Training and testing a classification model with scikit-learn

Introduction to Natural Language Processing in Python

Katharine Jarmul

Founder, kjamistan

Naive Bayes classifier

Naive Bayes Model
- Commonly used for testing NLP classification problems
- Basis in probability
Given a particular piece of data, how likely is a particular outcome?
Examples:
- If the plot has a spaceship, how likely is it to be sci-fi?
- Given a spaceship and an alien, how likely now is it sci-fi?
Each word from CountVectorizer acts as a feature
Naive Bayes: Simple and effective

Naive Bayes with scikit-learn

from sklearn.naive_bayes import MultinomialNB

from sklearn import metrics

nb_classifier = MultinomialNB()

nb_classifier.fit(count_train, y_train)

pred = nb_classifier.predict(count_test)

metrics.accuracy_score(y_test, pred)

0.85841849389820424

Confusion matrix

metrics.confusion_matrix(y_test, pred, labels=[0,1])

array([[6410,  563],
       [ 864, 2242]])

	Action	Sci-Fi
Action	6410	563
Sci-Fi	864	2242

Let's practice!

Introduction to Natural Language Processing in Python