def main_financial_statistic_process(path):
store_path = os.path.join(path,'statistic/')
if not os.path.exists(store_path):
os.makedirs(store_path)
scu = SCU(path=path)
stock_codes = scu.stock_codes_remove_no_stock_basic()
FFC =financail_factor_statistic(path=path)
sz50 = ts.get_sz50s()
stock_codes = sz50['code']
stock_industry = ts.get_industry_classified()
stock_codes = stock_industry[stock_industry['c_name'].isin(['房地产'])]['code']
#stock_codes = stock_codes.pop('000527')
#stock_codes = ['000001','000002','000004']
statistic_stock_data = {}
statistic_stock_min_len = 100
for stock_code in stock_codes:
print("stock:",stock_code)
FFC.FLS.load_all_financial_one_stock(stock_code)
FFC.FLS.load_all_processed_stock_basic_one_stock([stock_code])
data_processed = FFC.financial_index_calc(stock_code)
(row, colum) = data_processed.shape
if(row<statistic_stock_min_len):
statistic_stock_min_len = row
statistic_stock_data[stock_code] = data_processed
#plt.figure()
#data_processed.plot.bar(data_processed.index)
sum_data = statistic_stock_data[stock_codes[0]].iloc[-statistic_stock_min_len:,:]
for stock_code in stock_codes[1:]:
sum_data = sum_data + statistic_stock_data[stock_code].iloc[-statistic_stock_min_len:,:]
pct_data = sum_data.pct_change(periods=4)
pct_data.to_csv(store_path+'statistic_pct.csv');
sum_data.to_csv(store_path+'statistic_sum.csv');
def processed_all_stocks():
path_root = '../../../data/'
scu = SCU(path=path_root)
stock_codes = scu.stock_codes_remove_no_stock_basic()
#stock_codes = ['001965']
#get_dates = ['2018/6/30']
SB = stock_basic(stock_codes, path_root)
#SB.get_stocks_basic()
SB.processed_stocks_basic()
print('processed successfully')
def main_financial_data_process(path):
scu = SCU(path=path)
stock_codes = scu.stock_codes_remove_no_stock_basic()
FFC =financail_factor_calc(path=path)
#stock_codes = ['000001']
for stock_code in stock_codes:
print("stock:",stock_code)
FFC.FLS.load_all_financial_one_stock(stock_code)
FFC.FLS.load_all_stock_basic_one_stock([stock_code])
data_processed = FFC.financial_index_calc(stock_code)
FFC.FLS.store_process_financical_data(data_processed, stock_code)
def fetch_selected_factors(self, factors, dates):
if not os.path.exists(self.path_factor_io):
pd_factor_values = pd.DataFrame(dtype=float)
list_columns = []
for factor in factors:
print('processing factor is', factor)
factor_value, column = self.fetch_one_factor(factor, dates)
list_columns = list_columns + column
pd_factor_values = pd.concat([pd_factor_values, factor_value],
axis=1)
pd_factor_values.columns = list_columns
scu = SCU(path=self.path)
pd_factor_values.index = scu.add_allstock_sh_sz(self.stock_codes)
pd_factor_values.to_csv(self.path_factor_io, encoding='gbk')
else:
pd_factor_values = pd.read_csv(self.path_factor_io, index_col=0)
return pd_factor_values
try:
opts, args = getopt.getopt(sys.argv[1:],"f:",["filename="])
except getopt.GetoptError:
print('test.py -o <outputfile>')
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print('test.py -o <outputfile>')
elif opt in ("-f", "--filename"):
filename = arg
path = '../../../data/'
path_rank = '../../../data/factor_rank'
path_factor = '../../../data/factor_io'
path_cluster = outputfile
scu = SCU(path=path)
stocks = scu.stock_codes_remove_no_stock_basic()
#stocks = ['000001','000002','000004','000005','000006']
indexs = [
#earning capacity
FID['roe'],\
FID['roa'],\
FID['profit_revenue'],\
FID['cash_incr_rate'],\
#FID['profit_cost'],\
#FID['equlity_incr_rate'],\
#grow capacity
#FID['revenue_incr_rate'],\
#FID['profit_incr_rate'],\
#FID['cash_incr_rate'],\
#FID['asset_incr_rate'],\