eluka 0.1.0

data/ext/libsvm/java/svm_train.java

@@ -0,0 +1,318 @@
+import libsvm.*;
+import java.io.*;
+import java.util.*;
+
+class svm_train {
+	private svm_parameter param;		// set by parse_command_line
+	private svm_problem prob;		// set by read_problem
+	private svm_model model;
+	private String input_file_name;		// set by parse_command_line
+	private String model_file_name;		// set by parse_command_line
+	private String error_msg;
+	private int cross_validation;
+	private int nr_fold;
+
+	private static svm_print_interface svm_print_null = new svm_print_interface()
+	{
+		public void print(String s) {}
+	};
+
+	private static void exit_with_help()
+	{
+		System.out.print(
+		 "Usage: svm_train [options] training_set_file [model_file]\n"
+		+"options:\n"
+		+"-s svm_type : set type of SVM (default 0)\n"
+		+"	0 -- C-SVC\n"
+		+"	1 -- nu-SVC\n"
+		+"	2 -- one-class SVM\n"
+		+"	3 -- epsilon-SVR\n"
+		+"	4 -- nu-SVR\n"
+		+"-t kernel_type : set type of kernel function (default 2)\n"
+		+"	0 -- linear: u'*v\n"
+		+"	1 -- polynomial: (gamma*u'*v + coef0)^degree\n"
+		+"	2 -- radial basis function: exp(-gamma*|u-v|^2)\n"
+		+"	3 -- sigmoid: tanh(gamma*u'*v + coef0)\n"
+		+"	4 -- precomputed kernel (kernel values in training_set_file)\n"
+		+"-d degree : set degree in kernel function (default 3)\n"
+		+"-g gamma : set gamma in kernel function (default 1/num_features)\n"
+		+"-r coef0 : set coef0 in kernel function (default 0)\n"
+		+"-c cost : set the parameter C of C-SVC, epsilon-SVR, and nu-SVR (default 1)\n"
+		+"-n nu : set the parameter nu of nu-SVC, one-class SVM, and nu-SVR (default 0.5)\n"
+		+"-p epsilon : set the epsilon in loss function of epsilon-SVR (default 0.1)\n"
+		+"-m cachesize : set cache memory size in MB (default 100)\n"
+		+"-e epsilon : set tolerance of termination criterion (default 0.001)\n"
+		+"-h shrinking : whether to use the shrinking heuristics, 0 or 1 (default 1)\n"
+		+"-b probability_estimates : whether to train a SVC or SVR model for probability estimates, 0 or 1 (default 0)\n"
+		+"-wi weight : set the parameter C of class i to weight*C, for C-SVC (default 1)\n"
+		+"-v n : n-fold cross validation mode\n"
+		+"-q : quiet mode (no outputs)\n"
+		);
+		System.exit(1);
+	}
+
+	private void do_cross_validation()
+	{
+		int i;
+		int total_correct = 0;
+		double total_error = 0;
+		double sumv = 0, sumy = 0, sumvv = 0, sumyy = 0, sumvy = 0;
+		double[] target = new double[prob.l];
+
+		svm.svm_cross_validation(prob,param,nr_fold,target);
+		if(param.svm_type == svm_parameter.EPSILON_SVR ||
+		   param.svm_type == svm_parameter.NU_SVR)
+		{
+			for(i=0;i<prob.l;i++)
+			{
+				double y = prob.y[i];
+				double v = target[i];
+				total_error += (v-y)*(v-y);
+				sumv += v;
+				sumy += y;
+				sumvv += v*v;
+				sumyy += y*y;
+				sumvy += v*y;
+			}
+			System.out.print("Cross Validation Mean squared error = "+total_error/prob.l+"\n");
+			System.out.print("Cross Validation Squared correlation coefficient = "+
+				((prob.l*sumvy-sumv*sumy)*(prob.l*sumvy-sumv*sumy))/
+				((prob.l*sumvv-sumv*sumv)*(prob.l*sumyy-sumy*sumy))+"\n"
+				);
+		}
+		else
+		{
+			for(i=0;i<prob.l;i++)
+				if(target[i] == prob.y[i])
+					++total_correct;
+			System.out.print("Cross Validation Accuracy = "+100.0*total_correct/prob.l+"%\n");
+		}
+	}
+	
+	private void run(String argv[]) throws IOException
+	{
+		parse_command_line(argv);
+		read_problem();
+		error_msg = svm.svm_check_parameter(prob,param);
+
+		if(error_msg != null)
