def JOB_TTM_growth(codes, df, factor, db, measure):
influx = influxdbData()
save_res = []
for code in codes:
code_df = df.loc[df['code'] == code, :].copy()
code_df['{0}_growthQ'.format(factor)] = \
code_df.apply(lambda row: FactorBase.cal_growth(
row['{0}_last1Q'.format(factor)], row['{0}'.format(factor)]), axis=1)
code_df['{0}_growthY'.format(factor)] = \
code_df.apply(lambda row: FactorBase.cal_growth(
row['{0}_last4Q'.format(factor)], row['{0}'.format(factor)]), axis=1)
cols = ['{0}_growthQ'.format(factor), '{0}_growthY'.format(factor)]
for i in range(1, 8):
code_df['{0}_growthQ_last{1}Q'.format(factor, i)] = \
code_df.apply(lambda row: FactorBase.cal_growth(
row['{0}_last{1}Q'.format(factor, i + 1)], row['{0}_last{1}Q'.format(factor, i)]), axis=1)
cols.append('{0}_growthQ_last{1}Q'.format(factor, i))
code_df = code_df.loc[:, ['code', 'report_period'] + cols]
code_df = code_df.replace(np.inf, np.nan)
code_df = code_df.loc[np.any(pd.notnull(code_df[cols]), axis=1), :]
if code_df.empty:
continue
code_df = code_df.where(pd.notnull(code_df), None)
print('code: %s' % code)
r = influx.saveData(code_df, db, measure)
if r == 'No error occurred...':
pass
else:
save_res.append('%s_growth Error: %s' % (factor, r))
return save_res
def JOB_factors(df, field, codes, calendar, start, save_db):
columns = df.columns
influx = influxdbData()
save_res = []
for code in codes:
code_df = df.loc[df['code'] == code, :].copy()
insert_dates = calendar - set(code_df.index)
content = [[np.nan] * len(columns)] * len(insert_dates)
insert_df = pd.DataFrame(content, columns=columns, index=list(insert_dates))
code_df = code_df.append(insert_df, ignore_index=False).sort_index()
code_df = code_df.fillna(method='ffill')
code_df = code_df.dropna(subset=['code'])
code_df = code_df.loc[str(start):, ]
# 所有report_period 为 columns, 去掉第一列(code)
rps = np.flipud(code_df.columns[1:]).astype('datetime64[ns]')
rp_keys = np.flipud(code_df.columns[1:])
# 选择最新的report_period
code_df['report_period'] = code_df.apply(lambda row: row.dropna().index[-1], axis=1)
choices = []
for rp in rp_keys:
choices.append(code_df[rp].values)
# 计算 当期 和 去年同期
code_df['process_rp'] = code_df['report_period'].apply(lambda x: FactorBase.get_former_report_period(x, 0))
conditions = []
for rp in rps:
conditions.append(code_df['process_rp'].values == rp)
code_df[field] = np.select(conditions, choices, default=np.nan)
code_df['process_rp'] = code_df['report_period'].apply(lambda x: FactorBase.get_former_report_period(x, 4))
conditions = []
for rp in rps:
conditions.append(code_df['process_rp'].values == rp)
code_df[field + '_lastY'] = np.select(conditions, choices, default=np.nan)
# 计算过去每一季
res_flds = []
for i in range(1, 13):
res_field = field + '_last{0}Q'.format(str(i))
res_flds.append(res_field)
code_df['process_rp'] = code_df['report_period'].apply(
lambda x: FactorBase.get_former_report_period(x, i))
conditions = []
for rp in rps:
conditions.append(code_df['process_rp'].values == rp)
code_df[res_field] = np.select(conditions, choices, default=np.nan)
# 处理储存数据
code_df = code_df.loc[:, ['code', 'report_period', field, field + '_lastY'] + res_flds]
code_df['report_period'] = code_df['report_period'].apply(lambda x: x.strftime('%Y%m%d'))
code_df = code_df.where(pd.notnull(code_df), None)
print('code: %s' % code)
r = influx.saveData(code_df, save_db, field)
if r == 'No error occurred...':
pass
else:
save_res.append('WindIndicator Field: %s Error: %s' % (field, r))
return save_res
def get_former_data(series, n_Qs):
report_period = FactorBase.get_former_report_period(
series['report_period'], n_Qs)
if report_period not in series.index:
return np.nan
else:
return series[report_period]