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
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
// Copyright (C) 2013 Davis E. King (davis@dlib.net)
// License: Boost Software License See LICENSE.txt for the full license.
#include <dlib/python.h>
#include "testing_results.h"
#include <boost/shared_ptr.hpp>
#include <boost/python/args.hpp>
#include <dlib/svm.h>
using namespace dlib;
using namespace std;
using namespace boost::python;
typedef matrix<double,0,1> sample_type;
typedef std::vector<std::pair<unsigned long,double> > sparse_vect;
template <typename decision_function>
double predict (
const decision_function& df,
const typename decision_function::kernel_type::sample_type& samp
)
{
typedef typename decision_function::kernel_type::sample_type T;
if (df.basis_vectors.size() == 0)
{
return 0;
}
else if (is_matrix<T>::value && df.basis_vectors(0).size() != samp.size())
{
std::ostringstream sout;
sout << "Input vector should have " << df.basis_vectors(0).size()
<< " dimensions, not " << samp.size() << ".";
PyErr_SetString( PyExc_ValueError, sout.str().c_str() );
boost::python::throw_error_already_set();
}
return df(samp);
}
template <typename kernel_type>
void add_df (
const std::string name
)
{
typedef decision_function<kernel_type> df_type;
class_<df_type>(name.c_str())
.def("__call__", &predict<df_type>)
.def_pickle(serialize_pickle<df_type>());
}
template <typename df_type>
typename df_type::sample_type get_weights(
const df_type& df
)
{
if (df.basis_vectors.size() == 0)
{
PyErr_SetString( PyExc_ValueError, "Decision function is empty." );
boost::python::throw_error_already_set();
}
df_type temp = simplify_linear_decision_function(df);
return temp.basis_vectors(0);
}
template <typename df_type>
typename df_type::scalar_type get_bias(
const df_type& df
)
{
if (df.basis_vectors.size() == 0)
{
PyErr_SetString( PyExc_ValueError, "Decision function is empty." );
boost::python::throw_error_already_set();
}
return df.b;
}
template <typename df_type>
void set_bias(
df_type& df,
double b
)
{
if (df.basis_vectors.size() == 0)
{
PyErr_SetString( PyExc_ValueError, "Decision function is empty." );
boost::python::throw_error_already_set();
}
df.b = b;
}
template <typename kernel_type>
void add_linear_df (
const std::string name
)
{
typedef decision_function<kernel_type> df_type;
class_<df_type>(name.c_str())
.def("__call__", predict<df_type>)
.add_property("weights", &get_weights<df_type>)
.add_property("bias", get_bias<df_type>, set_bias<df_type>)
.def_pickle(serialize_pickle<df_type>());
}
// ----------------------------------------------------------------------------------------
std::string binary_test__str__(const binary_test& item)
{
std::ostringstream sout;
sout << "class1_accuracy: "<< item.class1_accuracy << " class2_accuracy: "<< item.class2_accuracy;
return sout.str();
}
std::string binary_test__repr__(const binary_test& item) { return "< " + binary_test__str__(item) + " >";}
std::string regression_test__str__(const regression_test& item)
{
std::ostringstream sout;
sout << "mean_squared_error: "<< item.mean_squared_error << " R_squared: "<< item.R_squared;
return sout.str();
}
std::string regression_test__repr__(const regression_test& item) { return "< " + regression_test__str__(item) + " >";}
std::string ranking_test__str__(const ranking_test& item)
{
std::ostringstream sout;
sout << "ranking_accuracy: "<< item.ranking_accuracy << " mean_ap: "<< item.mean_ap;
return sout.str();
}
std::string ranking_test__repr__(const ranking_test& item) { return "< " + ranking_test__str__(item) + " >";}
// ----------------------------------------------------------------------------------------
template <typename K>
binary_test _test_binary_decision_function (
const decision_function<K>& dec_funct,
const std::vector<typename K::sample_type>& x_test,
const std::vector<double>& y_test
) { return binary_test(test_binary_decision_function(dec_funct, x_test, y_test)); }
template <typename K>
regression_test _test_regression_function (
const decision_function<K>& reg_funct,
const std::vector<typename K::sample_type>& x_test,
const std::vector<double>& y_test
) { return regression_test(test_regression_function(reg_funct, x_test, y_test)); }
template < typename K >
ranking_test _test_ranking_function1 (
const decision_function<K>& funct,
const std::vector<ranking_pair<typename K::sample_type> >& samples
) { return ranking_test(test_ranking_function(funct, samples)); }
template < typename K >
ranking_test _test_ranking_function2 (
const decision_function<K>& funct,
const ranking_pair<typename K::sample_type>& sample
) { return ranking_test(test_ranking_function(funct, sample)); }
void bind_decision_functions()
{
using boost::python::arg;
add_linear_df<linear_kernel<sample_type> >("_decision_function_linear");
add_linear_df<sparse_linear_kernel<sparse_vect> >("_decision_function_sparse_linear");
add_df<histogram_intersection_kernel<sample_type> >("_decision_function_histogram_intersection");
add_df<sparse_histogram_intersection_kernel<sparse_vect> >("_decision_function_sparse_histogram_intersection");
add_df<polynomial_kernel<sample_type> >("_decision_function_polynomial");
