  [j, it, share, oo, go, more, replies, honchomi...         100   \n",
       "27  [j, it, share, oo, more, replies, suddenly, sa...         110   \n",
       "28  [al, a, messages, back, front, back, nv, i, m,...         160   \n",
       "29  [j, it, share, oo, q, reply, h, insertcaffeine...         161   \n",
       "30  [j, it, share, oo, more, replies, more, reply,...         156   \n",
       "31  [f, r, stopdrinking, u, days, a, very, sad, te...         244   \n",
       "32  [al, se, toniprufrock, apr, so, was, getting, ...         255   \n",
       "33  [fe, ice, comftort, ae, iy, wsyusuallyjread, a...          31   \n",
       "34  [wl, lte, hy, it, was, october, his, third, bi...         125   \n",
       "35  [it, share, oo, mrboombabdtlc, flinty, day, of...         145   \n",
       "36  [j, it, share, oo, ww, doo, vyuninieniso, www,...          94   \n",
       "37  [j, it, share, oo, mikevago, one, of, my, favo...         179   \n",
       "38  [it, share, oo, publicfigurex, it, s, fried, r...         214   \n",
       "39  [r, eatcheapandhealthy, u, best, tips, have, f...         229   \n",
       "40  [it, share, oo, specific, or, more, detailed, ...         195   \n",
       "41  [li, lte, clock, q, search, ed, sj, o, atwater...         200   \n",
       "42  [what, is, the, most, a, dollar, has, ever, go...         203   \n",
       "43  [at, o, ali, ho, today, am, recommendations, a...         102   \n",
       "44  [it, share, oo, empurpledprose, wrote, this, e...         193   \n",
       "45  [wi, fe, best, arrows, that, a, merchant, will...         268   \n",
       "46  [it, share, we, umnking, adoul, it, ana, e, na...         211   \n",
       "47  [j, it, share, oo, more, replies, honchominerv...         155   \n",
       "48  [being, a, pet, owner, is, like, being, a, sug...          89   \n",
       "49  [dana, schwartz, danaschwartzzz, belle, there,...          25   \n",
       "50  [all, all, inboxes, n, parker, from, interview...         159   \n",
       "51  [stupid, bumps, are, that, painful, pus, fille...         236   \n",
       "52  [jock, itch, is, normally, caused, by, a, fung...         107   \n",
       "53  [mail, ef, date, oct, location, los, angeles, ...         182   \n",
       "54  [mo, it, share, oo, vultesiupiilviavii, cii, s...         234   \n",
       "55  [a, couple, of, scenes, later, when, mr, robot...         241   \n",
       "56  [it, share, oo, tell, rachel, said, hi, o, mor...         153   \n",
       "57  [wf, google, deacon, fallout, voice, actor, x,...          48   \n",
       "\n",
       "                                            sentences  num_sentences  \\\n",
       "0   [ iS 11 23 1 Q Search If shine a white LED lig...              2   \n",
       "1   [6 51 ., 0 forums.nexusmods.com ee BrettM fosa...             16   \n",
       "2   [6 52 al Se forums.nexusmods.com 17 Apr 2012 S...             15   \n",
       "3   [4 06 aw Fe spokesman.com 4 ILULL., LL 1S SUUU...             10   \n",
       "4   [Parents do not own their children., No one ow...             14   \n",
       "5   [o changed shampoos cut out dairy litres of wa...             12   \n",
       "6   [WEIS 2P 40p o2ua8 yp i deyiaao SpJ0M Jo 3eq s...              1   \n",
       "7   [casispie hugealienpie thechubbynerd just show...              7   \n",
       "8   [527k J 173k it Share Oo elfmere 16h Why do yo...             11   \n",
       "9   [6 55 at google.com h Google strange women lyi...              2   \n",
       "10  [1 51 Mail glassdoor.com as GitHub Policy Deta...              6   \n",
       "11  [ fantasywriters u SlinkySlang 3h Writing advi...             11   \n",
       "12  [10 21 wil Mail jobs.capitalgroup.com Responsi...              5   \n",
       "13  [177k 3.9k it Share Oo GalacticPingvin 3h leml...             10   \n",
       "14  [a. Ricky Montgomery am upset with my parents ...              2   \n",
       "15  [ig nyx5 i prefer guys who make small dick jok...              1   \n",
       "16  [427 27 it Share Oo mrtrouble22 4h Believer i ...             10   \n",
       "17  [6 52 al Se forums.nexusmods.com 4 as Soon as ...             14   \n",
       "18  [11 54 a eG sciencedaily.com The medical commu...             10   \n",
       "19  [ lore 54352452524 deactivated201 you can repl...              1   \n",
       "20  [4128 8 it Share We Datadevourer 3h Recently s...             10   \n",
       "21  [ 53.2k 176k it Share o PyroSnakel41 13h Becom...              8   \n",
       "22  [r nosurf u fibonacciseries 9d Turning on the ...             10   \n",
       "23  [ Vote J 10 it Share Oo it2051229 36m In the b...             12   \n",
       "24  [4 50 Q Search News Home Popular 20k J 15 it S...              2   \n",
       "25  [e205 16 it Share o iseemath 18h think you ll ...              9   \n",
       "26  [ 124k J 49k it Share Oo Go 234 15 MORE REPLIE...              6   \n",
       "27  [ 124k J 49k it Share Oo 10 MORE REPLIES sudde...              7   \n",
       "28  [2 07 al a 2 Messages Back Front Back NV I m n...              7   \n",
       "29  [527k J 173k it Share Oo Q Reply 56k H insertc...             10   \n",
       "30  [ 124k J 49k it Share Oo 2 MORE REPLIES 1 MORE...              8   \n",
       "31  [f r stopdrinking u creaturefeaturel6 10h 689 ...             19   \n",
       "32  [6 51 al Se forums.nexusmods.com 4 ToniPrufroc...             12   \n",
       "33  [12 40 1 Fe ice comftort ae iY wsyusuallyjread...              4   \n",
       "34  [8 00 wl LTE google.com hy It was October 28 1...              6   \n",
       "35  [86k 3.5k it Share Oo MrBOOMbabdtlc 7h flinty ...              8   \n",
       "36  [21k J 2.1k it Share Oo Ww DOO VYUNINIENISO Ww...              7   \n",
       "37  [4 147k J 314 it Share Oo mikevago 4h One of m...              9   \n",
       "38  [631 4 59 it Share Oo PublicFigurex 28d It s f...             15   \n",
       "39  [r EatCheapAndHealthy u chickentender1995 12h ...             14   \n",
       "40  [423 M6 it Share Oo specific or more detailed ...              9   \n",
       "41  [9 01 li LTE 4 Clock Q Search ED SJ o Atwater ...             13   \n",
       "42  [What is the most a dollar has ever gotten you...             16   \n",
       "43  [2 48 at O Ali Ho 8 Today 10 40 AM Recommendat...              5   \n",
       "44  [27k 6.2k it Share Oo Empurpledprose 18h wrote...              9   \n",
       "45  [6 52 wi Fe 4 forums.nexusmods.com best arrows...             16   \n",
       "46  [4128 8 it Share We UMNKINg ADOUL It ana e naQ...              8   \n",
       "47  [ 124k J 49k it Share Oo 5 MORE REPLIES Honcho...              8   \n",
       "48  [Being a pet owner is like being a sugar daddy...              5   \n",
       "49  [Dana Schwartz DanaSchwartzzz BELLE There goes...              1   \n",
       "50  [7 42 all All inboxes N Parker from Interview ...              6   \n",
       "51  [stupid bumps are that painful pus filled kind...             13   \n",
       "52  [ spokesman.com 4 A. Jock itch is normally cau...              8   \n",
       "53  [10 21 Mail ef jobs.capitalgroup.com Date Oct ...              5   \n",
       "54  [47g Mo it Share Oo VULTESIUPIILVIAVII CII Ste...             11   \n",
       "55  [a couple of scenes later when Mr., Robot is w...             10   \n",
       "56  [27k 6.2k it Share Oo Tell Rachel said Hi., o ...              9   \n",
       "57  [10 01 WF 4 google.com Google deacon fallout 4...              2   \n",
       "\n",
       "                                                no_sw  \\\n",
       "0   [q, search, shine, white, led, light, prism, w...   \n",
       "1   [ee, brettm, fosaym, apr, stealth, archery, wo...   \n",
       "2   [al, se, apr, stealth, archery, works, great, ...   \n",
       "3   [aw, fe, ilull, suuuliiis, aalllu, culilallis,...   \n",
       "4   [parents, children, one, owns, anything, loan,...   \n",
       "5   [changed, shampoos, cut, dairy, litres, water,...   \n",
       "6   [weis, yp, deyiaao, jo, suunseayy, z, e, aeazz...   \n",
       "7   [casispie, hugealienpie, thechubbynerd, shower...   \n",
       "8   [j, share, oo, elfmere, work, factory, honors,...   \n",
       "9   [h, google, strange, women, lying, ponds, dist...   \n",
       "10  [mail, github, policy, details, encourage, hub...   \n",
       "11  [fantasywriters, u, slinkyslang, writing, advi...   \n",
       "12  [wil, mail, responsibilities, work, team, anal...   \n",
       "13  [share, oo, galacticpingvin, lemlang, atlienk,...   \n",
       "14  [ricky, montgomery, upset, parents, making, ex...   \n",
       "15  [ig, prefer, guys, make, small, dick, jokes, g...   \n",
       "16  [share, oo, believer, read, one, story, woman,...   \n",
       "17  [al, se, soon, dismount, use, key, wait, tor, ...   \n",
       "18  [eg, medical, community, used, think, obesity,...   \n",
       "19  [lore, replenish, health, drinking, water, bre...   \n",
       "20  [share, datadevourer, recently, started, using...   \n",
       "21  [share, become, politician, raise, pay, creati...   \n",
       "22  [r, nosurf, u, fibonacciseries, turning, greys...   \n",
       "23  [vote, j, share, oo, beginning, thing, compute...   \n",
       "24  [q, search, news, home, popular, j, share, r, ...   \n",
       "25  [share, iseemath, think, find, princeton, comp...   \n",
       "26  [j, share, oo, go, replies, honchominerva, cj,...   \n",
       "27  [j, share, oo, replies, suddenly, satire, augu...   \n",
       "28  [al, messages, back, front, back, nv, home, ri...   \n",
       "29  [j, share, oo, q, reply, h, insertcaffeine, qu...   \n",
       "30  [j, share, oo, replies, reply, replies, honcho...   \n",
       "31  [f, r, stopdrinking, u, days, sad, text, messa...   \n",
       "32  [al, se, toniprufrock, apr, getting, little, b...   \n",
       "33  [fe, ice, comftort, ae, iy, wsyusuallyjread, c...   \n",
       "34  [wl, lte, hy, october, third, birthday, phoeni...   \n",
       "35  [share, oo, mrboombabdtlc, flinty, day, lovesm...   \n",
       "36  [j, share, oo, ww, doo, vyuninieniso, www, fuc...   \n",
       "37  [j, share, oo, mikevago, one, favorite, things...   \n",
       "38  [share, oo, publicfigurex, fried, rice, kinda,...   \n",
       "39  [r, eatcheapandhealthy, u, best, tips, eating,...   \n",
       "40  [share, oo, specific, detailed, probably, talk...   \n",
