doc_complete = ["Human machine interface for lab abc computer applications",

"A survey of user opinion of computer system response time",

"The EPS user interface management system",

"System and human system engineering testing of EPS",

"Relation of user perceived response time to error measurement",

"The generation of random binary unordered trees",

"The intersection graph of paths in trees",

"Graph minors IV Widths of trees and well quasi ordering"]

doc_clean = [doc.split() for doc in doc_complete]

from sklearn.feature_extraction.text import TfidfVectorizer

obj = TfidfVectorizer(input=doc_clean, analyzer='word', ngram_range=(1,6),

lowercase=True,min_df = .25,use_idf=False,

stop_words = 'english')

corpus = doc_complete

X = obj.fit_transform(corpus)

print(X)

names=obj.get_feature_names()

from scipy.sparse.csr import csr_matrix

import pandas as pd

import nltk

w1=[]

def get_details(doc):

feature_index = X[doc,:].nonzero()[1]

tfidf_scores = zip(feature_index, [X[doc, x] for x in feature_index])

for w, s in [(names[i], s) for (i, s) in tfidf_scores]:

print(w, s)

w1.append(w)

for i in range(0,len(doc_complete)):

print('\n',doc_complete[i])

get_details(i)

pd.Series(w1).value_counts()

freq=nltk.FreqDist(w1)

list(freq.keys())

list(freq.values())

subst=freq.most_common(5)

subst