eluka 0.1.0

data/ext/libsvm/svm.def

@@ -0,0 +1,19 @@
+LIBRARY libsvm
+EXPORTS
+	svm_train	@1
+	svm_cross_validation	@2
+	svm_save_model	@3
+	svm_load_model	@4
+	svm_get_svm_type	@5
+	svm_get_nr_class	@6
+	svm_get_labels	@7
+	svm_get_svr_probability	@8
+	svm_predict_values	@9
+	svm_predict	@10
+	svm_predict_probability	@11
+	svm_free_model_content	@12
+	svm_free_and_destroy_model	@13
+	svm_destroy_param	@14
+	svm_check_parameter	@15
+	svm_check_probability_model	@16
+	svm_set_print_string_function	@17

data/ext/libsvm/svm.h

@@ -0,0 +1,105 @@
+#ifndef _LIBSVM_H
+#define _LIBSVM_H
+
+#define LIBSVM_VERSION 300
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+extern int libsvm_version;
+
+struct svm_node
+{
+	int index;
+	double value;
+};
+
+struct svm_problem
+{
+	int l;
+	double *y;
+	struct svm_node **x;
+};
+
+enum { C_SVC, NU_SVC, ONE_CLASS, EPSILON_SVR, NU_SVR };	/* svm_type */
+enum { LINEAR, POLY, RBF, SIGMOID, PRECOMPUTED }; /* kernel_type */
+
+struct svm_parameter
+{
+	int svm_type;
+	int kernel_type;
+	int degree;	/* for poly */
+	double gamma;	/* for poly/rbf/sigmoid */
+	double coef0;	/* for poly/sigmoid */
+
+	/* these are for training only */
+	double cache_size; /* in MB */
+	double eps;	/* stopping criteria */
+	double C;	/* for C_SVC, EPSILON_SVR and NU_SVR */
+	int nr_weight;		/* for C_SVC */
+	int *weight_label;	/* for C_SVC */
+	double* weight;		/* for C_SVC */
+	double nu;	/* for NU_SVC, ONE_CLASS, and NU_SVR */
+	double p;	/* for EPSILON_SVR */
+	int shrinking;	/* use the shrinking heuristics */
+	int probability; /* do probability estimates */
+};
+
+//
+// svm_model
+// 
+struct svm_model
+{
+	struct svm_parameter param;	/* parameter */
+	int nr_class;		/* number of classes, = 2 in regression/one class svm */
+	int l;			/* total #SV */
+	struct svm_node **SV;		/* SVs (SV[l]) */
+	double **sv_coef;	/* coefficients for SVs in decision functions (sv_coef[k-1][l]) */
+	double *rho;		/* constants in decision functions (rho[k*(k-1)/2]) */
+	double *probA;		/* pariwise probability information */
+	double *probB;
+
+	/* for classification only */
+
+	int *label;		/* label of each class (label[k]) */
+	int *nSV;		/* number of SVs for each class (nSV[k]) */
+				/* nSV[0] + nSV[1] + ... + nSV[k-1] = l */
+	/* XXX */
+	int free_sv;		/* 1 if svm_model is created by svm_load_model*/
+				/* 0 if svm_model is created by svm_train */
+};
+
+struct svm_model *svm_train(const struct svm_problem *prob, const struct svm_parameter *param);
+void svm_cross_validation(const struct svm_problem *prob, const struct svm_parameter *param, int nr_fold, double *target);
+
+int svm_save_model(const char *model_file_name, const struct svm_model *model);
+struct svm_model *svm_load_model(const char *model_file_name);
+
+int svm_get_svm_type(const struct svm_model *model);
+int svm_get_nr_class(const struct svm_model *model);
+void svm_get_labels(const struct svm_model *model, int *label);
+double svm_get_svr_probability(const struct svm_model *model);
+
+double svm_predict_values(const struct svm_model *model, const struct svm_node *x, double* dec_values);
+double svm_predict(const struct svm_model *model, const struct svm_node *x);
+double svm_predict_probability(const struct svm_model *model, const struct svm_node *x, double* prob_estimates);
+
+void svm_free_model_content(struct svm_model *model_ptr);
+void svm_free_and_destroy_model(struct svm_model **model_ptr_ptr);
+void svm_destroy_param(struct svm_parameter *param);
+
+const char *svm_check_parameter(const struct svm_problem *prob, const struct svm_parameter *param);
+int svm_check_probability_model(const struct svm_model *model);
+
+void svm_set_print_string_function(void (*print_func)(const char *));
+
+// deprecated
+// this function will be removed in future release
+void svm_destroy_model(struct svm_model *model_ptr); 
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _LIBSVM_H */

