FIX: added industry range and industry matrix

alphamind/data/engines/sqlengine_rl.py

@@ -26,7 +26,8 @@ from PyFin.api import advanceDateByCalendar
 
 from alphamind.data.dbmodel.models_rl import (
     Market,
-    Industry
+    Industry,
+    RiskExposure
 )
 
 if "DB_VENDOR" in os.environ and os.environ["DB_VENDOR"].lower() == "rl":
@@ -188,6 +189,92 @@ class SqlEngine:
 
         return pd.read_sql(query, self.engine).dropna().drop_duplicates(['code'])
 
+    def fetch_industry_matrix(self,
+                              ref_date: str,
+                              codes: Iterable[int] = None,
+                              category: str = 'sw',
+                              level: int = 1):
+        df = self.fetch_industry(ref_date, codes, category, level)
+        df['industry_name'] = df['industry']
+        df = pd.get_dummies(df, columns=['industry'], prefix="", prefix_sep="")
+        return df.drop('industry_code', axis=1)
+
+    def fetch_industry_range(self,
+                             universe: Universe,
+                             start_date: str = None,
+                             end_date: str = None,
+                             dates: Iterable[str] = None,
+                             category: str = 'sw',
+                             level: int = 1):
+        code_name = 'industry_code' + str(level)
+        category_name = 'industry_name' + str(level)
+
+        cond = universe._query_statements(start_date, end_date, dates)
+
+        query = select([Industry.code.label("code"),
+                        Industry.trade_date,
+                        getattr(Industry, code_name).label('industry_code'),
+                        getattr(Industry, category_name).label('industry')]).where(
+            and_(
+                *cond,
+                Industry.code == UniverseTable.code,
+                Industry.trade_date == UniverseTable.trade_date,
+                Industry.flag == 1
+            )
+        ).distinct()
+
+        return pd.read_sql(query, self.session.bind)
+
+    def fetch_risk_model(self,
+                         ref_date: str,
+                         codes: Iterable[int],
+                         risk_model: str = 'short',
+                         excluded: Iterable[str] = None,
+                         model_type: str = None) -> Union[
+        FactorRiskModel, Tuple[pd.DataFrame, pd.DataFrame]]:
+        risk_cov_table, special_risk_table = _map_risk_model_table(risk_model)
+
+        cov_risk_cols = [risk_cov_table.__table__.columns[f] for f in total_risk_factors]
+        query = select([risk_cov_table.FactorID,
+                        risk_cov_table.Factor]
+                       + cov_risk_cols).where(
+            risk_cov_table.trade_date == ref_date
+        )
+        risk_cov = pd.read_sql(query, self.engine).sort_values('FactorID')
+
+        if excluded:
+            risk_exposure_cols = [RiskExposure.__table__.columns[f] for f in total_risk_factors if
+                                  f not in set(excluded)]
+        else:
+            risk_exposure_cols = [RiskExposure.__table__.columns[f] for f in total_risk_factors]
+
+        big_table = join(RiskExposure,
+                         special_risk_table,
+                         and_(
+                             RiskExposure.code == special_risk_table.code,
+                             RiskExposure.trade_date == special_risk_table.trade_date
+                         ))
+
+        query = select(
+            [RiskExposure.code, special_risk_table.SRISK.label('srisk')] + risk_exposure_cols) \
+            .select_from(big_table).where(
+            and_(RiskExposure.trade_date == ref_date,
+                 RiskExposure.code.in_(codes)
+                 ))
+
+        risk_exp = pd.read_sql(query, self.engine).dropna()
+
+        if not model_type:
+            return risk_cov, risk_exp
+        elif model_type == 'factor':
+            factor_names = risk_cov.Factor.tolist()
+            new_risk_cov = risk_cov.set_index('Factor')
+            factor_cov = new_risk_cov.loc[factor_names, factor_names] / 10000.
+            new_risk_exp = risk_exp.set_index('code')
+            factor_loading = new_risk_exp.loc[:, factor_names]
+            idsync = new_risk_exp['srisk'] * new_risk_exp['srisk'] / 10000
+            return FactorRiskModel(factor_cov, factor_loading, idsync), risk_cov, risk_exp
+
 
 if __name__ == "__main__":
     db_url = "mysql+mysqldb://reader:Reader#2020@121.37.138.1:13317/vision?charset=utf8"
@@ -196,7 +283,7 @@ if __name__ == "__main__":
     universe = Universe("hs300")
     start_date = '2020-09-29'
     end_date = '2020-10-10'
-    df = sql_engine.fetch_codes_range(start_date='start_date', end_date=end_date, universe=Universe("hs300"))
+    df = sql_engine.fetch_codes_range(start_date=start_date, end_date=end_date, universe=Universe("hs300"))
     print(df)
     df = sql_engine.fetch_dx_return("2020-10-09", codes=["2010031963"])
     print(df)
@@ -204,3 +291,7 @@ if __name__ == "__main__":
     print(df)
     df = sql_engine.fetch_industry(ref_date="2020-10-09", codes=["2010031963"])
     print(df)
+    df = sql_engine.fetch_industry_matrix(ref_date="2020-10-09", codes=["2010031963"])
+    print(df)
+    df = sql_engine.fetch_industry_range(start_date=start_date, end_date=end_date, universe=Universe("hs300"))
+    print(df)