每日新闻预测金融市场的变化_版本2

######加载包#####
from sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizer
import pandas as pd
import numpy as np
from sklearn.svm import SVC
from sklearn.metrics import roc_auc_score
from datetime import date
import os


#####导入数据######
os.chdir(r'D:/夏俊红/数据分析/利用每日新闻预测金融市场变化')
data = pd.read_csv('Combined_News_DJIA.csv')


#####将headlines合并#####
data["combined_news"] = data.filter(regex = ("Top.*")).apply(lambda x: ''.join(str(x.values)),axis = 1)

########分割测试/训练集
train = data[data['Date'] < '2015-01-01']
test = data[data['Date'] > '2014-12-31']


############提取特征#############
feature_extraction = TfidfVectorizer()
X_train = feature_extraction.fit_transform(train["combined_news"].values)
#训练（fit）文本信息,transform我们所需要的TfidfVectorizer模型
X_test = feature_extraction.transform(test["combined_news"].v