python scikit learn 文本分类

<pre style="font-family: 'Courier New'; font-size: 17pt; background-color: rgb(255, 255, 255);"><pre name="code" class="python">#!/usr/bin/env python
#coding:utf-8

import jieba
from sklearn.feature_extraction.text import HashingVectorizer
import sys
import random
from sklearn.naive_bayes import MultinomialNB
import numpy as np

def extract_text_list(filename):
    with open(filename,"r") as file:
        return [line.strip().decode('utf-8') for line in file]


def split_data(inputlist,split_ratio):
    #拆分训练集与测试集
    random.shuffle(inputlist)
    split_num = int(len(inputlist)*split_ratio)
    train_data = inputlist[:split_num]
    test_data = inputlist[split_num:]
    return (train_data,test_data)


if __name__ == '__main__':
    reload(sys)
    sys.setdefaultencoding("utf-8")
    if len(sys.argv) != 3:
        print "Usage: %s <msgFile> <stopWordFile>" % sys.argv[0]
        sys.exit(1)

    input_file = sys.argv[1]
    stop_word_file = sys.argv[2]
    cn_stop_words = extract_text_list(stop_word_file)


    text_list = extract_text_list(input_file)
    print "文件中的消息数：%d" % len(text_list)

    train_data, test_data = split_data(text_list,0.6)
    print "训练集消息数：%d; 测试集消息数：%d" % (len(train_data),len(test_data))

    comma_tokenizer = lambda x: jieba.cut(x, cut_all=False)
    vectorizer = HashingVectorizer(encoding='utf-8',decode_error='ignore',tokenizer=comma_tokenizer,stop_words=cn_stop_words,non_negative=True)

    train_corpus = [''.join(text.split("\t")[1:]) for text in train_data]
    test_corpus = [''.join(text.split("\t")[1:]) for text in test_data]

    train_text = vectorizer.fit_transform(train_corpus)
    test_text = vectorizer.fit_transform(test_corpus)
    train_tags = np.asarray([text.split("\t")[0] for text in train_data])
    test_tags = [text.split("\t")[0] for text in test_data]


    clf = MultinomialNB()
    clf.fit(train_text.todense(),train_tags)
    pred = clf.predict(test_text.todense())


    true_positive = 0
    for i in xrange(len(pred)):
        if int(pred[i]) == int(test_tags[i]) and int(test_tags[i]) == 1:
            true_positive += 1

    pred_positive = sum([int(pred[i]) for i in xrange(len(pred))])
    print "预测准确率：%f" % float(true_positive*1.0/pred_positive)

    total_positive_num = sum([int(i) for i in test_tags])
    print "预测召回率：%f" % float(true_positive*1.0/total_positive_num)