       "41  [li, lte, clock, q, search, ed, sj, atwater, v...   \n",
       "42  [dollar, ever, gotten, eeae, tldr, wife, three...   \n",
       "43  [ali, ho, today, recommendations, ask, recomme...   \n",
       "44  [share, oo, empurpledprose, wrote, elsewhere, ...   \n",
       "45  [wi, fe, best, arrows, merchant, offer, charac...   \n",
       "46  [share, umnking, adoul, ana, e, naq, waslin, i...   \n",
       "47  [j, share, oo, replies, honchominerva, honchom...   \n",
       "48  [pet, owner, like, sugar, daddy, waste, money,...   \n",
       "49  [dana, schwartz, danaschwartzzz, belle, goes, ...   \n",
       "50  [inboxes, n, parker, interview, cake, yesthisi...   \n",
       "51  [stupid, bumps, painful, pus, filled, kinda, l...   \n",
       "52  [jock, itch, normally, caused, fungal, infecti...   \n",
       "53  [mail, ef, date, oct, location, los, angeles, ...   \n",
       "54  [mo, share, oo, vultesiupiilviavii, cii, steph...   \n",
       "55  [couple, scenes, later, mr, robot, wearing, sc...   \n",
       "56  [share, oo, tell, rachel, said, hi, replies, r...   \n",
       "57  [wf, google, deacon, fallout, voice, actor, x,...   \n",
       "\n",
       "                                            freq_dist  \\\n",
       "0   {'q': 0.25, 'search': 0.25, 'shine': 0.75, 'wh...   \n",
       "1   {'ee': 0.25, 'brettm': 0.25, 'fosaym': 0.25, '...   \n",
       "2   {'al': 0.25, 'se': 0.25, 'apr': 0.25, 'stealth...   \n",
       "3   {'aw': 0.3333333333333333, 'fe': 0.33333333333...   \n",
       "4   {'parents': 0.7142857142857143, 'children': 0....   \n",
       "5   {'changed': 0.2, 'shampoos': 0.2, 'cut': 0.4, ...   \n",
       "6   {'weis': 0.2, 'yp': 0.2, 'deyiaao': 0.2, 'jo':...   \n",
       "7   {'casispie': 0.5, 'hugealienpie': 0.5, 'thechu...   \n",
       "8   {'j': 0.5, 'share': 0.25, 'oo': 0.25, 'elfmere...   \n",
       "9   {'h': 0.25, 'google': 0.25, 'strange': 1.0, 'w...   \n",
       "10  {'mail': 0.2, 'github': 0.4, 'policy': 0.2, 'd...   \n",
       "11  {'fantasywriters': 0.2, 'u': 0.2, 'slinkyslang...   \n",
       "12  {'wil': 0.125, 'mail': 0.125, 'responsibilitie...   \n",
       "13  {'share': 0.3333333333333333, 'oo': 0.33333333...   \n",
       "14  {'ricky': 1.0, 'montgomery': 1.0, 'upset': 1.0...   \n",
       "15  {'ig': 0.3333333333333333, 'prefer': 0.3333333...   \n",
       "16  {'share': 0.5, 'oo': 0.5, 'believer': 0.5, 're...   \n",
       "17  {'al': 0.2, 'se': 0.2, 'soon': 0.2, 'dismount'...   \n",
       "18  {'eg': 0.14285714285714285, 'medical': 0.14285...   \n",
       "19  {'lore': 0.5, 'replenish': 0.5, 'health': 1.0,...   \n",
       "20  {'share': 0.125, 'datadevourer': 0.125, 'recen...   \n",
       "21  {'share': 0.25, 'become': 0.25, 'politician': ...   \n",
       "22  {'r': 0.125, 'nosurf': 0.125, 'u': 0.125, 'fib...   \n",
       "23  {'vote': 0.3333333333333333, 'j': 0.3333333333...   \n",
       "24  {'q': 0.5, 'search': 0.5, 'news': 0.5, 'home':...   \n",
       "25  {'share': 0.25, 'iseemath': 0.25, 'think': 0.2...   \n",
       "26  {'j': 0.5, 'share': 0.25, 'oo': 0.25, 'go': 0....   \n",
       "27  {'j': 0.3333333333333333, 'share': 0.333333333...   \n",
       "28  {'al': 0.25, 'messages': 0.25, 'back': 1.0, 'f...   \n",
       "29  {'j': 0.6666666666666666, 'share': 0.333333333...   \n",
       "30  {'j': 0.5, 'share': 0.25, 'oo': 0.25, 'replies...   \n",
       "31  {'f': 0.3333333333333333, 'r': 0.3333333333333...   \n",
       "32  {'al': 0.3333333333333333, 'se': 0.33333333333...   \n",
       "33  {'fe': 0.5, 'ice': 0.5, 'comftort': 0.5, 'ae':...   \n",
       "34  {'wl': 0.3333333333333333, 'lte': 0.3333333333...   \n",
       "35  {'share': 0.3333333333333333, 'oo': 0.33333333...   \n",
       "36  {'j': 0.25, 'share': 0.25, 'oo': 0.25, 'ww': 0...   \n",
       "37  {'j': 0.25, 'share': 0.25, 'oo': 0.25, 'mikeva...   \n",
       "38  {'share': 0.16666666666666666, 'oo': 0.1666666...   \n",
       "39  {'r': 0.25, 'eatcheapandhealthy': 0.25, 'u': 0...   \n",
       "40  {'share': 0.2, 'oo': 0.4, 'specific': 0.2, 'de...   \n",
       "41  {'li': 0.16666666666666666, 'lte': 0.166666666...   \n",
       "42  {'dollar': 1.0, 'ever': 0.2, 'gotten': 0.2, 'e...   \n",
       "43  {'ali': 1.0, 'ho': 0.25, 'today': 0.5, 'recomm...   \n",
       "44  {'share': 0.3333333333333333, 'oo': 0.33333333...   \n",
       "45  {'wi': 0.14285714285714285, 'fe': 0.1428571428...   \n",
       "46  {'share': 0.25, 'umnking': 0.25, 'adoul': 0.25...   \n",
       "47  {'j': 0.5, 'share': 0.25, 'oo': 0.25, 'replies...   \n",
       "48  {'pet': 0.5, 'owner': 0.5, 'like': 0.5, 'sugar...   \n",
       "49  {'dana': 0.5, 'schwartz': 0.5, 'danaschwartzzz...   \n",
       "50  {'inboxes': 0.2, 'n': 0.4, 'parker': 0.2, 'int...   \n",
       "51  {'stupid': 0.2, 'bumps': 0.2, 'painful': 0.2, ...   \n",
       "52  {'jock': 0.6666666666666666, 'itch': 0.6666666...   \n",
       "53  {'mail': 0.125, 'ef': 0.125, 'date': 0.25, 'oc...   \n",
       "54  {'mo': 0.25, 'share': 0.25, 'oo': 0.25, 'vulte...   \n",
       "55  {'couple': 0.2, 'scenes': 0.2, 'later': 0.2, '...   \n",
       "56  {'share': 0.3333333333333333, 'oo': 0.33333333...   \n",
       "57  {'wf': 0.25, 'google': 0.25, 'deacon': 0.5, 'f...   \n",
       "\n",
       "                                   weighted_freq_dist  \\\n",
       "0   {'q': 0.25, 'search': 0.25, 'shine': 0.75, 'wh...   \n",
       "1   {'ee': 0.25, 'brettm': 0.25, 'fosaym': 0.25, '...   \n",
       "2   {'al': 0.25, 'se': 0.25, 'apr': 0.25, 'stealth...   \n",
       "3   {'aw': 0.3333333333333333, 'fe': 0.33333333333...   \n",
       "4   {'parents': 0.7142857142857143, 'children': 0....   \n",
       "5   {'changed': 0.2, 'shampoos': 0.2, 'cut': 0.4, ...   \n",
       "6   {'weis': 0.2, 'yp': 0.2, 'deyiaao': 0.2, 'jo':...   \n",
       "7   {'casispie': 0.5, 'hugealienpie': 0.5, 'thechu...   \n",
       "8   {'j': 0.5, 'share': 0.25, 'oo': 0.25, 'elfmere...   \n",
       "9   {'h': 0.25, 'google': 0.25, 'strange': 1.0, 'w...   \n",
       "10  {'mail': 0.2, 'github': 0.4, 'policy': 0.2, 'd...   \n",
       "11  {'fantasywriters': 0.2, 'u': 0.2, 'slinkyslang...   \n",
       "12  {'wil': 0.125, 'mail': 0.125, 'responsibilitie...   \n",
       "13  {'share': 0.3333333333333333, 'oo': 0.33333333...   \n",
       "14  {'ricky': 1.0, 'montgomery': 1.0, 'upset': 1.0...   \n",
       "15  {'ig': 0.3333333333333333, 'prefer': 0.3333333...   \n",
       "16  {'share': 0.5, 'oo': 0.5, 'believer': 0.5, 're...   \n",
       "17  {'al': 0.2, 'se': 0.2, 'soon': 0.2, 'dismount'...   \n",
       "18  {'eg': 0.14285714285714285, 'medical': 0.14285...   \n",
       "19  {'lore': 0.5, 'replenish': 0.5, 'health': 1.0,...   \n",
       "20  {'share': 0.125, 'datadevourer': 0.125, 'recen...   \n",
       "21  {'share': 0.25, 'become': 0.25, 'politician': ...   \n",
       "22  {'r': 0.125, 'nosurf': 0.125, 'u': 0.125, 'fib...   \n",
       "23  {'vote': 0.3333333333333333, 'j': 0.3333333333...   \n",
       "24  {'q': 0.5, 'search': 0.5, 'news': 0.5, 'home':...   \n",
       "25  {'share': 0.25, 'iseemath': 0.25, 'think': 0.2...   \n",
       "26  {'j': 0.5, 'share': 0.25, 'oo': 0.25, 'go': 0....   \n",
       "27  {'j': 0.3333333333333333, 'share': 0.333333333...   \n",
       "28  {'al': 0.25, 'messages': 0.25, 'back': 1.0, 'f...   \n",
       "29  {'j': 0.6666666666666666, 'share': 0.333333333...   \n",
       "30  {'j': 0.5, 'share': 0.25, 'oo': 0.25, 'replies...   \n",
       "31  {'f': 0.3333333333333333, 'r': 0.3333333333333...   \n",
       "32  {'al': 0.3333333333333333, 'se': 0.33333333333...   \n",
       "33  {'fe': 0.5, 'ice': 0.5, 'comftort': 0.5, 'ae':...   \n",
       "34  {'wl': 0.3333333333333333, 'lte': 0.3333333333...   \n",
       "35  {'share': 0.3333333333333333, 'oo': 0.33333333...   \n",
       "36  {'j': 0.25, 'share': 0.25, 'oo': 0.25, 'ww': 0...   \n",
       "37  {'j': 0.25, 'share': 0.25, 'oo': 0.25, 'mikeva...   \n",
       "38  {'share': 0.16666666666666666, 'oo': 0.1666666...   \n",
       "39  {'r': 0.25, 'eatcheapandhealthy': 0.25, 'u': 0...   \n",
       "40  {'share': 0.2, 'oo': 0.4, 'specific': 0.2, 'de...   \n",
       "41  {'li': 0.16666666666666666, 'lte': 0.166666666...   \n",
       "42  {'dollar': 1.0, 'ever': 0.2, 'gotten': 0.2, 'e...   \n",
       "43  {'ali': 1.0, 'ho': 0.25, 'today': 0.5, 'recomm...   \n",
       "44  {'share': 0.3333333333333333, 'oo': 0.33333333...   \n",
       "45  {'wi': 0.14285714285714285, 'fe': 0.1428571428...   \n",
       "46  {'share': 0.25, 'umnking': 0.25, 'adoul': 0.25...   \n",
       "47  {'j': 0.5, 'share': 0.25, 'oo': 0.25, 'replies...   \n",
       "48  {'pet': 0.5, 'owner': 0.5, 'like': 0.5, 'sugar...   \n",
       "49  {'dana': 0.5, 'schwartz': 0.5, 'danaschwartzzz...   \n",
       "50  {'inboxes': 0.2, 'n': 0.4, 'parker': 0.2, 'int...   \n",
       "51  {'stupid': 0.2, 'bumps': 0.2, 'painful': 0.2, ...   \n",
       "52  {'jock': 0.6666666666666666, 'itch': 0.6666666...   \n",
       "53  {'mail': 0.125, 'ef': 0.125, 'date': 0.25, 'oc...   \n",
       "54  {'mo': 0.25, 'share': 0.25, 'oo': 0.25, 'vulte...   \n",
       "55  {'couple': 0.2, 'scenes': 0.2, 'later': 0.2, '...   \n",
       "56  {'share': 0.3333333333333333, 'oo': 0.33333333...   \n",
       "57  {'wf': 0.25, 'google': 0.25, 'deacon': 0.5, 'f...   \n",
       "\n",
       "                                      sentence_scores  \\\n",
       "0   {'r theemotionmac 140 1 Share r Serendipity u ...   \n",
       "1   {'0 forums.nexusmods.com ee BrettM fosaym 617 ...   \n",
       "2   {'6 52 al Se forums.nexusmods.com 17 Apr 2012 ...   \n",
       "3   {'4 06 aw Fe spokesman.com 4 ILULL.': 1.0, 'LL...   \n",
       "4   {'Parents do not own their children.': 0.78571...   \n",
       "5   {'o changed shampoos cut out dairy litres of w...   \n",
       "6                                                  {}   \n",
       "7   {'casispie hugealienpie thechubbynerd just sho...   \n",
       "8   {'distinctly recall a coworker of mine who wor...   \n",
       "9   {'In Pon Etsy Redbubble Turtles STRANGE WOMEN ...   \n",
       "10  {'1 51 Mail glassdoor.com as GitHub Policy Det...   \n",
       "11  {' fantasywriters u SlinkySlang 3h Writing adv...   \n",
       "12  {'Proven analytical and problem solving skills...   \n",
       "13  {'177k 3.9k it Share Oo GalacticPingvin 3h lem...   \n",
       "14  {'a. Ricky Montgomery am upset with my parents...   \n",
