remove the dependency of cython

alphamind/aggregate.py

@@ -11,11 +11,40 @@ import numba as nb
 
 
 def groupby(groups):
-    a = np.arange(groups.shape[0])
     order_group_idx = groups.argsort()
     counts = np.bincount(groups)
-    ret = np.split(a[order_group_idx], np.cumsum(counts)[:-1])
-    return ret
+    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):
+    length = groups.shape[0]
+    order = groups.argsort()
+    res = np.zeros(length, dtype=order.dtype)
+
+    start = 0
+    res[order[0]] = start
+    previous = groups[order[0]]
+
+    for i in range(1, length):
+        curr_idx = order[i]
+        curr_val = groups[curr_idx]
+        if curr_val != previous:
+            start += 1
+            res[curr_idx] = start
+        else:
+            res[curr_idx] = start
+        previous = curr_val
+    return res
 
 
 @nb.njit(nogil=True, cache=True)

alphamind/benchmarks/settlement/simplesettle.py

@@ -57,7 +57,7 @@ def benchmark_simple_settle_with_group(n_samples: int, n_portfolios: int, n_loop
     ret_series.shape = -1, 1
     for _ in range(n_loops):
         ret_mat = weights * ret_series
-        exp_ret = pd.DataFrame(ret_mat).groupby(groups, sort=False).sum().values
+        exp_ret = pd.DataFrame(ret_mat).groupby(groups).sum().values
     benchmark_model_time = dt.datetime.now() - start
 
     np.testing.assert_array_almost_equal(calc_ret, exp_ret)

alphamind/data/standardize.py

@@ -6,7 +6,7 @@ Created on 2017-4-25
 """
 
 import numpy as np
-from alphamind.groupby import group_mapping
+from alphamind.aggregate import group_mapping
 from alphamind.aggregate import transform
 from alphamind.aggregate import simple_mean
 from alphamind.aggregate import simple_std

alphamind/data/winsorize.py

@@ -7,7 +7,7 @@ Created on 2017-4-25
 
 import numpy as np
 import numba as nb
-from alphamind.groupby import group_mapping
+from alphamind.aggregate import group_mapping
 from alphamind.aggregate import transform
 from alphamind.aggregate import simple_mean
 from alphamind.aggregate import simple_std

alphamind/groupby.pyx

-# -*- coding: utf-8 -*-
-# distutils: language = c++
-"""
-Created on 2017-4-26
-
-@author: cheng.li
-"""
-
-import numpy as np
-from numpy import zeros
-cimport numpy as np
-cimport cython
-
-
-@cython.boundscheck(False)
-@cython.wraparound(False)
-@cython.initializedcheck(False)
-cpdef np.ndarray[long, ndim=1] group_mapping(long[:] groups):
-    cdef size_t length = groups.shape[0]
-    cdef np.ndarray[long, ndim=1] res= zeros(length, dtype=long)
-    cdef dict current_hold = {}
-    cdef long curr_tag
-    cdef long running_tag = -1
-    cdef size_t i
-
-    for i in range(length):
-        curr_tag = groups[i]
-        try:
-            res[i] = current_hold[curr_tag]
-        except KeyError:
-            running_tag += 1
-            res[i] = running_tag
-            current_hold[curr_tag] = running_tag
-
-    return res

alphamind/settlement/simplesettle.py

@@ -6,7 +6,7 @@ Created on 2017-4-28
 """
 
 import numpy as np
-from alphamind.groupby import group_mapping
+from alphamind.aggregate import group_mapping
 from alphamind.aggregate import aggregate
 from alphamind.aggregate import simple_sum
 

alphamind/tests/settlement/test_simplesettle.py

@@ -48,7 +48,7 @@ class TestSimpleSettle(unittest.TestCase):
 
         ret_series.shape = -1, 1
         ret_mat = weights * ret_series
-        expected_ret = pd.DataFrame(ret_mat).groupby(groups, sort=False).sum().values
+        expected_ret = pd.DataFrame(ret_mat).groupby(groups).sum().values
 
         np.testing.assert_array_almost_equal(calc_ret, expected_ret)
 
@@ -57,7 +57,7 @@ class TestSimpleSettle(unittest.TestCase):
         calc_ret = simple_settle(weights, ret_series, groups)
 
         ret_mat = weights * ret_series
-        expected_ret = pd.DataFrame(ret_mat).groupby(groups, sort=False).sum().values
+        expected_ret = pd.DataFrame(ret_mat).groupby(groups).sum().values
 
         np.testing.assert_array_almost_equal(calc_ret, expected_ret)
 

requirements.txt

 cython >= 0.25.2
 numpy >= 1.12.1
+numba >= 0.30.0
 scikit-learn >= 0.18.1
 scipy >= 0.19.0
 pandas >= 0.19.2
\ No newline at end of file

setup.py

@@ -5,63 +5,11 @@ 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/groupby.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',
@@ -71,7 +19,5 @@ setup(
     license='',
     author='wegamekinglc',
     author_email='',
-    ext_modules=ext_modules_settings,
-    include_dirs=[np.get_include()],
     description=''
 )