from sklearn.feature_extraction.text import CountVectorizer

import pandas as pd

​

documents = [

    "This is the first document.",

    "This document is the second document.",

    "And this is the third one.",

    "Is this the first document?",

]

​

# Create CountVectorizer with max_features and stop_words

vectorizer = CountVectorizer(max_features=100, stop_words='english', min_df=0.1, max_df=0.9)

# Fit and transform the documents (X is a sparse matrix)

X = vectorizer.fit_transform(documents)

# Get the feature names (words)

feature_names = vectorizer.get_feature_names_out()

# Convert the matrix to an array and create a DataFrame for better visualization

df = pd.DataFrame(X.toarray(), columns=feature_names)

# Display the DataFrame

print(df)

​