update examples

alphamind/examples/factor_analysis_example.py

@@ -26,7 +26,7 @@ strategies = {
 }
 
 
-engine = SqlEngine("mssql+pymssql://licheng:A12345678!@10.63.6.220/alpha")
+engine = SqlEngine('postgresql+psycopg2://postgres:A12345678!@10.63.6.220/alpha')
 universe = Universe('custom', ['zz500'])
 benchmark_code = 905
 neutralize_risk = industry_styles
@@ -53,17 +53,17 @@ for strategy in strategies:
 
     all_data = engine.fetch_data_range(universe, factors, dates=dates, benchmark=905)
     factor_all_data = all_data['factor']
-    factor_groups = factor_all_data.groupby('Date')
+    factor_groups = factor_all_data.groupby('trade_date')
 
     rets = []
     for i, value in enumerate(factor_groups):
         date = value[0]
         data = value[1]
-        codes = data.Code.tolist()
+        codes = data.code.tolist()
         ref_date = date.strftime('%Y-%m-%d')
         returns = engine.fetch_dx_return(ref_date, codes, horizon=horizon)
 
-        total_data = pd.merge(data, returns, on=['Code']).dropna()
+        total_data = pd.merge(data, returns, on=['code']).dropna()
         print(date, ': ', len(total_data))
         risk_exp = total_data[neutralize_risk].values.astype(float)
         industry = total_data.industry_code.values

alphamind/examples/formula_expression.py

@@ -13,19 +13,19 @@ from matplotlib import pyplot as plt
 
 
 # defind your alpha formula here
-base_factors = ['EPS', 'ROEDiluted', 'VAL', 'CFinc1']
+base_factors = ['EPS', 'ROEDiluted', 'BTOP']#, 'ROEDiluted', 'VAL', 'CFinc1']
 
 expression = 0.
 
 for name in base_factors:
-    expression = expression + RSI(10, name)
+    expression = expression + LAST(name)
 
 alpha_factor_name = 'alpha_factor'
 alpha_factor = {alpha_factor_name: expression}
 
 # end of formula definition
 
-engine = SqlEngine("mssql+pymssql://licheng:A12345678!@10.63.6.220/alpha")
+engine = SqlEngine('postgresql+psycopg2://postgres:A12345678!@10.63.6.220/alpha')
 universe = Universe('custom', ['zz500'])
 benchmark_code = 905
 neutralize_risk = ['SIZE'] + industry_styles
@@ -39,8 +39,8 @@ elif freq == '1w':
 elif freq == '1d':
     horizon = 0
 
-dates = makeSchedule('2017-01-01',
-                     '2017-08-18',
+dates = makeSchedule('2012-01-01',
+                     '2012-08-01',
                      tenor=freq,
                      calendar='china.sse')
 
@@ -48,18 +48,20 @@ factor_all_data = engine.fetch_data_range(universe,
                                           alpha_factor,
                                           dates=dates,
                                           benchmark=905)['factor']
+return_all_data = engine.fetch_dx_return_range(universe, dates=dates, horizon=horizon)
 
-factor_groups = factor_all_data.groupby('Date')
+factor_groups = factor_all_data.groupby('trade_date')
+return_groups = return_all_data.groupby('trade_date')
 final_res = np.zeros((len(dates), n_bins))
 
 for i, value in enumerate(factor_groups):
     date = value[0]
-    data = value[1][['Code', alpha_factor_name, 'isOpen', 'weight'] + neutralize_risk]
-    codes = data.Code.tolist()
+    data = value[1][['code', alpha_factor_name, 'isOpen', 'weight'] + neutralize_risk]
+    codes = data.code.tolist()
     ref_date = value[0].strftime('%Y-%m-%d')
-    returns = engine.fetch_dx_return(date, codes, horizon=horizon)
+    returns = return_groups.get_group(date)
 
-    total_data = pd.merge(data, returns, on=['Code']).dropna()
+    total_data = pd.merge(data, returns, on=['code']).dropna()
     risk_exp = total_data[neutralize_risk].values.astype(float)
     dx_return = total_data.dx.values
     benchmark = total_data.weight.values

alphamind/examples/plot_quantile_res.py

@@ -14,7 +14,7 @@ from matplotlib import pyplot as plt
 
 start = dt.datetime.now()
 
-engine = SqlEngine("mssql+pymssql://licheng:A12345678!@10.63.6.220/alpha")
+engine = SqlEngine('postgresql+psycopg2://postgres:A12345678!@10.63.6.220/alpha')
 universe = Universe('custom', ['zz500'])
 neutralize_risk = ['SIZE'] + industry_styles
 n_bins = 5
@@ -30,8 +30,8 @@ elif freq == '1w':
 elif freq == '1d':
     horizon = 0
 
