/
multiclass_metric.hpp
216 lines (188 loc) · 6.13 KB
/
multiclass_metric.hpp
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
#ifndef LIGHTGBM_METRIC_MULTICLASS_METRIC_HPP_
#define LIGHTGBM_METRIC_MULTICLASS_METRIC_HPP_
#include <LightGBM/utils/log.h>
#include <LightGBM/metric.h>
#include <cmath>
namespace LightGBM {
/*!
* \brief Metric for multiclass task.
* Use static class "PointWiseLossCalculator" to calculate loss point-wise
*/
template<typename PointWiseLossCalculator>
class MulticlassMetric: public Metric {
public:
explicit MulticlassMetric(const MetricConfig& config) {
num_class_ = config.num_class;
}
virtual ~MulticlassMetric() {
}
void Init(const Metadata& metadata, data_size_t num_data) override {
name_.emplace_back(PointWiseLossCalculator::Name());
num_data_ = num_data;
// get label
label_ = metadata.label();
// get weights
weights_ = metadata.weights();
if (weights_ == nullptr) {
sum_weights_ = static_cast<double>(num_data_);
} else {
sum_weights_ = 0.0f;
for (data_size_t i = 0; i < num_data_; ++i) {
sum_weights_ += weights_[i];
}
}
}
const std::vector<std::string>& GetName() const override {
return name_;
}
double factor_to_bigger_better() const override {
return -1.0f;
}
std::vector<double> Eval(const double* score) const override {
double sum_loss = 0.0;
if (weights_ == nullptr) {
#pragma omp parallel for schedule(static) reduction(+:sum_loss)
for (data_size_t i = 0; i < num_data_; ++i) {
std::vector<double> rec(num_class_);
for (int k = 0; k < num_class_; ++k) {
size_t idx = static_cast<size_t>(num_data_) * k + i;
rec[k] = static_cast<double>(score[idx]);
}
// add loss
sum_loss += PointWiseLossCalculator::LossOnPoint(label_[i], rec);
}
} else {
#pragma omp parallel for schedule(static) reduction(+:sum_loss)
for (data_size_t i = 0; i < num_data_; ++i) {
std::vector<double> rec(num_class_);
for (int k = 0; k < num_class_; ++k) {
size_t idx = static_cast<size_t>(num_data_) * k + i;
rec[k] = static_cast<double>(score[idx]);
}
// add loss
sum_loss += PointWiseLossCalculator::LossOnPoint(label_[i], rec) * weights_[i];
}
}
double loss = sum_loss / sum_weights_;
return std::vector<double>(1, loss);
}
private:
/*! \brief Number of data */
data_size_t num_data_;
/*! \brief Number of classes */
int num_class_;
/*! \brief Pointer of label */
const float* label_;
/*! \brief Pointer of weighs */
const float* weights_;
/*! \brief Sum weights */
double sum_weights_;
/*! \brief Name of this test set */
std::vector<std::string> name_;
};
/*! \brief L2 loss for multiclass task */
class MultiErrorMetric: public MulticlassMetric<MultiErrorMetric> {
public:
explicit MultiErrorMetric(const MetricConfig& config) :MulticlassMetric<MultiErrorMetric>(config) {}
inline static double LossOnPoint(float label, std::vector<double>& score) {
size_t k = static_cast<size_t>(label);
for (size_t i = 0; i < score.size(); ++i){
if (i != k && score[i] >= score[k]) {
return 1.0f;
}
}
return 0.0f;
}
inline static const char* Name() {
return "multi_error";
}
};
/*! \brief Logloss for multiclass task */
class MultiSoftmaxLoglossMetric: public MulticlassMetric<MultiSoftmaxLoglossMetric> {
public:
explicit MultiSoftmaxLoglossMetric(const MetricConfig& config) :MulticlassMetric<MultiSoftmaxLoglossMetric>(config) {}
inline static double LossOnPoint(float label, std::vector<double>& score) {
size_t k = static_cast<size_t>(label);
Common::Softmax(&score);
if (score[k] > kEpsilon) {
return static_cast<double>(-std::log(score[k]));
} else {
return -std::log(kEpsilon);
}
}
inline static const char* Name() {
return "multi_logloss";
}
};
class MultiOVALoglossMetric: public Metric {
public:
explicit MultiOVALoglossMetric(const MetricConfig& config) {
num_class_ = config.num_class;
sigmoid_ = config.sigmoid;
}
virtual ~MultiOVALoglossMetric() {
}
void Init(const Metadata& metadata, data_size_t num_data) override {
name_.emplace_back("multi_loglossova");
num_data_ = num_data;
// get label
label_ = metadata.label();
// get weights
weights_ = metadata.weights();
if (weights_ == nullptr) {
sum_weights_ = static_cast<double>(num_data_);
} else {
sum_weights_ = 0.0f;
for (data_size_t i = 0; i < num_data_; ++i) {
sum_weights_ += weights_[i];
}
}
}
const std::vector<std::string>& GetName() const override {
return name_;
}
double factor_to_bigger_better() const override {
return -1.0f;
}
std::vector<double> Eval(const double* score) const override {
double sum_loss = 0.0;
if (weights_ == nullptr) {
#pragma omp parallel for schedule(static) reduction(+:sum_loss)
for (data_size_t i = 0; i < num_data_; ++i) {
std::vector<double> rec(num_class_);
size_t idx = static_cast<size_t>(num_data_) * static_cast<int>(label_[i]) + i;
double prob = 1.0f / (1.0f + std::exp(-sigmoid_ * score[idx]));
if (prob < kEpsilon) { prob = kEpsilon; }
// add loss
sum_loss += -std::log(prob);
}
} else {
#pragma omp parallel for schedule(static) reduction(+:sum_loss)
for (data_size_t i = 0; i < num_data_; ++i) {
size_t idx = static_cast<size_t>(num_data_) * static_cast<int>(label_[i]) + i;
double prob = 1.0f / (1.0f + std::exp(-sigmoid_ * score[idx]));
if (prob < kEpsilon) { prob = kEpsilon; }
// add loss
sum_loss += -std::log(prob) * weights_[i];
}
}
double loss = sum_loss / sum_weights_;
return std::vector<double>(1, loss);
}
private:
/*! \brief Number of data */
data_size_t num_data_;
/*! \brief Number of classes */
int num_class_;
/*! \brief Pointer of label */
const float* label_;
/*! \brief Pointer of weighs */
const float* weights_;
/*! \brief Sum weights */
double sum_weights_;
/*! \brief Name of this test set */
std::vector<std::string> name_;
double sigmoid_;
};
} // namespace LightGBM
#endif // LightGBM_METRIC_MULTICLASS_METRIC_HPP_