data/ext/libsvm/tools/README

@@ -0,0 +1,149 @@
+This directory includes some useful codes:
+
+1. subset selection tools.
+2. parameter selection tools.
+3. LIBSVM format checking tools
+
+Part I: Subset selection tools
+
+Introduction
+============
+
+Training large data is time consuming. Sometimes one should work on a
+smaller subset first. The python script subset.py randomly selects a
+specified number of samples. For classification data, we provide a
+stratified selection to ensure the same class distribution in the
+subset.
+
+Usage: subset.py [options] dataset number [output1] [output2]
+
+This script selects a subset of the given data set.
+
+options:
+-s method : method of selection (default 0)
+     0 -- stratified selection (classification only)
+     1 -- random selection
+
+output1 : the subset (optional)
+output2 : the rest of data (optional)
+
+If output1 is omitted, the subset will be printed on the screen.
+
+Example
+=======
+
+> python subset.py heart_scale 100 file1 file2
+
+From heart_scale 100 samples are randomly selected and stored in
+file1. All remaining instances are stored in file2.
+
+
+Part II: Parameter Selection Tools
+
+Introduction
+============
+
+grid.py is a parameter selection tool for C-SVM classification using
+the RBF (radial basis function) kernel. It uses cross validation (CV)
+technique to estimate the accuracy of each parameter combination in
+the specified range and helps you to decide the best parameters for
+your problem.
+
+grid.py directly executes libsvm binaries (so no python binding is needed)
+for cross validation and then draw contour of CV accuracy using gnuplot.
+You must have libsvm and gnuplot installed before using it. The package
+gnuplot is available at http://www.gnuplot.info/
+
+On Mac OSX, the precompiled gnuplot file needs the library Aquarterm,
+which thus must be installed as well. In addition, this version of
+gnuplot does not support png, so you need to change "set term png
+transparent small" and use other image formats. For example, you may
+have "set term pbm small color".
+
+Usage: grid.py [-log2c begin,end,step] [-log2g begin,end,step] [-v fold]
+       [-svmtrain pathname] [-gnuplot pathname] [-out pathname] [-png pathname]
+       [additional parameters for svm-train] dataset
+
+The program conducts v-fold cross validation using parameter C (and gamma)
+= 2^begin, 2^(begin+step), ..., 2^end.
+
+You can specify where the libsvm executable and gnuplot are using the
+-svmtrain and -gnuplot parameters.
+
+For windows users, please use pgnuplot.exe. If you are using gnuplot
+3.7.1, please upgrade to version 3.7.3 or higher. The version 3.7.1
+has a bug. If you use cygwin on windows, please use gunplot-x11.
+
+Example
+=======
+
+> python grid.py -log2c -5,5,1 -log2g -4,0,1 -v 5 -m 300 heart_scale
+
+Users (in particular MS Windows users) may need to specify the path of
+executable files. You can either change paths in the beginning of
+grid.py or specify them in the command line. For example,
+
+> grid.py -log2c -5,5,1 -svmtrain c:\libsvm\windows\svm-train.exe -gnuplot c:\tmp\gnuplot\bin\pgnuplot.exe -v 10 heart_scale
+
+Output: two files
+dataset.png: the CV accuracy contour plot generated by gnuplot
+dataset.out: the CV accuracy at each (log2(C),log2(gamma))
+
+Parallel grid search
+====================
+
+You can conduct a parallel grid search by dispatching jobs to a
+cluster of computers which share the same file system. First, you add
+machine names in grid.py:
+
+ssh_workers = ["linux1", "linux5", "linux5"]
+
+and then setup your ssh so that the authentication works without
+asking a password.
+
+The same machine (e.g., linux5 here) can be listed more than once if
+it has multiple CPUs or has more RAM. If the local machine is the
+best, you can also enlarge the nr_local_worker. For example:
+
+nr_local_worker = 2
+
+Example:
+
+> python grid.py heart_scale
+[local] -1 -1 78.8889  (best c=0.5, g=0.5, rate=78.8889)
+[linux5] -1 -7 83.3333  (best c=0.5, g=0.0078125, rate=83.3333)
+[linux5] 5 -1 77.037  (best c=0.5, g=0.0078125, rate=83.3333)
+[linux1] 5 -7 83.3333  (best c=0.5, g=0.0078125, rate=83.3333)
+.
+.
+.
+
+If -log2c, -log2g, or -v is not specified, default values are used.
+
+If your system uses telnet instead of ssh, you list the computer names
+in telnet_workers.
+
+Part III: LIBSVM format checking tools
+
+Introduction
+============
+
+`svm-train' conducts only a simple check of the input data. To do a
+detailed check, we provide a python script `checkdata.py.'
+
+Usage: checkdata.py dataset
+
+Exit status (returned value): 1 if there are errors, 0 otherwise.
+
+This tool is written by Rong-En Fan at National Taiwan University.
+
+Example
+=======
+
+> cat bad_data
+1 3:1 2:4
+> python checkdata.py bad_data
+line 1: feature indices must be in an ascending order, previous/current features 3:1 2:4
+Found 1 lines with error.
+
+

