问从文本文档中预测多标签分类中的前3-4标签

EN

import numpy
import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline
from sklearn.cross_validation import KFold
from sklearn.metrics import confusion_matrix, accuracy_score

df = pd.read_csv("data/corpus.csv", sep=",", encoding="latin-1")

df = df.set_index('id')
df.columns = ['class', 'text']

data = df.reindex(numpy.random.permutation(df.index))

pipeline = Pipeline([
    ('count_vectorizer',   CountVectorizer(ngram_range=(1, 2))),
    ('classifier',         MultinomialNB())
])

k_fold = KFold(n=len(data), n_folds=6, shuffle=True)

for train_indices, test_indices in k_fold:
    train_text = data.iloc[train_indices]['text'].values
    train_y = data.iloc[train_indices]['class'].values.astype(str)

    test_text = data.iloc[test_indices]['text'].values
    test_y = data.iloc[test_indices]['class'].values.astype(str)

    pipeline.fit(train_text, train_y)
    predictions = pipeline.predict(test_text)
    confusion = confusion_matrix(test_y, predictions)

    accuracy = accuracy_score(test_y, predictions)
    print accuracy