import numpy as np
import pandas as pd
train=p.read_csv("kaggle-sentiment/train.tsv", delimiter='\t')
y=train['Sentiment'].values
X=train['Phrase'].values

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):
    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 = "{} | B? {} | CV: {} | Classifier: {}"
    print(pretty_line.format(avg, str(boolean)[0], cv, str(classifier).split('(')[0]))
    
runPipeline(BernoulliNB(), False, 2)
runPipeline(BernoulliNB(), False, 3)
runPipeline(MultinomialNB(), False, 2)
runPipeline(MultinomialNB(), False, 3)
runPipeline(MultinomialNB(), True, 2)
runPipeline(MultinomialNB(), True, 3)

0.5529026288030471 | B? F | CV: 2 | Classifier: BernoulliNB
0.5531524365695574 | B? F | CV: 3 | Classifier: BernoulliNB
0.5592720169584305 | B? F | CV: 2 | Classifier: MultinomialNB
0.5595474569680894 | B? F | CV: 3 | Classifier: MultinomialNB
0.5596116298457374 | B? T | CV: 2 | Classifier: MultinomialNB
0.5601369637205256 | B? T | CV: 3 | Classifier: MultinomialNB

y

array([1, 2, 2, ..., 3, 2, 2])

df = pd.read_csv('hw6_data_sentiment.csv')

