In [1]:

    

"""
    Perceptron allows for finding a linear separation between data sets. This model requires that the data be 
    linerally seperable though.
"""

from sklearn.datasets import fetch_20newsgroups
from sklearn.metrics.metrics import f1_score, classification_report
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import Perceptron


    

In [3]:

    

categories = ['rec.sport.hockey', 'rec.sport.baseball', 'rec.autos']

newsgroups_train = fetch_20newsgroups(subset='train', categories=categories, remove=('headers', 'footers', 'quotes'))
newsgroups_test = fetch_20newsgroups(subset='test', categories=categories, remove=('headers', 'footers', 'quotes'))


    

In [4]:

    

vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(newsgroups_train.data)
X_test = vectorizer.transform(newsgroups_test.data)


    

In [6]:

    

classifier = Perceptron(n_iter=100, eta0=0.1)
classifier.fit_transform(X_train, newsgroups_train.target)
predictions = classifier.predict(X_test)
print classification_report(newsgroups_test.target, predictions)


    

    




             precision    recall  f1-score   support

          0       0.89      0.87      0.88       396
          1       0.87      0.78      0.82       397
          2       0.79      0.88      0.83       399

avg / total       0.85      0.85      0.85      1192

In [ ]: