def test_gb_ranking(n_samples=1000): """ Testing RankingLossFunction """ distance = 0.6 testX, testY = generate_sample(n_samples, 10, distance) trainX, trainY = generate_sample(n_samples, 10, distance) rank_variable = 'column1' trainX[rank_variable] = numpy.random.randint(0, 3, size=len(trainX)) testX[rank_variable] = numpy.random.randint(0, 3, size=len(testX)) rank_loss1 = losses.RankBoostLossFunction(request_column=rank_variable, update_iterations=1) rank_loss2 = losses.RankBoostLossFunction(request_column=rank_variable, update_iterations=2) rank_loss3 = losses.RankBoostLossFunction(request_column=rank_variable, update_iterations=10) for loss in [rank_loss1, rank_loss2, rank_loss3]: clf = UGradientBoostingRegressor(loss=loss, min_samples_split=20, max_depth=5, learning_rate=0.2, subsample=0.7, n_estimators=25, train_features=None) \ .fit(trainX[:n_samples], trainY[:n_samples]) result = roc_auc_score(testY, clf.predict(testX)) assert result >= 0.8, "The quality is too poor: {} with loss: {}".format( result, loss)
def test_gb_regression(n_samples=1000): X, _ = generate_sample(n_samples, 10, distance=0.6) y = numpy.tanh(X.sum(axis=1)) clf = UGradientBoostingRegressor(loss=MSELossFunction()) clf.fit(X, y) y_pred = clf.predict(X) zeromse = 0.5 * mean_squared_error(y, y * 0.) assert mean_squared_error(y, y_pred) < zeromse, 'something wrong with regression quality'
def test_gb_regression(n_samples=1000): X, _ = generate_sample(n_samples, 10, distance=0.6) y = numpy.tanh(X.sum(axis=1)) clf = UGradientBoostingRegressor(loss=MSELossFunction()) clf.fit(X, y) y_pred = clf.predict(X) zeromse = 0.5 * mean_squared_error(y, y * 0.) assert mean_squared_error(y, y_pred) < zeromse, 'something wrong with regression quality'
def test_constant_fitting(n_samples=1000, n_features=5): """ Testing if initial constant fitted properly """ X, y = generate_sample(n_samples=n_samples, n_features=n_features) y = y.astype(numpy.float) + 1000. for loss in [MSELossFunction(), losses.MAELossFunction()]: gb = UGradientBoostingRegressor(loss=loss, n_estimators=10) gb.fit(X, y) p = gb.predict(X) assert mean_squared_error(p, y) < 0.5
def test_constant_fitting(n_samples=1000, n_features=5): """ Testing if initial constant fitted properly """ X, y = generate_sample(n_samples=n_samples, n_features=n_features) y = y.astype(numpy.float) + 1000. for loss in [MSELossFunction(), losses.MAELossFunction()]: gb = UGradientBoostingRegressor(loss=loss, n_estimators=10) gb.fit(X, y) p = gb.predict(X) assert mean_squared_error(p, y) < 0.5
def test_gb_ranking(n_samples=1000): distance = 0.6 testX, testY = generate_sample(n_samples, 10, distance) trainX, trainY = generate_sample(n_samples, 10, distance) rank_variable = 'column1' trainX[rank_variable] = numpy.random.randint(0, 3, size=len(trainX)) testX[rank_variable] = numpy.random.randint(0, 3, size=len(testX)) rank_loss1 = RankBoostLossFunction(request_column=rank_variable, update_iterations=1) rank_loss2 = RankBoostLossFunction(request_column=rank_variable, update_iterations=2) rank_loss3 = RankBoostLossFunction(request_column=rank_variable, update_iterations=10) for loss in [rank_loss1, rank_loss2, rank_loss3]: clf = UGradientBoostingRegressor(loss=loss, min_samples_split=20, max_depth=5, learning_rate=0.2, subsample=0.7, n_estimators=25, train_features=None) \ .fit(trainX[:n_samples], trainY[:n_samples]) result = roc_auc_score(testY, clf.predict(testX)) assert result >= 0.8, "The quality is too poor: {} with loss: {}".format(result, loss)