1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
|
// $Id$
//
// Copyright (C) 2003-2008 Greg Landrum and Rational Discovery LLC
// @@ All Rights Reserved @@
// This file is part of the RDKit.
// The contents are covered by the terms of the BSD license
// which is included in the file license.txt, found at the root
// of the RDKit source tree.
//
#define PY_ARRAY_UNIQUE_SYMBOL rdinfotheory_array_API
#include <RDBoost/Wrap.h>
#include <RDBoost/import_array.h>
#include <ML/InfoTheory/InfoBitRanker.h>
#include <ML/InfoTheory/InfoGainFuncs.h>
namespace python = boost::python;
using namespace RDInfoTheory;
namespace RDInfoTheory {
double infoEntropy(python::object resArr) {
PyObject *matObj = resArr.ptr();
if (!PyArray_Check(matObj)) {
throw_value_error("Expecting a Numeric array object");
}
PyArrayObject *copy;
copy = (PyArrayObject *)PyArray_ContiguousFromObject(
matObj, PyArray_DESCR((PyArrayObject *)matObj)->type_num, 1, 1);
double res = 0.0;
// we are expecting a 1 dimensional array
long int ncols = (long int)PyArray_DIM((PyArrayObject *)matObj, 0);
CHECK_INVARIANT(ncols > 0, "");
if (PyArray_DESCR((PyArrayObject *)matObj)->type_num == NPY_DOUBLE) {
double *data = (double *)PyArray_DATA(copy);
res = InfoEntropy(data, ncols);
} else if (PyArray_DESCR((PyArrayObject *)matObj)->type_num == NPY_FLOAT) {
float *data = (float *)PyArray_DATA(copy);
res = InfoEntropy(data, ncols);
} else if (PyArray_DESCR((PyArrayObject *)matObj)->type_num == NPY_INT) {
int *data = (int *)PyArray_DATA(copy);
res = InfoEntropy(data, ncols);
} else if (PyArray_DESCR((PyArrayObject *)matObj)->type_num == NPY_LONG) {
long int *data = (long int *)PyArray_DATA(copy);
res = InfoEntropy(data, ncols);
}
Py_DECREF(copy);
return res;
}
double infoGain(python::object resArr) {
PyObject *matObj = resArr.ptr();
if (!PyArray_Check(matObj)) {
throw_value_error("Expecting a Numeric array object");
}
PyArrayObject *copy;
copy = (PyArrayObject *)PyArray_ContiguousFromObject(
matObj, PyArray_DESCR((PyArrayObject *)matObj)->type_num, 2, 2);
long int rows = (long int)PyArray_DIM((PyArrayObject *)matObj, 0);
long int cols = (long int)PyArray_DIM((PyArrayObject *)matObj, 1);
double res = 0.0;
if (PyArray_DESCR((PyArrayObject *)matObj)->type_num == NPY_DOUBLE) {
double *data = (double *)PyArray_DATA(copy);
res = InfoEntropyGain(data, rows, cols);
} else if (PyArray_DESCR((PyArrayObject *)matObj)->type_num == NPY_FLOAT) {
float *data = (float *)PyArray_DATA(copy);
res = InfoEntropyGain(data, rows, cols);
} else if (PyArray_DESCR((PyArrayObject *)matObj)->type_num == NPY_INT) {
int *data = (int *)PyArray_DATA(copy);
res = InfoEntropyGain(data, rows, cols);
} else if (PyArray_DESCR((PyArrayObject *)matObj)->type_num == NPY_LONG) {
long int *data = (long int *)PyArray_DATA(copy);
res = InfoEntropyGain(data, rows, cols);
} else {
throw_value_error(
"Numeric array object of type int or long or float or double");
}
Py_DECREF(copy);
return res;
}
double chiSquare(python::object resArr) {
PyObject *matObj = resArr.ptr();
if (!PyArray_Check(matObj)) {
throw_value_error("Expecting a Numeric array object");
}
PyArrayObject *copy;
copy = (PyArrayObject *)PyArray_ContiguousFromObject(
matObj, PyArray_DESCR((PyArrayObject *)matObj)->type_num, 2, 2);
long int rows = (long int)PyArray_DIM((PyArrayObject *)matObj, 0);
long int cols = (long int)PyArray_DIM((PyArrayObject *)matObj, 1);
double res = 0.0;
if (PyArray_DESCR((PyArrayObject *)matObj)->type_num == NPY_DOUBLE) {
double *data = (double *)PyArray_DATA(copy);
res = ChiSquare(data, rows, cols);
} else if (PyArray_DESCR((PyArrayObject *)matObj)->type_num == NPY_FLOAT) {
float *data = (float *)PyArray_DATA(copy);
res = ChiSquare(data, rows, cols);
} else if (PyArray_DESCR((PyArrayObject *)matObj)->type_num == NPY_INT) {
int *data = (int *)PyArray_DATA(copy);
res = ChiSquare(data, rows, cols);
} else if (PyArray_DESCR((PyArrayObject *)matObj)->type_num == NPY_LONG) {
long int *data = (long int *)PyArray_DATA(copy);
res = ChiSquare(data, rows, cols);
} else {
throw_value_error(
"Numeric array object of type int or long or float or double");
}
Py_DECREF(copy);
return res;
}
}
void wrap_ranker();
void wrap_corrmatgen();
BOOST_PYTHON_MODULE(rdInfoTheory) {
python::scope().attr("__doc__") =
"Module containing bunch of functions for information metrics and a "
"ranker to rank bits";
rdkit_import_array();
wrap_ranker();
wrap_corrmatgen();
std::string docString =
"calculates the informational entropy of the values in an array\n\n\
ARGUMENTS:\n\
\n\
- resMat: pointer to a long int array containing the data\n\
- dim: long int containing the length of the _tPtr_ array.\n\n\
RETURNS:\n\n\
a double\n";
python::def("InfoEntropy", RDInfoTheory::infoEntropy, docString.c_str());
docString =
"Calculates the information gain for a variable\n\n\
ARGUMENTS:\n\n\
- varMat: a Numeric Array object\n\
varMat is a Numeric array with the number of possible occurances\n\
of each result for reach possible value of the given variable.\n\n\
So, for a variable which adopts 4 possible values and a result which\n\
has 3 possible values, varMat would be 4x3\n\n\
RETURNS:\n\n\
- a Python float object\n\n\
NOTES\n\n\
- this is a dropin replacement for _PyInfoGain()_ in entropy.py\n";
python::def("InfoGain", RDInfoTheory::infoGain, docString.c_str());
docString =
"Calculates the chi squared value for a variable\n\n\
ARGUMENTS:\n\n\
- varMat: a Numeric Array object\n\
varMat is a Numeric array with the number of possible occurances\n\
of each result for reach possible value of the given variable.\n\n\
So, for a variable which adopts 4 possible values and a result which\n\
has 3 possible values, varMat would be 4x3\n\n\
RETURNS:\n\n\
- a Python float object\n";
python::def("ChiSquare", RDInfoTheory::chiSquare, docString.c_str());
}
|
