This file is indexed.

/usr/lib/python3/dist-packages/liblinearutil.py is in python3-liblinear 2.1.0+dfsg-2.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
259
260
261
262
263
264
265
266
267
268
269
270
#!/usr/bin/env python

import os, sys
sys.path = [os.path.dirname(os.path.abspath(__file__))] + sys.path 
from liblinear import *
from liblinear import __all__ as liblinear_all
from ctypes import c_double

__all__ = ['svm_read_problem', 'load_model', 'save_model', 'evaluations',
           'train', 'predict'] + liblinear_all


def svm_read_problem(data_file_name):
	"""
	svm_read_problem(data_file_name) -> [y, x]

	Read LIBSVM-format data from data_file_name and return labels y
	and data instances x.
	"""
	prob_y = []
	prob_x = []
	for line in open(data_file_name):
		line = line.split(None, 1)
		# In case an instance with all zero features
		if len(line) == 1: line += ['']
		label, features = line
		xi = {}
		for e in features.split():
			ind, val = e.split(":")
			xi[int(ind)] = float(val)
		prob_y += [float(label)]
		prob_x += [xi]
	return (prob_y, prob_x)

def load_model(model_file_name):
	"""
	load_model(model_file_name) -> model

	Load a LIBLINEAR model from model_file_name and return.
	"""
	model = liblinear.load_model(model_file_name.encode())
	if not model:
		print("can't open model file %s" % model_file_name)
		return None
	model = toPyModel(model)
	return model

def save_model(model_file_name, model):
	"""
	save_model(model_file_name, model) -> None

	Save a LIBLINEAR model to the file model_file_name.
	"""
	liblinear.save_model(model_file_name.encode(), model)

def evaluations(ty, pv):
	"""
	evaluations(ty, pv) -> (ACC, MSE, SCC)

	Calculate accuracy, mean squared error and squared correlation coefficient
	using the true values (ty) and predicted values (pv).
	"""
	if len(ty) != len(pv):
		raise ValueError("len(ty) must equal to len(pv)")
	total_correct = total_error = 0
	sumv = sumy = sumvv = sumyy = sumvy = 0
	for v, y in zip(pv, ty):
		if y == v:
			total_correct += 1
		total_error += (v-y)*(v-y)
		sumv += v
		sumy += y
		sumvv += v*v
		sumyy += y*y
		sumvy += v*y
	l = len(ty)
	ACC = 100.0*total_correct/l
	MSE = total_error/l
	try:
		SCC = ((l*sumvy-sumv*sumy)*(l*sumvy-sumv*sumy))/((l*sumvv-sumv*sumv)*(l*sumyy-sumy*sumy))
	except:
		SCC = float('nan')
	return (ACC, MSE, SCC)

def train(arg1, arg2=None, arg3=None):
	"""
	train(y, x [, options]) -> model | ACC
	train(prob [, options]) -> model | ACC
	train(prob, param) -> model | ACC

	Train a model from data (y, x) or a problem prob using
	'options' or a parameter param.
	If '-v' is specified in 'options' (i.e., cross validation)
	either accuracy (ACC) or mean-squared error (MSE) is returned.

	options:
		-s type : set type of solver (default 1)
		  for multi-class classification
			 0 -- L2-regularized logistic regression (primal)
			 1 -- L2-regularized L2-loss support vector classification (dual)
			 2 -- L2-regularized L2-loss support vector classification (primal)
			 3 -- L2-regularized L1-loss support vector classification (dual)
			 4 -- support vector classification by Crammer and Singer
			 5 -- L1-regularized L2-loss support vector classification
			 6 -- L1-regularized logistic regression
			 7 -- L2-regularized logistic regression (dual)
		  for regression
			11 -- L2-regularized L2-loss support vector regression (primal)
			12 -- L2-regularized L2-loss support vector regression (dual)
			13 -- L2-regularized L1-loss support vector regression (dual)
		-c cost : set the parameter C (default 1)
		-p epsilon : set the epsilon in loss function of SVR (default 0.1)
		-e epsilon : set tolerance of termination criterion
			-s 0 and 2
				|f'(w)|_2 <= eps*min(pos,neg)/l*|f'(w0)|_2,
				where f is the primal function, (default 0.01)
			-s 11
				|f'(w)|_2 <= eps*|f'(w0)|_2 (default 0.001)
			-s 1, 3, 4, and 7
				Dual maximal violation <= eps; similar to liblinear (default 0.)
			-s 5 and 6
				|f'(w)|_inf <= eps*min(pos,neg)/l*|f'(w0)|_inf,
				where f is the primal function (default 0.01)
			-s 12 and 13
				|f'(alpha)|_1 <= eps |f'(alpha0)|,
				where f is the dual function (default 0.1)
		-B bias : if bias >= 0, instance x becomes [x; bias]; if < 0, no bias term added (default -1)
		-wi weight: weights adjust the parameter C of different classes (see README for details)
		-v n: n-fold cross validation mode
		-q : quiet mode (no outputs)
	"""
	prob, param = None, None
	if isinstance(arg1, (list, tuple)):
		assert isinstance(arg2, (list, tuple))
		y, x, options = arg1, arg2, arg3
		prob = problem(y, x)
		param = parameter(options)
	elif isinstance(arg1, problem):
		prob = arg1
		if isinstance(arg2, parameter):
			param = arg2
		else :
			param = parameter(arg2)
	if prob == None or param == None :
		raise TypeError("Wrong types for the arguments")

