导入相关的库
import numpy as np
import pandas as pd
import warnings
warnings.filterwarnings("ignore")
获取基础数据,使用流通市值因子
factor_name = 'mv' #流通市值
factor = pd.read_csv('mv_zz500.csv', index_col=0)
factor.index = [pd.to_datetime(str(dt)) for dt in factor.index]
if factor_name == 'mv':
factor = np.log(factor.replace(0., np.nan)) #把0替换成NaN,因为0无法取log
stocks = factor.columns.tolist() #获取股票代码列表
factor.head(3)
# 查看是否有缺失值
factor.isna().any().any()
# 获取中信一级行业分类信息
industry_info = pd.read_csv('info_zz500.csv', index_col=0)
industry_info.head(3)
进行数据预处理
1)去极值
# 定义函数,for循环也可用pandas的向量化操作
def winsorize(df):
new_data = []
for i in range(len(df)):
df_i = df.iloc[i, :]
df_i_median = df_i.med