+		{
+			System.err.print("Error: "+error_msg+"\n");
+			System.exit(1);
+		}
+
+		if(cross_validation != 0)
+		{
+			do_cross_validation();
+		}
+		else
+		{
+			model = svm.svm_train(prob,param);
+			svm.svm_save_model(model_file_name,model);
+		}
+	}
+
+	public static void main(String argv[]) throws IOException
+	{
+		svm_train t = new svm_train();
+		t.run(argv);
+	}
+
+	private static double atof(String s)
+	{
+		double d = Double.valueOf(s).doubleValue();
+		if (Double.isNaN(d) || Double.isInfinite(d))
+		{
+			System.err.print("NaN or Infinity in input\n");
+			System.exit(1);
+		}
+		return(d);
+	}
+
+	private static int atoi(String s)
+	{
+		return Integer.parseInt(s);
+	}
+
+	private void parse_command_line(String argv[])
+	{
+		int i;
+		svm_print_interface print_func = null;	// default printing to stdout
+
+		param = new svm_parameter();
+		// default values
+		param.svm_type = svm_parameter.C_SVC;
+		param.kernel_type = svm_parameter.RBF;
+		param.degree = 3;
+		param.gamma = 0;	// 1/num_features
+		param.coef0 = 0;
+		param.nu = 0.5;
+		param.cache_size = 100;
+		param.C = 1;
+		param.eps = 1e-3;
+		param.p = 0.1;
+		param.shrinking = 1;
+		param.probability = 0;
+		param.nr_weight = 0;
+		param.weight_label = new int[0];
+		param.weight = new double[0];
+		cross_validation = 0;
+
+		// parse options
+		for(i=0;i<argv.length;i++)
+		{
+			if(argv[i].charAt(0) != '-') break;
+			if(++i>=argv.length)
+				exit_with_help();
+			switch(argv[i-1].charAt(1))
+			{
+				case 's':
+					param.svm_type = atoi(argv[i]);
+					break;
+				case 't':
+					param.kernel_type = atoi(argv[i]);
+					break;
+				case 'd':
+					param.degree = atoi(argv[i]);
+					break;
+				case 'g':
+					param.gamma = atof(argv[i]);
+					break;
+				case 'r':
+					param.coef0 = atof(argv[i]);
+					break;
+				case 'n':
+					param.nu = atof(argv[i]);
+					break;
+				case 'm':
+					param.cache_size = atof(argv[i]);
+					break;
+				case 'c':
+					param.C = atof(argv[i]);
+					break;
+				case 'e':
+					param.eps = atof(argv[i]);
+					break;
+				case 'p':
+					param.p = atof(argv[i]);
+					break;
+				case 'h':
+					param.shrinking = atoi(argv[i]);
+					break;
+				case 'b':
+					param.probability = atoi(argv[i]);
+					break;
+				case 'q':
+					print_func = svm_print_null;
+					i--;
+					break;
+				case 'v':
+					cross_validation = 1;
+					nr_fold = atoi(argv[i]);
+					if(nr_fold < 2)
+					{
+						System.err.print("n-fold cross validation: n must >= 2\n");
+						exit_with_help();
+					}
+					break;
+				case 'w':
+					++param.nr_weight;
+					{
+						int[] old = param.weight_label;
+						param.weight_label = new int[param.nr_weight];
+						System.arraycopy(old,0,param.weight_label,0,param.nr_weight-1);
+					}
+
+					{
+						double[] old = param.weight;
+						param.weight = new double[param.nr_weight];
+						System.arraycopy(old,0,param.weight,0,param.nr_weight-1);
+					}
+
+					param.weight_label[param.nr_weight-1] = atoi(argv[i-1].substring(2));
+					param.weight[param.nr_weight-1] = atof(argv[i]);
+					break;
+				default:
+					System.err.print("Unknown option: " + argv[i-1] + "\n");
+					exit_with_help();
+			}
+		}
+
+		svm.svm_set_print_string_function(print_func);
+
+		// determine filenames
+
+		if(i>=argv.length)
+			exit_with_help();
+
+		input_file_name = argv[i];
+
+		if(i<argv.length-1)
+			model_file_name = argv[i+1];
+		else
+		{
+			int p = argv[i].lastIndexOf('/');
+			++p;	// whew...
+			model_file_name = argv[i].substring(p)+".model";
+		}
+	}
+
+	// read in a problem (in svmlight format)
+
+	private void read_problem() throws IOException
+	{
+		BufferedReader fp = new BufferedReader(new FileReader(input_file_name));
+		Vector<Double> vy = new Vector<Double>();
+		Vector<svm_node[]> vx = new Vector<svm_node[]>();
+		int max_index = 0;
+
+		while(true)
+		{
+			String line = fp.readLine();
+			if(line == null) break;
+
+			StringTokenizer st = new StringTokenizer(line," \t\n\r\f:");
+
+			vy.addElement(atof(st.nextToken()));
+			int m = st.countTokens()/2;
+			svm_node[] x = new svm_node[m];
+			for(int j=0;j<m;j++)
+			{
+				x[j] = new svm_node();
+				x[j].index = atoi(st.nextToken());
+				x[j].value = atof(st.nextToken());
+			}
+			if(m>0) max_index = Math.max(max_index, x[m-1].index);
+			vx.addElement(x);
+		}
+
+		prob = new svm_problem();
+		prob.l = vy.size();
+		prob.x = new svm_node[prob.l][];
+		for(int i=0;i<prob.l;i++)
+			prob.x[i] = vx.elementAt(i);
+		prob.y = new double[prob.l];
+		for(int i=0;i<prob.l;i++)
+			prob.y[i] = vy.elementAt(i);
+
+		if(param.gamma == 0 && max_index > 0)
+			param.gamma = 1.0/max_index;
+
+		if(param.kernel_type == svm_parameter.PRECOMPUTED)
+			for(int i=0;i<prob.l;i++)
+			{
+				if (prob.x[i][0].index != 0)
+				{
+					System.err.print("Wrong kernel matrix: first column must be 0:sample_serial_number\n");
+					System.exit(1);
+				}
+				if ((int)prob.x[i][0].value <= 0 || (int)prob.x[i][0].value > max_index)
+				{
+					System.err.print("Wrong input format: sample_serial_number out of range\n");
+					System.exit(1);
+				}
+			}
+
+		fp.close();
+	}
+}

data/ext/libsvm/java/test_applet.html

@@ -0,0 +1 @@
+<APPLET code="svm_toy.class" archive="libsvm.jar" width=300 height=350></APPLET>

data/ext/libsvm/python/Makefile

@@ -0,0 +1,4 @@
+all = lib
+
+lib:
+	cd ..; make lib; cd -

data/ext/libsvm/python/README

@@ -0,0 +1,331 @@
+----------------------------------
+--- Python interface of LIBSVM ---
+----------------------------------
+
+Table of Contents
+=================
+
+- Introduction
+- Installation
+- Quick Start
+- Design Description
+- Data Structures
+- Utility Functions
+- Additional Information
+
+Introduction
+============
+
+Python (http://www.python.org/) is a programming language suitable for rapid
+development. This tool provides a simple Python interface to LIBSVM, a library
+for support vector machines (http://www.csie.ntu.edu.tw/~cjlin/libsvm). The
+interface is very easy to use as the usage is the same as that of LIBSVM. The
+interface is developed with the built-in Python library "ctypes."
+
+Installation
+============
+
+On Unix systems, type
+
+> make
+
+The interface needs only LIBSVM shared library, which is generated by
+the above command. We assume that the shared library is on the LIBSVM
+main directory or in the system path.
+
+For windows, the shared library libsvm.dll is ready in the directory
+`..\windows'. You can also copy it to the system directory (e.g.,
+`C:\WINDOWS\system32\' for Windows XP). To regenerate the shared library,
+please follow the instruction of building windows binaries in LIBSVM README.
+
+Quick Start
+===========
+
+There are two levels of usage. The high-level one uses utility functions
+in svmutil.py and the usage is the same as the LIBSVM MATLAB interface.
+
+>>> from svmutil import *
+# Read data in LIBSVM format
+>>> y, x = svm_read_problem('../heart_scale')
+>>> m = svm_train(y[:200], x[:200], '-c 4')
+>>> p_label, p_acc, p_val = svm_predict(y[200:], x[200:], m)
+
+# Construct problem in python format
+# Dense data
+>>> y, x = [1,-1], [[1,0,1], [-1,0,-1]]
+# Sparse data
+>>> y, x = [1,-1], [{1:1, 3:1}, {1:-1,3:-1}]
+>>> prob  = svm_problem(y, x)
+>>> param = svm_parameter('-c 4 -b 1')
+>>> m = svm_train(prob, param)
+
+# Other utility functions
+>>> svm_save_model('heart_scale.model', m)
+>>> m = svm_load_model('heart_scale.model')
+>>> p_label, p_acc, p_val = svm_predict(y, x, m, '-b 1')
+>>> ACC, MSE, SCC = evaluations(y, p_val)
+
+# Getting online help
+>>> help(svm_train)
+
+The low-level use directly calls C interfaces imported by svm.py. Note that
+all arguments and return values are in ctypes format. You need to handle them
+carefully.