       "15                                                 {}   \n",
       "16  {'427 27 it Share Oo mrtrouble22 4h Believer i...   \n",
       "17  {'6 52 al Se forums.nexusmods.com 4 as Soon as...   \n",
       "18  {'11 54 a eG sciencedaily.com The medical comm...   \n",
       "19                                                 {}   \n",
       "20  {'4128 8 it Share We Datadevourer 3h Recently ...   \n",
       "21  {' 53.2k 176k it Share o PyroSnakel41 13h Beco...   \n",
       "22  {'r nosurf u fibonacciseries 9d Turning on the...   \n",
       "23  {' Vote J 10 it Share Oo it2051229 36m In the ...   \n",
       "24  {'4 50 Q Search News Home Popular 20k J 15 it ...   \n",
       "25  {'e205 16 it Share o iseemath 18h think you ll...   \n",
       "26  {'Bing Crosby single handedly managed to creat...   \n",
       "27  {'To date it is the strongest candidate for an...   \n",
       "28  {'read that and her other interview book.': 1....   \n",
       "29  {'527k J 173k it Share Oo Q Reply 56k H insert...   \n",
       "30  {'The particularly interesting part is that it...   \n",
       "31  {'f r stopdrinking u creaturefeaturel6 10h 689...   \n",
       "32  {'Not exactly the most dignified way to go.': ...   \n",
       "33  {'12 40 1 Fe ice comftort ae iY wsyusuallyjrea...   \n",
       "34  {'8 00 wl LTE google.com hy It was October 28 ...   \n",
       "35  {'86k 3.5k it Share Oo MrBOOMbabdtlc 7h flinty...   \n",
       "36  {'21k J 2.1k it Share Oo Ww DOO VYUNINIENISO W...   \n",
       "37  {'ie.': 0.25, 'the selfish short sighted schem...   \n",
       "38  {'631 4 59 it Share Oo PublicFigurex 28d It s ...   \n",
       "39  {'r EatCheapAndHealthy u chickentender1995 12h...   \n",
       "40  {'The fact that it is difficult and a lot of i...   \n",
       "41  {'If you know me you know that make most of my...   \n",
       "42  {'What is the most a dollar has ever gotten yo...   \n",
       "43  {'Overall you have d well.': 0.5, 'A grade of ...   \n",
       "44  {'Earth.': 0.6666666666666666, 'This incredibl...   \n",
       "45  {'6 52 wi Fe 4 forums.nexusmods.com best arrow...   \n",
       "46  {'4128 8 it Share We UMNKINg ADOUL It ana e na...   \n",
       "47  {'The particularly interesting part is that it...   \n",
       "48  {'Being a pet owner is like being a sugar dadd...   \n",
       "49                                                 {}   \n",
       "50  {'So instead of storing each of those characte...   \n",
       "51  {'stupid bumps are that painful pus filled kin...   \n",
       "52  {' spokesman.com 4 A. Jock itch is normally ca...   \n",
       "53  {'All investment group associates are expected...   \n",
       "54  {'47g Mo it Share Oo VULTESIUPIILVIAVII CII St...   \n",
       "55  {'a couple of scenes later when Mr.': 0.8, 'Ro...   \n",
       "56  {'27k 6.2k it Share Oo Tell Rachel said Hi.': ...   \n",
       "57  {'Fandom fallout wiki Ryan Al... Ryan Alosio F...   \n",
       "\n",
       "                                    summary_sentences  \\\n",
       "0   r theemotionmac 140 1 Share r Serendipity u se...   \n",
       "1   You should be far enough away from the first f...   \n",
       "2   You should be far enough away from the first f...   \n",
       "3   Listerine contains herbal oils that fight fung...   \n",
       "4   Kids are not carbon copies of parents adoptive...   \n",
       "5   So searched about antiseptics agents on MRSA a...   \n",
       "6                                                       \n",
       "7   casispie hugealienpie thechubbynerd just showe...   \n",
       "8   asked him one time vy what he was doing workin...   \n",
       "9   In Pon Etsy Redbubble Turtles STRANGE WOMEN AA...   \n",
       "10  1 51 Mail glassdoor.com as GitHub Policy Detai...   \n",
       "11  For the sake of your self esteem your sanity a...   \n",
       "12  Proven analytical and problem solving skills w...   \n",
       "13  Her husband at the time basically spent a few ...   \n",
       "14  u just decided to make a person one day who s ...   \n",
       "15                                                      \n",
       "16  427 27 it Share Oo mrtrouble22 4h Believer i r...   \n",
       "17  like using Shock damage Stamina damage enchant...   \n",
       "18  Obesity is increasing at 2.3 rate each year am...   \n",
       "19                                                      \n",
       "20  However it s not at all good to rely on others...   \n",
       "21  o 9 14k owningmclovin 10h Most of the federal ...   \n",
       "22  r nosurf u fibonacciseries 9d Turning on the G...   \n",
       "23  Rey 24 binjamin2 36m Computer science is heave...   \n",
       "24  4 50 Q Search News Home Popular 20k J 15 it Sh...   \n",
       "25  Reply Vote J AddemF 5h I ve been researching s...   \n",
       "26  Bing Crosby single handedly managed to create ...   \n",
       "27  The Wow signal was detected on August 16 1977 ...   \n",
       "28  promise to come back and extend the list when ...   \n",
       "29  Go 9 16 4 3 MORE REPLIES 75 MORE REPLIES imk 1...   \n",
       "30  Over the past 200 years numerous chess masters...   \n",
       "31  You looked like you were going to pass out in ...   \n",
       "32  faced 2 dragons from the offset outside each o...   \n",
       "33  12 40 1 Fe ice comftort ae iY wsyusuallyjread ...   \n",
       "34  8 00 wl LTE google.com hy It was October 28 19...   \n",
       "35  Go 9 2k y Mudders Milk Man 3h Fun fact Bryan A...   \n",
       "36  21k J 2.1k it Share Oo Ww DOO VYUNINIENISO WwW...   \n",
       "37  Back in the day the stern cardigan wearing pip...   \n",
       "38  Get the mushrooms in there and toss in some so...   \n",
       "39  All the veggies coincidentally came from last ...   \n",
       "40  oO 9 F Vote rookhunter 22d It s a feature of d...   \n",
       "41  have a good printing company because they adop...   \n",
       "42  What is the most a dollar has ever gotten you ...   \n",
       "43  This is GOOD GR We dazzled her eo c ocA grade ...   \n",
       "44  Oh and didja know Arsenic is extremely water s...   \n",
       "45  like using Shock damage Stamina damage enchant...   \n",
       "46  it ll help you keep track of what you break as...   \n",
       "47  Over the past 200 years numerous chess masters...   \n",
       "48  You waste all of your money on keeping them ha...   \n",
       "49                                                      \n",
       "50  So instead of storing each of those characters...   \n",
       "51  So searched about antiseptics agents on MRSA a...   \n",
       "52  You may want to alternate it with other OTC an...   \n",
       "53  A hallmark of Capital s philosophy is an overr...   \n",
       "54  took Stephen Grider s modern react redux 2019 ...   \n",
       "55  TL DR You re not elliot you re the alter think...   \n",
       "56  Oh and didja know Arsenic is extremely water s...   \n",
       "57  Fandom fallout wiki Ryan Al... Ryan Alosio Fal...   \n",
       "\n",
       "                                                clean  \\\n",
       "0    iS 11 23 1 Q Search If shine a white LED ligh...   \n",
       "1   6 51 . 0 forums.nexusmods.com ee BrettM fosaym...   \n",
       "2   6 52 al Se forums.nexusmods.com 17 Apr 2012 St...   \n",
       "3   4 06 aw Fe spokesman.com 4 ILULL. LL 1S SUUULI...   \n",
       "4   Parents do not own their children. No one owns...   \n",
       "5   o changed shampoos cut out dairy litres of wat...   \n",
       "6   WEIS 2P 40p o2ua8 yp i deyiaao SpJ0M Jo 3eq su...   \n",
       "7   casispie hugealienpie thechubbynerd just showe...   \n",
       "8   527k J 173k it Share Oo elfmere 16h Why do you...   \n",
       "9   6 55 at google.com h Google strange women lyin...   \n",
       "10  1 51 Mail glassdoor.com as GitHub Policy Detai...   \n",
       "11   fantasywriters u SlinkySlang 3h Writing advic...   \n",
       "12  10 21 wil Mail jobs.capitalgroup.com Responsib...   \n",
       "13  177k 3.9k it Share Oo GalacticPingvin 3h lemla...   \n",
       "14  a. Ricky Montgomery am upset with my parents f...   \n",
       "15  ig nyx5 i prefer guys who make small dick joke...   \n",
       "16  427 27 it Share Oo mrtrouble22 4h Believer i r...   \n",
       "17  6 52 al Se forums.nexusmods.com 4 as Soon as y...   \n",
       "18  11 54 a eG sciencedaily.com The medical commun...   \n",
       "19   lore 54352452524 deactivated201 you can reple...   \n",
       "20  4128 8 it Share We Datadevourer 3h Recently st...   \n",
       "21   53.2k 176k it Share o PyroSnakel41 13h Become...   \n",
       "22  r nosurf u fibonacciseries 9d Turning on the G...   \n",
       "23   Vote J 10 it Share Oo it2051229 36m In the be...   \n",
       "24  4 50 Q Search News Home Popular 20k J 15 it Sh...   \n",
       "25  e205 16 it Share o iseemath 18h think you ll f...   \n",
       "26   124k J 49k it Share Oo Go 234 15 MORE REPLIES...   \n",
       "27   124k J 49k it Share Oo 10 MORE REPLIES sudden...   \n",
       "28  2 07 al a 2 Messages Back Front Back NV I m no...   \n",
       "29  527k J 173k it Share Oo Q Reply 56k H insertca...   \n",
       "30   124k J 49k it Share Oo 2 MORE REPLIES 1 MORE ...   \n",
       "31  f r stopdrinking u creaturefeaturel6 10h 689 d...   \n",
       "32  6 51 al Se forums.nexusmods.com 4 ToniPrufrock...   \n",
       "33  12 40 1 Fe ice comftort ae iY wsyusuallyjread ...   \n",
       "34  8 00 wl LTE google.com hy It was October 28 19...   \n",
       "35  86k 3.5k it Share Oo MrBOOMbabdtlc 7h flinty d...   \n",
       "36  21k J 2.1k it Share Oo Ww DOO VYUNINIENISO WwW...   \n",
       "37  4 147k J 314 it Share Oo mikevago 4h One of my...   \n",
       "38  631 4 59 it Share Oo PublicFigurex 28d It s fr...   \n",
       "39  r EatCheapAndHealthy u chickentender1995 12h B...   \n",
       "40  423 M6 it Share Oo specific or more detailed w...   \n",
       "41  9 01 li LTE 4 Clock Q Search ED SJ o Atwater V...   \n",
       "42  What is the most a dollar has ever gotten you ...   \n",
       "43  2 48 at O Ali Ho 8 Today 10 40 AM Recommendati...   \n",
       "44  27k 6.2k it Share Oo Empurpledprose 18h wrote ...   \n",
       "45  6 52 wi Fe 4 forums.nexusmods.com best arrows ...   \n",
       "46  4128 8 it Share We UMNKINg ADOUL It ana e naQ ...   \n",
       "47   124k J 49k it Share Oo 5 MORE REPLIES HonchoM...   \n",
       "48  Being a pet owner is like being a sugar daddy....   \n",