	prob.set_bias(param.bias)
	liblinear.set_print_string_function(param.print_func)
	err_msg = liblinear.check_parameter(prob, param)
	if err_msg :
		raise ValueError('Error: %s' % err_msg)

	if param.flag_find_C:
		nr_fold = param.nr_fold
		best_C = c_double()
		best_rate = c_double()		
		max_C = 1024
		if param.flag_C_specified:
			start_C = param.C
		else:
			start_C = -1.0
		liblinear.find_parameter_C(prob, param, nr_fold, start_C, max_C, best_C, best_rate)
		print("Best C = %lf  CV accuracy = %g%%\n"% (best_C.value, 100.0*best_rate.value))
		return best_C.value,best_rate.value


	elif param.flag_cross_validation:
		l, nr_fold = prob.l, param.nr_fold
		target = (c_double * l)()
		liblinear.cross_validation(prob, param, nr_fold, target)
		ACC, MSE, SCC = evaluations(prob.y[:l], target[:l])
		if param.solver_type in [L2R_L2LOSS_SVR, L2R_L2LOSS_SVR_DUAL, L2R_L1LOSS_SVR_DUAL]:
			print("Cross Validation Mean squared error = %g" % MSE)
			print("Cross Validation Squared correlation coefficient = %g" % SCC)
			return MSE
		else:
			print("Cross Validation Accuracy = %g%%" % ACC)
			return ACC
	else :
		m = liblinear.train(prob, param)
		m = toPyModel(m)

		return m

def predict(y, x, m, options=""):
	"""
	predict(y, x, m [, options]) -> (p_labels, p_acc, p_vals)

	Predict data (y, x) with the SVM model m.
	options:
	    -b probability_estimates: whether to output probability estimates, 0 or 1 (default 0); currently for logistic regression only
	    -q quiet mode (no outputs)

	The return tuple contains
	p_labels: a list of predicted labels
	p_acc: a tuple including  accuracy (for classification), mean-squared
	       error, and squared correlation coefficient (for regression).
	p_vals: a list of decision values or probability estimates (if '-b 1'
	        is specified). If k is the number of classes, for decision values,
	        each element includes results of predicting k binary-class
	        SVMs. if k = 2 and solver is not MCSVM_CS, only one decision value
	        is returned. For probabilities, each element contains k values
	        indicating the probability that the testing instance is in each class.
	        Note that the order of classes here is the same as 'model.label'
	        field in the model structure.
	"""

	def info(s):
		print(s)

	predict_probability = 0
	argv = options.split()
	i = 0
	while i < len(argv):
		if argv[i] == '-b':
			i += 1
			predict_probability = int(argv[i])
		elif argv[i] == '-q':
			info = print_null
		else:
			raise ValueError("Wrong options")
		i+=1

	solver_type = m.param.solver_type
	nr_class = m.get_nr_class()
	nr_feature = m.get_nr_feature()
	is_prob_model = m.is_probability_model()
	bias = m.bias
	if bias >= 0:
		biasterm = feature_node(nr_feature+1, bias)
	else:
		biasterm = feature_node(-1, bias)
	pred_labels = []
	pred_values = []

	if predict_probability:
		if not is_prob_model:
			raise TypeError('probability output is only supported for logistic regression')
		prob_estimates = (c_double * nr_class)()
		for xi in x:
			xi, idx = gen_feature_nodearray(xi, feature_max=nr_feature)
			xi[-2] = biasterm
			label = liblinear.predict_probability(m, xi, prob_estimates)
			values = prob_estimates[:nr_class]
			pred_labels += [label]
			pred_values += [values]
	else:
		if nr_class <= 2:
			nr_classifier = 1
		else:
			nr_classifier = nr_class
		dec_values = (c_double * nr_classifier)()
		for xi in x:
			xi, idx = gen_feature_nodearray(xi, feature_max=nr_feature)
			xi[-2] = biasterm
			label = liblinear.predict_values(m, xi, dec_values)
			values = dec_values[:nr_classifier]
			pred_labels += [label]
			pred_values += [values]
	if len(y) == 0:
		y = [0] * len(x)
	ACC, MSE, SCC = evaluations(y, pred_labels)
	l = len(y)
	if m.is_regression_model():
		info("Mean squared error = %g (regression)" % MSE)
		info("Squared correlation coefficient = %g (regression)" % SCC)
	else:
		info("Accuracy = %g%% (%d/%d) (classification)" % (ACC, int(l*ACC/100), l))

	return pred_labels, (ACC, MSE, SCC), pred_values