data/ext/libsvm/tools/checkdata.py

@@ -0,0 +1,108 @@
+#!/usr/bin/env python
+
+#
+# A format checker for LIBSVM
+#
+
+#
+# Copyright (c) 2007, Rong-En Fan
+#
+# All rights reserved.
+#
+# This program is distributed under the same license of the LIBSVM package.
+# 
+
+from sys import argv, exit
+import os.path
+
+def err(line_no, msg):
+	print("line %d: %s" % (line_no, msg))
+
+# works like float() but does not accept nan and inf
+def my_float(x):
+	if x.lower().find("nan") != -1 or x.lower().find("inf") != -1:
+		raise ValueError
+
+	return float(x)
+
+def main():
+	if len(argv) != 2:
+		print("Usage: %s dataset" % (argv[0]))
+		exit(1)
+
+	dataset = argv[1]
+
+	if not os.path.exists(dataset):
+		print("dataset %s not found" % (dataset))
+		exit(1)
+
+	line_no = 1
+	error_line_count = 0
+	for line in open(dataset, 'r'):
+		line_error = False
+
+		# each line must end with a newline character
+		if line[-1] != '\n':
+			err(line_no, "missing a newline character in the end")
+			line_error = True
+
+		nodes = line.split()
+
+		# check label
+		try:
+			label = nodes.pop(0)
+			
+			if label.find(',') != -1:
+				# multi-label format
+				try:
+					for l in label.split(','):
+						l = my_float(l)
+				except:
+					err(line_no, "label %s is not a valid multi-label form" % label)
+					line_error = True
+			else:
+				try:
+					label = my_float(label)
+				except:
+					err(line_no, "label %s is not a number" % label)
+					line_error = True
+		except:
+			err(line_no, "missing label, perhaps an empty line?")
+			line_error = True
+
+		# check features
+		prev_index = -1
+		for i in range(len(nodes)):
+			try:
+				(index, value) =  nodes[i].split(':')
+
+				index = int(index)
+				value = my_float(value)
+
+				# precomputed kernel's index starts from 0 and LIBSVM
+				# checks it. Hence, don't treat index 0 as an error.
+				if index < 0:
+					err(line_no, "feature index must be positive; wrong feature %s" % nodes[i])
+					line_error = True
+				elif index < prev_index:
+					err(line_no, "feature indices must be in an ascending order, previous/current features %s %s" % (nodes[i-1], nodes[i]))
+					line_error = True
+				prev_index = index
+			except:
+				err(line_no, "feature '%s' not an <index>:<value> pair, <index> integer, <value> real number " % nodes[i])
+				line_error = True
+
+		line_no += 1
+
+		if line_error:
+			error_line_count += 1
+	
+	if error_line_count > 0:
+		print("Found %d lines with error." % (error_line_count))
+		return 1
+	else:
+		print("No error.")
+		return 0
+
+if __name__ == "__main__":
+	exit(main())