df

	0	PoN	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	no_shared_words
0	I went to XYZ restaurant last week and I was v...	N	['i', 'went', 'to', 'xyz', 'restaurant', 'last...	50	['I went to XYZ restaurant last week and I was...	3	['went', 'xyz', 'restaurant', 'last', 'week', ...	25	[('was', 4), ('to', 3), ('i', 2), ('and', 2), ...	[('went', 1), ('xyz', 1), ('restaurant', 1), (...	...	0.186	Counter({'was': 4, 'to': 3, 'i': 2, 'and': 2, ...	Counter({'went': 1, 'xyz': 1, 'restaurant': 1,...	i went to xyz restaurant last week and i was v...	went restaurant last week very disappointed. f...	['i', 'went', 'to', 'xyz', 'restaurant', 'last...	['was', 'to', 'i', 'and', 'the', 'a_NEG', 'for...	['i_went', 'went_to', 'to_xyz', 'xyz_restauran...	['i_went', 'went_to', 'to_xyz', 'xyz_restauran...	['i', 'to', 'xyz', 'week', 'and', 'i', 'was', ...
1	In each of the diner dish there are at least o...	N	['in', 'each', 'of', 'the', 'diner', 'dish', '...	78	['In each of the diner dish there are at least...	4	['diner', 'dish', 'least', 'one', 'fly', 'wait...	31	[('the', 6), ('in', 4), ('to', 4), ('of', 3), ...	[('want', 3), ('dish', 2), ('diner', 1), ('lea...	...	0.042	Counter({'the': 6, 'in': 4, 'to': 4, 'of': 3, ...	Counter({'want': 3, 'dish': 2, 'diner': 1, 'le...	in each of the diner dish there are at least o...	each diner dish there least waiting hour dish ...	['in', 'each', 'of', 'the', 'diner', 'dish', '...	['to_NEG', 'the', 'want_NEG', 'the_NEG', 'in',...	['in_each', 'each_of', 'of_the', 'the_diner', ...	['in_each', 'each_of', 'of_the', 'the_diner', ...	['in', 'of', 'the', 'diner', 'are', 'at', 'lea...
2	This is the last place you would want to dine ...	N	['this', 'is', 'the', 'last', 'place', 'you', ...	151	['This is the last place you would want to din...	7	['last', 'place', 'would', 'want', 'dine', 'pr...	61	[('to', 10), ('the', 9), ('and', 7), ('we', 5)...	[('minutes', 3), ('place', 2), ('price', 2), (...	...	0.171	Counter({'to': 10, 'the': 9, 'and': 7, 'we': 5...	Counter({'minutes': 3, 'place': 2, 'price': 2,...	this is the last place you would want to dine ...	this last place would want dine price that exp...	['this', 'is', 'the', 'last', 'place', 'you', ...	['to_NEG', 'the_NEG', 'and_NEG', 'we_NEG', 'ha...	['this_is', 'is_the', 'the_last', 'last_place'...	['this_is', 'is_the', 'the_last', 'last_place'...	['is', 'the', 'you', 'to', 'dine', 'at', 'the'...
3	I went to this restaurant where I had ordered ...	N	['i', 'went', 'to', 'this', 'restaurant', 'whe...	75	['I went to this restaurant where I had ordere...	6	['went', 'restaurant', 'ordered', 'complimenta...	33	[('i', 6), ('the', 6), ('to', 3), ('for', 3), ...	[('salad', 3), ('restaurant', 2), ('waiter', 2...	...	0.162	Counter({'i': 6, 'the': 6, 'to': 3, 'for': 3, ...	Counter({'salad': 3, 'restaurant': 2, 'waiter'...	i went to this restaurant where i had ordered ...	went this restaurant where ordered complimenta...	['i', 'went', 'to', 'this', 'restaurant', 'whe...	['the', 'i', 'salad', 'had', 'for', 'waiter', ...	['i_went', 'went_to', 'to_this', 'this_restaur...	['i_went', 'went_to', 'to_this', 'this_restaur...	['i', 'to', 'i', 'had', 'for', 'the', 'complim...
4	I went there with two friends at 6pm. Long que...	N	['i', 'went', 'there', 'with', 'two', 'friends...	73	['I went there with two friends at 6pm.', 'Lon...	10	['went', 'two', 'friends', 'long', 'queue', 'd...	38	[('there', 3), ('but', 3), ('it', 3), ('a', 3)...	[('two', 2), ('friends', 2), ('long', 2), ('di...	...	0.353	Counter({'there': 3, 'but': 3, 'it': 3, 'a': 3...	Counter({'two': 2, 'friends': 2, 'long': 2, 'd...	i went there with two friends at 6pm. long que...	went there with friends 6pm. long queue there....	['i', 'went', 'there', 'with', 'two', 'friends...	['a_NEG', 'there', 'us_NEG', 'but_NEG', 'and_N...	['i_went', 'went_there', 'there_with', 'with_t...	['i_went', 'went_there', 'there_with', 'with_t...	['i', 'two', 'at', 'queue', 'was', 'but', 'it'...
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
83	This place was one of the best restaurant I ha...	P	['this', 'place', 'was', 'one', 'of', 'the', '...	70	['This place was one of the best restaurant I ...	6	['place', 'one', 'best', 'restaurant', 'price'...	32	[('the', 5), ('i', 3), ('and', 3), ('this', 2)...	[('best', 2), ('area', 2), ('place', 1), ('one...	...	0.300	Counter({'the': 5, 'i': 3, 'and': 3, 'this': 2...	Counter({'best': 2, 'area': 2, 'place': 1, 'on...	this place was one of the best restaurant i ha...	this place best restaurant have been. price li...	['this', 'place', 'was', 'one', 'of', 'the', '...	['the', 'i', 'and', 'this', 'best', 'is', 'are...	['this_place', 'place_was', 'was_one', 'one_of...	['this_place', 'place_was', 'was_one', 'one_of...	['was', 'one', 'of', 'the', 'i', 'the', 'is', ...
84	The best experience I ever had happened in Lon...	P	['the', 'best', 'experience', 'i', 'ever', 'ha...	42	['The best experience I ever had happened in L...	3	['best', 'experience', 'ever', 'happened', 'lo...	21	[('the', 3), ('in', 3), ('food', 2), ('a', 2),...	[('food', 2), ('best', 1), ('experience', 1), ...	...	0.283	Counter({'the': 3, 'in': 3, 'food': 2, 'a': 2,...	Counter({'food': 2, 'best': 1, 'experience': 1...	the best experience i ever had happened in lon...	best experience ever happened london britain. ...	['the', 'best', 'experience', 'i', 'ever', 'ha...	['in', 'the', 'best', 'experience', 'i', 'ever...	['the_best', 'best_experience', 'experience_i'...	['the_best', 'best_experience', 'experience_i'...	['the', 'i', 'had', 'happened', 'in', 'london'...
85	This Japanese restaurant is so popular recentl...	P	['this', 'japanese', 'restaurant', 'is', 'so',...	88	['This Japanese restaurant is so popular recen...	12	['japanese', 'restaurant', 'popular', 'recentl...	49	[('is', 4), ('the', 4), ('japanese', 2), ('a',...	[('japanese', 2), ('food', 2), ('right', 2), (...	...	0.462	Counter({'is': 4, 'the': 4, 'japanese': 2, 'a'...	Counter({'japanese': 2, 'food': 2, 'right': 2,...	this japanese restaurant is so popular recentl...	this japanese restaurant popular recently that...	['this', 'japanese', 'restaurant', 'is', 'so',...	['the_NEG', 'is_NEG', 'japanese', 'a', 'and_NE...	['this_japanese', 'japanese_restaurant', 'rest...	['this_japanese', 'japanese_restaurant', 'rest...	['is', 'so', 'popular', 'recently', 'as', 'a',...
86	Hibachi the grill is one of my favorite restau...	P	['hibachi', 'the', 'grill', 'is', 'one', 'of',...	65	['Hibachi the grill is one of my favorite rest...	5	['hibachi', 'grill', 'one', 'favorite', 'resta...	30	[('the', 8), ('is', 6), ('it', 3), ('hibachi',...	[('hibachi', 2), ('grill', 2), ('restaurants',...	...	0.388	Counter({'the': 8, 'is': 6, 'it': 3, 'hibachi'...	Counter({'hibachi': 2, 'grill': 2, 'restaurant...	hibachi the grill is one of my favorite restau...	hibachi grill favorite restaurants. like drama...	['hibachi', 'the', 'grill', 'is', 'one', 'of',...	['the', 'is', 'it', 'hibachi', 'grill', 'of', ...	['hibachi_the', 'the_grill', 'grill_is', 'is_o...	['hibachi_the', 'the_grill', 'grill_is', 'is_o...	['hibachi', 'the', 'grill', 'is', 'one', 'of',...
87	I went to this ultra-luxurious restaurant in D...	P	['i', 'went', 'to', 'this', 'restaurant', 'in'...	63	['I went to this ultra-luxurious restaurant in...	5	['went', 'restaurant', 'downtown', 'new', 'yor...	35	[('i', 4), ('this', 3), ('and', 3), ('restaura...	[('restaurant', 2), ('expensive', 2), ('went',...	...	0.223	Counter({'i': 4, 'this': 3, 'and': 3, 'restaur...	Counter({'restaurant': 2, 'expensive': 2, 'wen...	i went to this ultra-luxurious restaurant in d...	went this ultra-luxurious restaurant downtown ...	['i', 'went', 'to', 'this', 'restaurant', 'in'...	['i', 'this', 'and', 'restaurant', 'in', 'expe...	['i_went', 'went_to', 'to_this', 'this_restaur...	['i_went', 'went_to', 'to_this', 'this_restaur...	['i', 'to', 'in', 'downtown', 'new', 'york', '...