NaelsonDouglas/tfidf.py

## tfidf.py
from sklearn.feature_extraction.text import TfidfVectorizer
import glob
import pandas as pd

files = [x for x in glob.glob("inputs/*.txt")]

#Read data from a folder
data = [open(f).read() for f in files]

#Random data
data =['all your base are belong to us',
       'a dead horse is a lifeless animal',
       'all the horses are inside the base even the dead']

tfidf_vectorizer = TfidfVectorizer(use_idf=True)
vectors = tfidf_vectorizer.fit_transform(data)

#It will print only the table relative to the first 'file', i.e. vectors[0]
df = pd.DataFrame(vectors[0].T.todense(), index=tfidf_vectorizer.get_feature_names(), columns=["tfidf"])
df = df.sort_values(by=["tfidf"],ascending=False)
print(df)
	from sklearn.feature_extraction.text import TfidfVectorizer
	import glob
	import pandas as pd

	files = [x for x in glob.glob("inputs/*.txt")]

	#Read data from a folder
	data = [open(f).read() for f in files]

	#Random data
	data =['all your base are belong to us',
	'a dead horse is a lifeless animal',
	'all the horses are inside the base even the dead']

	tfidf_vectorizer = TfidfVectorizer(use_idf=True)
	vectors = tfidf_vectorizer.fit_transform(data)

	#It will print only the table relative to the first 'file', i.e. vectors[0]
	df = pd.DataFrame(vectors[0].T.todense(), index=tfidf_vectorizer.get_feature_names(), columns=["tfidf"])
	df = df.sort_values(by=["tfidf"],ascending=False)
	print(df)