added example for uniform percent build in factor analysis

alphamind/benchmarks/benchmarks.py

@@ -13,6 +13,8 @@ from alphamind.benchmarks.data.winsorize import benchmark_winsorize_normal
 from alphamind.benchmarks.data.winsorize import benchmark_winsorize_normal_with_group
 from alphamind.benchmarks.portfolio.rankbuild import benchmark_build_rank
 from alphamind.benchmarks.portfolio.rankbuild import benchmark_build_rank_with_group
+from alphamind.benchmarks.portfolio.percentbuild import benchmark_build_percent
+from alphamind.benchmarks.portfolio.percentbuild import benchmark_build_percent_with_group
 from alphamind.benchmarks.settlement.simplesettle import benchmark_simple_settle
 from alphamind.benchmarks.settlement.simplesettle import benchmark_simple_settle_with_group
 
@@ -43,6 +45,12 @@ if __name__ == '__main__':
     benchmark_build_rank_with_group(30, 50000, 1, 3)
     benchmark_build_rank(50000, 20, 3000)
     benchmark_build_rank_with_group(50000, 20, 10, 300)
+    benchmark_build_percent(3000, 1000, 0.1)
+    benchmark_build_percent_with_group(3000, 1000, 0.1, 30)
+    benchmark_build_percent(30, 50000, 0.1)
+    benchmark_build_percent_with_group(30, 50000, 0.1, 3)
+    benchmark_build_percent(50000, 20, 0.1)
+    benchmark_build_percent_with_group(50000, 20, 0.1, 300)
     benchmark_simple_settle(3000, 10, 1000)
     benchmark_simple_settle_with_group(3000, 10, 1000, 30)
     benchmark_simple_settle(30, 10, 50000)

alphamind/benchmarks/portfolio/percentbuild.py

+# -*- coding: utf-8 -*-
+"""
+Created on 2017-5-4
+
+@author: cheng.li
+"""
+
+import datetime as dt
+import numpy as np
+import pandas as pd
+from alphamind.portfolio.percentbuilder import percent_build
+
+
+def benchmark_build_percent(n_samples: int, n_loops: int, p_included: float) -> None:
+    print("-" * 60)
+    print("Starting portfolio construction by percent benchmarking")
+    print("Parameters(n_samples: {0}, p_included: {1}, n_loops: {2})".format(n_samples, p_included, n_loops))
+
+    n_portfolio = 10
+
+    x = np.random.randn(n_samples, n_portfolio)
+
+    start = dt.datetime.now()
+    for _ in range(n_loops):
+        calc_weights = percent_build(x, p_included)
+    impl_model_time = dt.datetime.now() - start
+
+    print('{0:20s}: {1}'.format('Implemented model', impl_model_time))
+
+    start = dt.datetime.now()
+    for _ in range(n_loops):
+        exp_weights = np.zeros((len(x), n_portfolio))
+        n_incuded = int(p_included * len(x))
+        choosed_index = (-x).argsort(axis=0).argsort(axis=0) < n_incuded
+        for j in range(n_portfolio):
+            exp_weights[choosed_index[:, j], j] = 1.
+    benchmark_model_time = dt.datetime.now() - start
+
+    np.testing.assert_array_almost_equal(calc_weights, exp_weights)
+
+    print('{0:20s}: {1}'.format('Benchmark model', benchmark_model_time))
+
+
+def benchmark_build_percent_with_group(n_samples: int, n_loops: int, p_included: float, n_groups: int) -> None:
+    print("-" * 60)
+    print("Starting  portfolio construction by percent with group-by values benchmarking")
+    print("Parameters(n_samples: {0}, p_included: {1}, n_loops: {2}, n_groups: {3})".format(n_samples, p_included, n_loops, n_groups))
+
+    n_portfolio = 10
+
+    x = np.random.randn(n_samples, n_portfolio)
+    groups = np.random.randint(n_groups, size=n_samples)
+
+    start = dt.datetime.now()
+    for _ in range(n_loops):
+        calc_weights = percent_build(x, p_included, groups=groups)
+    impl_model_time = dt.datetime.now() - start
+
+    print('{0:20s}: {1}'.format('Implemented model', impl_model_time))
+
+    start = dt.datetime.now()
+    for _ in range(n_loops):
+        grouped_ordering = pd.DataFrame(-x).groupby(groups).rank()
+        grouped_count = pd.DataFrame(-x).groupby(groups).transform(lambda x: x.count())
+        exp_weights = np.zeros((len(x), n_portfolio))
+        n_included = (grouped_count * p_included).astype(int)
+        masks = (grouped_ordering <= n_included).values
+        for j in range(n_portfolio):
+            exp_weights[masks[:, j], j] = 1.
+    benchmark_model_time = dt.datetime.now() - start
+
+    np.testing.assert_array_almost_equal(calc_weights, exp_weights)
+
+    print('{0:20s}: {1}'.format('Benchmark model', benchmark_model_time))
+
+
+if __name__ == '__main__':
+    benchmark_build_percent(3000, 1000, 0.1)
+    benchmark_build_percent_with_group(3000, 1000, 0.1, 30)

alphamind/tests/test_suite.py

@@ -13,6 +13,7 @@ from alphamind.tests.data.test_neutralize import TestNeutralize
 from alphamind.tests.data.test_standardize import TestStandardize
 from alphamind.tests.data.test_winsorize import TestWinsorize
 from alphamind.tests.portfolio.test_rankbuild import TestRankBuild
+from alphamind.tests.portfolio.test_percentbuild import TestPercentBuild
 from alphamind.tests.settlement.test_simplesettle import TestSimpleSettle
 from alphamind.utilities import alpha_logger
 from alphamind.utilities import TestRunner
@@ -23,6 +24,7 @@ if __name__ == '__main__':
                          TestStandardize,
                          TestWinsorize,
                          TestRankBuild,
+                         TestPercentBuild,
                          TestSimpleSettle],
                         alpha_logger)
     runner.run()