sorry... I have to revert back some code to depend on cython

alphamind/cyimpl.pyx

+# -*- coding: utf-8 -*-
+# distutils: language = c++
+"""
+Created on 2017-4-25
+
+@author: cheng.li
+"""
+
+import numpy as np
+cimport numpy as np
+cimport cython
+from libcpp.vector cimport vector as cpp_vector
+from libcpp.unordered_map cimport unordered_map as cpp_map
+from cython.operator cimport dereference as deref
+
+
+ctypedef long long int64_t
+
+
+@cython.boundscheck(False)
+@cython.wraparound(False)
+@cython.initializedcheck(False)
+cpdef groupby(long[:] groups):
+    cdef long long length = groups.shape[0]
+    cdef cpp_map[long, cpp_vector[int64_t]] group_ids
+    cdef long long i
+    cdef long curr_tag
+    cdef cpp_map[long, cpp_vector[int64_t]].iterator it
+    cdef np.ndarray[long long, ndim=1] npy_array
+    for i in range(length):
+        curr_tag = groups[i]
+        it = group_ids.find(curr_tag)
+        if it == group_ids.end():
+            group_ids[curr_tag] = [i]
+        else:
+            deref(it).second.push_back(i)
+    return [np.array(v) for v in group_ids.values()]
\ No newline at end of file

alphamind/data/neutralize.py

@@ -12,7 +12,7 @@ from numpy.linalg import solve
 from typing import Tuple
 from typing import Union
 from typing import Dict
-from alphamind.utilities import groupby
+from alphamind.cyimpl import groupby
 
 
 def neutralize(x: np.ndarray, y: np.ndarray, groups: np.ndarray=None, output_explained=False, output_exposure=False) \

alphamind/portfolio/rankbuilder.py

@@ -9,7 +9,7 @@ import numpy as np
 import numba as nb
 from numpy import zeros
 from numpy import zeros_like
-from alphamind.utilities import groupby
+from alphamind.cyimpl import groupby
 
 
 @nb.njit(nogil=True, cache=True)

alphamind/utilities.py

@@ -52,21 +52,6 @@ class TestRunner(object):
             sys.exit(0)
 
 
-def groupby(groups: np.ndarray) -> List[np.ndarray]:
-    order_group_idx = groups.argsort()
-    counts = np.bincount(groups)
-    nonzero_idx = counts.nonzero()[0]
-
-    start = 0
-    res = []
-
-    for i in nonzero_idx:
-        num_g = counts[i]
-        res.append(order_group_idx[start:start+num_g])
-        start += num_g
-    return res
-
-
 @nb.njit(nogil=True, cache=True)
 def group_mapping(groups: np.ndarray) -> np.ndarray:
     length = groups.shape[0]

setup.py

 # -*- coding: utf-8 -*-
 """
 Created on 2017-4-25
-
 @author: cheng.li
 """
-
+import platform
+import sys
 from setuptools import setup
 from setuptools import find_packages
+from distutils.extension import Extension
+import numpy as np
+import Cython
+from Cython.Build import cythonize
+Cython.Compiler.Options.annotate = True
 
 VERSION = "0.1.0"
 
+if "--line_trace" in sys.argv:
+    line_trace = True
+    print("Build with line trace enabled ...")
+    sys.argv.remove("--line_trace")
+else:
+    line_trace = False
+ext_modules = ['alphamind/cyimpl.pyx']
+
+
+def generate_extensions(ext_modules, line_trace=False):
+    extensions = []
+    if line_trace:
+        print("define cython trace to True ...")
+        define_macros = [('CYTHON_TRACE', 1), ('CYTHON_TRACE_NOGIL', 1)]
+    else:
+        define_macros = []
+    if platform.system() != "Windows":
+        extra_compile_args = ['-O3', '-std=c++11']
+    else:
+        extra_compile_args = ['/Ox']
+    for pyxfile in ext_modules:
+        ext = Extension(name='.'.join(pyxfile.split('/'))[:-4],
+                        sources=[pyxfile],
+                        define_macros=define_macros,
+                        extra_compile_args=extra_compile_args)
+        extensions.append(ext)
+    return extensions
+
+if platform.system() != "Windows":
+    import multiprocessing
+    n_cpu = multiprocessing.cpu_count()
+else:
+    n_cpu = 0
 
+ext_modules_settings = cythonize(generate_extensions(ext_modules, line_trace),
+                                 compiler_directives={'embedsignature': True, 'linetrace': line_trace},
+                                 nthreads=n_cpu)
 setup(
     name='Alpha-Mind',
     version=VERSION,
@@ -19,5 +60,7 @@ setup(
     license='',
     author='wegamekinglc',
     author_email='',
+    ext_modules=ext_modules_settings,
+    include_dirs=[np.get_include()],
     description=''
-)
+)
\ No newline at end of file