+
+>>> from svm import *
+>>> prob = svm_problem([1,-1], [{1:1, 3:1}, {1:-1,3:-1}])
+>>> param = svm_parameter('-c 4')
+>>> m = libsvm.svm_train(prob, param) # m is a ctype pointer to an svm_model
+# Convet a Python-fromat instance to svm_nodearray, a ctypes structure
+>>> x0, max_idx = gen_svm_nodearray({1:1, 3:1})
+>>> label = libsvm.svm_predict(m, x0)
+
+Design Description
+==================
+
+There are two files svm.py and svmutil.py, which respectively correspond to
+low-level and high-level use of the interface.
+
+In svm.py, we adopt the Python built-in library "ctypes," so that
+Python can directly access C structures and interface functions defined
+in svm.h.
+
+While advanced users can use structures/functions in svm.py, to
+avoid handling ctypes structures, in svmutil.py we provide some easy-to-use
+functions. The usage is similar to LIBSVM MATLAB interface.
+
+Data Structures
+===============
+
+Three data structures derived from svm.h are svm_node, svm_problem, and
+svm_parameter. They all contain fields with the same names in
+svm.h. Access these fields carefully because you directly use a C structure
+instead of a Python object. The following description introduces additional
+fields and methods.
+
+Before using the data structures, execute the following command to load the
+LIBSVM shared library:
+
+    >>> from svm import *
+
+- class svm_node:
+
+    Construct an svm_node.
+
+    >>> node = svm_node(idx, val)
+
+    idx: an integer indicates the feature index.
+
+    val: a float indicates the feature value.
+
+- Function: gen_svm_nodearray(xi [,feature_max=None [,issparse=False]])
+
+    Generate a feature vector from a Python list/tuple or a dictionary:
+
+    >>> xi, max_idx = gen_svm_nodearray({1:1, 3:1, 5:-2})
+
+    xi: the returned svm_nodearray (a ctypes structure)
+
+    max_idx: the maximal feature index of xi
+
+    issparse: if issparse == True, zero feature values are removed. The default
+              value is False for supporting the pre-computed kernel.
+
+    feature_max: if feature_max is assigned, features with indices larger than
+                 feature_max are removed.
+
+- class svm_problem:
+
+    Construct an svm_problem instance
+
+    >>> prob = svm_problem(y, x)
+
+    y: a Python list/tuple of l labels (type must be int/double).
+
+    x: a Python list/tuple of l data instances. Each element of x must be
+       an instance of list/tuple/dictionary type.
+
+    Note that if your x contains sparse data (i.e., dictionary), the internal
+    ctypes data format is still sparse.
+
+- class svm_parameter:
+
+    Construct an svm_parameter instance
+
+    >>> param = svm_parameter('training_options')
+
+    If 'training_options' is empty, LIBSVM default values are applied.
+
+    Set param to LIBSVM default values.
+
+    >>> param.set_to_default_values()
+
+    Parse a string of options.
+
+    >>> param.parse_options('training_options')
+
+    Show values of parameters.
+
+    >>> param.show()
+
+- class svm_model:
+
+    There are two ways to obtain an instance of svm_model:
+
+    >>> model = svm_train(y, x)
+    >>> model = svm_load_model('model_file_name')
+
+    Note that the returned structure of interface functions
+    libsvm.svm_train and libsvm.svm_load_model is a ctypes pointer of
+    svm_model, which is different from the svm_model object returned
+    by svm_train and svm_load_model in svmutil.py. We provide a
+    function toPyModel for the conversion:
+
+    >>> model_ptr = libsvm.svm_train(prob, param)
+    >>> model = toPyModel(model_ptr)
+
+    If you obtain a model in a way other than the above approaches,
+    handle it carefully to avoid memory leak or segmentation fault.
