Last active
August 26, 2016 16:44
-
-
Save mkbouaziz/5bdb463c99ba9da317a1495d4635d0fc to your computer and use it in GitHub Desktop.
Multi Cassification with Multi output using Scikit-Learn
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
import numpy as np | |
from sklearn.pipeline import Pipeline | |
from sklearn.feature_extraction.text import CountVectorizer | |
from sklearn.svm import LinearSVC | |
from sklearn.feature_extraction.text import TfidfTransformer | |
from sklearn.multiclass import OneVsRestClassifier | |
from sklearn import preprocessing | |
from sklearn.preprocessing import MultiLabelBinarizer | |
X_train = np.array(["new york is a hell of a town", | |
"new york was originally dutch", | |
"the big apple is great", | |
"new york is also called the big apple", | |
"nyc is nice", | |
"people abbreviate new york city as nyc", | |
"the capital of great britain is london", | |
"london is in the uk", | |
"london is in england", | |
"london is in great britain", | |
"it rains a lot in london", | |
"london hosts the british museum", | |
"new york is great and so is london", | |
"i like london better than new york"]) | |
y_train_text = [["new york"],["new york"],["new york"],["new york"],["new york"], | |
["new york"],["london"],["london"],["london"],["london"], | |
["london"],["london"],["new york","london"],["new york","london"]] | |
X_test = np.array(['nice day in nyc', | |
'welcome to london', | |
'london is rainy', | |
'it is raining in britian', | |
'it is raining in britian and the big apple', | |
'it is raining in britian and nyc', | |
'hello welcome to new york. enjoy it here and london too']) | |
target_names = ['New York', 'London'] | |
mlb = MultiLabelBinarizer() | |
Y = mlb.fit_transform(y_train_text) | |
classifier = Pipeline([ | |
('vectorizer', CountVectorizer()), | |
('tfidf', TfidfTransformer()), | |
('clf', OneVsRestClassifier(LinearSVC()))]) | |
classifier.fit(X_train, Y) | |
predicted = classifier.predict(X_test) | |
all_labels = mlb.inverse_transform(predicted) | |
for item, labels in zip(X_test, all_labels): | |
print '%s => %s' % (item, ', '.join(labels)) | |
###output | |
# nice day in nyc => New York | |
# welcome to london => London | |
# hello welcome to new york. enjoy it here and london too => New York, London |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment