liblinear-ruby 1.0.1 → 1.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +1 -1
- data/ext/blasp.h +8 -8
- data/ext/daxpy.c +3 -3
- data/ext/ddot.c +3 -3
- data/ext/dnrm2.c +7 -7
- data/ext/dscal.c +4 -4
- data/ext/liblinear_wrap.cxx +382 -382
- data/ext/linear.cpp +44 -55
- data/ext/linear.h +5 -1
- data/ext/tron.cpp +13 -5
- data/ext/tron.h +1 -1
- data/lib/liblinear.rb +2 -0
- data/lib/liblinear/version.rb +1 -1
- metadata +2 -41
- data/liblinear-2.1/COPYRIGHT +0 -31
- data/liblinear-2.1/Makefile +0 -37
- data/liblinear-2.1/Makefile.win +0 -24
- data/liblinear-2.1/README +0 -600
- data/liblinear-2.1/blas/Makefile +0 -22
- data/liblinear-2.1/blas/blas.h +0 -25
- data/liblinear-2.1/blas/blasp.h +0 -438
- data/liblinear-2.1/blas/daxpy.c +0 -57
- data/liblinear-2.1/blas/ddot.c +0 -58
- data/liblinear-2.1/blas/dnrm2.c +0 -70
- data/liblinear-2.1/blas/dscal.c +0 -52
- data/liblinear-2.1/heart_scale +0 -270
- data/liblinear-2.1/linear.cpp +0 -3053
- data/liblinear-2.1/linear.def +0 -22
- data/liblinear-2.1/linear.h +0 -79
- data/liblinear-2.1/matlab/Makefile +0 -49
- data/liblinear-2.1/matlab/README +0 -208
- data/liblinear-2.1/matlab/libsvmread.c +0 -212
- data/liblinear-2.1/matlab/libsvmwrite.c +0 -119
- data/liblinear-2.1/matlab/linear_model_matlab.c +0 -176
- data/liblinear-2.1/matlab/linear_model_matlab.h +0 -2
- data/liblinear-2.1/matlab/make.m +0 -22
- data/liblinear-2.1/matlab/predict.c +0 -341
- data/liblinear-2.1/matlab/train.c +0 -492
- data/liblinear-2.1/predict.c +0 -243
- data/liblinear-2.1/python/Makefile +0 -4
- data/liblinear-2.1/python/README +0 -380
- data/liblinear-2.1/python/liblinear.py +0 -323
- data/liblinear-2.1/python/liblinearutil.py +0 -270
- data/liblinear-2.1/train.c +0 -449
- data/liblinear-2.1/tron.cpp +0 -241
- data/liblinear-2.1/tron.h +0 -35
- data/liblinear-2.1/windows/liblinear.dll +0 -0
- data/liblinear-2.1/windows/libsvmread.mexw64 +0 -0
- data/liblinear-2.1/windows/libsvmwrite.mexw64 +0 -0
- data/liblinear-2.1/windows/predict.exe +0 -0
- data/liblinear-2.1/windows/predict.mexw64 +0 -0
- data/liblinear-2.1/windows/train.exe +0 -0
- data/liblinear-2.1/windows/train.mexw64 +0 -0
@@ -1,323 +0,0 @@
|
|
1
|
-
#!/usr/bin/env python
|
2
|
-
|
3
|
-
from ctypes import *
|
4
|
-
from ctypes.util import find_library
|
5
|
-
from os import path
|
6
|
-
import sys
|
7
|
-
|
8
|
-
__all__ = ['liblinear', 'feature_node', 'gen_feature_nodearray', 'problem',
|
9
|
-
'parameter', 'model', 'toPyModel', 'L2R_LR', 'L2R_L2LOSS_SVC_DUAL',
|
10
|
-
'L2R_L2LOSS_SVC', 'L2R_L1LOSS_SVC_DUAL', 'MCSVM_CS',
|
11
|
-
'L1R_L2LOSS_SVC', 'L1R_LR', 'L2R_LR_DUAL', 'L2R_L2LOSS_SVR',
|
12
|
-
'L2R_L2LOSS_SVR_DUAL', 'L2R_L1LOSS_SVR_DUAL', 'print_null']
|
13
|
-
|
14
|
-
try:
|
15
|
-
dirname = path.dirname(path.abspath(__file__))
|
16
|
-
if sys.platform == 'win32':
|
17
|
-
liblinear = CDLL(path.join(dirname, r'..\windows\liblinear.dll'))
|
18
|
-
else:
|
19
|
-
liblinear = CDLL(path.join(dirname, '../liblinear.so.3'))
|
20
|
-
except:
|
21
|
-
# For unix the prefix 'lib' is not considered.
|
22
|
-
if find_library('linear'):
|
23
|
-
liblinear = CDLL(find_library('linear'))
|
24
|
-
elif find_library('liblinear'):
|
25
|
-
liblinear = CDLL(find_library('liblinear'))
|
26
|
-
else:
|
27
|
-
raise Exception('LIBLINEAR library not found.')
