HW4 PIPELINE + HW6 + HW7 + Final Project

Building off HW2 + HW3

In [28]:
## =======================================================
## IMPORTING
## =======================================================
import os
def get_data_from_files(path):
    directory = os.listdir(path)
    results = []
    for file in directory:
        f=open(path+file)
        results.append(f.read())
        f.close()
    return results

## =======================================================
## TOKENIZING
## =======================================================
from nltk.tokenize import word_tokenize, sent_tokenize
def get_tokens(sentence):
    tokens = word_tokenize(sentence)
    clean_tokens = [word.lower() for word in tokens if word.isalpha()]
    return clean_tokens

def get_sentence_tokens(review):
    return sent_tokenize(review)

## =======================================================
## REMOVING STOPWORDS
## =======================================================
from nltk.corpus import stopwords
stop_words = set(stopwords.words("english"))
def remove_stopwords(sentence):
    filtered_text = []
    for word in sentence:
        if word not in stop_words:
            filtered_text.append(word)
    return filtered_text

## =======================================================
## FREQUENCY DISTRIBUTIONS
## =======================================================
from nltk.probability import FreqDist
def get_most_common(tokens):
    fdist = FreqDist(tokens)
    return fdist.most_common(12)

def get_most_common(tokens):
    fdist = FreqDist(tokens)
    return fdist.most_common(12)

def get_fdist(tokens):
    return (FreqDist(tokens))

## =======================================================
## SENTIMENT ANALYSIS
## =======================================================
from nltk.sentiment import SentimentAnalyzer
from nltk.sentiment.util import *
from nltk.sentiment.vader import SentimentIntensityAnalyzer
sid = SentimentIntensityAnalyzer()

def get_vader_score(review):
    return sid.polarity_scores(review)

def separate_vader_score(vader_score, key):
    return vader_score[key]

## =======================================================
## SUMMARIZER
## =======================================================
def get_weighted_freq_dist(review, freq_dist):
    try:
        max_freq = max(freq_dist.values())
        for word in freq_dist.keys():
            freq_dist[word] = (freq_dist[word]/max_freq)
        return freq_dist
    except:
        for word in freq_dist.keys():
            freq_dist[word] = (freq_dist[word]/1)
        return freq_dist
        

def get_sentence_score(review, freq_dist):
    sentence_scores = {}
    for sent in review:
        for word in nltk.word_tokenize(sent.lower()):
            if word in freq_dist.keys():
                if len(sent.split(' ')) < 30:
                    if sent not in sentence_scores.keys():
                        sentence_scores[sent] = freq_dist[word]
                    else:
                        sentence_scores[sent] += freq_dist[word]
    return sentence_scores

def get_summary_sentences(sentence_scores):
    sorted_sentences = sorted(sentence_scores.items(), key=lambda kv: kv[1], reverse=True)
    return ''.join(sent[0] for sent in sorted_sentences[:5])

def get_freq_words(freq_dist):
    sorted_words = sorted(freq_dist.items(), key=lambda kv: kv[1], reverse=True)
    return ' '.join(word[0] for word in sorted_words[:50])

## =======================================================
## MACHINE LEARNING -- NAIVE BAYES
## =======================================================
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB, MultinomialNB, BernoulliNB
from sklearn import metrics
from sklearn.metrics import confusion_matrix, classification_report

# def get_NB(small_df, labels):
#     x_train, x_test, y_train, y_test = train_test_split(small_df.values, labels, test_size=0.3, random_state = 109)

#     gnb = GaussianNB()
#     gnb.fit(x_train, y_train)
#     y_pred = gnb.predict(x_test)
#     print("Accuracy:", metrics.accuracy_score(y_test, y_pred))
    
    
def get_NB(small_df, labels, classifier, title):
    seeds = [109, 210, 420, 19, 7]
    dfs = []
    overall = []
    print(title)
    for seed in seeds:
        x_train, x_test, y_train, y_test = train_test_split(small_df.values, 
                                                            labels, test_size=0.3, random_state = seed)
        gnb = classifier
        gnb.fit(x_train, y_train).score(x_train, y_train)
        y_pred = gnb.predict(x_test)
        accuracy =  metrics.accuracy_score(y_test, y_pred)
        report = metrics.classification_report(y_test, y_pred)
        print("Accuracy:", accuracy)
#         print(report)
        overall.append(accuracy)
        cm = confusion_matrix(y_test, y_pred)
        # confusion_matrix_graph(cm, accuracy, "NB Multinomial Tokenized")
#         tn, fp, fn, tp = cm.ravel()
        df = pd.DataFrame(cm.ravel())
        dfs.append(df)
    print('AVERAGE ACCURACY:', sum(overall)/len(overall))
    return dfs


def display_NB_tables(dfs):
    for df in dfs:
        print(display(df))
        
