modified sql engine and factor analysis implementation

alphamind/analysis/factoranalysis.py

@@ -66,7 +66,7 @@ class FDataPack(object):
 
     def __init__(self,
                  raw_factors: np.ndarray,
-                 d1returns,
+                 d1returns=None,
                  factor_names: List[str]=None,
                  codes: List=None,
                  groups: Optional[np.ndarray]=None,
@@ -75,7 +75,13 @@ class FDataPack(object):
                  risk_names: List[str]=None):
 
         self.raw_factors = raw_factors
-        self.d1returns = d1returns.flatten()
+
+
+        if d1returns is not None:
+            self.d1returns = d1returns.flatten()
+        else:
+            self.d1returns = None
+
         if factor_names:
             self.factor_names = factor_names
         else:
@@ -93,6 +99,10 @@ class FDataPack(object):
         return self.risk_exp @ self.benchmark
 
     def settle(self, weights: np.ndarray) -> pd.DataFrame:
+
+        if self.d1returns is None:
+            raise ValueError("No return is offered")
+
         weights = weights.flatten()
 
         if self.benchmark is not None:
@@ -158,7 +168,7 @@ class FDataPack(object):
 def factor_analysis(factors: pd.DataFrame,
                     factor_weights: np.ndarray,
                     industry: np.ndarray,
-                    d1returns: np.ndarray,
+                    d1returns: np.ndarray=None,
                     detail_analysis=True,
                     benchmark: Optional[np.ndarray]=None,
                     risk_exp: Optional[np.ndarray]=None,
@@ -208,7 +218,8 @@ def factor_analysis(factors: pd.DataFrame,
     else:
         analysis = None
     return pd.DataFrame({'weight': weights,
-                         'industry': industry},
+                         'industry': industry,
+                         'er': er},
                         index=factors.index),\
            analysis
 

alphamind/data/engines/sqlengine.py

@@ -102,6 +102,12 @@ class SqlEngine(object):
 
         return sorted(codes_set)
 
+    def fetch_d1_return(self, ref_date, codes):
+        codes_str = ','.join(str(c) for c in codes)
+        sql = "select Code, d1 from daily_return where Date = '{ref_date}' and Code in ({codes})".format(ref_date=ref_date,
+                                                                                                   codes=codes_str)
+        return pd.read_sql(sql, self.engine)
+
     def fetch_data(self, ref_date,
                    factors: Iterable[str],
                    codes: Iterable[int],
@@ -124,13 +130,12 @@ class SqlEngine(object):
         special_risk_table = 'specific_risk_' + risk_model
         codes_str = ','.join(str(c) for c in codes)
 
-        sql = "select uqer.Code, {factors}, {risks}, market.isOpen, daily_return.d1, {risk_table}.SRISK" \
+        sql = "select uqer.Code, {factors}, {risks}, market.isOpen, {risk_table}.SRISK" \
               " from (uqer INNER JOIN" \
               " risk_exposure on uqer.Date = risk_exposure.Date and uqer.Code = risk_exposure.Code)" \
               " INNER JOIN market on uqer.Date = market.Date and uqer.Code = market.Code" \
               " LEFT JOIN tiny on uqer.Date = tiny.Date and uqer.Code = tiny.Code" \
               " LEFT JOIN legacy_factor on uqer.Date = legacy_factor.Date and uqer.Code = legacy_factor.Code" \
-              " INNER JOIN daily_return on uqer.Date = daily_return.Date and uqer.Code = daily_return.Code" \
               " INNER JOIN {risk_table} on uqer.Date = {risk_table}.Date and uqer.Code = {risk_table}.Code" \
               " where uqer.Date = '{ref_date}' and uqer.Code in ({codes})".format(factors=factor_str,
                                                                                   ref_date=ref_date,