-start_date = '2017-01-01'
-end_date = '2017-08-22'
+start_date = '2012-01-01'
+end_date = '2012-08-01'
 
 dates = makeSchedule(start_date,
                      end_date,
@@ -39,9 +39,10 @@ dates = makeSchedule(start_date,
                      calendar='china.sse',
                      dateRule=BizDayConventions.Following)
 
-prod_factors = ['CHV']
+prod_factors = ['EPS']
 
 all_data = engine.fetch_data_range(universe, prod_factors, dates=dates, benchmark=905)
+return_all_data = engine.fetch_dx_return_range(universe, dates=dates, horizon=horizon)
 factor_all_data = all_data['factor']
 
 total_df = pd.DataFrame()
@@ -51,15 +52,16 @@ for factor in prod_factors:
     factors = [factor]
     final_res = np.zeros((len(dates), n_bins))
 
-    factor_groups = factor_all_data.groupby('Date')
+    factor_groups = factor_all_data.groupby('trade_date')
+    return_groups = return_all_data.groupby('trade_date')
     for i, value in enumerate(factor_groups):
         date = value[0]
-        data = value[1][['Code', factor, 'isOpen', 'weight'] + neutralize_risk]
-        codes = data.Code.tolist()
+        data = value[1][['code', factor, 'isOpen', 'weight'] + neutralize_risk]
+        codes = data.code.tolist()
         ref_date = value[0].strftime('%Y-%m-%d')
-        returns = engine.fetch_dx_return(date, codes, horizon=horizon)
+        returns = return_groups.get_group(date)
 
-        total_data = pd.merge(data, returns, on=['Code']).dropna()
+        total_data = pd.merge(data, returns, on=['code']).dropna()
         print('{0}: {1}'.format(date, len(data)))
         risk_exp = total_data[neutralize_risk].values.astype(float)
         dx_return = total_data.dx.values

alphamind/examples/quantile_analysis_example.py

@@ -13,7 +13,7 @@ from alphamind.data.dbmodel.models import Uqer
 from alphamind.data.dbmodel.models import Tiny
 from alphamind.data.dbmodel.models import LegacyFactor
 
-engine = SqlEngine('postgresql+psycopg2://postgres:we083826@localhost/alpha')
+engine = SqlEngine('postgresql+psycopg2://postgres:A12345678!@10.63.6.220/alpha')
 universe = Universe('custom', ['zz500'])
 neutralize_risk = ['SIZE'] + industry_styles
 n_bins = 24
@@ -45,7 +45,7 @@ for t in factor_tables:
     for c in t.__table__.columns:
         col_names.add(c.name)
 
-col_names = col_names.difference(set(['Date', 'Code']))
+col_names = col_names.difference(set(['trade_date', 'code']))
 
 prod_factors = list(col_names)
 
@@ -54,20 +54,20 @@ return_all_data = engine.fetch_dx_return_range(universe, dates=dates, horizon=ho
 factor_all_data = all_data['factor']
 
 total_df = pd.DataFrame()
-factor_groups = factor_all_data.groupby('Date')
-return_groups = return_all_data.groupby('Date')
+factor_groups = factor_all_data.groupby('trade_date')
+return_groups = return_all_data.groupby('trade_date')
 
 for date, factor_data in factor_groups:
     ref_date = date.strftime('%Y-%m-%d')
     returns = return_groups.get_group(date)
     final_res = np.zeros((len(prod_factors), n_bins))
-    this_date_data = factor_data[['Code', 'isOpen', 'weight'] + prod_factors + neutralize_risk]
-    this_date_data = pd.merge(this_date_data, returns, on=['Code'])
-    codes = this_date_data.Code.tolist()
+    this_date_data = factor_data[['code', 'isOpen', 'weight'] + prod_factors + neutralize_risk]
+    this_date_data = pd.merge(this_date_data, returns, on=['code'])
+    codes = this_date_data.code.tolist()
 
     for i, factor in enumerate(prod_factors):
         factors = [factor]
-        total_data = this_date_data[['Code', 'isOpen', 'weight', 'dx'] + factors + neutralize_risk].dropna()
+        total_data = this_date_data[['code', 'isOpen', 'weight', 'dx'] + factors + neutralize_risk].dropna()
         risk_exp = total_data[neutralize_risk].values.astype(float)
         dx_return = total_data.dx.values
         benchmark = total_data.weight.values
@@ -87,7 +87,7 @@ for date, factor_data in factor_groups:
 
     df = pd.DataFrame(final_res, index=prod_factors)
     df.sort_index(inplace=True)
-    df['Date'] = date
+    df['trade_date'] = date
 
     total_df = total_df.append(df)
     print('{0} is finished'.format(date))