## =======================================================
## PLOTS
## =======================================================        
import seaborn as sns
import matplotlib.pyplot as plt 
def bar_plot(df, title): 
    graph = sns.barplot(y = "count", x = "word", data = df, palette = "husl")
    plt.title(title)
    plt.xlabel("Word")
    plt.ylabel("Count")
    sns.set_context("talk")
    plt.xticks(rotation = 90)
    return plt

from nltk.tokenize import casual_tokenize
from collections import Counter


## =======================================================
## CLEANERS
## =======================================================   
import re, string
def diy_cleaner(review):
    try:
        both = review.split('\n')
        title = both[0]
        review = both[1]
        review = review.replace("'","")
    except:
        review = review.replace("'","")
    pattern = re.compile('[\W_]+')
    review = pattern.sub(' ', review)
    cleaned = title + ' ' + title + ' ' + review
    return cleaned.lower()

def pruner(review):
    clean_review = ' '.join([word for word in review.split() if len(word) > 3])
    return clean_review

sentim_analyzer = SentimentAnalyzer()
def get_nltk_negs(tokens):
    all_words_neg = sentim_analyzer.all_words([mark_negation(tokens)])
    return all_words_neg

def get_unigram_feats(neg_tokens):
    unigram_feats = sentim_analyzer.unigram_word_feats(neg_tokens)
    return unigram_feats
    
def get_bigram_feats(tokens):
    ngrams = zip(*[tokens[i:] for i in range(2)])
    return ["_".join(ngram) for ngram in ngrams]

## =======================================================
## HELPERS
## =======================================================  
def get_bow_from_column(df, column):
    all_column_data = ' '.join(df[column].tolist())
    all_column_fd = Counter(all_column_data.split())
    return all_column_fd

def get_common_words(num):
    most_common_neg = [word[0] for word in big_bow_n.most_common(num)]
    most_common_pos = [word[0] for word in big_bow_p.most_common(num)]
    in_both = np.intersect1d(most_common_neg, most_common_pos)
    neg_notpos = np.setdiff1d(most_common_neg, most_common_pos)
    pos_notneg = np.setdiff1d(most_common_pos, most_common_neg)
    return [len(in_both), len(neg_notpos), len(pos_notneg), len(in_both)/num, in_both, neg_notpos, pos_notneg]

def get_only_polarized(tokens, common_words):
    return [token for token in tokens if token not in common_words[4]] # 70

## =======================================================
## VISUALS
## =======================================================  
import wordcloud
from wordcloud import WordCloud, ImageColorGenerator
from PIL import Image
import seaborn as sns
import matplotlib.pyplot as plt 
def create_word_cloud_with_mask(path_of_mask_image, dictionary, 
                                max_num_words, title):
        mask = np.array(Image.open(path_of_mask_image))
        word_cloud = WordCloud(background_color = "white", 
                               max_words = max_num_words, 
                               mask = mask, max_font_size = 125, 
                               random_state = 1006)
        word_cloud.generate_from_frequencies(dictionary)
        image_colors = ImageColorGenerator(mask)
        plt.figure(figsize = [8,8])
        plt.imshow(word_cloud.recolor(color_func = image_colors), interpolation = "bilinear")
        plt.title(title)
        sns.set_context("poster")
        plt.axis("off")
        return plt
    
import seaborn as sns
import matplotlib.pyplot as plt 
def bar_plot(df, title): 
    graph = sns.barplot(y = "count", x = "word", data = df, palette = "husl")
    plt.title(title)
    plt.xlabel("Word")
    plt.ylabel("Count")
    sns.set_context("talk")
    plt.xticks(rotation = 90)
    return plt
In [29]:
import pandas as pd
import numpy as np



# train=pd.read_csv("../WK7/kaggle-sentiment/train.tsv", delimiter='\t')
# y=train['Sentiment'].values
# X=train['Phrase'].values

