问Scikit-学习多标签分类

EN

import sys

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.datasets import make_multilabel_classification
from sklearn.preprocessing import LabelBinarizer

from sklearn.svm import LinearSVC
from sklearn.pipeline import Pipeline
from sklearn.datasets import load_files
from sklearn.cross_validation import train_test_split
from sklearn import metrics
from sklearn.multiclass import OneVsRestClassifier
#change model_selection to cross_validation

# The training data folder must be passed as first argument - This uses the example wiki language data files
languages_data_folder = sys.argv[1]
dataset = load_files(languages_data_folder)

# Split the dataset in training and test set:
docs_train, docs_test, y_train, y_test = train_test_split(
dataset.data, dataset.target, test_size=0.5)


#pipeline
clf = Pipeline([
('vectorizer', CountVectorizer(ngram_range=(1,2))),
('tfidf', TfidfTransformer()),
('clf', OneVsRestClassifier(LinearSVC())),
])
    target_names=dataset.target_names



# TASK: Fit the pipeline on the training set
clf.fit(docs_train, y_train)

# TASK: Predict the outcome on the testing set in a variable named y_predicted
y_predicted = clf.predict(docs_test)

print target_names


# Predict the result on some short new sentences:
sentences = [
    u'This is a language detection test.',
    u'Ceci est un test de d\xe9tection de la langue.',
    u'Dies ist ein Test, um die Sprache zu erkennen.',
    u'Bonjour Mon ami. This is a language detection test.',

]
predicted = clf.predict(sentences)

for s, p in zip(sentences, predicted):
    print(u'The language of "%s" is "%s"' % (s, target_names[p]))