       "49  Dana Schwartz DanaSchwartzzz BELLE There goes ...   \n",
       "50  7 42 all All inboxes N Parker from Interview C...   \n",
       "51  stupid bumps are that painful pus filled kinda...   \n",
       "52   spokesman.com 4 A. Jock itch is normally caus...   \n",
       "53  10 21 Mail ef jobs.capitalgroup.com Date Oct 1...   \n",
       "54  47g Mo it Share Oo VULTESIUPIILVIAVII CII Step...   \n",
       "55  a couple of scenes later when Mr. Robot is wea...   \n",
       "56  27k 6.2k it Share Oo Tell Rachel said Hi. o 9 ...   \n",
       "57  10 01 WF 4 google.com Google deacon fallout 4 ...   \n",
       "\n",
       "                                             clean_v2  \\\n",
       "0    iS 11 23 1 Q Search If shine a white LED ligh...   \n",
       "1   6 51 . 0 forums.nexusmods.com ee BrettM fosaym...   \n",
       "2   6 52 al Se forums.nexusmods.com 17 Apr 2012 St...   \n",
       "3   4 06 aw Fe spokesman.com 4 ILULL. LL 1S SUUULI...   \n",
       "4   Parents do not own their children. No one owns...   \n",
       "5   o changed shampoos cut out dairy litres of wat...   \n",
       "6   WEIS 2P 40p o2ua8 yp i deyiaao SpJ0M Jo 3eq su...   \n",
       "7   casispie hugealienpie thechubbynerd just showe...   \n",
       "8   527k J 173k it Share Oo elfmere 16h Why do you...   \n",
       "9   6 55 at google.com h Google strange women lyin...   \n",
       "10  1 51 Mail glassdoor.com as GitHub Policy Detai...   \n",
       "11   fantasywriters u SlinkySlang 3h Writing advic...   \n",
       "12  10 21 wil Mail jobs.capitalgroup.com Responsib...   \n",
       "13  177k 3.9k it Share Oo GalacticPingvin 3h lemla...   \n",
       "14  a. Ricky Montgomery am upset with my parents f...   \n",
       "15  ig nyx5 i prefer guys who make small dick joke...   \n",
       "16  427 27 it Share Oo mrtrouble22 4h Believer i r...   \n",
       "17  6 52 al Se forums.nexusmods.com 4 as Soon as y...   \n",
       "18  11 54 a eG sciencedaily.com The medical commun...   \n",
       "19   lore 54352452524 deactivated201 you can reple...   \n",
       "20  4128 8 it Share We Datadevourer 3h Recently st...   \n",
       "21   53.2k 176k it Share o PyroSnakel41 13h Become...   \n",
       "22  r nosurf u fibonacciseries 9d Turning on the G...   \n",
       "23   Vote J 10 it Share Oo it2051229 36m In the be...   \n",
       "24  4 50 Q Search News Home Popular 20k J 15 it Sh...   \n",
       "25  e205 16 it Share o iseemath 18h think you ll f...   \n",
       "26   124k J 49k it Share Oo Go 234 15 MORE REPLIES...   \n",
       "27   124k J 49k it Share Oo 10 MORE REPLIES sudden...   \n",
       "28  2 07 al a 2 Messages Back Front Back NV I m no...   \n",
       "29  527k J 173k it Share Oo Q Reply 56k H insertca...   \n",
       "30   124k J 49k it Share Oo 2 MORE REPLIES 1 MORE ...   \n",
       "31  f r stopdrinking u creaturefeaturel6 10h 689 d...   \n",
       "32  6 51 al Se forums.nexusmods.com 4 ToniPrufrock...   \n",
       "33  12 40 1 Fe ice comftort ae iY wsyusuallyjread ...   \n",
       "34  8 00 wl LTE google.com hy It was October 28 19...   \n",
       "35  86k 3.5k it Share Oo MrBOOMbabdtlc 7h flinty d...   \n",
       "36  21k J 2.1k it Share Oo Ww DOO VYUNINIENISO WwW...   \n",
       "37  4 147k J 314 it Share Oo mikevago 4h One of my...   \n",
       "38  631 4 59 it Share Oo PublicFigurex 28d It s fr...   \n",
       "39  r EatCheapAndHealthy u chickentender1995 12h B...   \n",
       "40  423 M6 it Share Oo specific or more detailed w...   \n",
       "41  9 01 li LTE 4 Clock Q Search ED SJ o Atwater V...   \n",
       "42  What is the most a dollar has ever gotten you ...   \n",
       "43  2 48 at O Ali Ho 8 Today 10 40 AM Recommendati...   \n",
       "44  27k 6.2k it Share Oo Empurpledprose 18h wrote ...   \n",
       "45  6 52 wi Fe 4 forums.nexusmods.com best arrows ...   \n",
       "46  4128 8 it Share We UMNKINg ADOUL It ana e naQ ...   \n",
       "47   124k J 49k it Share Oo 5 MORE REPLIES HonchoM...   \n",
       "48  Being a pet owner is like being a sugar daddy....   \n",
       "49  Dana Schwartz DanaSchwartzzz BELLE There goes ...   \n",
       "50  7 42 all All inboxes N Parker from Interview C...   \n",
       "51  stupid bumps are that painful pus filled kinda...   \n",
       "52   spokesman.com 4 A. Jock itch is normally caus...   \n",
       "53  10 21 Mail ef jobs.capitalgroup.com Date Oct 1...   \n",
       "54  47g Mo it Share Oo VULTESIUPIILVIAVII CII Step...   \n",
       "55  a couple of scenes later when Mr. Robot is wea...   \n",
       "56  27k 6.2k it Share Oo Tell Rachel said Hi. o 9 ...   \n",
       "57  10 01 WF 4 google.com Google deacon fallout 4 ...   \n",
       "\n",
       "                                                 FREQ  \\\n",
       "0   [(r, 1.0), (shine, 0.75), (see, 0.75), (line, ...   \n",
       "1   [(sneak, 1.0), (one, 1.0), (get, 1.0), (bow, 1...   \n",
       "2   [(sneak, 1.0), (one, 1.0), (get, 1.0), (bow, 1...   \n",
       "3   [(fungus, 1.0), (antifungal, 0.666666666666666...   \n",
       "4   [(kids, 1.0), (parents, 0.7142857142857143), (...   \n",
       "5   [(mrsa, 1.0), (folliculitis, 0.8), (like, 0.6)...   \n",
       "6   [(aq, 1.0), (jo, 0.8), (z, 0.6), (du, 0.6), (t...   \n",
       "7   [(language, 1.0), (kind, 1.0), (casispie, 0.5)...   \n",
       "8   [(one, 1.0), (working, 1.0), (home, 0.75), (de...   \n",
       "9   [(strange, 1.0), (women, 1.0), (lying, 0.75), ...   \n",
       "10  [(manager, 1.0), (work, 0.6), (github, 0.4), (...   \n",
       "11  [(first, 1.0), (draft, 0.6), (stop, 0.6), (wri...   \n",
       "12  [(research, 1.0), (portfolio, 0.5), (asset, 0....   \n",
       "13  [(marriage, 1.0), (time, 0.6666666666666666), ...   \n",
       "14  [(ricky, 1.0), (montgomery, 1.0), (upset, 1.0)...   \n",
       "15  [(dick, 1.0), (guys, 0.6666666666666666), (mak...   \n",
       "16  [(bigfoot, 1.0), (greys, 1.0), (long, 1.0), (s...   \n",
       "17  [(damage, 1.0), (bow, 0.8), (arrows, 0.8), (be...   \n",
       "18  [(obesity, 1.0), (also, 0.42857142857142855), ...   \n",
       "19  [(health, 1.0), (breathing, 1.0), (fresh, 1.0)...   \n",
       "20  [(time, 1.0), (try, 0.5), (sometimes, 0.375), ...   \n",
       "21  [(rich, 1.0), (raise, 0.75), (would, 0.75), (p...   \n",
       "22  [(phone, 1.0), (attractive, 0.5), (filter, 0.3...   \n",
       "23  [(take, 1.0), (efficiently, 1.0), (computers, ...   \n",
       "24  [(share, 1.0), (r, 1.0), (u, 1.0), (bullet, 1....   \n",
       "25  [(mathematics, 1.0), (j, 0.75), (find, 0.5), (...   \n",
       "26  [(honchominerva, 1.0), (bing, 1.0), (crosby, 1...   \n",
       "27  [(replies, 1.0), (august, 1.0), (radio, 1.0), ...   \n",
       "28  [(back, 1.0), (recommend, 0.75), (problems, 0....   \n",
       "29  [(asked, 1.0), (j, 0.6666666666666666), (reply...   \n",
       "30  [(alphazero, 1.0), (chess, 1.0), (j, 0.5), (re...   \n",
       "31  [(feel, 1.0), (like, 1.0), (sad, 0.66666666666...   \n",
       "32  [(go, 1.0), (dragons, 1.0), (getting, 0.666666...   \n",
       "33  [(images, 1.0), (fe, 0.5), (ice, 0.5), (comfto...   \n",
       "34  [(phoenix, 1.0), (venezuela, 1.0), (parents, 1...   \n",
       "35  [(porch, 1.0), (adams, 1.0), (forever, 0.66666...   \n",
       "36  [(nerves, 1.0), (skydiving, 0.5), (super, 0.5)...   \n",
       "37  [(dad, 1.0), (deep, 0.75), (one, 0.5), (shows,...   \n",
       "38  [(sauce, 1.0), (toss, 0.8333333333333334), (ch...   \n",
       "39  [(food, 1.0), (one, 0.75), (month, 0.75), (che...   \n",
       "40  [(hunt, 1.0), (would, 0.6), (solved, 0.6), (oo...   \n",
       "41  [(dog, 1.0), (good, 0.6666666666666666), (adop...   \n",
       "42  [(dollar, 1.0), (back, 0.8), (three, 0.4), (st...   \n",
       "43  [(ali, 1.0), (data, 0.75), (today, 0.5), (prof...   \n",
       "44  [(enough, 1.0), (yellowknife, 0.66666666666666...   \n",
       "45  [(damage, 1.0), (arrows, 0.5714285714285714), ...   \n",
       "46  [(make, 1.0), (problem, 0.75), (time, 0.5), (t...   \n",
       "47  [(alphazero, 1.0), (chess, 1.0), (replies, 0.7...   \n",
       "48  [(jack, 1.0), (pet, 0.5), (owner, 0.5), (like,...   \n",
       "49  [(belle, 1.0), (goes, 1.0), (baker, 1.0), (dan...   \n",
       "50  [(stack, 1.0), (problem, 0.8), (week, 0.8), (i...   \n",
       "51  [(mrsa, 1.0), (like, 0.6), (folliculitis, 0.6)...   \n",
       "52  [(contains, 1.0), (antifungal, 1.0), (jock, 0....   \n",
       "53  [(capital, 1.0), (group, 0.875), (solutions, 0...   \n",
       "54  [(react, 1.0), (took, 0.75), (way, 0.75), (end...   \n",
       "55  [(think, 1.0), (actually, 0.8), (elliot, 0.6),...   \n",
       "56  [(enough, 1.0), (replies, 0.6666666666666666),...   \n",
       "57  [(fallout, 1.0), (ryan, 1.0), (alosio, 0.75), ...   \n",
       "\n",
       "                                               pruned  \\\n",
       "0   search shine white light through prism would s...   \n",
       "1   forums.nexusmods.com brettm fosaym 2012 stealt...   \n",
       "2   forums.nexusmods.com 2012 stealth archery work...   \n",
       "3   spokesman.com ilull. suuuliiis aalllu culilall...   \n",
       "4   parents their children. owns anything just loa...   \n",
       "5   changed shampoos dairy litres water fast food ...   \n",
       "6   weis o2ua8 deyiaao spj0m suunseayy aeazze yoty...   \n",
       "7   casispie hugealienpie thechubbynerd just showe...   \n",
       "8   527k 173k share elfmere work factory when have...   \n",
       "9   google.com google strange women lying ponds di...   \n",
       "10  mail glassdoor.com github policy details encou...   \n",
       "11  fantasywriters slinkyslang writing advice...fr...   \n",
       "12  mail jobs.capitalgroup.com responsibilities wo...   \n",
       "13  177k 3.9k share galacticpingvin lemlang atlien...   \n",
       "14  ricky montgomery upset with parents making exi...   \n",
       "15  nyx5 prefer guys make small dick jokes about t...   \n",
       "16  share mrtrouble22 believer read story where wo...   \n",
       "17  forums.nexusmods.com soon dismount wait dark. ...   \n",
       "18  sciencedaily.com medical community used think ...   \n",
       "19  lore 54352452524 deactivated201 replenish your...   \n",
       "20  4128 share datadevourer recently started using...   \n",
       "21  53.2k 176k share pyrosnakel41 become politicia...   \n",
       "22  nosurf fibonacciseries turning greyscale filte...   \n",
       "23  vote share it2051229 beginning there such thin...   \n",
       "24  search news home popular share basicbulletjour...   \n",
       "25  e205 share iseemath think find princeton compa...   \n",
       "26  124k share more replies honchominerva moki hon...   \n",
       "27  124k share more replies suddenly satire august...   \n",
       "28  messages back front back home right going give...   \n",
       "29  527k 173k share reply insertcaffeine questions...   \n",
       "30  124k share more replies more reply more replie...   \n",
       "31  stopdrinking creaturefeaturel6 days very text ...   \n",
       "32  forums.nexusmods.com toniprufrock 2012 getting...   \n",
       "33  comftort wsyusuallyjread chapter book lightsjo...   \n",
       "34  google.com october 1977 third birthday phoenix...   \n",
       "35  3.5k share mrboombabdtlc flinty lovesmesomered...   \n",
       "36  2.1k share vyuninieniso fuckin mate happy8day ...   \n",
       "37  147k share mikevago favorite things about both...   \n",
       "38  share publicfigurex fried rice. kinda chicken ...   \n",
       "39  eatcheapandhealthy chickentender1995 best tips...   \n",
       "40  share specific more detailed probably wouldn t...   \n",
       "41  clock search atwater village topics neighborho...   \n",
       "42  what most dollar ever gotten eeae tldr wife th...   \n",
       "43  today recommendations recommended received giv...   \n",
       "44  6.2k share empurpledprose wrote this elsewhere...   \n",
       "45  forums.nexusmods.com best arrows that merchant...   \n",
       "46  4128 share umnking adoul waslin spiral into pr...   \n",
       "47  124k share more replies honchominerva honchomi...   \n",
       "48  being owner like being sugar daddy. waste your...   \n",
       "49  dana schwartz danaschwartzzz belle there goes ...   \n",
       "50  inboxes parker from interview cake 00pm yesthi...   \n",
       "51  stupid bumps that painful filled kinda like ac...   \n",
       "52  spokesman.com jock itch normally caused fungal...   \n",
       "53  mail jobs.capitalgroup.com date 2019 location ...   \n",
       "54  share vultesiupiilviavii stephen grider been p...   \n",
       "55  couple scenes later when robot wearing scarf p...   \n",
       "56  6.2k share tell rachel said 3324 more replies ...   \n",
       "57  google.com google deacon fallout voice actor n...   \n",
       "\n",
       "                                          pruned_nosw  \n",
       "0   search shine white light prism would spectrum ...  \n",
       "1   forums.nexusmods.com brettm fosaym 2012 stealt...  \n",
       "2   forums.nexusmods.com 2012 stealth archery work...  \n",
       "3   spokesman.com ilull. suuuliiis aalllu culilall...  \n",
       "4   parents children. owns anything loan duration ...  \n",
       "5   changed shampoos dairy litres water fast food ...  \n",
       "6   weis o2ua8 deyiaao spj0m suunseayy aeazze yoty...  \n",
       "7   casispie hugealienpie thechubbynerd shower tho...  \n",
       "8   527k 173k share elfmere work factory honors de...  \n",
       "9   google.com google strange women lying ponds di...  \n",
       "10  mail glassdoor.com github policy details encou...  \n",
       "11  fantasywriters slinkyslang writing advice...fr...  \n",
       "12  mail jobs.capitalgroup.com responsibilities wo...  \n",
       "13  177k 3.9k share galacticpingvin lemlang atlien...  \n",
       "14  ricky montgomery upset parents making exist. d...  \n",
       "15  nyx5 prefer guys make small dick jokes guys ma...  \n",
       "16  share mrtrouble22 believer read story woman gr...  \n",
       "17  forums.nexusmods.com soon dismount wait dark. ...  \n",
       "18  sciencedaily.com medical community used think ...  \n",
       "19  lore 54352452524 deactivated201 replenish heal...  \n",
       "20  4128 share datadevourer recently started using...  \n",
       "21  53.2k 176k share pyrosnakel41 become politicia...  \n",
       "22  nosurf fibonacciseries turning greyscale filte...  \n",
       "23  vote share it2051229 beginning thing computer ...  \n",
       "24  search news home popular share basicbulletjour...  \n",
       "25  e205 share iseemath think find princeton compa...  \n",
       "26  124k share more replies honchominerva moki hon...  \n",
       "27  124k share more replies suddenly satire august...  \n",
       "28  messages back front back home right going give...  \n",
       "29  527k 173k share reply insertcaffeine questions...  \n",
       "30  124k share more replies more reply more replie...  \n",
       "31  stopdrinking creaturefeaturel6 days text messa...  \n",
       "32  forums.nexusmods.com toniprufrock 2012 getting...  \n",
       "33  comftort wsyusuallyjread chapter book lightsjo...  \n",
       "34  google.com october 1977 third birthday phoenix...  \n",
       "35  3.5k share mrboombabdtlc flinty lovesmesomered...  \n",
       "36  2.1k share vyuninieniso fuckin mate happy8day ...  \n",
       "37  147k share mikevago favorite things shows ralp...  \n",
       "38  share publicfigurex fried rice. kinda chicken ...  \n",
       "39  eatcheapandhealthy chickentender1995 best tips...  \n",
       "40  share specific detailed probably talking never...  \n",
       "41  clock search atwater village topics neighborho...  \n",
       "42  what dollar ever gotten eeae tldr wife three b...  \n",
       "43  today recommendations recommended received giv...  \n",
       "44  6.2k share empurpledprose wrote elsewhere thin...  \n",
       "45  forums.nexusmods.com best arrows merchant offe...  \n",
       "46  4128 share umnking adoul waslin spiral problem...  \n",
       "47  124k share more replies honchominerva honchomi...  \n",
       "48  being owner like sugar daddy. waste money keep...  \n",
       "49  dana schwartz danaschwartzzz belle there goes ...  \n",
       "50  inboxes parker interview cake 00pm yesthisiske...  \n",
       "51  stupid bumps painful filled kinda like acne ye...  \n",
       "52  spokesman.com jock itch normally caused fungal...  \n",
       "53  mail jobs.capitalgroup.com date 2019 location ...  \n",
       "54  share vultesiupiilviavii stephen grider profes...  \n",
       "55  couple scenes later robot wearing scarf protec...  \n",
       "56  6.2k share tell rachel said 3324 more replies ...  \n",
       "57  google.com google deacon fallout voice actor n...  "
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_bow_from_column(df, column):\n",
    "    all_column_data = ' '.join(df[column].tolist())\n",
    "    all_column_fd = Counter(all_column_data.split())\n",
    "    return all_column_fd\n",
    "\n",
    "big_bow = get_bow_from_column(all_df, 'pruned_nosw')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('share', 34),\n",
       " ('time', 32),\n",
       " ('like', 32),\n",
       " ('would', 26),\n",
       " ('best', 22),\n",
       " ('enough', 21),\n",
       " ('back', 21),\n",
       " ('more', 19),\n",
       " ('first', 17),\n",
       " ('people', 17),\n",
       " ('using', 16),\n",
       " ('arrows', 16),\n",
       " ('parents', 16),\n",
       " ('reply', 16),\n",
       " ('good', 15),\n",
       " ('make', 15),\n",
       " ('work', 15),\n",
       " ('think', 15),\n",
       " ('problem', 14),\n",
       " ('this', 14),\n",
       " ('years', 14),\n",
       " ('replies', 14),\n",
       " ('damage', 13),\n",
       " ('kids', 13),\n",
       " ('research', 13),\n",
       " ('every', 13),\n",
       " ('also', 13),\n",
       " ('thing', 12),\n",
       " ('things', 12),\n",
       " ('know', 12),\n",
       " ('acomment', 12),\n",
       " ('long', 11),\n",
       " ('sneak', 11),\n",
       " ('even', 11),\n",
       " ('many', 11),\n",
       " ('vote', 11),\n",
       " ('solutions', 11),\n",
       " ('find', 10),\n",
       " ('able', 10),\n",
       " ('take', 10),\n",
       " ('away', 10),\n",
       " ('said', 10),\n",
       " ('need', 10),\n",
       " ('made', 10),\n",
       " ('since', 9),\n",
       " ('less', 9),\n",
       " ('much', 9),\n",
       " ('couple', 9),\n",
       " ('keep', 9),\n",
       " ('then', 9)]"
      ]
     },
     "execution_count": 114,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "big_bow.most_common(50)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Counter({'share': 29, 'one': 25, 'oo': 22, 'like': 21, 'would': 17, 'time': 17, 'go': 17, 'j': 17, 'back': 16, 'get': 15, 'use': 13, 'work': 13, 'best': 12, 'good': 12, 'people': 12, 'add': 12, 'reply': 12, 'using': 11, 'first': 11, 'thing': 11, 'make': 11, 'things': 11, 'years': 11, 'enough': 10, 'said': 10, 'day': 10, 'also': 10, 'acomment': 10, 'level': 9, 'even': 9, 'problem': 9, 'need': 9, 'every': 9, 'made': 9, 'know': 9, 'think': 9, 'u': 8, 'q': 8, 'since': 8, 'got': 8, 'find': 8, 'around': 8, 'could': 8, 'al': 8, 'keep': 8, 'came': 8, 'making': 8, 'see': 7, 'less': 7, 'way': 7, 'away': 7, 'long': 7, 'far': 7, 'much': 7, 'take': 7, 'started': 7, 'course': 7, 'well': 7, 'many': 7, 'research': 7, 'vote': 7, 'us': 7, 'something': 7, 'really': 7, 'times': 7, 'want': 6, 'life': 6, 'understand': 6, 'home': 6, 'water': 6, 'found': 6, 'repy': 6, 'went': 6, 'amazing': 6, 'never': 6, 'lot': 6, 'learning': 6, 'looking': 6, 'replies': 6, 'r': 5, 'little': 5, 'put': 5, 'x': 5, 'great': 5, 'without': 5, 'soon': 5, 'dragons': 5, 'finally': 5, 'shows': 5, 'may': 5, 'try': 5, 'parents': 5, 'person': 5, 'sure': 5, 'say': 5, 'gone': 5, 'mine': 5, 'used': 5, 'thought': 5, 'food': 5, 'right': 5, 'full': 5, 'next': 5, 'real': 5, 'bit': 5, 'old': 5, 'high': 5, 'spent': 5, 'everyone': 5, 'etc': 5, 'decided': 5, 'ask': 5, 'better': 5, 'year': 5, 'human': 5, 'instead': 5, 'done': 5, 'give': 5, 'based': 5, 'led': 4, 'light': 4, 'search': 4, 'room': 4, 'post': 4, 'sneak': 4, 'bow': 4, 'arrows': 4, 'draugr': 4, 'able': 4, 'couple': 4, 'pick': 4, 'perk': 4, 'damage': 4, 'wait': 4, 'characters': 4, 'attention': 4, 'dragon': 4, 'apr': 4, 'takes': 4, 'especially': 4, 'foes': 4, 'sneaky': 4, 'quick': 4, 'either': 4, 'nice': 4, 'perks': 4, 'glycol': 4, 'let': 4, 'help': 4, 'world': 4, 'children': 4, 'always': 4, 'tell': 4, 'exactly': 4, 'change': 4, 'often': 4, 'others': 4, 'money': 4, 'dinner': 4, 'cut': 4, 'saying': 4, 'super': 4, 'fast': 4, 'usually': 4, 'kind': 4, 'must': 4, 'two': 4, 'ago': 4, 'mind': 4, 'e': 4, 'c': 4, 'word': 4, 'sometimes': 4, 'pretty': 4, 'man': 4, 'google': 4, 'ca': 4, 'self': 4, 'development': 4, 