fixed rank bug

alphamind/data/rank.py

@@ -24,6 +24,6 @@ def rank(x: np.ndarray, groups: Optional[np.ndarray]=None) -> np.ndarray:
             curr_idx = order[start:diff_loc + 1]
             res[curr_idx] = x[curr_idx].argsort(axis=0)
             start = diff_loc + 1
-
+        return res
     else:
-        return x.argsort(axis=0)
\ No newline at end of file
+        return x.argsort(axis=0).argsort(axis=0)

alphamind/model/composer.py

@@ -16,12 +16,14 @@ from alphamind.model.data_preparing import fetch_predict_phase
 from alphamind.data.engines.universe import Universe
 from alphamind.data.engines.sqlengine import SqlEngine
 from alphamind.data.winsorize import winsorize_normal
+from alphamind.data.rank import rank
 from alphamind.data.standardize import standardize
 from alphamind.model.loader import load_model
 
 PROCESS_MAPPING = {
     'winsorize_normal': winsorize_normal,
-    'standardize': standardize
+    'standardize': standardize,
+    'rank': rank,
 }
 
 

alphamind/tests/data/test_rank.py

@@ -6,9 +6,33 @@ Created on 2017-8-8
 """
 
 import unittest
+import numpy as np
+import pandas as pd
+from alphamind.data.rank import rank
 
 
 class TestRank(unittest.TestCase):
 
+    def setUp(self):
+        self.x = np.random.randn(1000, 1)
+        self.groups = np.random.randint(0, 10, 1000)
+
     def test_rank(self):
-        pass
\ No newline at end of file
+        data_rank = rank(self.x)
+
+        sorted_array = np.zeros_like(self.x)
+        for i in range(self.x.shape[0]):
+            for j in range(self.x.shape[1]):
+                sorted_array[data_rank[i, j], j] = self.x[i, j]
+
+        arr_diff = np.diff(sorted_array, axis=0)
+        np.testing.assert_array_less(0, arr_diff)
+
+    def test_rank_with_groups(self):
+        data_rank = rank(self.x, groups=self.groups)
+
+        df = pd.DataFrame(self.x, index=self.groups)
+        expected_rank = df.groupby(level=0).apply(lambda x: x.values.argsort().argsort())
+        print(expected_rank)
+
+