def form_stock2_second_indus(panel_path, save_path):
'''
:param panel_path: 月度数据的存储地址
:param save_path: 目标文件的存储地址
:return:
'''
# 把股票的月度数据转换为行业的形式
data = Data()
indus_infor = data.secondindustryname
indus_infor = data.reindex(indus_infor)
dirlist = os.listdir(panel_path)
indux_wei_total = pd.DataFrame()
for f in dirlist:
stock_wei = pd.read_csv(os.path.join(panel_path, f),
encoding='gbk',
engine='python')
stock_wei = stock_wei.set_index('wind_code')
if f.split('.')[0] in indus_infor.columns:
stock_wei['second_indus'] = indus_infor[f.split('.')[0]]
else:
stock_wei['second_indus'] = indus_infor[indus_infor.columns[-1]]
stock_wei = stock_wei.dropna(axis=0, how='any')
stock_wei['i_weight'] = 100 * stock_wei['i_weight'] / np.sum(
stock_wei['i_weight'])
grouped = stock_wei[['i_weight',
'second_indus']].groupby('second_indus')
indus_wei = grouped.sum()
indus_wei = indus_wei.T
indus_wei.index = [f.split('.')[0]]
indux_wei_total = pd.concat([indux_wei_total, indus_wei], axis=0)
indux_wei_total = indux_wei_total.fillna(0)
indux_wei_total.to_csv(os.path.join(save_path, '二级行业权重.csv'),
encoding='gbk')
def get_indus_wt_in_index(index, indus_level='second'):
index_wt = get_stock_wt_in_index(index)
data = Data()
if indus_level == 'first':
industry = data.firstindustryname
elif indus_level == 'second':
industry = data.secondindustryname
industry = data.reindex(industry)
industry = industry.loc[index_wt.index, index_wt.columns]
indus_wt = pd.DataFrame()
for d in index_wt.columns:
# d = index_wt.columns[0]
tmp_df = pd.concat([index_wt.loc[:, d], industry.loc[:, d]], axis=1)
tmp_df = tmp_df.dropna()
tmp_df.columns = ['wt', 'industry']
indus_wt_tmp = tmp_df['wt'].groupby(tmp_df['industry']).sum()
indus_wt_df = pd.DataFrame(indus_wt_tmp.values, index=indus_wt_tmp.index, columns=[d])
indus_wt = pd.concat([indus_wt, indus_wt_df], axis=1)
indus_wt = indus_wt.fillna(0)
return indus_wt