snip5.txt

#that was just testing the calls and poking around - now let's go deeper and use the tfidf transformer from prior cell
#tf_transformer = TfidfTransformer(use_idf=False).fit(counts) already sets us up
#set precision for printing to 4 decimals
#import numpy as np
from sklearn.feature_extraction.text import TfidfVectorizer


tfidf = TfidfTransformer()
tfarray=tfidf.fit_transform(count_vect.fit_transform(docs)).toarray()
#or
sklearn_tfidf = TfidfVectorizer(norm='l2',min_df=0, use_idf=True, smooth_idf=False, sublinear_tf=True)
sklearn_representation = sklearn_tfidf.fit_transform(docs)
print('first doc idf \n ', sklearn_representation.toarray()[0].tolist()) 
print('---------------now let''s look at one word across the 10 docs------')

#print(tfarray.shape)
#print(type(tfarray))
np.set_printoptions(precision=6,suppress=True)
#print(type(tfarray[0,0]))
print(tfarray[0:,wordloc].tolist())                                   #show the nth word in wordtoloc