# all_df = pd.DataFrame(X)
# all_df['labels'] = y
# all_df

df = pd.read_csv('../death_row_discritized.csv')

def to_string(tokens):
    try:
        return " ".join(eval(tokens))
    except:
        return "error"
    
df['statement_string'] = df.apply(lambda x: to_string(x['last_statement']), axis=1)
# y=df['vic_kid'].values
y=df['prior_record'].values
y_labels = list(set(y))
X=df['statement_string'].values

all_df = pd.DataFrame(X)
all_df['labels'] = y
all_df

# neg_df = pd.DataFrame(neg)
# pos_df = pd.DataFrame(pos)

# pos_df['PoN'] = 'P'
# neg_df['PoN'] = 'N'
# all_df = neg_df.append(pos_df)
Out[29]:
0 labels
0 yeah first_person_pronoun want to address the ... yes
1 umm pamela can pronoun hear first_person_prono... yes
2 its on september th kayla and david first_pers... yes
3 hi ladies first_person_pronoun wanted to tell ... yes
4 lord forgive pronoun pronoun dont know what pr... yes
... ... ...
561 i pray that first_person_pronoun family will r... unknown
562 when asked if pronoun had a last statement pro... yes
563 what is about to transpire in a few moments is... no
564 none yes
565 statement to the media first_person_pronoun at... yes

566 rows × 2 columns

In [30]:
# neg = get_data_from_files('../NEG_JK/')
# pos = get_data_from_files('../POS_JK/')

# neg = get_data_from_files('../neg_cornell/')
# pos = get_data_from_files('../pos_cornell/')

# neg = get_data_from_files('../neg_hw4/')
# pos = get_data_from_files('../pos_hw4/')

# neg = get_data_from_files('../hw4_lie_false/')
# pos = get_data_from_files('../hw4_lie_true/')

# pos = get_data_from_files('../hw4_lie_false/')
# neg = get_data_from_files('../hw4_lie_true/')



all_df['tokens'] = all_df.apply(lambda x: get_tokens(x[0]), axis=1)
all_df['num_tokens'] = all_df.apply(lambda x: len(x['tokens']), axis=1)

all_df = all_df.drop(all_df[all_df.num_tokens < 1].index)

all_df['sentences'] = all_df.apply(lambda x: get_sentence_tokens(x[0]), axis=1)
all_df['num_sentences'] = all_df.apply(lambda x: len(x['sentences']), axis=1)

all_df['no_sw'] = all_df.apply(lambda x: remove_stopwords(x['tokens']),axis=1)
all_df['num_no_sw'] = all_df.apply(lambda x: len(x['no_sw']),axis=1)

all_df['topwords_unfil'] = all_df.apply(lambda x: get_most_common(x['tokens']),axis=1)
all_df['topwords_fil'] = all_df.apply(lambda x: get_most_common(x['no_sw']),axis=1)

all_df['freq_dist'] = all_df.apply(lambda x: get_fdist(x['no_sw']),axis=1)
all_df['freq_dist_unfil'] = all_df.apply(lambda x: get_fdist(x['tokens']),axis=1)

all_df['vader_all'] = all_df.apply(lambda x: get_vader_score(x[0]),axis=1)
all_df['v_compound'] = all_df.apply(lambda x: separate_vader_score(x['vader_all'], 'compound'),axis=1)
all_df['v_neg'] = all_df.apply(lambda x: separate_vader_score(x['vader_all'], 'neg'),axis=1)
all_df['v_neu'] = all_df.apply(lambda x: separate_vader_score(x['vader_all'], 'neu'),axis=1)
all_df['v_pos'] = all_df.apply(lambda x: separate_vader_score(x['vader_all'], 'pos'),axis=1)

all_df['weighted_freq_dist'] = all_df.apply(lambda x: get_weighted_freq_dist(x['sentences'], x['freq_dist']),axis=1)
all_df['sentence_scores'] = all_df.apply(lambda x: get_sentence_score(x['sentences'], x['freq_dist']),axis=1)
all_df['summary_sentences'] = all_df.apply(lambda x: get_summary_sentences(x['sentence_scores']), axis=1)

all_df['vader_sum_all'] = all_df.apply(lambda x: get_vader_score(x['summary_sentences']),axis=1)
all_df['v_compound_sum'] = all_df.apply(lambda x: separate_vader_score(x['vader_sum_all'], 'compound'),axis=1)
all_df['v_neg_sum'] = all_df.apply(lambda x: separate_vader_score(x['vader_sum_all'], 'neg'),axis=1)
all_df['v_neu_sum'] = all_df.apply(lambda x: separate_vader_score(x['vader_sum_all'], 'neu'),axis=1)
all_df['v_pos_sum'] = all_df.apply(lambda x: separate_vader_score(x['vader_sum_all'], 'pos'),axis=1)