|
28
|
-
|
29
|
-
L2R_LR = 0
|
30
|
-
L2R_L2LOSS_SVC_DUAL = 1
|
31
|
-
L2R_L2LOSS_SVC = 2
|
32
|
-
L2R_L1LOSS_SVC_DUAL = 3
|
33
|
-
MCSVM_CS = 4
|
34
|
-
L1R_L2LOSS_SVC = 5
|
35
|
-
L1R_LR = 6
|
36
|
-
L2R_LR_DUAL = 7
|
37
|
-
L2R_L2LOSS_SVR = 11
|
38
|
-
L2R_L2LOSS_SVR_DUAL = 12
|
39
|
-
L2R_L1LOSS_SVR_DUAL = 13
|
40
|
-
|
41
|
-
PRINT_STRING_FUN = CFUNCTYPE(None, c_char_p)
|
42
|
-
def print_null(s):
|
43
|
-
return
|
44
|
-
|
45
|
-
def genFields(names, types):
|
46
|
-
return list(zip(names, types))
|
47
|
-
|
48
|
-
def fillprototype(f, restype, argtypes):
|
49
|
-
f.restype = restype
|
50
|
-
f.argtypes = argtypes
|
51
|
-
|
52
|
-
class feature_node(Structure):
|
53
|
-
_names = ["index", "value"]
|
54
|
-
_types = [c_int, c_double]
|
55
|
-
_fields_ = genFields(_names, _types)
|
56
|
-
|
57
|
-
def __str__(self):
|
58
|
-
return '%d:%g' % (self.index, self.value)
|
59
|
-
|
60
|
-
def gen_feature_nodearray(xi, feature_max=None, issparse=True):
|
61
|
-
if isinstance(xi, dict):
|
62
|
-
index_range = xi.keys()
|
63
|
-
elif isinstance(xi, (list, tuple)):
|
64
|
-
xi = [0] + xi # idx should start from 1
|
65
|
-
index_range = range(1, len(xi))
|
66
|
-
else:
|
67
|
-
raise TypeError('xi should be a dictionary, list or tuple')
|
68
|
-
|
69
|
-
if feature_max:
|
70
|
-
assert(isinstance(feature_max, int))
|
71
|
-
index_range = filter(lambda j: j <= feature_max, index_range)
|
72
|
-
if issparse:
|
73
|
-
index_range = filter(lambda j:xi[j] != 0, index_range)
|
74
|
-
|
75
|
-
index_range = sorted(index_range)
|
76
|
-
ret = (feature_node * (len(index_range)+2))()
|
77
|
-
ret[-1].index = -1 # for bias term
|
78
|
-
ret[-2].index = -1
|
79
|
-
for idx, j in enumerate(index_range):
|
80
|
-
ret[idx].index = j
|
81
|
-
ret[idx].value = xi[j]
|
82
|
-
max_idx = 0
|
83
|
-
if index_range :
|
84
|
-
max_idx = index_range[-1]
|
85
|
-
return ret, max_idx
|
86
|
-
|
87
|
-
class problem(Structure):
|
88
|
-
_names = ["l", "n", "y", "x", "bias"]
|
89
|
-
_types = [c_int, c_int, POINTER(c_double), POINTER(POINTER(feature_node)), c_double]
|
90
|
-
_fields_ = genFields(_names, _types)
|
91
|
-
|
92
|
-
def __init__(self, y, x, bias = -1):
|
93
|
-
if len(y) != len(x) :
|
94
|
-
raise ValueError("len(y) != len(x)")
|
95
|
-
self.l = l = len(y)
|
96
|
-
self.bias = -1
|
97
|
-
|
98
|
-
max_idx = 0
|
99
|
-
x_space = self.x_space = []
|
100
|
-
for i, xi in enumerate(x):
|
101
|
-