'data': 4, 'health': 4, 'ever': 4, 'weeks': 4, 'source': 4, 'solutions': 4, 'topics': 4, 'learn': 4, 'live': 4, 'together': 4, 'pay': 4, 'big': 4, 'saw': 4, 'given': 4, 'yet': 4, 'method': 4, 'past': 4, 'part': 4, 'end': 4, 'might': 4, 'whatever': 4, 'messages': 4, 'v': 4, 'forever': 4, 'days': 4, 'honchominerva': 4, 'hours': 4, 'later': 4, 'front': 4, 'look': 4, 'interesting': 4, 'set': 4, 'yes': 4, 'blue': 3, 'actually': 3, 'anything': 3, 'makes': 3, 'ought': 3, 'dark': 3, 'archery': 3, 'works': 3, 'eagle': 3, 'eye': 3, 'dismount': 3, 'key': 3, 'notice': 3, 'shout': 3, 'fus': 3, 'battle': 3, 'taken': 3, 'nearby': 3, 'closest': 3, 'dragur': 3, 'engage': 3, 'draw': 3, 'sort': 3, 'enchant': 3, 'armor': 3, 'fond': 3, 'elven': 3, 'weight': 3, 'ratio': 3, 'improved': 3, 'max': 3, 'invested': 3, 'smithing': 3, 'se': 3, 'supply': 3, 'activity': 3, 'skin': 3, 'fe': 3, 'young': 3, 'woman': 3, 'affected': 3, 'job': 3, 'second': 3, 'face': 3, 'break': 3, 'come': 3, 'early': 3, 'least': 3, 'beginning': 3, 'completely': 3, 'worse': 3, 'took': 3, 'antibiotic': 3, 'fungal': 3, 'resistant': 3, 'antibiotics': 3, 'tools': 3, 'clean': 3, 'guy': 3, 'cure': 3, 'worked': 3, 'gon': 3, 'na': 3, 'almost': 3, 'coming': 3, 'lol': 3, 'asked': 3, 'point': 3, 'several': 3, 'hell': 3, 'love': 3, 'images': 3, 'videos': 3, 'news': 3, 'manager': 3, 'director': 3, 'mail': 3, 'offer': 3, 'support': 3, 'global': 3, 'contribute': 3, 'advice': 3, 'new': 3, 'probably': 3, 'asset': 3, 'skills': 3, 'develop': 3, 'ways': 3, 'problems': 3, 'experience': 3, 'friend': 3, 'closed': 3, 'care': 3, 'reason': 3, 'upset': 3, 'talk': 3, 'earth': 3, 'f': 3, 'read': 3, 'story': 3, 'studied': 3, 'character': 3, 'types': 3, 'effect': 3, 'review': 3, 'however': 3, 'lead': 3, 'passed': 3, 'feel': 3, 'trying': 3, 'recently': 3, 'kinda': 3, 'happy': 3, 'solving': 3, 'start': 3, 'different': 3, 'getting': 3, 'fucking': 3, 'ones': 3, 'products': 3, 'advantage': 3, 'algorithms': 3, 'related': 3, 'popular': 3, 'helpful': 3, 'similar': 3, 'north': 3, 'likely': 3, 'going': 3, 'coding': 3, 'million': 3, 'last': 3, 'wrong': 3, 'still': 3, 'track': 3, 'playing': 3, 'seemed': 3, 'somehow': 3, 'game': 3, 'main': 3, 'gold': 3, 'wrote': 3, 'girl': 3, 'elsewhere': 3, 'thinking': 2, 'w': 2, 'question': 2, 'simple': 2, 'act': 2, 'powerful': 2, 'step': 2, 'ee': 2, 'shots': 2, 'stealth': 2, 'range': 2, 'deathlord': 2, 'shot': 2, 'triple': 2, 'helps': 2, 'dusk': 2, 'maximize': 2, 'potential': 2, 'arrive': 2, 'daylight': 2, 'crouch': 2, 'fungus': 2, 'antifungal': 2, 'area': 2, 'propylene': 2, 'cetyl': 2, 'alcohol': 2, 'effective': 2, 'men': 2, 'minutes': 2, 'rinse': 2, 'ingredient': 2, 'contains': 2, 'kids': 2, 'someone': 2, 'individuals': 2, 'slow': 2, 'drives': 2, 'push': 2, 'heart': 2, 'family': 2, 'initially': 2, 'changes': 2, 'relationship': 2, 'applies': 2, 'mrsa': 2, 'folliculitis': 2, 'dettol': 2, 'searched': 2, 'inhibits': 2, 'choloroxylenol': 2, 'solution': 2, 'remembered': 2, 'clorox': 2, 'hair': 2, 'changed': 2, 'shampoos': 2, 'dairy': 2, 'litres': 2, 'pills': 2, 'bacterial': 2, 'idk': 2, 'imagined': 2, 'antiseptics': 2, 'agents': 2, 'methicillin': 2, 'staph': 2, 'dont': 2, 'hospitals': 2, 'stations': 2, 'papers': 2, 'chlorhexidine': 2, 'multipurpose': 2, 'grandpa': 2, 'bathes': 2, 'safe': 2, 'study': 2, 'showed': 2, 'week': 2, 'ta': 2, 'ae': 2, 'le': 2, 'language': 2, 'thoughts': 2, 'function': 2, 'weird': 2, 'needs': 2, 'talking': 2, 'ina': 2, 'mention': 2, 'enjoy': 2, 'subjects': 2, 'straight': 2, 'required': 2, 'stop': 2, 'h': 2, 'python': 2, 'holy': 2, 'build': 2, 'balance': 2, 'sales': 2, 'creative': 2, 'field': 2, 'senior': 2, 'insurance': 2, 'writing': 2, 'manuscript': 2, 'following': 2, 'sub': 2, 'guess': 2, 'single': 2, 'mostly': 2, 'magic': 2, 'aside': 2, 'asking': 2, 'finish': 2, 'comments': 2, 'portfolio': 2, 'portfolios': 2, 'analytical': 2, 'industry': 2, 'apply': 2, 'team': 2, 'business': 2, 'multi': 2, 'platforms': 2, 'maintain': 2, 'deep': 2, 'dive': 2, 'publications': 2, 'needed': 2, 'knowledge': 2, 'solve': 2, 'effort': 2, 'investment': 2, 'equity': 2, 'income': 2, 'knew': 2, 'basically': 2, 'expected': 2, 'cook': 2, 'married': 2, 'vacation': 2, 'outside': 2, 'ricky': 2, 'montgomery': 2, 'exist': 2, 'bills': 2, 'medium': 2, 'space': 2, 'grey': 2, 'lights': 2, 'star': 2, 'systems': 2, 'bound': 2, 'sense': 2, 'shock': 2, 'ebony': 2, 'elrindir': 2, 'merchant': 2, 'stamina': 2, 'enchants': 2, 'utility': 2, 'dual': 2, 'enchanting': 2, 'fire': 2, 'medicine': 2, 'school': 2, 'series': 2, 'author': 2, 'professor': 2, 'disease': 2, 'journal': 2, 'birth': 2, 'natural': 2, 'fresh': 2, 'lore': 2, 'drinking': 2, 'eating': 2, 'suddenly': 2, 'googling': 2, 'rely': 2, 'goals': 2, 'lh': 2, 'clearly': 2, 'sound': 2, 'obvious': 2, 'spiral': 2, 'proceed': 2, 'spend': 2, 'exact': 2, 'perfect': 2, 'head': 2, 'error': 2, 'approached': 2, 'refrain': 2, 'spending': 2, 'eleanor': 2, 'roosevelt': 2, 'mistakes': 2, 'tr': 2, 'become': 2, 'creating': 2, 'coincidentally': 2, 'younger': 2, 'businesses': 2, 'mean': 2, 'option': 2, 'heard': 2, 'machine': 2, 'scale': 2, 'tried': 2, 'night': 2, 'anymore': 2, 'charge': 2, 'quite': 2, 'science': 2, 'stuff': 2, 'rey': 2, 'theory': 2, 'software': 2, 'lots': 2, 'focus': 2, 'award': 2, 'available': 2, 'wanted': 2, 'reading': 2, 'hank': 2, 'piece': 2, 'bill': 2, 'vv': 2, 'date': 2, 'bedroom': 2, 'name': 2, 'interview': 2, 'book': 2, 'detailed': 2, 'huge': 2, 'whole': 2, 'recommended': 2, 'practice': 2, 'difficulty': 2, 'questions': 2, 'idea': 2, 'eventually': 2, 'cold': 2, 'looked': 2, 'co': 2, 'alphazero': 2, 'chess': 2, 'play': 2, 'deepmind': 2, 'proceeded': 2, 'beat': 2, 'top': 2, 'engine': 2, 'particularly': 2, 'wins': 2, 'engines': 2, 'tend': 2, 'run': 2, 'assess': 2, 'board': 2, 'move': 2, 'chosen': 2, 'millions': 2, 'moves': 2, 'decide': 2, 'parameters': 2, 'direct': 2, 'playstyle': 2, 'seeing': 2, 'quantifiable': 2, 'position': 2, 'numerous': 2, 'masters': 2, 'style': 2, 'means': 2, 'developed': 2, 'understanding': 2, 'scary': 2, 'sad': 2, 'daughter': 2, 'received': 2, 'wife': 2, 'left': 2, 'dealing': 2, 'drive': 2, 'picture': 2, 'birthday': 2, 'quest': 2, 'shall': 2, 'toniprufrock': 2, 'essentially': 2, 'group': 2, 'refused': 2, 'whatnot': 2, 'reload': 2, 'anyone': 2, 'tips': 2, 'www': 2, 'angela': 2, 'lte': 2, 'third': 2, 'lives': 2, 'called': 2, 'along': 2, 'born': 2, 'organization': 2, 'dad': 2, 'milk': 2, 'fact': 2, 'song': 2, 'says': 2, 'mr': 2, 'model': 2, 'modern': 2, 'wearing': 2, 'show': 2, 'carrots': 2, 'onion': 2, 'place': 2, 'veggies': 2, 'size': 2, 'minute': 2, 'goes': 2, 'month': 2, 'sale': 2, 'today': 2, 'number': 2, 'proof': 2, 'items': 2, 'fully': 2, 'thank': 2, 'seen': 2, 'company': 2, 'free': 2, 'results': 2, 'dollar': 2, 'awesome': 2, 'block': 2, 'recommendations': 2, 'analysis': 2, 'engineer': 2, 'oct': 2, 'pm': 2, 'eo': 2, 'yellowknife': 2, 'arsenic': 2, 'kill': 2, 'amount': 2, 'infrastructure': 2, 'empurpledprose': 2, 'terestine': 2, 'terrifying': 2, 'repost': 2, 'directly': 2, 'underneath': 2, 'city': 2, 'northwest': 2, 'territories': 2, 'canada': 2, 'quarter': 2, 'tons': 2, 'trioxide': 2, 'remain': 2, 'frozen': 2, 'cooling': 2, 'technology': 2, 'order': 2, 'leak': 2, 'potentially': 2, 'incredible': 2, 'carcinogen': 2, 'tailings': 2, 'depleted': 2, 'giant': 2, 'sixty': 2, 'operation': 2, 'oh': 2, 'didja': 2, 'extremely': 2, 'soluble': 2, 'pro': 2, 'rata': 2, 'ground': 2, 'permafrost': 2, 'crumbling': 2, 'fails': 2, 'catastrophically': 2, 'due': 2, 'hi': 2, 'worth': 2, 'ryan': 2, 'alternate': 2, 'shine': 1, 'line': 1, 'white': 1, 'prism': 1, 'spectrum': 1, 'red': 1, 'green': 1, 'window': 1, 'hangers': 1, 'rainbows': 1, 'refracting': 1, 'dispersing': 1, 'sunlight': 1, 'bright': 1, 'zenhabits': 1, 'lightfiend': 1, 'feelings': 1, 'emotions': 1, 'automatically': 1, 'distances': 1, 'enables': 1, 'easily': 1, 'analyze': 1, 'channel': 1, 'emotion': 1, 'positive': 1, 'constructive': 1, 'theemotionmac': 1, 'serendipity': 1, 'serendipitybot': 1, 'cheating': 1, 'cunt': 1, 'imgoingtohellforthis': 1, 'brettm': 1, 'fosaym': 1, 'vinegar': 1, 'listerine': 1, 'aw': 1, 'ilull': 1, 'suuuliiis': 1, 'aalllu': 1, 'culilallis': 1, 'benefit': 1, 'applying': 1, 'dandruff': 1, 'shampoo': 1, 'selsun': 1, 'lather': 1, 'stay': 1, 'zone': 1, 'five': 1, 'selenium': 1, 'sulfide': 1, 'active': 1, 'inflamed': 1, 'healed': 1, 'applications': 1, 'original': 1, 'amber': 1, 'herbal': 1, 'oils': 1, 'fight': 1, 'acidic': 1, 'hospitable': 1, 'antiperspirant': 1, 'groin': 1, 'dry': 1, 'discourage': 1, 'overgrowth': 1, 'parent': 1, 'child': 1, 'survive': 1, 'owns': 1, 'loan': 1, 'duration': 1, 'lifetime': 1, 'slaves': 1, 'donated': 1, 'genetic': 1, 'material': 1, 'carbon': 1, 'copies': 1, 'adoptive': 1, 'biological': 1, 'catch': 1, 'likes': 1, 'dislikes': 1, 'ensuring': 1, 'independent': 1, 'spiritual': 1, 'extent': 1, 'beliefs': 1, 'purpose': 1, 'crazy': 1, 'belief': 1, 'teach': 1, 'lesson': 1, 'ifa': 1, 'lacking': 1, 'discipline': 1, 'limit': 1, 'involuntarily': 1, 'hypocritical': 1, 'mock': 1, 'amusement': 1, 'indecisive': 1, 'situations': 1, 'immediate': 1, 'decisions': 1, 'spot': 1, 'workaholic': 1, 'chances': 1, 'offering': 1, 'test': 1, 'dependent': 1, 'adjusting': 1, 'alone': 1, 'ownership': 1, 'ingredients': 1, 'ph': 1, 'alkali': 1, 'showering': 1, 'caps': 1, 'diluted': 1, 'oily': 1, 'rinsing': 1, 'happens': 1, 'update': 1, 'progress': 1, 'aq': 1, 'jo': 1, 'z': 1, 'du': 1, 'edeysez': 1, 'dn': 1, 'uo': 1, 'ued': 1, 'te': 1, 'ay': 1, 'ut': 1, 'st': 1, 'nod': 1, 'oz': 1, 'si': 1, 'pd': 1, 'ayy': 1, 'weis': 1, 'yp': 1, 'deyiaao': 1, 'suunseayy': 1, 'aeazze': 1, 'yotym': 1, 'za': 1, 'aur': 1, 'suorsuaump': 1, 'izuut': 1, 'os': 1, 'xn': 1, 'uwin': 1, 'od': 1, 'om': 1, 'pueylioyus': 1, 'sity': 1, 'asn': 1, 'ud': 1, 'noa': 1, 'sodleut': 1, 'nxt': 1, 'txn': 1, 'pausing': 1, 'aduts': 1, 'uonoung': 1, 'thujew': 1, 'yw': 1, 'adumu': 1, 'paysydurosse': 1, 'oq': 1, 'yiym': 1, 'fonpoud': 1, 'xwjyoum': 1, 'ayi': 1, 'uateamba': 1, 'yonposd': 1, 'oy': 1, 'di': 1, 'xuqvul': 1, 'xt': 1, 'uiyiim': 1, 'inpod': 1, 'sepess': 1, 'sindjno': 1, 'l': 1, 'tt': 1, 'ssi': 1, 'ot': 1, 'sutsodsuen': 1, 'auijedid': 1, 'anoa': 1, 'umop': 1, 'mojs': 1, 'juem': 1, 'nox': 1, 'ssajun': 1, 'aem': 1, 'siy': 1, 'upjnoys': 1, 'noy': 1, 'xx': 1, 'txx': 1, 'quaiaiya': 1, 'aida': 1, 'ey': 1, 'uoizeaadoo': 1, 'cue': 1, 'chae': 1, 'aee': 1, 'skesae': 1, 'aduinu': 1, 'uoije': 1, 'rop': 1, 'lp': 1, 'ha': 1, 'onpoid': 1, 'casispie': 1, 'hugealienpie': 1, 'thechubbynerd': 