From a294149f9518583e3c522ba38ccff701d6980671 Mon Sep 17 00:00:00 2001
From: Hanmin Qin <qinhanmin2005@sina.com>
Date: Tue, 4 Jul 2017 20:41:24 +0800
Subject: [PATCH] TST Change dataset for
test_classifier_chain_vs_independent_models (#9255)
---
sklearn/tests/test_multioutput.py | 20 ++++++++------------
1 file changed, 8 insertions(+), 12 deletions(-)
diff --git a/sklearn/tests/test_multioutput.py b/sklearn/tests/test_multioutput.py
index 00085a32af..0c58d04c27 100644
--- a/sklearn/tests/test_multioutput.py
+++ b/sklearn/tests/test_multioutput.py
@@ -356,7 +356,8 @@ def generate_multilabel_dataset_with_correlations():
X, y = make_classification(n_samples=1000,
n_features=100,
n_classes=16,
- n_informative=10)
+ n_informative=10,
+ random_state=0)
Y_multi = np.array([[int(yyy) for yyy in format(yy, '#06b')[2:]]
for yy in y])
@@ -470,22 +471,17 @@ def test_classifier_chain_vs_independent_models():
# Verify that an ensemble of classifier chains (each of length
# N) can achieve a higher Jaccard similarity score than N independent
# models
- yeast = fetch_mldata('yeast')
- X = yeast['data']
- Y = yeast['target'].transpose().toarray()
- X_train = X[:2000, :]
- X_test = X[2000:, :]
- Y_train = Y[:2000, :]
- Y_test = Y[2000:, :]
+ X, Y = generate_multilabel_dataset_with_correlations()
+ X_train = X[:600, :]
+ X_test = X[600:, :]
+ Y_train = Y[:600, :]
+ Y_test = Y[600:, :]
ovr = OneVsRestClassifier(LogisticRegression())
ovr.fit(X_train, Y_train)
Y_pred_ovr = ovr.predict(X_test)
- chain = ClassifierChain(LogisticRegression(),
- order=np.array([0, 2, 4, 6, 8, 10,
- 12, 1, 3, 5, 7, 9,
- 11, 13]))
+ chain = ClassifierChain(LogisticRegression())
chain.fit(X_train, Y_train)
Y_pred_chain = chain.predict(X_test)
--
GitLab