all_df['v_freq_words'] = all_df.apply(lambda x: get_freq_words(x['freq_dist']), axis=1)

all_df['vader_fq_all'] = all_df.apply(lambda x: get_vader_score(x['v_freq_words']),axis=1)
all_df['v_compound_fd'] = all_df.apply(lambda x: separate_vader_score(x['vader_fq_all'], 'compound'),axis=1)
all_df['v_neg_fd'] = all_df.apply(lambda x: separate_vader_score(x['vader_fq_all'], 'neg'),axis=1)
all_df['v_neu_fd'] = all_df.apply(lambda x: separate_vader_score(x['vader_fq_all'], 'neu'),axis=1)
all_df['v_pos_fd'] = all_df.apply(lambda x: separate_vader_score(x['vader_fq_all'], 'pos'),axis=1)

all_df['bow'] = all_df.apply(lambda x: Counter(x['tokens']), axis=1)
all_df['bow_nosw'] = all_df.apply(lambda x: Counter(x['no_sw']), axis=1)

all_df['diy_cleaner'] = all_df.apply(lambda x: diy_cleaner(x[0]), axis=1)
all_df['pruned'] = all_df.apply(lambda x: pruner(x['diy_cleaner']), axis=1)

all_df['nltk_negs'] = all_df.apply(lambda x: get_nltk_negs(x['tokens']), axis=1)
all_df['unigram_feats'] = all_df.apply(lambda x: get_unigram_feats(x['nltk_negs']), axis=1)
all_df['bigram_feats'] = all_df.apply(lambda x: get_bigram_feats(x['tokens']), axis=1)
all_df['bigram_feats_neg'] = all_df.apply(lambda x: get_bigram_feats(x['nltk_negs']), axis=1)

big_bow = get_bow_from_column(all_df, 'pruned')
big_bow_1 = get_bow_from_column(all_df[all_df['labels'] == 'yes'], 'pruned')
big_bow_2 = get_bow_from_column(all_df[all_df['labels'] == 'no'], 'pruned')
big_bow_3 = get_bow_from_column(all_df[all_df['labels'] == 'unknown'], 'pruned')
# big_bow_4 = get_bow_from_column(all_df[all_df['labels'] == 4], 'pruned')
# big_bow_5 = get_bow_from_column(all_df[all_df['labels'] == 5], 'pruned')

# most_common_1 = [word[0] for word in big_bow_n.most_common(100)]
# most_common_2 = [word[0] for word in big_bow_p.most_common(100)]



# all_df['no_shared_words'] = all_df.apply(lambda x: get_only_polarized(x['tokens'], get_common_words(500)), axis=1)
In [31]:
all_df['PoN'] = all_df['labels']
all_df[:3]
Out[31]:
0 labels tokens num_tokens sentences num_sentences no_sw num_no_sw topwords_unfil topwords_fil ... v_pos_fd bow bow_nosw diy_cleaner pruned nltk_negs unigram_feats bigram_feats bigram_feats_neg PoN
0 yeah first_person_pronoun want to address the ... yes [yeah, want, to, address, the, roundtree, fami... 48 [yeah first_person_pronoun want to address the... 1 [yeah, want, address, roundtree, family, apolo... 26 [(and, 6), (to, 5), (pronoun, 4), (the, 3), (f... [(pronoun, 4), (family, 2), (im, 2), (yeah, 1)... ... 0.356 {'yeah': 1, 'want': 1, 'to': 5, 'address': 1, ... {'yeah': 1, 'want': 1, 'address': 1, 'roundtre... yeah first_person_pronoun want to address the ... yeah first_person_pronoun want address roundtr... [yeah, want, to, address, the, roundtree, fami... [to, the, and, and_NEG, family, pronoun, to_NE... [yeah_want, want_to, to_address, address_the, ... [yeah_want, want_to, to_address, address_the, ... yes
1 umm pamela can pronoun hear first_person_prono... yes [umm, pamela, can, pronoun, hear, stephanie, h... 52 [umm pamela can pronoun hear first_person_pron... 1 [umm, pamela, pronoun, hear, stephanie, hardy,... 34 [(pronoun, 4), (and, 4), (yall, 4), (tell, 3),... [(pronoun, 4), (yall, 4), (tell, 3), (love, 2)... ... 0.272 {'umm': 1, 'pamela': 1, 'can': 1, 'pronoun': 4... {'umm': 1, 'pamela': 1, 'pronoun': 4, 'hear': ... umm pamela can pronoun hear first_person_prono... pamela pronoun hear first_person_pronoun steph... [umm, pamela, can, pronoun, hear, stephanie, h... [pronoun, and, yall, tell, the, love, am, for,... [umm_pamela, pamela_can, can_pronoun, pronoun_... [umm_pamela, pamela_can, can_pronoun, pronoun_... yes
2 its on september th kayla and david first_pers... yes [its, on, september, th, kayla, and, david, wa... 110 [its on september th kayla and david first_per... 1 [september, th, kayla, david, wanted, apologiz... 60 [(to, 6), (the, 5), (yall, 5), (pain, 4), (cau... [(yall, 5), (pain, 4), (caused, 4), (apologize... ... 0.199 {'its': 1, 'on': 1, 'september': 1, 'th': 1, '... {'september': 1, 'th': 1, 'kayla': 1, 'david':... its on september th kayla and david first_pers... september kayla david first_person_pronoun wan... [its, on, september, th, kayla, and, david, wa... [yall_NEG, to, the_NEG, pain_NEG, caused_NEG, ... [its_on, on_september, september_th, th_kayla,... [its_on, on_september, september_th, th_kayla,... yes