1, 'shower': 1, 'contractions': 1, 'identically': 1, 'phrase': 1, 'appropriate': 1, 'places': 1, 'sentence': 1, 'quirks': 1, 'warning': 1, 'sign': 1, 'idid': 1, 'english': 1, 'confusing': 1, 'isay': 1, 'linguist': 1, 'working': 1, 'depot': 1, 'physics': 1, 'tile': 1, 'loved': 1, 'hands': 1, 'mentioned': 1, 'master': 1, 'degrees': 1, 'despite': 1, 'elfmere': 1, 'factory': 1, 'honors': 1, 'degree': 1, 'dillingerradio': 1, 'awards': 1, 'distinctly': 1, 'recall': 1, 'coworker': 1, 'department': 1, 'eccentric': 1, 'personality': 1, 'outgoing': 1, 'knowledgeable': 1, 'discussion': 1, 'education': 1, 'definitely': 1, 'turned': 1, 'dillinger': 1, 'fields': 1, 'loving': 1, 'various': 1, 'manual': 1, 'labor': 1, 'hardware': 1, 'workers': 1, 'definition': 1, 'remind': 1, 'legally': 1, 'throughout': 1, 'vy': 1, 'sinc': 1, 'retirement': 1, 'age': 1, 'aniuildhin': 1, 'ctannad': 1, 'vwinvliine': 1, 'annadanc': 1, 'ancn': 1, 'cinnn': 1, 'strange': 1, 'women': 1, 'lying': 1, 'ponds': 1, 'distributing': 1, 'distrib': 1, 'shopping': 1, 'latest': 1, 'gif': 1, 'hd': 1, 'product': 1, 'gy': 1, 'gp': 1, 'moistened': 1, 'bint': 1, 'monty': 1, 'grail': 1, 'sponsored': 1, 'strang': 1, 'pon': 1, 'etsy': 1, 'redbubble': 1, 'turtles': 1, 'aai': 1, 'github': 1, 'remote': 1, 'marketing': 1, 'account': 1, 'analyst': 1, 'policy': 1, 'details': 1, 'encourage': 1, 'hubbers': 1, 'autonomy': 1, 'direction': 1, 'important': 1, 'flexible': 1, 'schedules': 1, 'unlimited': 1, 'pto': 1, 'believe': 1, 'allows': 1, 'wherever': 1, 'happiest': 1, 'hiring': 1, 'san': 1, 'francisco': 1, 'roles': 1, 'event': 1, 'sponsorship': 1, 'technical': 1, 'workplace': 1, 'operations': 1, 'strategic': 1, 'finance': 1, 'analytics': 1, 'public': 1, 'relations': 1, 'employees': 1, 'absorb': 1, 'costs': 1, 'hsa': 1, 'caaimictiijabietletbfeleiaesy': 1, 'match': 1, 'draft': 1, 'words': 1, 'feedback': 1, 'sake': 1, 'fantasywriters': 1, 'slinkyslang': 1, 'writer': 1, 'february': 1, 'critiques': 1, 'opinions': 1, 'chapters': 1, 'prologues': 1, 'seeking': 1, 'please': 1, 'reread': 1, 'ican': 1, 'assure': 1, 'garbage': 1, 'ona': 1, 'soldiering': 1, 'finishing': 1, 'setting': 1, 'wtf': 1, 'esteem': 1, 'sanity': 1, 'completion': 1, 'constant': 1, 'thudly': 1, 'comfort': 1, 'insecurities': 1, 'relevant': 1, 'quantitative': 1, 'models': 1, 'databases': 1, 'internal': 1, 'allocation': 1, 'construction': 1, 'strong': 1, 'ability': 1, 'wil': 1, 'responsibilities': 1, 'analysts': 1, 'managers': 1, 'deliver': 1, 'impact': 1, 'applied': 1, 'frameworks': 1, 'initiate': 1, 'foundational': 1, 'cuts': 1, 'across': 1, 'geographies': 1, 'europe': 1, 'asia': 1, 'utilize': 1, 'proprietary': 1, 'additional': 1, 'resources': 1, 'compile': 1, 'bring': 1, 'domain': 1, 'broad': 1, 'identify': 1, 'areas': 1, 'monitoring': 1, 'attribution': 1, 'participates': 1, 'computing': 1, 'platform': 1, 'enhance': 1, 'processes': 1, 'collaborative': 1, 'environment': 1, 'requirements': 1, 'minimum': 1, 'involving': 1, 'building': 1, 'multiple': 1, 'classes': 1, 'spanning': 1, 'fixed': 1, 'proven': 1, 'marriage': 1, 'galacticpingvin': 1, 'lemlang': 1, 'atlienk': 1, 'female': 1, 'husband': 1, 'prior': 1, 'salesman': 1, 'behind': 1, 'doors': 1, 'traditional': 1, 'roots': 1, 'moving': 1, 'careers': 1, 'ok': 1, 'career': 1, 'dogs': 1, 'lifted': 1, 'finger': 1, 'pound': 1, 'drinks': 1, 'grumblell': 1, 'trial': 1, 'period': 1, 'piens': 1, 'haed': 1, 'usual': 1, 'surroundings': 1, 'dick': 1, 'guys': 1, 'jokes': 1, 'ig': 1, 'prefer': 1, 'small': 1, 'cg': 1, 'driad': 1, 'ghosts': 1, 'ea': 1, 'princess': 1, 'laya': 1, 'nearly': 1, 'spat': 1, 'tea': 1, 'bigfoot': 1, 'greys': 1, 'planet': 1, 'believer': 1, 'carrying': 1, 'babies': 1, 'insinuating': 1, 'scrignutz': 1, 'combination': 1, 'sky': 1, 'monsters': 1, 'happening': 1, 'assume': 1, 'extra': 1, 'complicated': 1, 'layer': 1, 'beings': 1, 'traveled': 1, 'cool': 1, 'wondered': 1, 'maybe': 1, 'outer': 1, 'hide': 1, 'reports': 1, 'abductions': 1, 'ajarraccoon': 1, 'lyle': 1, 'blackburn': 1, 'meet': 1, 'ata': 1, 'convention': 1, 'signed': 1, 'vite': 1, 'tor': 1, 'hopefully': 1, 'glass': 1, 'drunken': 1, 'huntsman': 1, 'skyrim': 1, 'carries': 1, 'obesity': 1, 'yadav': 1, 'studies': 1, 'gut': 1, 'wake': 1, 'forest': 1, 'states': 1, 'current': 1, 'mother': 1, 'eg': 1, 'medical': 1, 'community': 1, 'result': 1, 'consuming': 1, 'calories': 1, 'decade': 1, 'confirmed': 1, 'microbes': 1, 'living': 1, 'associ': 1, 'ated': 1, 'causes': 1, 'hariom': 1, 'sistant': 1, 'molecular': 1, 'baptist': 1, 'united': 1, 'percentage': 1, 'adolescents': 1, 'tripled': 1, 'according': 1, 'centers': 1, 'control': 1, 'prevention': 1, 'increasing': 1, 'rate': 1, 'among': 1, 'aged': 1, 'unacceptably': 1, 'indicates': 1, 'worrisome': 1, 'prospects': 1, 'generation': 1, 'article': 1, 'published': 1, 'issue': 1, 'reviews': 1, 'reviewed': 1, 'existing': 1, 'animal': 1, 'interaction': 1, 'microbiome': 1, 'immune': 1, 'cells': 1, 'baby': 1, 'gestation': 1, 'con': 1, 'tribute': 1, 'childhood': 1, 'described': 1, 'diet': 1, 'exercise': 1, 'cesarean': 1, 'feeding': 1, 'breathing': 1, 'air': 1, 'replenish': 1, 'wild': 1, 'strawberry': 1, 'restore': 1, 'mana': 1, 'listening': 1, 'folk': 1, 'music': 1, 'taking': 1, 'walk': 1, 'nerdgasrnz': 1, 'pessimistic': 1, 'suggestions': 1, 'improving': 1, 'mental': 1, 'purely': 1, 'bc': 1, 'worded': 1, 'xanthera': 1, 'therapy': 1, 'longterm': 1, 'ritual': 1, 'deal': 1, 'debuffs': 1, 'datadevourer': 1, 'codewar': 1, 'practicing': 1, 'stuck': 1, 'sone': 1, 'clue': 1, 'voila': 1, 'seek': 1, 'save': 1, 'copy': 1, 'pasting': 1, 'easyncheesy': 1, 'logically': 1, 'map': 1, 'intermediate': 1, 'actively': 1, 'wasting': 1, 'rich': 1, 'raise': 1, 'debt': 1, 'congress': 1, 'politicians': 1, 'salary': 1, 'politician': 1, 'taxes': 1, 'exempt': 1, 'itsnunyabusiness': 1, 'nation': 1, 'accumulates': 1, 'members': 1, 'senate': 1, 'disqualified': 1, 'betcha': 1, 'accumulating': 1, 'begin': 1, 'owningmclovin': 1, 'federal': 1, 'already': 1, 'arent': 1, 'poor': 1, 'backgrounds': 1, 'thos': 1, 'campaign': 1, 'donations': 1, 'paid': 1, 'largely': 1, 'unaffected': 1, 'lack': 1, 'impression': 1, 'bulk': 1, 'sources': 1, 'actual': 1, 'salaries': 1, 'private': 1, 'investments': 1, 'bribes': 1, 'congressman': 1, 'wealthy': 1, 'phone': 1, 'attractive': 1, 'filter': 1, 'color': 1, 'daniel': 1, 'gross': 1, 'nosurf': 1, 'fibonacciseries': 1, 'turning': 1, 'greyscale': 1, 'iphone': 1, 'filters': 1, 'scales': 1, 'yr': 1, 'ex': 1, 'apple': 1, 'leaves': 1, 'reduce': 1, 'usage': 1, 'difference': 1, 'magically': 1, 'becomes': 1, 'checking': 1, 'standby': 1, 'placebo': 1, 'fan': 1, 'urge': 1, 'seems': 1, 'teams': 1, 'engineers': 1, 'choosing': 1, 'vibrant': 1, 'guarantee': 1, 'tna': 1, 'ni': 1, 'efficiently': 1, 'computers': 1, 'computer': 1, 'designed': 1, 'structures': 1, 'scientist': 1, 'discovered': 1, 'electricity': 1, 'perform': 1, 'calculations': 1, 'programming': 1, 'languages': 1, 'represent': 1, 'computations': 1, 'artificial': 1, 'intelligence': 1, 'scientists': 1, 'discovery': 1, 'theories': 1, 'future': 1, 'information': 1, 'cs': 1, 'crossing': 1, 'heavenly': 1, 'focused': 1, 'computational': 1, 'assembly': 1, 'math': 1, 'electives': 1, 'db': 1, 'administration': 1, 'studying': 1, 'picking': 1, 'easy': 1, 'prograr': 1, 'bullet': 1, 'basicbulletjournals': 1, 'irenic': 1, 'rose': 1, 'returned': 1, 'basic': 1, 'form': 1, 'format': 1, 'ryder': 1, 'caroll': 1, 'detrashed': 1, 'tdgonex': 1, 'imgur': 1, 'oe': 1, 'mathematics': 1, 'maths': 1, 'history': 1, 'iseemath': 1, 'princeton': 1, 'companion': 1, 'comprehensive': 1, 'readily': 1, 'written': 1, 'respected': 1, 'authors': 1, 'hacksaw': 1, 'overview': 1, 'plenty': 1, 'youtube': 1, 'binge': 1, 'drunk': 1, 'hope': 1, 'eulerfangirl': 1, 'factorials': 1, 'k': 1, 'addemf': 1, 'researching': 1, 'although': 1, 'restricted': 1, 'curious': 1, 'generally': 1, 'kinds': 1, 'inference': 1, 'figured': 1, 'navigation': 1, 'iron': 1, 'smelting': 1, 'mathematical': 1, 'inferences': 1, 'osceandriiver': 1, 'vervw': 1, 'oand': 1, 'bing': 1, 'crosby': 1, 'danish': 1, 'salmon': 1, 'conservation': 1, 'denmark': 1, 'government': 1, 'law': 1, 'cj': 1, 'moki': 1, 'advocated': 1, 'atlantic': 1, 'overfishing': 1, 'banned': 1, 'everything': 1, 'protested': 1, 'overturn': 1, 'enact': 1, 'legislation': 1, 'handedly': 1, 'managed': 1, 'create': 1, 'atrociousthoughts': 1, 'cosby': 1, 'confused': 1, 'aande': 1, 'dedi': 1, 'iec': 1, 'august': 1, 'radio': 1, 'detected': 1, 'signal': 1, 'astronomer': 1, 'wow': 1, 'elvis': 1, 'dead': 1, 'cdt': 1, 'satire': 1, 'ohio': 1, 'state': 1, 'telescope': 1, 'prompted': 1, 'write': 1, 'margin': 1, 'printout': 1, 'strongest': 1, 'candidate': 1, 'alien': 1, 'transmission': 1, 'nine': 1, 'though': 1, 'pronounced': 1, 'died': 1, 'shortly': 1, 'leaving': 1, 'bathroom': 1, 'lenny': 1, 'owen': 1, 'wilson': 1, 'recommend': 1, 'leetcode': 1, 'nv': 1, 'answer': 1, 'highly': 1, 'cracking': 1, 'clrs': 1, 'reference': 1, 'ds': 1, 'pdf': 1, 'online': 1, 'java': 1, 'starting': 1, 'orders': 1, 'revisits': 1, 'reinforced': 1, 'promise': 1, 'extend': 1, 'list': 1, 'busy': 1, 'tuesday': 1, 'fri': 1, 'yay': 1, 'pat': 1, 'tremor': 1, 'thyroid': 1, 'insertcaffeine': 1, 'heartfelt': 1, 'damn': 1, 'imk': 1, 'rough': 1, 'smile': 1, 'drink': 1, 'drugs': 1, 'diagnosed': 1, 'graves': 1, 'treated': 1, 'kinky': 1, 'snorlax': 1, 'hyperthyroidism': 1, 'underwent': 1, 'radioactive': 1, 'iodine': 1, 'treatment': 1, 'hypothyroid': 1, 'lips': 1, 'pale': 1, 'sunken': 1, 'eyes': 1, 'sick': 1, 'dying': 1, 'shit': 1, 'fucks': 1, 'explain': 1, 'knows': 1, 'ft': 1, 'text': 1, 'seat': 1, 'car': 1, 'stopdrinking': 1, 'message': 1, 'reminder': 1, 'gratitude': 1, 'lam': 1, 'angry': 1, 'moderate': 1, 'alcoho': 1, 'prioritize': 1, 'therapist': 1, 'pass': 1, 'restaurant': 1, 'driver': 1, 'sat': 1, 'passenger': 1, 'forgot': 1, 'throw': 1, 'fell': 1, 'asleep': 1, 'bed': 1, 'checked': 1, 'guest': 1, 'ruin': 1, 'continue': 1, 'comprised': 1, 'notes': 1, 'skuldafn': 1, 'ended': 1, 'potions': 1, 'draugrs': 1, 'fighting': 1, 'bored': 1, 'ready': 1, 'running': 1, 'everywhere': 1, 'screaming': 1, 'sissy': 1, 'avoid': 1, 'killed': 1, 'foiled': 1, 'etistertclarge': 1, 'puzzle': 1, 'dignified': 1, 'faced': 1, 'offset': 1, 'near': 1, 'unless': 1, 'posse': 1, 'drauger': 1, 'deathlords': 1, 'wights': 1, 'leap': 1, 'touched': 1, 'within': 1, 'moments': 1, 'exhausted': 1, 'soulgems': 1, 'weapons': 1, 'methinks': 1, 'prepared': 1, 'completed': 1, 'khajiit': 1, 'nightinggale': 1, 'armour': 1, 