data/ext/libsvm/tools/easy.py

@@ -0,0 +1,79 @@
+#!/usr/bin/env python
+
+import sys
+import os
+from subprocess import *
+
+if len(sys.argv) <= 1:
+	print('Usage: %s training_file [testing_file]' % sys.argv[0])
+	raise SystemExit
+
+# svm, grid, and gnuplot executable files
+
+is_win32 = (sys.platform == 'win32')
+if not is_win32:
+	svmscale_exe = "../svm-scale"
+	svmtrain_exe = "../svm-train"
+	svmpredict_exe = "../svm-predict"
+	grid_py = "./grid.py"
+	gnuplot_exe = "/usr/bin/gnuplot"
+else:
+        # example for windows
+	svmscale_exe = r"..\windows\svm-scale.exe"
+	svmtrain_exe = r"..\windows\svm-train.exe"
+	svmpredict_exe = r"..\windows\svm-predict.exe"
+	gnuplot_exe = r"c:\tmp\gnuplot\bin\pgnuplot.exe"
+	grid_py = r".\grid.py"
+
+assert os.path.exists(svmscale_exe),"svm-scale executable not found"
+assert os.path.exists(svmtrain_exe),"svm-train executable not found"
+assert os.path.exists(svmpredict_exe),"svm-predict executable not found"
+assert os.path.exists(gnuplot_exe),"gnuplot executable not found"
+assert os.path.exists(grid_py),"grid.py not found"
+
+train_pathname = sys.argv[1]
+assert os.path.exists(train_pathname),"training file not found"
+file_name = os.path.split(train_pathname)[1]
+scaled_file = file_name + ".scale"
+model_file = file_name + ".model"
+range_file = file_name + ".range"
+
+if len(sys.argv) > 2:
+	test_pathname = sys.argv[2]
+	file_name = os.path.split(test_pathname)[1]
+	assert os.path.exists(test_pathname),"testing file not found"
+	scaled_test_file = file_name + ".scale"
+	predict_test_file = file_name + ".predict"
+
+cmd = '%s -s "%s" "%s" > "%s"' % (svmscale_exe, range_file, train_pathname, scaled_file)
+print('Scaling training data...')
+Popen(cmd, shell = True, stdout = PIPE).communicate()	
+
+cmd = '%s -svmtrain "%s" -gnuplot "%s" "%s"' % (grid_py, svmtrain_exe, gnuplot_exe, scaled_file)
+print('Cross validation...')
+f = Popen(cmd, shell = True, stdout = PIPE).stdout
+
+line = ''
+while True:
+	last_line = line
+	line = f.readline()
+	if not line: break
+c,g,rate = map(float,last_line.split())
+
+print('Best c=%s, g=%s CV rate=%s' % (c,g,rate))
+
+cmd = '%s -c %s -g %s "%s" "%s"' % (svmtrain_exe,c,g,scaled_file,model_file)
+print('Training...')
+Popen(cmd, shell = True, stdout = PIPE).communicate()
+
+print('Output model: %s' % model_file)
+if len(sys.argv) > 2:
+	cmd = '%s -r "%s" "%s" > "%s"' % (svmscale_exe, range_file, test_pathname, scaled_test_file)
+	print('Scaling testing data...')
+	Popen(cmd, shell = True, stdout = PIPE).communicate()	
+
+	cmd = '%s "%s" "%s" "%s"' % (svmpredict_exe, scaled_test_file, model_file, predict_test_file)
+	print('Testing...')
+	Popen(cmd, shell = True).communicate()	
+
+	print('Output prediction: %s' % predict_test_file)