update models to store formulas

alphamind/model/data_preparing.py

@@ -402,9 +402,9 @@ if __name__ == '__main__':
     universe = Universe('zz500', ['hs300', 'zz500'])
     neutralized_risk = ['SIZE']
     res = fetch_predict_phase(engine, ['ep_q'],
-                            '2018-01-08',
-                            '5b',
-                            universe,
-                            16,
-                            neutralized_risk=neutralized_risk)
+                              '2012-01-05',
+                              '5b',
+                              universe,
+                              16,
+                              neutralized_risk=neutralized_risk)
     print(res)

alphamind/model/linearmodel.py

@@ -32,8 +32,9 @@ class ConstLinearModel(ModelBase):
 
     def __init__(self,
                  features: list = None,
-                 weights: np.ndarray = None):
-        super().__init__(features)
+                 weights: np.ndarray = None,
+                 **kwargs):
+        super().__init__(features, **kwargs)
         if features is not None and weights is not None:
             pyFinAssert(len(features) == len(weights),
                         ValueError,
@@ -57,7 +58,7 @@ class ConstLinearModel(ModelBase):
 class LinearRegression(ModelBase):
 
     def __init__(self, features: list = None, fit_intercept: bool = False, **kwargs):
-        super().__init__(features)
+        super().__init__(features, **kwargs)
         self.impl = LinearRegressionImpl(fit_intercept=fit_intercept, **kwargs)
         self.trained_time = None
 
@@ -85,7 +86,7 @@ class LinearRegression(ModelBase):
 class LassoRegression(ModelBase):
 
     def __init__(self, alpha=0.01, features: list = None, fit_intercept: bool = False, **kwargs):
-        super().__init__(features)
+        super().__init__(features, **kwargs)
         self.impl = Lasso(alpha=alpha, fit_intercept=fit_intercept, **kwargs)
         self.trained_time = None
 
@@ -113,7 +114,7 @@ class LassoRegression(ModelBase):
 class LogisticRegression(ModelBase):
 
     def __init__(self, features: list = None, fit_intercept: bool = False, **kwargs):
-        super().__init__(features)
+        super().__init__(features, **kwargs)
         self.impl = LogisticRegressionImpl(fit_intercept=fit_intercept, **kwargs)
 
     def save(self) -> dict:

alphamind/model/modelbase.py

@@ -15,10 +15,13 @@ from alphamind.utilities import decode
 
 class ModelBase(metaclass=abc.ABCMeta):
 
-    def __init__(self, features: list=None):
+    def __init__(self, features: list=None, formulas: dict=None, **kwargs):
         if features is not None:
             self.features = list(features)
+        else:
+            self.features = formulas
         self.impl = None
+        self.formulas = formulas
         self.trained_time = None
 
     def fit(self, x: np.ndarray, y: np.ndarray):
@@ -43,6 +46,7 @@ class ModelBase(metaclass=abc.ABCMeta):
                           features=list(self.features),
                           trained_time=self.trained_time,
                           desc=encode(self.impl),
+                          formulas=encode(self.formulas),
                           internal_model=self.impl.__class__.__module__ + "." + self.impl.__class__.__name__)
         return model_desc
 
@@ -50,6 +54,7 @@ class ModelBase(metaclass=abc.ABCMeta):
     def load(cls, model_desc: dict):
         obj_layout = cls()
         obj_layout.features = model_desc['features']
+        obj_layout.formulas = model_desc['formulas']
         obj_layout.trained_time = model_desc['trained_time']
         obj_layout.impl = decode(model_desc['desc'])
         return obj_layout

alphamind/model/treemodel.py

@@ -28,7 +28,7 @@ class RandomForestRegressor(ModelBase):
                  max_features: str='auto',
                  features: List=None,
                  **kwargs):
-        super().__init__(features)
+        super().__init__(features, **kwargs)
         self.impl = RandomForestRegressorImpl(n_estimators=n_estimators,
                                               max_features=max_features,
                                               **kwargs)
@@ -62,7 +62,7 @@ class RandomForestClassifier(ModelBase):
                  max_features: str='auto',
                  features: List = None,
                  **kwargs):
-        super().__init__(features)
+        super().__init__(features, **kwargs)
         self.impl = RandomForestClassifierImpl(n_estimators=n_estimators,
                                                max_features=max_features,
                                                **kwargs)
@@ -97,7 +97,7 @@ class XGBRegressor(ModelBase):
                  max_depth: int=3,
                  features: List=None,
                  **kwargs):
-        super().__init__(features)
+        super().__init__(features, **kwargs)
         self.impl = XGBRegressorImpl(n_estimators=n_estimators,
                                      learning_rate=learning_rate,
                                      max_depth=max_depth,
@@ -132,7 +132,7 @@ class XGBClassifier(ModelBase):
                  max_depth: int=3,
                  features: List = None,
                  **kwargs):
-        super().__init__(features)
+        super().__init__(features, **kwargs)
         self.impl = XGBClassifierImpl(n_estimators=n_estimators,
                                      learning_rate=learning_rate,
                                      max_depth=max_depth,