from sklearn.feature_extraction.text import CountVectorizer
import pandas as pd
vectorizer = CountVectorizer()
doc = [
"it is going to rain today",
"i am going to drink coffee",
"i am going to capital today"
]
X = vectorizer.fit_transform(doc)
column = vectorizer.get_feature_names()
df = pd.DataFrame(X.toarray(), columns=column)
df
from sklearn.feature_extraction.text import TfidfTransformer
vectorizer = TfidfTransformer()
bow = CountVectorizer()
wordCount = bow.fit_transform(doc)
X = vectorizer.fit_transform(wordCount)
column = bow.get_feature_names()
df = pd.DataFrame(X.toarray(), columns=column)
df
from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(doc)
column = vectorizer.get_feature_names()
df = pd.DataFrame(X.toarray(), columns=column)
df