def test_fetch_drug_protein(): dataset = fetch_drug_interaction(tmpdir) assert_equal(dataset.data.shape, (1862, 660)) assert_equal(dataset.target.shape, (1862, 1554)) assert_equal(len(dataset.feature_names), 660) assert_equal(len(dataset.target_names), 1554) dataset = fetch_protein_interaction(tmpdir) assert_equal(dataset.data.shape, (1554, 876)) assert_equal(dataset.target.shape, (1554, 1862)) assert_equal(len(dataset.feature_names), 876)
import numpy as np import matplotlib.pyplot as plt from sklearn.base import clone from sklearn.cross_validation import train_test_split from sklearn.random_projection import SparseRandomProjection from sklearn.metrics import label_ranking_average_precision_score as lrap_score from random_output_trees.datasets import fetch_drug_interaction from random_output_trees.ensemble import RandomForestClassifier random_state = np.random.RandomState(0) # Let's load a multilabel dataset dataset = fetch_drug_interaction() X = dataset.data y = dataset.target # y.shape = (1862, 1554) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=0) n_outputs = y.shape[1] def benchmark(base_estimator, random_state=None, n_iter=3): scores = [] times = [] for iter_ in range(n_iter): estimator = clone(base_estimator) estimator.set_params(random_state=random_state) time_start = time()
import numpy as np import matplotlib.pyplot as plt from sklearn.base import clone from sklearn.cross_validation import train_test_split from sklearn.random_projection import SparseRandomProjection from sklearn.metrics import label_ranking_average_precision_score as lrap_score from random_output_trees.datasets import fetch_drug_interaction from random_output_trees.ensemble import RandomForestClassifier random_state = np.random.RandomState(0) # Let's load a multilabel dataset dataset = fetch_drug_interaction() X = dataset.data y = dataset.target # y.shape = (1862, 1554) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=0) n_outputs = y.shape[1] def benchmark(base_estimator, random_state=None, n_iter=3): scores = [] times = [] for iter_ in range(n_iter): estimator = clone(base_estimator) estimator.set_params(random_state=random_state)