add_df<sparse_polynomial_kernel<sparse_vect> >("_decision_function_sparse_polynomial");
add_df<radial_basis_kernel<sample_type> >("_decision_function_radial_basis");
add_df<sparse_radial_basis_kernel<sparse_vect> >("_decision_function_sparse_radial_basis");
add_df<sigmoid_kernel<sample_type> >("_decision_function_sigmoid");
add_df<sparse_sigmoid_kernel<sparse_vect> >("_decision_function_sparse_sigmoid");
def("test_binary_decision_function", _test_binary_decision_function<linear_kernel<sample_type> >,
(arg("function"), arg("samples"), arg("labels")));
def("test_binary_decision_function", _test_binary_decision_function<sparse_linear_kernel<sparse_vect> >,
(arg("function"), arg("samples"), arg("labels")));
def("test_binary_decision_function", _test_binary_decision_function<radial_basis_kernel<sample_type> >,
(arg("function"), arg("samples"), arg("labels")));
def("test_binary_decision_function", _test_binary_decision_function<sparse_radial_basis_kernel<sparse_vect> >,
(arg("function"), arg("samples"), arg("labels")));
def("test_binary_decision_function", _test_binary_decision_function<polynomial_kernel<sample_type> >,
(arg("function"), arg("samples"), arg("labels")));
def("test_binary_decision_function", _test_binary_decision_function<sparse_polynomial_kernel<sparse_vect> >,
(arg("function"), arg("samples"), arg("labels")));
def("test_binary_decision_function", _test_binary_decision_function<histogram_intersection_kernel<sample_type> >,
(arg("function"), arg("samples"), arg("labels")));
def("test_binary_decision_function", _test_binary_decision_function<sparse_histogram_intersection_kernel<sparse_vect> >,
(arg("function"), arg("samples"), arg("labels")));
def("test_binary_decision_function", _test_binary_decision_function<sigmoid_kernel<sample_type> >,
(arg("function"), arg("samples"), arg("labels")));
def("test_binary_decision_function", _test_binary_decision_function<sparse_sigmoid_kernel<sparse_vect> >,
(arg("function"), arg("samples"), arg("labels")));
def("test_regression_function", _test_regression_function<linear_kernel<sample_type> >,
(arg("function"), arg("samples"), arg("targets")));
def("test_regression_function", _test_regression_function<sparse_linear_kernel<sparse_vect> >,
(arg("function"), arg("samples"), arg("targets")));
def("test_regression_function", _test_regression_function<radial_basis_kernel<sample_type> >,
(arg("function"), arg("samples"), arg("targets")));
def("test_regression_function", _test_regression_function<sparse_radial_basis_kernel<sparse_vect> >,
(arg("function"), arg("samples"), arg("targets")));
def("test_regression_function", _test_regression_function<histogram_intersection_kernel<sample_type> >,
(arg("function"), arg("samples"), arg("targets")));
def("test_regression_function", _test_regression_function<sparse_histogram_intersection_kernel<sparse_vect> >,
(arg("function"), arg("samples"), arg("targets")));
def("test_regression_function", _test_regression_function<sigmoid_kernel<sample_type> >,
(arg("function"), arg("samples"), arg("targets")));
def("test_regression_function", _test_regression_function<sparse_sigmoid_kernel<sparse_vect> >,
(arg("function"), arg("samples"), arg("targets")));
def("test_regression_function", _test_regression_function<polynomial_kernel<sample_type> >,
(arg("function"), arg("samples"), arg("targets")));
def("test_regression_function", _test_regression_function<sparse_polynomial_kernel<sparse_vect> >,
(arg("function"), arg("samples"), arg("targets")));
def("test_ranking_function", _test_ranking_function1<linear_kernel<sample_type> >,
(arg("function"), arg("samples")));
def("test_ranking_function", _test_ranking_function1<sparse_linear_kernel<sparse_vect> >,
(arg("function"), arg("samples")));
def("test_ranking_function", _test_ranking_function2<linear_kernel<sample_type> >,
(arg("function"), arg("sample")));
def("test_ranking_function", _test_ranking_function2<sparse_linear_kernel<sparse_vect> >,
(arg("function"), arg("sample")));
class_<binary_test>("_binary_test")
.def("__str__", binary_test__str__)
.def("__repr__", binary_test__repr__)
.add_property("class1_accuracy", &binary_test::class1_accuracy,
"A value between 0 and 1, measures accuracy on the +1 class.")
.add_property("class2_accuracy", &binary_test::class2_accuracy,
"A value between 0 and 1, measures accuracy on the -1 class.");
class_<ranking_test>("_ranking_test")
.def("__str__", ranking_test__str__)
.def("__repr__", ranking_test__repr__)
.add_property("ranking_accuracy", &ranking_test::ranking_accuracy,
"A value between 0 and 1, measures the fraction of times a relevant sample was ordered before a non-relevant sample.")
.add_property("mean_ap", &ranking_test::mean_ap,
"A value between 0 and 1, measures the mean average precision of the ranking.");
class_<regression_test>("_regression_test")
.def("__str__", regression_test__str__)
.def("__repr__", regression_test__repr__)
.add_property("mean_squared_error", ®ression_test::mean_squared_error,
"The mean squared error of a regression function on a dataset.")
.add_property("R_squared", ®ression_test::R_squared,
"A value between 0 and 1, measures the squared correlation between the output of a \n"
"regression function and the target values.");
}