Created
September 8, 2014 15:37
-
-
Save alep/49594a86255afaad9866 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# coding: utf-8 | |
import scipy as sp | |
from sklearn.feature_extraction.text import CountVectorizer, HashingVectorizer | |
from sklearn.naive_bayes import BernoulliNB | |
from sklearn.linear_model import LogisticRegression | |
from sklearn import cross_validation | |
from sklearn import metrics | |
datafile = open("data.tsv") | |
data = sp.genfromtxt(datafile, delimiter="\t", dtype='<i8,object', names='category,url') | |
vec = CountVectorizer(analyzer='char', ngram_range=(4, 4)) | |
spliter = cross_validation.StratifiedShuffleSplit(data['category'], n_iter=1, train_size=0.1) | |
train_index, test_index = list(spliter)[0] | |
X_train = instances = data['url'][train_index] | |
y_train = labels = data['category'][train_index] | |
X_test = data['url'][test_index] | |
y_test = data['category'][test_index] | |
print len(X_train) | |
print len(X_test) | |
X_train_vectorized = vec.fit_transform(X_train, y_train) | |
X_test_vectorized = vec.transform(X_test) | |
nb_clf = BernoulliNB() | |
nb_clf.fit(X_train_vectorized, labels) | |
predicted_nb = clf.predict(X_test_vectorized) | |
print metrics.classification_report(y_text, predicted_nb) | |
# This takes some time... | |
lr_clf = LogisticRegression() | |
lr_clf.fit(X_train_vectorized, y_train) | |
predicted_lr = lr_clf.predict(X_test_counts) | |
print metrics.classification_report(y_test, predicted_lr) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment