added one more std step to factor analysis

alphamind/analysis/factoranalysis.py

@@ -33,7 +33,7 @@ def factor_processing(raw_factors: np.ndarray,
     if risk_factors is not None:
         new_factors = neutralize(risk_factors, new_factors)
 
-    return new_factors
+    return standardize(new_factors)
 
 
 def build_portfolio(er: np.ndarray,

alphamind/data/engines/sqlengine.py

@@ -174,13 +174,17 @@ if __name__ == '__main__':
     engine = SqlEngine(db_url)
     ref_date = '2017-07-04'
 
+    factors = engine.fetch_factors_meta()[['factor', 'source']]
+    factors['factor'] = factors.factor.str.strip()
+    factors['source'] = factors.source.str.strip()
+
     import datetime as dt
 
     start = dt.datetime.now()
-    for i in range(10):
+    for i in range(1):
         factors = engine.fetch_factors_meta()
         codes = engine.fetch_codes('2017-07-04', universe)
-        total_data = engine.fetch_data(ref_date, ['EPS', 'DROEAfterNonRecurring'], [1, 5], 905)
+        total_data = engine.fetch_data(ref_date, factors.factor.tolist(), [1, 5], 905)
 
     print(dt.datetime.now() - start)
 

alphamind/examples/example2.py

+# -*- coding: utf-8 -*-
+"""
+Created on 2017-7-10
+
+@author: cheng.li
+"""
+
+import pandas as pd
+from alphamind.analysis.factoranalysis import factor_analysis
+from alphamind.data.engines.sqlengine import SqlEngine
+from alphamind.data.engines.universe import Universe
+from alphamind.data.engines.sqlengine import risk_styles
+from alphamind.data.engines.sqlengine import industry_styles
+from PyFin.api import bizDatesList
+
+engine = SqlEngine('mssql+pymssql://licheng:A12345678!@10.63.6.220/alpha')
+universe = Universe('custom', ['zz500'])
+total_risks = risk_styles + industry_styles
+type = 'risk_neutral'
+
+
+def calculate_one_day(ref_date, factors, weights):
+    print(ref_date)
+    codes = engine.fetch_codes(ref_date, universe)
+    total_data = engine.fetch_data(ref_date, factors, codes, 905)
+
+    factor_data = total_data['factor']
+    factor_df = factor_data[['Code', 'industry', 'd1', 'weight', 'isOpen'] + total_risks + factors].dropna()
+
+    weights, _ = factor_analysis(factor_df[factors],
+                                 weights,
+                                 factor_df.industry.values,
+                                 factor_df.d1.values,
+                                 detail_analysis=False,
+                                 benchmark=factor_df.weight.values,
+                                 risk_exp=factor_df[total_risks].values,
+                                 is_tradable=factor_df.isOpen.values,
+                                 method=type)
+    return ref_date, (weights.weight - factor_df.weight).dot(factor_df.d1)
+
+
+if __name__ == '__main__':
+
+    from matplotlib import pyplot as plt
+
+    factors = ['EPS']#, 'FY12P', 'VAL', 'CFinc1', 'BDTO', 'RVOL']
+    weights = [1.]#, 1., 1., 1., 0.5, 0.5]
+    biz_dates = bizDatesList('china.sse', '2013-01-01', '2017-07-05')
+
+    ers = []
+    dates = []
+
+    for ref_date in biz_dates:
+        ref_date, er = calculate_one_day(ref_date, factors, weights)
+        dates.append(ref_date)
+        ers.append(er)
+
+    res = pd.Series(ers, index=dates)
+    res.cumsum().plot()
+    plt.show()