X_train, X_test, y_train, y_test, ind_train, ind_test = load_data(full=False) clf = GradientBoostingClassifier(n_estimators=500, max_depth=6, learning_rate=0.1, max_features=256, min_samples_split=15, verbose=3, random_state=13) print('_' * 80) print('training') print print clf clf.fit(X_train, y_train) if y_test is not None: from sklearn.metrics import auc_score print clf y_scores = clf.decision_function(X_test).ravel() print "AUC: %.6f" % auc_score(y_test, y_scores) if generate_report: from error_analysis import error_report data = np.load("data/train.npz") X = data['X_train'] X_test_raw = X[ind_test] error_report(clf, X_test_raw, y_test, y_scores=y_scores, ind=ind_test) np.savetxt("gbrt3.txt", clf.decision_function(X_test))
from transform import SpectrogramTransformer from ranking import RankSVM from ranking import SVMPerf from ranking import RGradientBoostingClassifier import IPython data = np.load("data/train_small.npz") X = data["X_train"] y = data["y_train"] clf = LinearSVC(C=1e-5, tol=0.001, loss='l1', dual=True) clf = Pipeline( steps=[('spectrogram', SpectrogramTransformer( NFFT=256, noverlap=0.5, dtype=np.float64)), ('svm', clf)]) ind = np.arange(X.shape[0]) X_train, X_test, y_train, y_test, ind_train, ind_test = train_test_split( X, y, ind, test_size=0.5, random_state=42) clf.fit(X_train, y_train) from error_analysis import error_report error_report(clf, X_test, y=y_test, ind=ind_test, spec_func=None)
from sklearn.pipeline import Pipeline from transform import SpectrogramTransformer from ranking import RankSVM from ranking import SVMPerf from ranking import RGradientBoostingClassifier import IPython data = np.load("data/train_small.npz") X = data["X_train"] y = data["y_train"] clf = LinearSVC(C=1e-5, tol=0.001, loss="l1", dual=True) clf = Pipeline( steps=[("spectrogram", SpectrogramTransformer(NFFT=256, noverlap=0.5, dtype=np.float64)), ("svm", clf)] ) ind = np.arange(X.shape[0]) X_train, X_test, y_train, y_test, ind_train, ind_test = train_test_split(X, y, ind, test_size=0.5, random_state=42) clf.fit(X_train, y_train) from error_analysis import error_report error_report(clf, X_test, y=y_test, ind=ind_test, spec_func=None)