'primary': 1, 'normal': 1, 'combat': 1, 'handed': 1, 'restoration': 1, 'conjuration': 1, 'spells': 1, 'ice': 1, 'comftort': 1, 'iy': 1, 'wsyusuallyjread': 1, 'chapter': 1, 'ofa': 1, 'ras': 1, 'lightsjout': 1, 'sy': 1, 'em': 1, 'angelamartin': 1, 'subject': 1, 'copyright': 1, 'phoenix': 1, 'venezuela': 1, 'god': 1, 'rain': 1, 'wl': 1, 'hy': 1, 'october': 1, 'aboard': 1, 'cargo': 1, 'ship': 1, 'miami': 1, 'abandoned': 1, 'followers': 1, 'notorious': 1, 'religious': 1, 'cult': 1, 'charismatic': 1, 'former': 1, 'preacher': 1, 'named': 1, 'david': 1, 'berg': 1, 'moses': 1, 'late': 1, 'wandering': 1, 'west': 1, 'coast': 1, 'vw': 1, 'microbus': 1, 'missionaries': 1, 'traveling': 1, 'southern': 1, 'puerto': 1, 'rico': 1, 'giving': 1, 'joaquin': 1, 'liberty': 1, 'sing': 1, 'river': 1, 'busking': 1, 'street': 1, 'archbishops': 1, 'trinidad': 1, 'psychedelic': 1, 'porch': 1, 'adams': 1, 'summer': 1, 'mrboombabdtlc': 1, 'flinty': 1, 'lovesmesomeredhead': 1, 'movie': 1, 'dropping': 1, 'kissed': 1, 'flicking': 1, 'jf': 1, 'antwoord': 1, 'standing': 1, 'mama': 1, 'told': 1, 'oooh': 1, 'held': 1, 'hand': 1, 'mudders': 1, 'fun': 1, 'bryan': 1, 'singer': 1, 'november': 1, 'interviewer': 1, 'replied': 1, 'mm': 1, 'nerves': 1, 'skydiving': 1, 'ww': 1, 'doo': 1, 'vyuninieniso': 1, 'fuckin': 1, 'luv': 1, 'mate': 1, 'randomthoughts': 1, 'fine': 1, 'dangerouspuhson': 1, 'timeline': 1, 'intensityyyyyyyyyyyyyyyyy': 1, 'loudnessssssssss': 1, 'sudden': 1, 'crotch': 1, 'pain': 1, 'excess': 1, 'adrenaline': 1, 'calm': 1, 'situation': 1, 'bumpy': 1, 'landing': 1, 'hobble': 1, 'muted': 1, 'fey': 1, 'lisping': 1, 'lynx': 1, 'descriptions': 1, 'added': 1, 'encyclopedia': 1, 'articles': 1, 'certain': 1, 'feels': 1, 'trope': 1, 'mikevago': 1, 'favorite': 1, 'ralph': 1, 'kramden': 1, 'influenced': 1, 'sitcom': 1, 'homer': 1, 'simpson': 1, 'ie': 1, 'selfish': 1, 'short': 1, 'sighted': 1, 'schemer': 1, 'grudgingly': 1, 'bob': 1, 'opposite': 1, 'else': 1, 'schemes': 1, 'dragged': 1, 'anyway': 1, 'hj': 1, 'action': 1, 'lawyer': 1, 'comics': 1, 'funny': 1, 'mom': 1, 'smart': 1, 'useless': 1, 'oaf': 1, 'subversion': 1, 'older': 1, 'stern': 1, 'cardigan': 1, 'pipe': 1, 'smoking': 1, 'lessons': 1, 'teaching': 1, 'episode': 1, 'archetype': 1, 'roseanne': 1, 'simpsons': 1, 'became': 1, 'subverting': 1, 'tropes': 1, 'copied': 1, 'datalnthestone': 1, 'thats': 1, 'sauce': 1, 'toss': 1, 'chicken': 1, 'rice': 1, 'oil': 1, 'soy': 1, 'mushrooms': 1, 'garlic': 1, 'veggie': 1, 'bowl': 1, 'cooked': 1, 'publicfigurex': 1, 'fried': 1, 'broccolini': 1, 'pepper': 1, 'serrano': 1, 'loooots': 1, 'yer': 1, 'mis': 1, 'steam': 1, 'broccoli': 1, 'wok': 1, 'ripping': 1, 'hot': 1, 'hey': 1, 'smokey': 1, 'onions': 1, 'peppers': 1, 'soften': 1, 'adding': 1, 'toasting': 1, 'throwing': 1, 'marinate': 1, 'sesame': 1, 'gochuchuang': 1, 'till': 1, 'juuuust': 1, 'thighs': 1, 'pieces': 1, 'depending': 1, 'fry': 1, 'rest': 1, 'teriyaki': 1, 'adam': 1, 'liaw': 1, 'cheap': 1, 'eatcheapandhealthy': 1, 'healthy': 1, 'fitness': 1, 'buy': 1, 'meats': 1, 'freeze': 1, 'immediately': 1, 'posted': 1, 'seriously': 1, 'saver': 1, 'literally': 1, 'pulled': 1, 'corned': 1, 'beef': 1, 'freezer': 1, 'patrick': 1, 'chucked': 1, 'crock': 1, 'pot': 1, 'cabbage': 1, 'potatoes': 1, 'celery': 1, 'tonight': 1, 'thoroughly': 1, 'local': 1, 'qualify': 1, 'thursday': 1, 'cupboard': 1, 'eggs': 1, 'sorts': 1, 'varies': 1, 'season': 1, 'monthly': 1, 'janitor': 1, 'fianc': 1, 'dayshift': 1, 'hunt': 1, 'solved': 1, 'treasure': 1, 'specific': 1, 'difficult': 1, 'icons': 1, 'removed': 1, 'predict': 1, 'casque': 1, 'okay': 1, 'possibility': 1, 'srepy': 1, 'metal': 1, 'art': 1, 'sculpture': 1, 'kryptos': 1, 'cia': 1, 'headquarters': 1, 'lilibie': 1, 'rabbit': 1, 'hole': 1, 'rookhunter': 1, 'feature': 1, 'landmarks': 1, 'locations': 1, 'casques': 1, 'horrible': 1, 'condition': 1, 'dimensional': 1, 'via': 1, 'media': 1, 'archived': 1, 'records': 1, 'longer': 1, 'accessible': 1, 'dog': 1, 'adopted': 1, 'atwater': 1, 'village': 1, 'facial': 1, 'li': 1, 'clock': 1, 'ed': 1, 'sj': 1, 'neighborhoods': 1, 'opies': 1, 'courtney': 1, 'morris': 1, 'la': 1, 'corner': 1, 'connections': 1, 'rescue': 1, 'realtor': 1, 'accountant': 1, 'printing': 1, 'lover': 1, 'healer': 1, 'books': 1, 'wonderful': 1, 'prices': 1, 'reasonable': 1, 'pampering': 1, 'deserve': 1, 'cruelty': 1, 'non': 1, 'toxic': 1, 'striking': 1, 'clinical': 1, 'actives': 1, 'botanicals': 1, 'happier': 1, 'https': 1, 'restingwitchfacials': 1, 'resting': 1, 'witch': 1, 'facials': 1, 'glendale': 1, 'notifications': 1, 'three': 1, 'gum': 1, 'slipped': 1, 'forth': 1, 'gotten': 1, 'eeae': 1, 'tldr': 1, 'beautiful': 1, 'frankly': 1, 'liked': 1, 'flirted': 1, 'band': 1, 'trip': 1, 'stopped': 1, 'gas': 1, 'station': 1, 'bought': 1, 'pack': 1, 'pocket': 1, 'backpack': 1, 'began': 1, 'silly': 1, 'mailed': 1, 'house': 1, 'stuffed': 1, 'wrapper': 1, 'offered': 1, 'note': 1, 'gave': 1, 'terrible': 1, 'otherwise': 1, 'suppose': 1, 'four': 1, 'kept': 1, 'anniversary': 1, 'marry': 1, 'bottom': 1, 'stored': 1, 'ali': 1, 'gregory': 1, 'dazzled': 1, 'ho': 1, 'syracuse': 1, 'university': 1, 'graduate': 1, 'program': 1, 'attest': 1, 'enthusiasm': 1, 'acumen': 1, 'teammate': 1, 'outstanding': 1, 'preparing': 1, 'presenting': 1, 'aggregation': 1, 'phd': 1, 'mba': 1, 'ne': 1, 'adjunct': 1, 'principal': 1, 'taught': 1, 'alison': 1, 'recc': 1, 'ins': 1, 'overall': 1, 'grade': 1, 'iess': 1, 'gr': 1, 'oc': 1, 'disaster': 1, 'failure': 1, 'system': 1, 'ramifications': 1, 'miles': 1, 'fucked': 1, 'arsen': 1, 'hit': 1, 'ocean': 1, 'die': 1, 'horribly': 1, 'stock': 1, 'dwarven': 1, 'elvish': 1, 'wi': 1, 'worst': 1, 'worry': 1, 'brett': 1, 'thanks': 1, 'tip': 1, 'darkness': 1, 'swept': 1, 'missed': 1, 'solitude': 1, 'fletcher': 1, 'mainly': 1, 'seem': 1, 'arrow': 1, 'bows': 1, 'charmed': 1, 'soul': 1, 'capture': 1, 'nightingale': 1, 'charged': 1, 'points': 1, 'frost': 1, 'umnking': 1, 'adoul': 1, 'ana': 1, 'naq': 1, 'waslin': 1, 'io': 1, 'ume': 1, 'toastedstapler': 1, 'jchevertonwynne': 1, 'steps': 1, 'class': 1, 'tests': 1, 'code': 1, 'expect': 1, 'assert': 1, 'statements': 1, 'wa': 1, 'jack': 1, 'pet': 1, 'owner': 1, 'sugar': 1, 'daddy': 1, 'waste': 1, 'keeping': 1, 'cute': 1, 'en': 1, 'jungle': 1, 'jackryan': 1, 'brings': 1, 'unstop': 1, 'watch': 1, 'pre': 1, 'ere': 1, 'etic': 1, 'eus': 1, 'belle': 1, 'baker': 1, 'dana': 1, 'schwartz': 1, 'danaschwartzzz': 1, 'tray': 1, 'singing': 1, 'daily': 1, 'stack': 1, 'n': 1, 'cake': 1, 'recursive': 1, 'string': 1, 'permutations': 1, 'parsing': 1, 'inboxes': 1, 'parker': 1, 'yesthisiskendra': 1, 'weekly': 1, 'parenthesis': 1, 'matching': 1, 'trick': 1, 'brackets': 1, 'phrases': 1, 'open': 1, 'realize': 1, 'hold': 1, 'storing': 1, 'store': 1, 'holding': 1, 'gets': 1, 'aa': 1, 'bcs': 1, 'thru': 1, 'stupid': 1, 'bumps': 1, 'painful': 1, 'pus': 1, 'filled': 1, 'acne': 1, 'thinned': 1, 'suffering': 1, 'asap': 1, 'bald': 1, 'lines': 1, 'embarrassing': 1, 'drank': 1, 'jock': 1, 'itch': 1, 'lotrimin': 1, 'af': 1, 'normally': 1, 'caused': 1, 'infection': 1, 'neosporin': 1, 'topical': 1, 'ultra': 1, 'butenafine': 1, 'helped': 1, 'otc': 1, 'clotrimazole': 1, 'mycelex': 1, 'miconazole': 1, 'micatin': 1, 'zeasorb': 1, 'tolnaftate': 1, 'aftate': 1, 'tinactin': 1, 'readers': 1, 'column': 1, 'report': 1, 'cleanser': 1, 'cetaphil': 1, 'chronic': 1, 'soothing': 1, 'capital': 1, 'unit': 1, 'background': 1, 'culture': 1, 'rigorous': 1, 'associates': 1, 'term': 1, 'funds': 1, 'ef': 1, 'location': 1, 'los': 1, 'angeles': 1, 'collegial': 1, 'honest': 1, 'intellectually': 1, 'member': 1, 'ofateam': 1, 'hallmark': 1, 'philosophy': 1, 'overriding': 1, 'whether': 1, 'regarding': 1, 'management': 1, 'stewardship': 1, 'built': 1, 'foundation': 1, 'shared': 1, 'values': 1, 'influence': 1, 'decision': 1, 'interact': 1, 'clients': 1, 'investors': 1, 'another': 1, 'integrity': 1, 'accountability': 1, 'collaboration': 1, 'humility': 1, 'consistency': 1, 'respect': 1, 'responsible': 1, 'performing': 1, 'include': 1, 'limited': 1, 'american': 1, 'fund': 1, 'target': 1, 'pcs': 1, 'institutional': 1, 'overseen': 1, 'react': 1, 'stephen': 1, 'grider': 1, 'dev': 1, 'redux': 1, 'courses': 1, 'explains': 1, 'mo': 1, 'vultesiupiilviavii': 1, 'cii': 1, 'professional': 1, 'developer': 1, 'contract': 1, 'freelancer': 1, 'moved': 1, 'engineering': 1, 'refresher': 1, 'insanely': 1, 'node': 1, 'memorizing': 1, 'talks': 1, 'advanced': 1, 'css': 1, 'html': 1, 'general': 1, 'intro': 1, 'confident': 1, 'thorough': 1, 'hooks': 1, 'section': 1, 'starts': 1, 'funky': 1, 'wants': 1, 'broken': 1, 'fail': 1, 'practices': 1, 'honestly': 1, 'hire': 1, 'junior': 1, 'projects': 1, 'check': 1, 'curriculums': 1, 'courseson': 1, 'rallycoding': 1, 'elliot': 1, 'protective': 1, 'watcher': 1, 'hello': 1, 'personalities': 1, 'sam': 1, 'scenes': 1, 'robot': 1, 'scarf': 1, 'hat': 1, 'mode': 1, 'fake': 1, 'whiterose': 1, 'project': 1, 'stein': 1, 'sgate': 1, 'type': 1, 'travel': 1, 'westworld': 1, 'interest': 1, 'stealing': 1, 'timelines': 1, 'dimensions': 1, 'interviewed': 1, 'beleiving': 1, 'philip': 1, 'price': 1, 'willing': 1, 'sacrifice': 1, 'tl': 1, 'dr': 1, 'alter': 1, 'quote': 1, 'hear': 1, 'entire': 1, 'assuming': 1, 'created': 1, 'watching': 1, 'screen': 1, 'assumption': 1, 'whichever': 1, 'elliott': 1, 'esmail': 1, 'thinks': 1, 'perspective': 1, 'narration': 1, 'meta': 1, 'bravo': 1, 'rachel': 1, 'fallout': 1, 'alosio': 1, 'deacon': 1, 'actor': 1, 'fandom': 1, 'wiki': 1, 'wf': 1, 'voice': 1, 'maps': 1, 'voiced': 1, 'powered': 1, 'wikia': 1})\n"
     ]
    }
   ],
   "source": [
    "def get_bow_from_dict(df, column):\n",
    "    each_freq = df[column].tolist()\n",
    "    most_freq = []\n",
    "    for freq in each_freq:\n",
    "        for f in freq:\n",
    "            most_freq.append(f[0])\n",
    "#         print(freq[0])\n",
    "        \n",
    "#     print(most_freq)\n",
    "    print(Counter(most_freq))\n",
    "    \n",
    "#     just_words = [k for (k,v) in  df[column].tolist()]\n",
    "#     print(just_words)\n",
    "    \n",
    "#     all_column_data = ' '.join(df[column].tolist())\n",
    "#     all_column_fd = Counter(all_column_data.split())\n",
    "#     return all_column_fd\n",
    "\n",
    "get_bow_from_dict(all_df, 'FREQ')\n",
    "\n",
    "# [my_series[c].value_counts() for c in list(my_series.select_dtypes(include=['O']).columns)]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 1. create a frequen"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}