tmp_xi, tmp_idx = gen_feature_nodearray(xi)
|
102
|
-
x_space += [tmp_xi]
|
103
|
-
max_idx = max(max_idx, tmp_idx)
|
104
|
-
self.n = max_idx
|
105
|
-
|
106
|
-
self.y = (c_double * l)()
|
107
|
-
for i, yi in enumerate(y): self.y[i] = y[i]
|
108
|
-
|
109
|
-
self.x = (POINTER(feature_node) * l)()
|
110
|
-
for i, xi in enumerate(self.x_space): self.x[i] = xi
|
111
|
-
|
112
|
-
self.set_bias(bias)
|
113
|
-
|
114
|
-
def set_bias(self, bias):
|
115
|
-
if self.bias == bias:
|
116
|
-
return
|
117
|
-
if bias >= 0 and self.bias < 0:
|
118
|
-
self.n += 1
|
119
|
-
node = feature_node(self.n, bias)
|
120
|
-
if bias < 0 and self.bias >= 0:
|
121
|
-
self.n -= 1
|
122
|
-
node = feature_node(-1, bias)
|
123
|
-
|
124
|
-
for xi in self.x_space:
|
125
|
-
xi[-2] = node
|
126
|
-
self.bias = bias
|
127
|
-
|
128
|
-
|
129
|
-
class parameter(Structure):
|
130
|
-
_names = ["solver_type", "eps", "C", "nr_weight", "weight_label", "weight", "p", "init_sol"]
|
131
|
-
_types = [c_int, c_double, c_double, c_int, POINTER(c_int), POINTER(c_double), c_double, POINTER(c_double)]
|
132
|
-
_fields_ = genFields(_names, _types)
|
133
|
-
|
134
|
-
def __init__(self, options = None):
|
135
|
-
if options == None:
|
136
|
-
options = ''
|
137
|
-
self.parse_options(options)
|
138
|
-
|
139
|
-
def __str__(self):
|
140
|
-
s = ''
|
141
|
-
attrs = parameter._names + list(self.__dict__.keys())
|
142
|
-
values = map(lambda attr: getattr(self, attr), attrs)
|
143
|
-
for attr, val in zip(attrs, values):
|
144
|
-
s += (' %s: %s\n' % (attr, val))
|
145
|
-
s = s.strip()
|
146
|
-
|
147
|
-
return s
|
148
|
-
|
149
|
-
def set_to_default_values(self):
|
150
|
-
self.solver_type = L2R_L2LOSS_SVC_DUAL
|
151
|
-
self.eps = float('inf')
|
152
|
-
self.C = 1
|
153
|
-
self.p = 0.1
|
154
|
-
self.nr_weight = 0
|
155
|
-
self.weight_label = None
|
156
|
-
self.weight = None
|
157
|
-
self.init_sol = None
|
158
|
-
self.bias = -1
|
159
|
-
self.flag_cross_validation = False
|
160
|
-
self.flag_C_specified = False
|
161
|
-
self.flag_solver_specified = False
|
162
|
-
self.flag_find_C = False
|
163
|
-
self.nr_fold = 0
|
164
|
-
self.print_func = cast(None, PRINT_STRING_FUN)
|
165
|
-
|
166
|
-
def parse_options(self, options):
|
167
|
-
if isinstance(options, list):
|
168
|
-
argv = options
|
169
|
-
elif isinstance(options, str):
|
170
|
-
argv = options.split()
|
171
|
-
else:
|
172
|
-
raise TypeError("arg 1 should be a list or a str.")
