improve the performance of winsorize

alphamind/aggregate.py

@@ -75,16 +75,18 @@ def agg_std(groups, x, ddof=1):
 
 
 @nb.njit
-def set_value(groups, source, destinantion):
-    length, width = destinantion.shape
+def copy_value(groups, source):
+    length = groups.shape[0]
+    width = source.shape[1]
+    destination = np.zeros((length, width))
     for i in range(length):
         k = groups[i]
         for j in range(width):
-            destinantion[i, j] = source[k, j]
+            destination[i, j] = source[k, j]
+    return destination
 
 
 def transform(groups, x, func):
-    res = np.zeros_like(x)
 
     if func == 'mean':
         value_data = agg_mean(groups, x)
@@ -97,8 +99,7 @@ def transform(groups, x, func):
     else:
         raise ValueError('({0}) is not recognized as valid functor'.format(func))
 
-    set_value(groups, value_data, res)
-    return res
+    return copy_value(groups, value_data)
 
 
 def aggregate(groups, x, func):

alphamind/benchmarks/benchmarks.py

@@ -19,33 +19,33 @@ from alphamind.benchmarks.settlement.simplesettle import benchmark_simple_settle
 
 if __name__ == '__main__':
 
-    # benchmark_neutralize(3000, 10, 1000)
-    # benchmark_neutralize_with_groups(3000, 10, 1000, 30)
-    # benchmark_neutralize(30, 3, 50000)
-    # benchmark_neutralize_with_groups(30, 3, 50000, 3)
-    # benchmark_neutralize(50000, 50, 20)
-    # benchmark_neutralize_with_groups(50000, 50, 20, 50)
-    # benchmark_standardize(3000, 10, 1000)
-    # benchmark_standardize_with_group(3000, 10, 1000, 30)
-    # benchmark_standardize(30, 10, 50000)
-    # benchmark_standardize_with_group(30, 10, 5000, 5)
-    # benchmark_standardize(50000, 50, 20)
-    # benchmark_standardize_with_group(50000, 50, 20, 50)
+    benchmark_neutralize(3000, 10, 1000)
+    benchmark_neutralize_with_groups(3000, 10, 1000, 30)
+    benchmark_neutralize(30, 3, 50000)
+    benchmark_neutralize_with_groups(30, 3, 50000, 3)
+    benchmark_neutralize(50000, 50, 20)
+    benchmark_neutralize_with_groups(50000, 50, 20, 50)
+    benchmark_standardize(3000, 10, 1000)
+    benchmark_standardize_with_group(3000, 10, 1000, 30)
+    benchmark_standardize(100, 10, 50000)
+    benchmark_standardize_with_group(100, 10, 5000, 4)
+    benchmark_standardize(50000, 50, 20)
+    benchmark_standardize_with_group(50000, 50, 20, 50)
     benchmark_winsorize_normal(3000, 10, 1000)
     benchmark_winsorize_normal_with_group(3000, 10, 1000, 30)
     benchmark_winsorize_normal(30, 10, 50000)
     benchmark_winsorize_normal_with_group(30, 10, 5000, 5)
     benchmark_winsorize_normal(50000, 50, 20)
     benchmark_winsorize_normal_with_group(50000, 50, 20, 50)
-    # benchmark_build_rank(3000, 1000, 300)
-    # benchmark_build_rank_with_group(3000, 1000, 10, 30)
-    # benchmark_build_rank(30, 50000, 3)
-    # 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_simple_settle(3000, 10, 1000)
-    # benchmark_simple_settle_with_group(3000, 10, 1000, 30)
-    # benchmark_simple_settle(30, 10, 50000)
-    # benchmark_simple_settle_with_group(30, 10, 50000, 5)
-    # benchmark_simple_settle(50000, 50, 20)
-    # benchmark_simple_settle_with_group(50000, 50, 20, 50)
+    benchmark_build_rank(3000, 1000, 300)
+    benchmark_build_rank_with_group(3000, 1000, 10, 30)
+    benchmark_build_rank(30, 50000, 3)
+    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_simple_settle(3000, 10, 1000)
+    benchmark_simple_settle_with_group(3000, 10, 1000, 30)
+    benchmark_simple_settle(30, 10, 50000)
+    benchmark_simple_settle_with_group(30, 10, 50000, 5)
+    benchmark_simple_settle(50000, 50, 20)
+    benchmark_simple_settle_with_group(50000, 50, 20, 50)