{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'pd' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-1-ec0ffcc8cd61>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mtrain\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"kaggle-sentiment/train.tsv\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdelimiter\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'\\t'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      2\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Sentiment'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mX\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Phrase'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0mpred_vec\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mbigram_tv_v3\u001b[0m \u001b[0;31m# 60.4\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mNameError\u001b[0m: name 'pd' is not defined"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "train=pd.read_csv(\"kaggle-sentiment/train.tsv\", delimiter='\\t')\n",
    "y=train['Sentiment'].values\n",
    "X=train['Phrase'].values\n",
    "\n",
    "pred_vec = bigram_tv_v3 # 60.4\n",
    "\n",
    "\n",
    "test = pd.read_csv(\"kaggle-sentiment/test.tsv\", delimiter='\\t')\n",
    "k_id = test['PhraseId']\n",
    "k_text = test['Phrase']\n",
    "\n",
    "# k_vec = bigram_tv_v3.transform(k_text)\n",
    "# k_vec\n",
    "\n",
    "def get_kaggle_test_train_vec(X,y,vectorizer):\n",
    "    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=None, random_state=0)\n",
    "    X_train_vec = vectorizer.fit_transform(X_train)\n",
    "#     X_test_vec = vectorizer.transform(X_test)\n",
    "    return X_train_vec, y_train,\n",
    "\n",
    "def do_the_kaggle(X,y,vec):\n",
    "    X_train_vec, y_train = get_kaggle_test_train_vec(X,y,vec)\n",
    "    svm_clf = LinearSVC(C=1)\n",
    "    k_vec = pred_vec.transform(k_text)\n",
    "    print(len(X), X_train_vec.shape, k_vec.shape)\n",
    "\n",
    "    prediction = svm_clf.fit(X_train_vec,y_train).predict(k_vec)\n",
    "    kaggle_submission = zip(k_id, prediction)\n",
    "    outf=open('kaggle_submission_linearSVC_v8.csv', 'w')\n",
    "    outf.write('PhraseId,Sentiment\\n')\n",
    "    for x, value in enumerate(kaggle_submission): outf.write(str(value[0]) + ',' + str(value[1]) + '\\n')\n",
    "    outf.close()\n",
    "    print('prediction complete')\n",
    "\n",
    "do_the_kaggle(X,y,pred_vec)"
   ]
  },
  {
   "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}