def predict(y, x, m, options=""): """ predict(y, x, m [, options]) -> (p_labels, p_acc, p_vals) y: a list/tuple/ndarray of l true labels (type must be int/double). It is used for calculating the accuracy. Use [] if true labels are unavailable. x: 1. a list/tuple of l training instances. Feature vector of each training instance is a list/tuple or dictionary. 2. an l * n numpy ndarray or scipy spmatrix (n: number of features). 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) if scipy and isinstance(x, scipy.ndarray): x = scipy.ascontiguousarray(x) # enforce row-major elif sparse and isinstance(x, sparse.spmatrix): x = x.tocsr() elif not isinstance(x, (list, tuple)): raise TypeError("type of x: {0} is not supported!".format(type(x))) if (not isinstance(y, (list, tuple))) and (not (scipy and isinstance(y, scipy.ndarray))): raise TypeError("type of y: {0} is not supported!".format(type(y))) 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 scipy and isinstance(x, sparse.spmatrix): nr_instance = x.shape[0] else: nr_instance = len(x) 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 i in range(nr_instance): if scipy and isinstance(x, sparse.spmatrix): indslice = slice(x.indptr[i], x.indptr[i+1]) xi, idx = gen_feature_nodearray((x.indices[indslice], x.data[indslice]), feature_max=nr_feature) else: xi, idx = gen_feature_nodearray(x[i], 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 i in range(nr_instance): if scipy and isinstance(x, sparse.spmatrix): indslice = slice(x.indptr[i], x.indptr[i+1]) xi, idx = gen_feature_nodearray((x.indices[indslice], x.data[indslice]), feature_max=nr_feature) else: xi, idx = gen_feature_nodearray(x[i], 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] * nr_instance ACC, MSE, SCC = evaluations(y, pred_labels) 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(round(nr_instance*ACC/100)), nr_instance)) return pred_labels, (ACC, MSE, SCC), pred_values
def predict(y, x, m, options=""): """ predict(y, x, m [, options]) -> (p_labels, p_acc, p_vals) y: a list/tuple/ndarray of l true labels (type must be int/double). It is used for calculating the accuracy. Use [] if true labels are unavailable. x: 1. a list/tuple of l training instances. Feature vector of each training instance is a list/tuple or dictionary. 2. an l * n numpy ndarray or scipy spmatrix (n: number of features). 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) if scipy and isinstance(x, scipy.ndarray): x = scipy.ascontiguousarray(x) # enforce row-major elif sparse and isinstance(x, sparse.spmatrix): x = x.tocsr() elif not isinstance(x, (list, tuple)): raise TypeError("type of x: {0} is not supported!".format(type(x))) if (not isinstance( y, (list, tuple))) and (not (scipy and isinstance(y, scipy.ndarray))): raise TypeError("type of y: {0} is not supported!".format(type(y))) 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 scipy and isinstance(x, sparse.spmatrix): nr_instance = x.shape[0] else: nr_instance = len(x) 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 i in range(nr_instance): if scipy and isinstance(x, sparse.spmatrix): indslice = slice(x.indptr[i], x.indptr[i + 1]) xi, idx = gen_feature_nodearray( (x.indices[indslice], x.data[indslice]), feature_max=nr_feature) else: xi, idx = gen_feature_nodearray(x[i], 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 i in range(nr_instance): if scipy and isinstance(x, sparse.spmatrix): indslice = slice(x.indptr[i], x.indptr[i + 1]) xi, idx = gen_feature_nodearray( (x.indices[indslice], x.data[indslice]), feature_max=nr_feature) else: xi, idx = gen_feature_nodearray(x[i], 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] * nr_instance ACC, MSE, SCC = evaluations(y, pred_labels) 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(round(nr_instance * ACC / 100)), nr_instance)) return pred_labels, (ACC, MSE, SCC), pred_values