|
173
|
-
self.set_to_default_values()
|
174
|
-
self.print_func = cast(None, PRINT_STRING_FUN)
|
175
|
-
weight_label = []
|
176
|
-
weight = []
|
177
|
-
|
178
|
-
i = 0
|
179
|
-
while i < len(argv) :
|
180
|
-
if argv[i] == "-s":
|
181
|
-
i = i + 1
|
182
|
-
self.solver_type = int(argv[i])
|
183
|
-
self.flag_solver_specified = True
|
184
|
-
elif argv[i] == "-c":
|
185
|
-
i = i + 1
|
186
|
-
self.C = float(argv[i])
|
187
|
-
self.flag_C_specified = True
|
188
|
-
elif argv[i] == "-p":
|
189
|
-
i = i + 1
|
190
|
-
self.p = float(argv[i])
|
191
|
-
elif argv[i] == "-e":
|
192
|
-
i = i + 1
|
193
|
-
self.eps = float(argv[i])
|
194
|
-
elif argv[i] == "-B":
|
195
|
-
i = i + 1
|
196
|
-
self.bias = float(argv[i])
|
197
|
-
elif argv[i] == "-v":
|
198
|
-
i = i + 1
|
199
|
-
self.flag_cross_validation = 1
|
200
|
-
self.nr_fold = int(argv[i])
|
201
|
-
if self.nr_fold < 2 :
|
202
|
-
raise ValueError("n-fold cross validation: n must >= 2")
|
203
|
-
elif argv[i].startswith("-w"):
|
204
|
-
i = i + 1
|
205
|
-
self.nr_weight += 1
|
206
|
-
weight_label += [int(argv[i-1][2:])]
|
207
|
-
weight += [float(argv[i])]
|
208
|
-
elif argv[i] == "-q":
|
209
|
-
self.print_func = PRINT_STRING_FUN(print_null)
|
210
|
-
elif argv[i] == "-C":
|
211
|
-
self.flag_find_C = True
|
212
|
-
|
213
|
-
else :
|
214
|
-
raise ValueError("Wrong options")
|
215
|
-
i += 1
|
216
|
-
|
217
|
-
liblinear.set_print_string_function(self.print_func)
|
218
|
-
self.weight_label = (c_int*self.nr_weight)()
|
219
|
-
self.weight = (c_double*self.nr_weight)()
|
220
|
-
for i in range(self.nr_weight):
|
221
|
-
self.weight[i] = weight[i]
|
222
|
-
self.weight_label[i] = weight_label[i]
|
223
|
-
|
224
|
-
# default solver for parameter selection is L2R_L2LOSS_SVC
|
225
|
-
if self.flag_find_C:
|
226
|
-
if not self.flag_cross_validation:
|
227
|
-
self.nr_fold = 5
|
228
|
-
if not self.flag_solver_specified:
|
229
|
-
self.solver_type = L2R_L2LOSS_SVC
|
230
|
-
self.flag_solver_specified = True
|
231
|
-
elif self.solver_type not in [L2R_LR, L2R_L2LOSS_SVC]:
|
232
|
-
raise ValueError("Warm-start parameter search only available for -s 0 and -s 2")
|
233
|
-
|
234
|
-
if self.eps == float('inf'):
|
235
|
-
if self.solver_type in [L2R_LR, L2R_L2LOSS_SVC]:
|
236
|
-
self.eps = 0.01
|
237
|
-
elif self.solver_type in [L2R_L2LOSS_SVR]:
|
238
|
-
self.eps = 0.001
|
239
|
-
elif self.solver_type in [L2R_L2LOSS_SVC_DUAL, L2R_L1LOSS_SVC_DUAL, MCSVM_CS, L2R_LR_DUAL]:
|
240
|
-
self.eps = 0.1
|
241
|
-
elif self.solver_type in [L1R_L2LOSS_SVC, L1R_LR]:
|
242
|
-
self.eps = 0.01
|
243
|
-
elif self.solver_type in [L2R_L2LOSS_SVR_DUAL, L2R_L1LOSS_SVR_DUAL]:
|
244
|
-
self.eps = 0.1
|
245
|
-
|
246
|
-
class model(Structure):
|
247
|
-
_names = ["param", "nr_class", "nr_feature", "w", "label", "bias"]
|
248
|
-
_types = [parameter, c_int, c_int, POINTER(c_double), POINTER(c_int), c_double]
|
249
|
-
_fields_ = genFields(_names, _types)
|
250
|
-
|
251
|
-
def __init__(self):
|
252
|
-
self.__createfrom__ = 'python'
|
253
|
-
|
254
|
-
def __del__(self):
|
255
|
-
# free memory created by C to avoid memory leak
|
256
|
-
if hasattr(self, '__createfrom__') and self.__createfrom__ == 'C':
|
257
|
-
liblinear.free_and_destroy_model(pointer(self))
|
258
|
-
|
259
|
-
def get_nr_feature(self):
|
260
|
-
return liblinear.get_nr_feature(self)
|
261
|
-
|
262
|
-
def get_nr_class(self):
|
263
|
-
return liblinear.get_nr_class(self)
|
264
|
-
|
265
|
-
def get_labels(self):
|
266
|
-
nr_class = self.get_nr_class()
|
267
|
-
labels = (c_int * nr_class)()
|
268
|
-
liblinear.get_labels(self, labels)
|
269
|
-
return labels[:nr_class]
|
270
|
-
|
271
|
-
