update schedule setting

alphamind/api.py

@@ -50,6 +50,8 @@ def map_freq(freq):
         horizon = 19
     elif freq == '1d':
         horizon = 0
+    elif freq[-1] == "b":
+        horizon = int(freq[:-1]) - 1
     else:
         raise ValueError("Unrecognized freq: {0}".format(freq))
     return horizon

alphamind/data/engines/sqlengine.py

@@ -184,18 +184,19 @@ class SqlEngine(object):
                         ref_date: str,
                         codes: Iterable[int],
                         expiry_date: str = None,
-                        horizon: int = 0) -> pd.DataFrame:
+                        horizon: int = 0,
+                        offset: int = 0) -> pd.DataFrame:
         start_date = ref_date
 
         if not expiry_date:
-            end_date = advanceDateByCalendar('china.sse', ref_date, str(horizon + DAILY_RETURN_OFFSET) + 'b').strftime('%Y%m%d')
+            end_date = advanceDateByCalendar('china.sse', ref_date, str(horizon + offset + DAILY_RETURN_OFFSET) + 'b').strftime('%Y%m%d')
         else:
             end_date = expiry_date
 
         stats = func.sum(self.ln_func(1. + DailyReturn.d1)).over(
             partition_by=DailyReturn.code,
             order_by=DailyReturn.trade_date,
-            rows=(DAILY_RETURN_OFFSET, horizon + DAILY_RETURN_OFFSET)).label('dx')
+            rows=(DAILY_RETURN_OFFSET + offset, horizon + DAILY_RETURN_OFFSET + offset)).label('dx')
 
         query = select([DailyReturn.trade_date, DailyReturn.code, stats]).where(
             and_(
@@ -213,13 +214,14 @@ class SqlEngine(object):
                               start_date: str = None,
                               end_date: str = None,
                               dates: Iterable[str] = None,
-                              horizon: int = 0) -> pd.DataFrame:
+                              horizon: int = 0,
+                              offset: int = 0) -> pd.DataFrame:
 
         if dates:
             start_date = dates[0]
             end_date = dates[-1]
 
-        end_date = advanceDateByCalendar('china.sse', end_date, str(horizon + DAILY_RETURN_OFFSET) + 'b').strftime('%Y-%m-%d')
+        end_date = advanceDateByCalendar('china.sse', end_date, str(horizon + offset + DAILY_RETURN_OFFSET) + 'b').strftime('%Y-%m-%d')
 
         cond = universe.query_range(start_date, end_date)
         big_table = join(DailyReturn, UniverseTable,
@@ -230,7 +232,7 @@ class SqlEngine(object):
         stats = func.sum(self.ln_func(1. + DailyReturn.d1)).over(
             partition_by=DailyReturn.code,
             order_by=DailyReturn.trade_date,
-            rows=(DAILY_RETURN_OFFSET, horizon + DAILY_RETURN_OFFSET)).label('dx')
+            rows=(offset + DAILY_RETURN_OFFSET, horizon + offset + DAILY_RETURN_OFFSET)).label('dx')
 
         query = select([DailyReturn.trade_date, DailyReturn.code, stats]) \
             .select_from(big_table)

alphamind/examples/combined_model_training.py

@@ -25,18 +25,18 @@ end_date = '2017-11-15'
 benchmark_code = 300
 universe_name = ['zz500', 'hs300']
 universe = Universe(universe_name, universe_name)
-frequency = '2w'
+frequency = '2b'
 batch = 8
 method = 'risk_neutral'
 use_rank = 100
 industry_lower = 1.
 industry_upper = 1.
 neutralize_risk = ['SIZE'] + industry_styles
-constraint_risk = industry_styles
+constraint_risk = ['SIZE'] + industry_styles
 size_risk_lower = 0
 size_risk_upper = 0
-turn_over_target_base = 0.2
-weight_gap = 0.03
+turn_over_target_base = 0.1
+weight_gaps = [0.01, 0.02, 0.03, 0.04]
 benchmark_total_lower = 0.8
 benchmark_total_upper = 1.
 horizon = map_freq(frequency)
@@ -101,7 +101,7 @@ for ref_date in ref_dates:
     alpha_logger.info('trade_date: {0} training finished'.format(ref_date))
 
 
-frequency = '1w'
+frequency = '2b'
 ref_dates = makeSchedule(start_date, end_date, frequency, 'china.sse')
 
 const_model_factor_data = engine.fetch_data_range(universe,
@@ -117,14 +117,17 @@ Predicting and re-balance phase
 
 factor_groups = const_model_factor_data.groupby('trade_date')
 