3 rows × 40 columns

SAVE TO CSV!

In [32]:
# all_df.to_csv('hw7_data_sentiment.csv',index=False)
# all_df['PoN'] = all_df['labels']
# all_df
In [33]:
small_df = all_df.filter(['v_compound','v_pos', 'v_neg', 'v_neu'])
tables = get_NB(small_df, all_df['PoN'], GaussianNB(), 'Vader Scores -- Gaussian')
# display_NB_tables(tables)
Vader Scores -- Gaussian
Accuracy: 0.5058823529411764
Accuracy: 0.5117647058823529
Accuracy: 0.49411764705882355
Accuracy: 0.5176470588235295
Accuracy: 0.5176470588235295
AVERAGE ACCURACY: 0.5094117647058823
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
In [34]:
small_df = all_df.filter(['v_pos','v_neu'])
tables = get_NB(small_df, all_df['PoN'], MultinomialNB(), 'Positive Vader Scores -- Multinomial')
Positive Vader Scores -- Multinomial
Accuracy: 0.5470588235294118
Accuracy: 0.5764705882352941
Accuracy: 0.5058823529411764
Accuracy: 0.5176470588235295
Accuracy: 0.5352941176470588
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
AVERAGE ACCURACY: 0.536470588235294
In [35]:
small_df = all_df.filter(['v_compound_sum','v_pos_sum', 'v_neg_sum', 'v_neu_sum']) 
tables = get_NB(small_df, all_df['PoN'], GaussianNB(), 'Vader Scores from Summary -- Gaussian')
Vader Scores from Summary -- Gaussian
Accuracy: 0.06470588235294118
Accuracy: 0.06470588235294118
Accuracy: 0.10588235294117647
Accuracy: 0.06470588235294118
Accuracy: 0.08823529411764706
AVERAGE ACCURACY: 0.07764705882352942
In [36]:
small_df = all_df.filter(['v_compound_sum','v_pos_sum', 'v_neg_sum', 'v_neu_sum', 
                          'v_compound','v_pos', 'v_neg', 'v_neu'])
tables = get_NB(small_df, all_df['PoN'], GaussianNB(), 'Vader Scores (original) and Vader Scores (summary) -- Gaussian')
Vader Scores (original) and Vader Scores (summary) -- Gaussian
Accuracy: 0.07058823529411765
Accuracy: 0.07058823529411765
Accuracy: 0.08823529411764706
Accuracy: 0.10588235294117647
Accuracy: 0.1
AVERAGE ACCURACY: 0.08705882352941177
In [37]:
small_df = all_df.filter(['v_compound_fd','v_pos_fd', 'v_neu_fd', 'v_neg_fd'])
tables = get_NB(small_df, all_df['PoN'], GaussianNB(), 'Vader Scores 50 most frequent filtered words -- Gaussian')
Vader Scores 50 most frequent filtered words -- Gaussian
Accuracy: 0.47058823529411764
Accuracy: 0.45294117647058824
Accuracy: 0.4588235294117647
Accuracy: 0.49411764705882355
Accuracy: 0.5235294117647059
AVERAGE ACCURACY: 0.48
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)

