中文文本情感分析（word2vec)

gensim做word2vec文本处理，sklearn.svm做建模

from sklearn.cross_validation import train_test_split
from gensim.models.word2vec import Word2Vec
import numpy as np
import pandas as pd
import jieba
from sklearn.externals import joblib
from sklearn.svm import SVC
import sys
sys.reload(sys)
sys.setdefaultencoding("utf8")

载入数据,数据预处理，切分训练集与测试集

def load_file_and_preprocessing():
    neg=pd.read_excel("data/neg.xls",header=None,index=None)
    pos=pd.read_excel("data/pos.xls",header=None,index=None)
    cw=lambda x:list(jieba.cut(x))
    pos["words"]=pos[0].apply(cw)
    neg["words"]=neg[0].apply(cw)
    y=np.concatenate((np.ones(len(pos)),np.zeros(len(neg))))
    x_train,x_test,y_train,y_test=train_test_split(np.concatenate((pos["words"],neg["words"])),y,test)size&