def get_decfun_coef(self, feat_idx, label_idx=0):
|
272
|
-
return liblinear.get_decfun_coef(self, feat_idx, label_idx)
|
273
|
-
|
274
|
-
def get_decfun_bias(self, label_idx=0):
|
275
|
-
return liblinear.get_decfun_bias(self, label_idx)
|
276
|
-
|
277
|
-
def get_decfun(self, label_idx=0):
|
278
|
-
w = [liblinear.get_decfun_coef(self, feat_idx, label_idx) for feat_idx in range(1, self.nr_feature+1)]
|
279
|
-
b = liblinear.get_decfun_bias(self, label_idx)
|
280
|
-
return (w, b)
|
281
|
-
|
282
|
-
def is_probability_model(self):
|
283
|
-
return (liblinear.check_probability_model(self) == 1)
|
284
|
-
|
285
|
-
def is_regression_model(self):
|
286
|
-
return (liblinear.check_regression_model(self) == 1)
|
287
|
-
|
288
|
-
def toPyModel(model_ptr):
|
289
|
-
"""
|
290
|
-
toPyModel(model_ptr) -> model
|
291
|
-
|
292
|
-
Convert a ctypes POINTER(model) to a Python model
|
293
|
-
"""
|
294
|
-
if bool(model_ptr) == False:
|
295
|
-
raise ValueError("Null pointer")
|
296
|
-
m = model_ptr.contents
|
297
|
-
m.__createfrom__ = 'C'
|
298
|
-
return m
|
299
|
-
|
300
|
-
fillprototype(liblinear.train, POINTER(model), [POINTER(problem), POINTER(parameter)])
|
301
|
-
fillprototype(liblinear.find_parameter_C, None, [POINTER(problem), POINTER(parameter), c_int, c_double, c_double, POINTER(c_double), POINTER(c_double)])
|
302
|
-
fillprototype(liblinear.cross_validation, None, [POINTER(problem), POINTER(parameter), c_int, POINTER(c_double)])
|
303
|
-
|
304
|
-
fillprototype(liblinear.predict_values, c_double, [POINTER(model), POINTER(feature_node), POINTER(c_double)])
|
305
|
-
fillprototype(liblinear.predict, c_double, [POINTER(model), POINTER(feature_node)])
|
306
|
-
fillprototype(liblinear.predict_probability, c_double, [POINTER(model), POINTER(feature_node), POINTER(c_double)])
|
307
|
-
|
308
|
-
fillprototype(liblinear.save_model, c_int, [c_char_p, POINTER(model)])
|
309
|
-
fillprototype(liblinear.load_model, POINTER(model), [c_char_p])
|
310
|
-
|
311
|
-
fillprototype(liblinear.get_nr_feature, c_int, [POINTER(model)])
|
312
|
-
fillprototype(liblinear.get_nr_class, c_int, [POINTER(model)])
|
313
|
-
fillprototype(liblinear.get_labels, None, [POINTER(model), POINTER(c_int)])
|
314
|
-
fillprototype(liblinear.get_decfun_coef, c_double, [POINTER(model), c_int, c_int])
|
315
|
-
fillprototype(liblinear.get_decfun_bias, c_double, [POINTER(model), c_int])
|
316
|
-
|
317
|
-
fillprototype(liblinear.free_model_content, None, [POINTER(model)])
|
318
|
-
fillprototype(liblinear.free_and_destroy_model, None, [POINTER(POINTER(model))])
|
319
|
-
fillprototype(liblinear.destroy_param, None, [POINTER(parameter)])
|
320
|
-
fillprototype(liblinear.check_parameter, c_char_p, [POINTER(problem), POINTER(parameter)])
|
321
|
-
fillprototype(liblinear.check_probability_model, c_int, [POINTER(model)])
|
322
|
-
fillprototype(liblinear.check_regression_model, c_int, [POINTER(model)])
|
323
|
-
fillprototype(liblinear.set_print_string_function, None, [CFUNCTYPE(None, c_char_p)])
|
@@ -1,270 +0,0 @@
|
|
1
|
-
#!/usr/bin/env python
|
2
|
-
|
3
|
-
import os, sys
|
4
|
-
sys.path = [os.path.dirname(os.path.abspath(__file__))] + sys.path
|
5
|
-
from liblinear import *
|
6
|
-
from liblinear import __all__ as liblinear_all
|
7
|
-
from ctypes import c_double
|
8
|
-
|
9
|
-
__all__ = ['svm_read_problem', 'load_model', 'save_model', 'evaluations',
|
10
|
-
'train', 'predict'] + liblinear_all
|
11
|
-
|
12
|
-
|
13
|
-
def svm_read_problem(data_file_name):
|
14
|
-
"""
|
15
|
-
svm_read_problem(data_file_name) -> [y, x]
|
16
|
-
|
17
|
-
Read LIBSVM-format data from data_file_name and return labels y
|
18
|
-
and data instances x.