Bag of Words & Machine Learning

In [38]:
all_df['bow_v1'] = all_df.apply(lambda x: Counter(x['tokens']), axis=1)
all_df
new_df = pd.DataFrame(all_df['bow_v1'].tolist(), all_df['PoN'])
new_df = new_df.fillna(0).astype(int)
new_df[:5]
tables = get_NB(new_df, new_df.index, GaussianNB(), 'Starting point -- Gaussian')
Starting point -- Gaussian
Accuracy: 0.34705882352941175
Accuracy: 0.34705882352941175
Accuracy: 0.3588235294117647
Accuracy: 0.4176470588235294
Accuracy: 0.4294117647058823
AVERAGE ACCURACY: 0.38
In [39]:
tables = get_NB(new_df, new_df.index, GaussianNB(), 'Starting point -- Gaussian')
Starting point -- Gaussian
Accuracy: 0.34705882352941175
Accuracy: 0.34705882352941175
Accuracy: 0.3588235294117647
Accuracy: 0.4176470588235294
Accuracy: 0.4294117647058823
AVERAGE ACCURACY: 0.38
In [40]:
all_df['bow_v1'] = all_df.apply(lambda x: Counter(x['tokens']), axis=1)
new_df = pd.DataFrame(all_df['bow_v1'].tolist(), all_df['PoN'])
new_df = new_df.fillna(0).astype(int)
new_df[:5]
tables = get_NB(new_df, new_df.index, MultinomialNB(), 'Starting point -- Multinomial')
Starting point -- Multinomial
Accuracy: 0.4647058823529412
Accuracy: 0.5
Accuracy: 0.48823529411764705
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
Accuracy: 0.5117647058823529
Accuracy: 0.5058823529411764
AVERAGE ACCURACY: 0.49411764705882355
In [41]:
new_df = new_df.astype(bool).astype(int)
tables = get_NB(new_df, new_df.index, BernoulliNB(), 'Starting point -- Bernoulli')
Starting point -- Bernoulli
Accuracy: 0.48823529411764705
Accuracy: 0.49411764705882355
Accuracy: 0.5470588235294118
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
Accuracy: 0.4588235294117647
Accuracy: 0.5117647058823529
AVERAGE ACCURACY: 0.5
In [42]:
all_df['bow_v2'] = all_df.apply(lambda x: Counter(casual_tokenize(x['diy_cleaner'])), axis=1)
new_df = pd.DataFrame(all_df['bow_v2'].tolist(), all_df['PoN'])
new_df = new_df.fillna(0).astype(int)
new_df[:5]
tables = get_NB(new_df, new_df.index, GaussianNB(), 'DIY Cleaner -- Gaussian')
DIY Cleaner -- Gaussian
Accuracy: 0.34705882352941175
Accuracy: 0.34705882352941175
Accuracy: 0.3588235294117647
Accuracy: 0.4176470588235294
Accuracy: 0.4294117647058823
AVERAGE ACCURACY: 0.38
In [43]:
all_df['bow_v2'] = all_df.apply(lambda x: Counter(casual_tokenize(x['diy_cleaner'])), axis=1)
new_df = pd.DataFrame(all_df['bow_v2'].tolist(), all_df['PoN'])
new_df = new_df.fillna(0).astype(int)
new_df[:5]
tables = get_NB(new_df, new_df.index, MultinomialNB(), 'DIY Cleaner -- Multinomial')
DIY Cleaner -- Multinomial
Accuracy: 0.4647058823529412
Accuracy: 0.4823529411764706
Accuracy: 0.47058823529411764
Accuracy: 0.48823529411764705
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
Accuracy: 0.48823529411764705
AVERAGE ACCURACY: 0.4788235294117647
In [44]:
new_df = new_df.astype(bool).astype(int)
tables = get_NB(new_df, new_df.index, BernoulliNB(), 'DIY Cleaner -- Bernoulli')
DIY Cleaner -- Bernoulli
Accuracy: 0.48823529411764705
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
Accuracy: 0.5
Accuracy: 0.5470588235294118
Accuracy: 0.4588235294117647
Accuracy: 0.5117647058823529
AVERAGE ACCURACY: 0.5011764705882353
In [45]:
all_df['bow_v3'] = all_df.apply(lambda x: Counter(casual_tokenize(x['pruned'])), axis=1)
new_df = pd.DataFrame(all_df['bow_v3'].tolist(), all_df['PoN'])
new_df = new_df.fillna(0).astype(int)
new_df[:5]
tables = get_NB(new_df, new_df.index, GaussianNB(), 'Pruned Words -- Gaussian')
Pruned Words -- Gaussian
Accuracy: 0.37058823529411766
Accuracy: 0.34705882352941175
Accuracy: 0.36470588235294116
Accuracy: 0.40588235294117647
Accuracy: 0.43529411764705883
AVERAGE ACCURACY: 0.3847058823529412
In [46]:
all_df['bow_v3'] = all_df.apply(lambda x: Counter(casual_tokenize(x['pruned'])), axis=1)
new_df = pd.DataFrame(all_df['bow_v3'].tolist(), all_df['PoN'])
new_df = new_df.fillna(0).astype(int)
new_df[:5]
tables = get_NB(new_df, new_df.index, MultinomialNB(), 'Pruned Words -- Multinomial')
Pruned Words -- Multinomial
Accuracy: 0.4823529411764706
Accuracy: 0.49411764705882355
Accuracy: 0.47058823529411764
Accuracy: 0.5
Accuracy: 0.4588235294117647
AVERAGE ACCURACY: 0.48117647058823537
In [47]:
new_df = new_df.astype(bool).astype(int)
tables = get_NB(new_df, new_df.index, BernoulliNB(), 'Pruned Words -- Bernoulli')
Pruned Words -- Bernoulli
Accuracy: 0.5
Accuracy: 0.5117647058823529
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
