Merge pull request #4 from alpha-miner/master

merge update

alphamind/analysis/brisonanalysis.py

-# -*- coding: utf-8 -*-
-"""
-Created on 2017-5-17
-
-@author: cheng.li
-"""

alphamind/analysis/crosssetctions.py

@@ -76,10 +76,7 @@ def cross_section_analysis(ref_date,
 
 
 if __name__ == '__main__':
-    import numpy as np
-    import pandas as pd
-    import statsmodels.api as sm
-    from alphamind.api import *
+    from alphamind.api import SqlEngine, Universe, risk_styles, industry_styles
 
     factor_name = 'SIZE'
     data_source = 'postgres+psycopg2://postgres:A12345678!@10.63.6.220/alpha'

alphamind/analysis/factoranalysis.py

@@ -14,7 +14,7 @@ from alphamind.data.standardize import standardize
 from alphamind.data.winsorize import winsorize_normal
 from alphamind.portfolio.constraints import Constraints
 from alphamind.portfolio.constraints import LinearConstraints
-from alphamind.portfolio.longshortbulder import long_short_build
+from alphamind.portfolio.longshortbulder import long_short_builder
 from alphamind.portfolio.rankbuilder import rank_build
 from alphamind.portfolio.linearbuilder import linear_builder
 from alphamind.portfolio.meanvariancebuilder import mean_variance_builder
@@ -109,7 +109,7 @@ def er_portfolio_analysis(er: np.ndarray,
         weights = rank_build(er, use_rank=kwargs['use_rank'], masks=is_tradable).flatten() * benchmark.sum() / kwargs[
             'use_rank']
     elif method == 'ls' or method == 'long_short':
-        weights = long_short_build(er).flatten()
+        weights = long_short_builder(er).flatten()
     elif method == 'mv' or method == 'mean_variance':
         lbound, ubound, cons_exp, risk_lbound, risk_ubound = create_constraints(benchmark, **kwargs)
         cov = kwargs['cov']

alphamind/analysis/turnoveranalysis.py

-# -*- coding: utf-8 -*-
-"""
-Created on 2018-1-15
-
-@author: cheng.li
-"""
-
-import numpy as np
-from alphamind.data.standardize import standardize
-
-
-def factor_turn_over(factor_values: np.ndarray,
-                     trade_dates: np.ndarray,
-                     codes: np.ndarray,
-                     use_standize: bool=True):
-    if use_standize:
-        factor_values = standardize(factor_values, trade_dates)
-
-
-if __name__ == '__main__':
-    from alphamind.api import *
-    engine = SqlEngine()
-
-    factor = 'ep_q'
-    freq = '5b'
-    start_date = '2017-06-01'
-    end_date = '2017-08-01'
-    universe = Universe('custom', ['zz500'])
-
-

alphamind/portfolio/longshortbulder.py

@@ -11,15 +11,15 @@ from alphamind.utilities import simple_abssum
 from alphamind.utilities import transform
 
 
-def long_short_build(er: np.ndarray,
-                     leverage: float=1.,
-                     groups: np.ndarray=None,
-                     masks: np.ndarray=None) -> np.ndarray:
-
+def long_short_builder(er: np.ndarray,
+                       leverage: float = 1.,
+                       groups: np.ndarray = None,
+                       masks: np.ndarray = None) -> np.ndarray:
     er = er.copy()
 
     if masks is not None:
-        er[~masks] = 0.
+        er[masks] = 0.
+        er[~masks] = er[~masks] - er[~masks].mean()
 
     if er.ndim == 1:
         er = er.reshape((-1, 1))

alphamind/tests/portfolio/test_longshortbuild.py

@@ -8,7 +8,7 @@ Created on 2017-5-9
 import unittest
 import numpy as np
 import pandas as pd
-from alphamind.portfolio.longshortbulder import long_short_build
+from alphamind.portfolio.longshortbulder import long_short_builder
 
 
 class TestLongShortBuild(unittest.TestCase):
@@ -17,37 +17,38 @@ class TestLongShortBuild(unittest.TestCase):
         self.x = np.random.randn(3000, 10)
         self.groups = np.random.randint(10, 40, size=3000)
         choices = np.random.choice(3000, 100, replace=False)
-        self.masks = np.full(3000, True, dtype=bool)
-        self.masks[choices] = False
+        self.masks = np.full(3000, False, dtype=bool)
+        self.masks[choices] = True
 
     def test_long_short_build(self):
         x = self.x[:, 0].flatten()
-        calc_weights = long_short_build(x).flatten()
+        calc_weights = long_short_builder(x).flatten()
         expected_weights = x / np.abs(x).sum()
         np.testing.assert_array_almost_equal(calc_weights, expected_weights)
 
-        calc_weights = long_short_build(self.x, leverage=2)
+        calc_weights = long_short_builder(self.x, leverage=2)
         expected_weights = self.x / np.abs(self.x).sum(axis=0) * 2
         np.testing.assert_array_almost_equal(calc_weights, expected_weights)
 
     def test_long_short_build_with_group(self):
         x = self.x[:, 0].flatten()
-        calc_weights = long_short_build(x, groups=self.groups).flatten()
+        calc_weights = long_short_builder(x, groups=self.groups).flatten()
         expected_weights = pd.Series(x).groupby(self.groups).apply(lambda s: s / np.abs(s).sum())
         np.testing.assert_array_almost_equal(calc_weights, expected_weights)
 
-        calc_weights = long_short_build(self.x, groups=self.groups)
+        calc_weights = long_short_builder(self.x, groups=self.groups)
         expected_weights = pd.DataFrame(self.x).groupby(self.groups).apply(lambda s: s / np.abs(s).sum(axis=0))
         np.testing.assert_array_almost_equal(calc_weights, expected_weights)
 
     def test_long_short_build_with_masks(self):
         x = self.x[:, 0].flatten()
+        calc_weights = long_short_builder(x, masks=self.masks, leverage=1.).flatten()
+        self.assertAlmostEqual(calc_weights.sum(), 0.)
+
         masked_x = x.copy()
-        masked_x[~self.masks] = 0.
-        leverage = np.abs(masked_x).sum()
-        calc_weights = long_short_build(x, masks=self.masks, leverage=leverage).flatten()
-        expected_weights = x.copy()
-        expected_weights[~self.masks] = 0.
+        masked_x[self.masks] = 0.
+        masked_x[~self.masks] = masked_x[~self.masks] - masked_x[~self.masks].mean()
+        expected_weights = masked_x / np.abs(masked_x).sum()
         np.testing.assert_array_almost_equal(calc_weights, expected_weights)
 
 

notebooks/Example 10 - Quadratic Optimizer Comparison with CVXOPT.ipynb

@@ -42,7 +42,7 @@
     "all_styles = risk_styles + industry_styles + macro_styles\n",
     "\n",
     "risk_exposure_values = total_data[all_styles].values.astype(float)\n",
-    "special_risk_values = total_data['s_srisk'].values.astype(float)\n",
+    "special_risk_values = total_data['srisk'].values.astype(float)\n",
     "risk_cov_values = risk_cov[all_styles].values\n",
     "\n",
     "sec_cov_values_full = risk_exposure_values @ risk_cov_values @ risk_exposure_values.T / 10000  + np.diag(special_risk_values ** 2) / 10000\n",
@@ -293,6 +293,20 @@
     "    print(\"{0:<8}{1:>12.2f}{2:>12.2f}{3:>12.2f}\".format(n, cvxpy_times[i], cvxopt_times[i], ipopt_times[i]))"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "code",
    "execution_count": null,