update data preparing

alphamind/model/composer.py

@@ -128,26 +128,32 @@ def train_model(ref_date: str,
     return base_model
 
 
+def fetch_predict_data(ref_date: str,
+                       alpha_model: ModelBase,
+                       data_meta):
+
+    predict_data = fetch_predict_phase(data_meta.engine,
+                                       alpha_model.formulas,
+                                       ref_date,
+                                       data_meta.freq,
+                                       data_meta.universe,
+                                       data_meta.batch,
+                                       data_meta.neutralized_risk,
+                                       data_meta.risk_model,
+                                       data_meta.pre_process,
+                                       data_meta.post_process,
+                                       data_meta.warm_start,
+                                       fillna=True)
+    return predict_data['predict']['code'], predict_data['predict']['x']
+
+
 def predict_by_model(ref_date: str,
                      alpha_model: ModelBase,
                      data_meta: DataMeta=None,
                      x_values: pd.DataFrame=None,
                      codes: Iterable[int]=None):
     if x_values is None:
-        predict_data = fetch_predict_phase(data_meta.engine,
-                                           alpha_model.formulas,
-                                           ref_date,
-                                           data_meta.freq,
-                                           data_meta.universe,
-                                           data_meta.batch,
-                                           data_meta.neutralized_risk,
-                                           data_meta.risk_model,
-                                           data_meta.pre_process,
-                                           data_meta.post_process,
-                                           data_meta.warm_start)
-
-        x_values = predict_data['predict']['x']
-        codes = predict_data['predict']['code']
+        codes, x_values = fetch_predict_data(ref_date, alpha_model, data_meta)
 
     return pd.DataFrame(alpha_model.predict(x_values).flatten(), index=codes)
 

alphamind/model/data_preparing.py

@@ -335,7 +335,8 @@ def fetch_predict_phase(engine,
                         risk_model: str = 'short',
                         pre_process: Iterable[object] = None,
                         post_process: Iterable[object] = None,
-                        warm_start: int = 0):
+                        warm_start: int = 0,
+                        fillna: str=None):
     if isinstance(alpha_factors, Transformer):
         transformer = alpha_factors
     else:
@@ -352,7 +353,12 @@ def fetch_predict_phase(engine,
                          dateRule=BizDayConventions.Following,
                          dateGenerationRule=DateGeneration.Backward)
 
-    factor_df = engine.fetch_factor_range(universe, factors=transformer, dates=dates).dropna()
+    factor_df = engine.fetch_factor_range(universe, factors=transformer, dates=dates)
+
+    if fillna:
+        factor_df = factor_df.groupby('trade_date').apply(lambda x: x.fillna(x.median())).reset_index(drop=True).dropna()
+    else:
+        factor_df = factor_df.dropna()
 
     names = transformer.names