Accuracy: 0.5411764705882353
Accuracy: 0.45294117647058824
Accuracy: 0.5235294117647059
AVERAGE ACCURACY: 0.5058823529411764
In [48]:
all_df['bow_v4'] = all_df.apply(lambda x: Counter(casual_tokenize(' '.join(x['nltk_negs']))), axis=1)
new_df = pd.DataFrame(all_df['bow_v4'].tolist(), all_df['PoN'])
new_df = new_df.fillna(0).astype(int)
new_df[:5]
tables = get_NB(new_df, new_df.index, GaussianNB(), 'NLTK negs -- Gaussian')
NLTK negs -- Gaussian
Accuracy: 0.32941176470588235
Accuracy: 0.36470588235294116
Accuracy: 0.4
Accuracy: 0.43529411764705883
Accuracy: 0.4588235294117647
AVERAGE ACCURACY: 0.3976470588235294
In [49]:
all_df['bow_v4'] = all_df.apply(lambda x: Counter(casual_tokenize(' '.join(x['nltk_negs']))), axis=1)
new_df = pd.DataFrame(all_df['bow_v4'].tolist(), all_df['PoN'])
new_df = new_df.fillna(0).astype(int)
new_df[:5]
tables = get_NB(new_df, new_df.index, GaussianNB(), 'NLTK negs -- Multinomial')
NLTK negs -- Multinomial
Accuracy: 0.32941176470588235
Accuracy: 0.36470588235294116
Accuracy: 0.4
Accuracy: 0.43529411764705883
Accuracy: 0.4588235294117647
AVERAGE ACCURACY: 0.3976470588235294
In [50]:
new_df = new_df.astype(bool).astype(int)
tables = get_NB(new_df, new_df.index, BernoulliNB(), 'NLTK negs -- Bernoulli')
NLTK negs -- Bernoulli
Accuracy: 0.5176470588235295
Accuracy: 0.5235294117647059
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
Accuracy: 0.5823529411764706
Accuracy: 0.4647058823529412
Accuracy: 0.5
AVERAGE ACCURACY: 0.5176470588235295
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
In [51]:
all_df['bow_v5'] = all_df.apply(lambda x: Counter(casual_tokenize(' '.join(x['bigram_feats']))), axis=1)
new_df = pd.DataFrame(all_df['bow_v5'].tolist(), all_df['PoN'])
new_df = new_df.fillna(0).astype(int)
new_df[:5]
tables = get_NB(new_df, new_df.index, GaussianNB(), 'Bigram Feats -- Gaussian')
Bigram Feats -- Gaussian
Accuracy: 0.40588235294117647
Accuracy: 0.4176470588235294
Accuracy: 0.4117647058823529
Accuracy: 0.40588235294117647
Accuracy: 0.4647058823529412
AVERAGE ACCURACY: 0.4211764705882353
In [52]:
all_df['bow_v5'] = all_df.apply(lambda x: Counter(casual_tokenize(' '.join(x['bigram_feats']))), axis=1)
new_df = pd.DataFrame(all_df['bow_v5'].tolist(), all_df['PoN'])
new_df = new_df.fillna(0).astype(int)
new_df[:5]
tables = get_NB(new_df, new_df.index, MultinomialNB(), 'Bigram Feats -- Multinomial')
Bigram Feats -- Multinomial
Accuracy: 0.5117647058823529
Accuracy: 0.5470588235294118
Accuracy: 0.45294117647058824
Accuracy: 0.5
Accuracy: 0.4823529411764706
AVERAGE ACCURACY: 0.4988235294117647
In [53]:
new_df = new_df.astype(bool).astype(int)
tables = get_NB(new_df, new_df.index, BernoulliNB(), 'Bigram Feats -- Bernoulli')
Bigram Feats -- Bernoulli
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
Accuracy: 0.5470588235294118
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
Accuracy: 0.5588235294117647
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
Accuracy: 0.5294117647058824
/Users/danielcaraway/anaconda3/lib/python3.7/site-packages/sklearn/metrics/classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
Accuracy: 0.48823529411764705
Accuracy: 0.5235294117647059
AVERAGE ACCURACY: 0.5294117647058824
In [55]:
# all_df['bow_v6'] = all_df.apply(lambda x: Counter(casual_tokenize(' '.join(x['no_shared_words']))), axis=1)
# new_df = pd.DataFrame(all_df['bow_v6'].tolist(), all_df['PoN'])
# new_df = new_df.fillna(0).astype(int)
# new_df[:5]
# tables = get_NB(new_df, new_df.index, GaussianNB(), 'No Shared Words -- Gaussian')
In [ ]:
all_df['bow_v6'] = all_df.apply(lambda x: Counter(casual_tokenize(' '.join(x['no_shared_words']))), axis=1)
new_df = pd.DataFrame(all_df['bow_v6'].tolist(), all_df['PoN'])
new_df = new_df.fillna(0).astype(int)
new_df[:5]
tables = get_NB(new_df, new_df.index, MultinomialNB(), 'No Shared Words -- Multinomial')
In [ ]:
new_df = new_df.astype(bool).astype(int)
tables = get_NB(new_df, new_df.index, BernoulliNB(), 'No Shared Words -- Bernoulli')
In [ ]:
create_word_cloud_with_mask('yellow_square.png', big_bow, 750, "Top Words")
In [ ]:
create_word_cloud_with_mask('red_square.png', big_bow_n, 750, "Top Negative Words")
In [ ]:
create_word_cloud_with_mask('green_square.png', big_bow_p, 750, "Top Positive Words")
In [ ]:
from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import cross_val_score
from sklearn.naive_bayes import BernoulliNB, MultinomialNB