|
19
|
-
"""
|
20
|
-
prob_y = []
|
21
|
-
prob_x = []
|
22
|
-
for line in open(data_file_name):
|
23
|
-
line = line.split(None, 1)
|
24
|
-
# In case an instance with all zero features
|
25
|
-
if len(line) == 1: line += ['']
|
26
|
-
label, features = line
|
27
|
-
xi = {}
|
28
|
-
for e in features.split():
|
29
|
-
ind, val = e.split(":")
|
30
|
-
xi[int(ind)] = float(val)
|
31
|
-
prob_y += [float(label)]
|
32
|
-
prob_x += [xi]
|
33
|
-
return (prob_y, prob_x)
|
34
|
-
|
35
|
-
def load_model(model_file_name):
|
36
|
-
"""
|
37
|
-
load_model(model_file_name) -> model
|
38
|
-
|
39
|
-
Load a LIBLINEAR model from model_file_name and return.
|
40
|
-
"""
|
41
|
-
model = liblinear.load_model(model_file_name.encode())
|
42
|
-
if not model:
|
43
|
-
print("can't open model file %s" % model_file_name)
|
44
|
-
return None
|
45
|
-
model = toPyModel(model)
|
46
|
-
return model
|
47
|
-
|
48
|
-
def save_model(model_file_name, model):
|
49
|
-
"""
|
50
|
-
save_model(model_file_name, model) -> None
|
51
|
-
|
52
|
-
Save a LIBLINEAR model to the file model_file_name.
|
53
|
-
"""
|
54
|
-
liblinear.save_model(model_file_name.encode(), model)
|
55
|
-
|
56
|
-
def evaluations(ty, pv):
|
57
|
-
"""
|
58
|
-
evaluations(ty, pv) -> (ACC, MSE, SCC)
|
59
|
-
|
60
|
-
Calculate accuracy, mean squared error and squared correlation coefficient
|
61
|
-
using the true values (ty) and predicted values (pv).
|
62
|
-
"""
|
63
|
-
if len(ty) != len(pv):
|
64
|
-
raise ValueError("len(ty) must equal to len(pv)")
|
65
|
-
total_correct = total_error = 0
|
66
|
-
sumv = sumy = sumvv = sumyy = sumvy = 0
|
67
|
-
for v, y in zip(pv, ty):
|
68
|
-
if y == v:
|
69
|
-
total_correct += 1
|
70
|
-
total_error += (v-y)*(v-y)
|
71
|
-
sumv += v
|
72
|
-
sumy += y
|
73
|
-
sumvv += v*v
|
74
|
-
sumyy += y*y
|
75
|
-
sumvy += v*y
|
76
|
-
l = len(ty)
|
77
|
-
ACC = 100.0*total_correct/l
|
78
|
-
MSE = total_error/l
|
79
|
-
try:
|
80
|
-
SCC = ((l*sumvy-sumv*sumy)*(l*sumvy-sumv*sumy))/((l*sumvv-sumv*sumv)*(l*sumyy-sumy*sumy))
|
81
|
-
except:
|
82
|
-
SCC = float('nan')
|
83
|
-
return (ACC, MSE, SCC)
|
84
|
-
|
85
|
-
def train(arg1, arg2=None, arg3=None):
|
86
|
-
"""
|
87
|
-
train(y, x [, options]) -> model | ACC
|
88
|
-
train(prob [, options]) -> model | ACC
|
89
|
-
train(prob, param) -> model | ACC
|
90
|
-
|
91
|
-
Train a model from data (y, x) or a problem prob using
|
92
|
-
'options' or a parameter param.
|
93
|
-
If '-v' is specified in 'options' (i.e., cross validation)
|
94
|
-
either accuracy (ACC) or mean-squared error (MSE) is returned.
|
95
|
-
|
96
|
-
options:
|
97
|
-
-s type : set type of solver (default 1)
|
98
|
-
for multi-class classification
|
99
|
-
0 -- L2-regularized logistic regression (primal)
|
100
|
-
1 -- L2-regularized L2-loss support vector classification (dual)
|
101
|
-
2 -- L2-regularized L2-loss support vector classification (primal)
|
102
|
-
3 -- L2-regularized L1-loss support vector classification (dual)
|
103
|
-
4 -- support vector classification by Crammer and Singer
|
104
|
-
5 -- L1-regularized L2-loss support vector classification
|
105
|
-
6 -- L1-regularized logistic regression
|
106
|
-
7 -- L2-regularized logistic regression (dual)
|
107
|
-
for regression
|
108
|
-
11 -- L2-regularized L2-loss support vector regression (primal)
|
109
|
-
12 -- L2-regularized L2-loss support vector regression (dual)
|
110
|
-
13 -- L2-regularized L1-loss support vector regression (dual)
|
111
|
-
-c cost : set the parameter C (default 1)
|
112
|
-
-p epsilon : set the epsilon in loss function of SVR (default 0.1)
|
113
|
-
-e epsilon : set tolerance of termination criterion
|
114
|
-
-s 0 and 2
|
115
|
-
|f'(w)|_2 <= eps*min(pos,neg)/l*|f'(w0)|_2,
|
116
|
-
where f is the primal function, (default 0.01)
|
117
|
-
-s 11
|
118
|
-
|f'(w)|_2 <= eps*|f'(w0)|_2 (default 0.001)
|
119
|
-
-s 1, 3, 4, and 7
|
120
|
-
Dual maximal violation <= eps; similar to liblinear (default 0.)
|
121
|
-
-s 5 and 6
|
122
|
-
|f'(w)|_inf <= eps*min(pos,neg)/l*|f'(w0)|_inf,
|
123
|
-
where f is the primal function (default 0.01)
|
124
|
-
-s 12 and 13
|
125
|
-
|f'(alpha)|_1 <= eps |f'(alpha0)|,
|
126
|
-
where f is the dual function (default 0.1)
|
127
|
-
-B bias : if bias >= 0, instance x becomes [x; bias]; if < 0, no bias term added (default -1)
|
128
|
-
-wi weight: weights adjust the parameter C of different classes (see README for details)
|
129
|
-
-v n: n-fold cross validation mode
|
130
|
-
-q : quiet mode (no outputs)
|
131
|
-
"""
|
132
|
-
prob, param = None, None
|
133
|
-
if isinstance(arg1, (list, tuple)):
|
134
|
-
assert isinstance(arg2, (list, tuple))
|
135
|
-
y, x, options = arg1, arg2, arg3
|
136
|
-
prob = problem(y, x)
|
137
|
-
param = parameter(options)
|
138
|
-
elif isinstance(arg1, problem):
|
139
|
-
prob = arg1
|
140
|
-
if isinstance(arg2, parameter):
|
141
|
-
param = arg2
|
142
|
-
else :
|
143
|
-
param = parameter(arg2)
|
144
|
-
if prob == None or param == None :
|
145
|
-
raise TypeError("Wrong types for the arguments")
|
146
|
-
|
147
|
-
prob.set_bias(param.bias)
|
148
|
-
liblinear.set_print_string_function(param.print_func)
|
149
|
-
err_msg = liblinear.check_parameter(prob, param)
|
150
|
-
if err_msg :
|
151
|
-
raise ValueError('Error: %s' % err_msg)
|
152
|
-
|
153
|
-
if param.flag_find_C:
|
154
|
-
nr_fold = param.nr_fold
|
155
|
-
best_C = c_double()
|
156
|
-
best_rate = c_double()
|
157
|
-
max_C = 1024
|
158
|
-
if param.flag_C_specified:
|
159
|
-
start_C = param.C
|
160
|
-
else:
|
161
|
-
start_C = -1.0
|
162
|
-
liblinear.find_parameter_C(prob, param, nr_fold, start_C, max_C, best_C, best_rate)
|
163
|
-
print("Best C = %lf CV accuracy = %g%%\n"% (best_C.value, 100.0*best_rate.value))
|
164
|
-
return best_C.value,best_rate.value
|
165
|
-
|
166
|
-
|
167
|
-
elif param.flag_cross_validation:
|
168
|
-
l, nr_fold = prob.l, param.nr_fold
|
169
|
-
target = (c_double * l)()
|
170
|
-
liblinear.cross_validation(prob, param, nr_fold, target)
|
171
|
-
ACC, MSE, SCC = evaluations(prob.y[:l], target[:l])
|
172
|
-
if param.solver_type in [L2R_L2LOSS_SVR, L2R_L2LOSS_SVR_DUAL, L2R_L1LOSS_SVR_DUAL]:
|
173
|
-
print("Cross Validation Mean squared error = %g" % MSE)
|
174
|
-
print("Cross Validation Squared correlation coefficient = %g" % SCC)
|
175
|
-
return MSE
|
176
|
-
else:
|
177
|
-
print("Cross Validation Accuracy = %g%%" % ACC)
|
178
|
-
return ACC
|
179
|
-
else :
|
180
|
-
m = liblinear.train(prob, param)
|
181
|
-
m = toPyModel(m)
|
182
|
-
|
183
|
-
return m
|
184
|
-
|
185
|
-
def predict(y, x, m, options=""):
|
186
|
-
"""
|
187
|
-
predict(y, x, m [, options]) -> (p_labels, p_acc, p_vals)
|
188
|
-
|
189
|
-
Predict data (y, x) with the SVM model m.
