Sentiment analysis for movie reviews
In this exercise you'll explore the probabilities outputted by logistic regression on a subset of the Large Movie Review Dataset.
The variables X and y are already loaded into the environment. X contains features based on the number of times words appear in the movie reviews, and y contains labels for whether the review sentiment is positive (+1) or negative (-1).
Cet exercice fait partie du cours
Linear Classifiers in Python
Instructions
- Train a logistic regression model on the movie review data.
- Predict the probabilities of negative vs. positive for the two given reviews.
- Feel free to write your own reviews and get probabilities for those too!
Exercice interactif pratique
Essayez cet exercice en complétant cet exemple de code.
# Instantiate logistic regression and train
lr = ____
lr.fit(____)
# Predict sentiment for a glowing review
review1 = "LOVED IT! This movie was amazing. Top 10 this year."
review1_features = get_features(review1)
print("Review:", review1)
print("Probability of positive review:", lr.predict_proba(____)[0,1])
# Predict sentiment for a poor review
review2 = "Total junk! I'll never watch a film by that director again, no matter how good the reviews."
review2_features = get_features(review2)
print("Review:", review2)
print("Probability of positive review:", lr.predict_proba(____)[0,1])