+
+    Some interface functions to access LIBSVM models are wrapped as
+    members of the class svm_model:
+
+    >>> svm_type = model.get_svm_type()
+    >>> nr_class = model.get_nr_class()
+    >>> svr_probability = model.get_svr_probability()
+    >>> class_labels = model.get_labels()
+    >>> is_prob_model = model.is_probability_model()
+
+Utility Functions
+=================
+
+To use utility functions, type
+
+    >>> from svmutil import *
+
+The above command loads
+    svm_train()        : train an SVM model
+    svm_predict()      : predict testing data
+    svm_read_problem() : read the data from a LIBSVM-format file.
+    svm_load_model()   : load a LIBSVM model.
+    svm_save_model()   : save model to a file.
+    evaluations()      : evaluate prediction results.
+
+- Function: svm_train
+
+    There are three ways to call svm_train()
+
+    >>> model = svm_train(y, x [, 'training_options'])
+    >>> model = svm_train(prob [, 'training_options'])
+    >>> model = svm_train(prob, param)
+
+    y: a list/tuple of l training labels (type must be int/double).
+
+    x: a list/tuple of l training instances. The feature vector of
+       each training instance is an instance of list/tuple or dictionary.
+
+    training_options: a string in the same form as that for LIBSVM command
+                      mode.
+
+    prob: an svm_problem instance generated by calling
+          svm_problem(y, x).
+
+    param: an svm_parameter instance generated by calling
+           svm_parameter('training_options')
+
+    model: the returned svm_model instance. See svm.h for details of this
+           structure. If '-v' is specified, cross validation is
+           conducted and the returned model is just a scalar: cross-validation
+           accuracy for classification and mean-squared error for regression.
+
+    To train the same data many times with different
+    parameters, the second and the third ways should be faster..
+
+    Examples:
+
+    >>> y, x = svm_read_problem('../heart_scale')
+    >>> prob = svm_problem(y, x)
+    >>> param = svm_parameter('-s 3 -c 5 -h 0')
+    >>> m = svm_train(y, x, '-c 5')
+    >>> m = svm_train(prob, '-t 2 -c 5')
+    >>> m = svm_train(prob, param)
+    >>> CV_ACC = svm_train(y, x, '-v 3')
+
+- Function: svm_predict
+
+    To predict testing data with a model, use
+
+    >>> p_labs, p_acc, p_vals = svm_predict(y, x, model [,'predicting_options'])
+
+    y: a list/tuple of l true labels (type must be int/double). It is used
+       for calculating the accuracy. Use [0]*len(x) if true labels are
+       unavailable.
+
+    x: a list/tuple of l predicting instances. The feature vector of
+       each predicting instance is an instance of list/tuple or dictionary.
+
+    predicting_options: a string of predicting options in the same format as
+                        that of LIBSVM.
+
+    model: an svm_model instance.
+
+    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(k-1)/2 binary-class
+            SVMs. For probabilities, each element contains k values indicating
+            the probability that the testing instance is in each class.
+            Note that the order of classes is the same as the 'model.label'
+            field in the model structure.
+
+    Example:
+
+    >>> m = svm_train(y, x, '-c 5')
+    >>> p_labels, p_acc, p_vals = svm_predict(y, x, m)
+
+- Functions:  svm_read_problem/svm_load_model/svm_save_model
+
+    See the usage by examples:
+
+    >>> y, x = svm_read_problem('data.txt')
+    >>> m = svm_load_model('model_file')
+    >>> svm_save_model('model_file', m)
+
+- Function: evaluations
+
+    Calculate some evaluations using the true values (ty) and predicted
+    values (pv):
+
+    >>> (ACC, MSE, SCC) = evaluations(ty, pv)
+
+    ty: a list of true values.
+
+    pv: a list of predict values.
+
+    ACC: accuracy.
+
+    MSE: mean squared error.
+
+    SCC: squared correlation coefficient.
+
+
+Additional Information
+======================
+
+This interface was written by Hsiang-Fu Yu from Department of Computer
+Science, National Taiwan University. If you find this tool useful, please
+cite LIBSVM as follows
+
+Chih-Chung Chang and Chih-Jen Lin, LIBSVM : a library for
+support vector machines, 2001. Software available at
+http://www.csie.ntu.edu.tw/~cjlin/libsvm
+
+For any question, please contact Chih-Jen Lin <cjlin@csie.ntu.edu.tw>,
+or check the FAQ page:
+
+http://www.csie.ntu.edu.tw/~cjlin/libsvm/faq.html