|
190
|
-
options:
|
191
|
-
-b probability_estimates: whether to output probability estimates, 0 or 1 (default 0); currently for logistic regression only
|
192
|
-
-q quiet mode (no outputs)
|
193
|
-
|
194
|
-
The return tuple contains
|
195
|
-
p_labels: a list of predicted labels
|
196
|
-
p_acc: a tuple including accuracy (for classification), mean-squared
|
197
|
-
error, and squared correlation coefficient (for regression).
|
198
|
-
p_vals: a list of decision values or probability estimates (if '-b 1'
|
199
|
-
is specified). If k is the number of classes, for decision values,
|
200
|
-
each element includes results of predicting k binary-class
|
201
|
-
SVMs. if k = 2 and solver is not MCSVM_CS, only one decision value
|
202
|
-
is returned. For probabilities, each element contains k values
|
203
|
-
indicating the probability that the testing instance is in each class.
|
204
|
-
Note that the order of classes here is the same as 'model.label'
|
205
|
-
field in the model structure.
|
206
|
-
"""
|
207
|
-
|
208
|
-
def info(s):
|
209
|
-
print(s)
|
210
|
-
|
211
|
-
predict_probability = 0
|
212
|
-
argv = options.split()
|
213
|
-
i = 0
|
214
|
-
while i < len(argv):
|
215
|
-
if argv[i] == '-b':
|
216
|
-
i += 1
|
217
|
-
predict_probability = int(argv[i])
|
218
|
-
elif argv[i] == '-q':
|
219
|
-
info = print_null
|
220
|
-
else:
|
221
|
-
raise ValueError("Wrong options")
|
222
|
-
i+=1
|
223
|
-
|
224
|
-
solver_type = m.param.solver_type
|
225
|
-
nr_class = m.get_nr_class()
|
226
|
-
nr_feature = m.get_nr_feature()
|
227
|
-
is_prob_model = m.is_probability_model()
|
228
|
-
bias = m.bias
|
229
|
-
if bias >= 0:
|
230
|
-
biasterm = feature_node(nr_feature+1, bias)
|
231
|
-
else:
|
232
|
-
biasterm = feature_node(-1, bias)
|
233
|
-
pred_labels = []
|
234
|
-
pred_values = []
|
235
|
-
|
236
|
-
if predict_probability:
|
237
|
-
if not is_prob_model:
|
238
|
-
raise TypeError('probability output is only supported for logistic regression')
|
239
|
-
prob_estimates = (c_double * nr_class)()
|
240
|
-
for xi in x:
|
241
|
-
xi, idx = gen_feature_nodearray(xi, feature_max=nr_feature)
|
242
|
-
xi[-2] = biasterm
|
243
|
-
label = liblinear.predict_probability(m, xi, prob_estimates)
|
244
|
-
values = prob_estimates[:nr_class]
|
245
|
-
pred_labels += [label]
|
246
|
-
pred_values += [values]
|
247
|
-
else:
|
248
|
-
if nr_class <= 2:
|
249
|
-
nr_classifier = 1
|
250
|
-
else:
|
251
|
-
nr_classifier = nr_class
|
252
|
-
dec_values = (c_double * nr_classifier)()
|
253
|
-
for xi in x:
|
254
|
-
xi, idx = gen_feature_nodearray(xi, feature_max=nr_feature)
|
255
|
-
xi[-2] = biasterm
|
256
|
-
label = liblinear.predict_values(m, xi, dec_values)
|
257
|
-
values = dec_values[:nr_classifier]
|
258
|
-
pred_labels += [label]
|
259
|
-
pred_values += [values]
|
260
|
-
if len(y) == 0:
|
261
|
-
y = [0] * len(x)
|
262
|
-
ACC, MSE, SCC = evaluations(y, pred_labels)
|
263
|
-
l = len(y)
|
264
|
-
if m.is_regression_model():
|
265
|
-
info("Mean squared error = %g (regression)" % MSE)
|
266
|
-
info("Squared correlation coefficient = %g (regression)" % SCC)
|
267
|
-
else:
|
268
|
-
info("Accuracy = %g%% (%d/%d) (classification)" % (ACC, int(l*ACC/100), l))
|
269
|
-
|
270
|
-
return pred_labels, (ACC, MSE, SCC), pred_values
|