-rets = []
-turn_overs = []
-leverags = []
-previous_pos = pd.DataFrame()
+for weight_gap in weight_gaps:
+    print("start {0} weight gap simulation ...".format(weight_gap))
 
-index_dates = []
+    rets = []
+    turn_overs = []
+    leverags = []
+    previous_pos = pd.DataFrame()
 
-for i, value in enumerate(factor_groups):
+    index_dates = []
+
+    for i, value in enumerate(factor_groups):
         date = value[0]
         data = value[1]
         ref_date = date.strftime('%Y-%m-%d')
@@ -245,7 +248,7 @@ for i, value in enumerate(factor_groups):
         turn_over, executed_pos = executor.execute(target_pos=target_pos)
 
         executed_codes = executed_pos.code.tolist()
-    dx_returns = engine.fetch_dx_return(date, executed_codes, horizon=horizon)
+        dx_returns = engine.fetch_dx_return(date, executed_codes, horizon=horizon, offset=1)
 
         result = pd.merge(executed_pos, total_data[['code', 'weight']], on=['code'], how='inner')
         result = pd.merge(result, dx_returns, on=['code'])
@@ -261,27 +264,27 @@ for i, value in enumerate(factor_groups):
         previous_pos = executed_pos
         alpha_logger.info('{0} is finished'.format(date))
 
-ret_df = pd.DataFrame({'returns': rets, 'turn_over': turn_overs, 'leverage': leverage}, index=index_dates)
-ret_df.loc[advanceDateByCalendar('china.sse', ref_dates[-1], frequency)] = 0.
-ret_df = ret_df.shift(1)
-ret_df.iloc[0] = 0.
-ret_df['tc_cost'] = ret_df.turn_over * 0.002
+    ret_df = pd.DataFrame({'returns': rets, 'turn_over': turn_overs, 'leverage': leverage}, index=index_dates)
+    ret_df.loc[advanceDateByCalendar('china.sse', ref_dates[-1], frequency)] = 0.
+    ret_df = ret_df.shift(1)
+    ret_df.iloc[0] = 0.
+    ret_df['tc_cost'] = ret_df.turn_over * 0.002
 
-ret_df[['returns', 'tc_cost']].cumsum().plot(figsize=(12, 6),
+    ret_df[['returns', 'tc_cost']].cumsum().plot(figsize=(12, 6),
                                                  title='Fixed frequency rebalanced: {0}'.format(frequency),
                                                  secondary_y='tc_cost')
 
-ret_df['ret_after_tc'] = ret_df['returns'] - ret_df['tc_cost']
+    ret_df['ret_after_tc'] = ret_df['returns'] - ret_df['tc_cost']
 
-sharp_calc = MovingSharp(52)
-drawdown_calc = MovingMaxDrawdown(52)
-max_drawdown_calc = MovingMaxDrawdown(len(ret_df))
+    sharp_calc = MovingSharp(49)
+    drawdown_calc = MovingMaxDrawdown(49)
+    max_drawdown_calc = MovingMaxDrawdown(len(ret_df))
 
-res_df = pd.DataFrame(columns=['daily_return', 'cum_ret', 'sharp', 'drawdown', 'max_drawn'])
+    res_df = pd.DataFrame(columns=['daily_return', 'cum_ret', 'sharp', 'drawdown', 'max_drawn'])
 
-total_returns = 0.
+    total_returns = 0.
 
-for i, ret in enumerate(ret_df['ret_after_tc']):
+    for i, ret in enumerate(ret_df['ret_after_tc']):
         date = ret_df.index[i]
         total_returns += ret
         sharp_calc.push({'ret': ret, 'riskFree': 0.})
@@ -296,8 +299,8 @@ for i, ret in enumerate(ret_df['ret_after_tc']):
         if i < 10:
             res_df.loc[date, 'sharp'] = 0.
         else:
-        res_df.loc[date, 'sharp'] = sharp_calc.result() * np.sqrt(52)
+            res_df.loc[date, 'sharp'] = sharp_calc.result() * np.sqrt(49)
 
-res_df.to_csv('hs300_{0}.csv'.format(int(weight_gap * 100)))
+    res_df.to_csv('hs300_{0}.csv'.format(int(weight_gap * 100)))
 
-#plt.show()
+# plt.show()