def runPipeline(classifier, boolean, cv, X, y):
    nb_clf_pipe = Pipeline([('vect', CountVectorizer(encoding='latin-1', binary=boolean)),('nb', classifier)])
    scores = cross_val_score(nb_clf_pipe, X, y, cv=cv)
    avg=sum(scores)/len(scores)
#     pretty_line = "{} | Accuracy using {} -- and booleans? {}"
    pretty_line = "{} | B? {} | CV: {} | Classifier: {}"
    print(pretty_line.format(avg, str(boolean)[0], cv, str(classifier).split('(')[0]))

# X = array of data
# y = array of labels

hw6 = all_df[[0,'PoN']]
X = hw6[0].tolist()
y = hw6['PoN'].tolist()

runPipeline(BernoulliNB(), False, 5, X=X, y=y)
runPipeline(BernoulliNB(), False, 3, X=X, y=y)
runPipeline(MultinomialNB(), False, 5, X=X, y=y)
runPipeline(MultinomialNB(), False, 3, X=X, y=y)
runPipeline(MultinomialNB(), True, 5,  X=X, y=y)
runPipeline(MultinomialNB(), True, 3,  X=X, y=y)
In [ ]:
from tabulate import tabulate

df = hw6
def shorten(long_string):
    return long_string[:1] if len(long_string) < 21 else long_string[:20]

def df_for_tabulate(df, column):
    pretty_df = df.copy()
    pretty_df[column] = pretty_df.apply(lambda x: shorten(x[column]), axis = 1)
    return pretty_df
    
tabulate_df = df_for_tabulate(df, 0)
print(tabulate(tabulate_df[:10], tablefmt="simple", headers=tabulate_df.columns))
In [ ]:
 
In [ ]: