Merge pull request #44 from TeamHG-Memex/set-random-state-more

Set random state more
TeamHG-Memex · Nov 2, 2016 · f9ae971 · f9ae971
2 parents 223279e + ea2fd3c
commit f9ae971
Show file tree

Hide file tree

Showing 4 changed files with 19 additions and 19 deletions.
diff --git a/tests/test_lime_utils.py b/tests/test_lime_utils.py
@@ -33,7 +33,7 @@ def test_fit_proba():
     print(y_pred, mae)
 
     # fit on probabilities
-    clf2 = LogisticRegression(C=10)
+    clf2 = LogisticRegression(C=10, random_state=42)
     fit_proba(clf2, X, y_proba, expand_factor=200)
     y_pred2 = clf2.predict_proba(X)[:,1]
     mae2 = mean_absolute_error(y_proba[:,1], y_pred2)
@@ -43,7 +43,7 @@ def test_fit_proba():
 
     # let's get 3th example really right
     sample_weight = np.array([0.1, 0.1, 0.1, 10.0, 0.1])
-    clf3 = LogisticRegression(C=10)
+    clf3 = LogisticRegression(C=10, random_state=42)
     fit_proba(clf3, X, y_proba, expand_factor=200, sample_weight=sample_weight)
     y_pred3 = clf3.predict_proba(X)[:,1]
     print(y_pred3)

diff --git a/tests/test_sklearn_explain_prediction.py b/tests/test_sklearn_explain_prediction.py
@@ -132,7 +132,7 @@ def test_explain_linear(newsgroups_train, clf):
     [Lars()],
     [Lasso(random_state=42)],
     [LinearRegression()],
-    [LinearSVR()],
+    [LinearSVR(random_state=42)],
     [Ridge(random_state=42)],
     [RidgeCV()],
     [SGDRegressor(random_state=42)],

diff --git a/tests/test_sklearn_explain_weights.py b/tests/test_sklearn_explain_weights.py
@@ -56,7 +56,7 @@ def check_newsgroups_explanation_linear(clf, vec, target_names):
     assert 'atheists' in pos
 
     pos, neg = _top('talk.religion.misc')
-    assert 'jesus' in pos
+    assert 'jesus' in pos or 'christians' in pos
 
     for expl in [expl_text, expl_html]:
         assert 'space' in expl
@@ -68,15 +68,15 @@ def check_newsgroups_explanation_linear(clf, vec, target_names):
 
 
 @pytest.mark.parametrize(['clf'], [
-    [LogisticRegression()],
-    [LogisticRegression(multi_class='multinomial', solver='lbfgs')],
-    [LogisticRegression(fit_intercept=False)],
-    [LogisticRegressionCV()],
+    [LogisticRegression(random_state=42)],
+    [LogisticRegression(random_state=42, multi_class='multinomial', solver='lbfgs')],
+    [LogisticRegression(random_state=42, fit_intercept=False)],
+    [LogisticRegressionCV(random_state=42)],
     [SGDClassifier(random_state=42)],
-    [SGDClassifier(loss='log', random_state=42)],
-    [PassiveAggressiveClassifier()],
-    [Perceptron()],
-    [LinearSVC()],
+    [SGDClassifier(random_state=42, loss='log')],
+    [PassiveAggressiveClassifier(random_state=42)],
+    [Perceptron(random_state=42)],
+    [LinearSVC(random_state=42)],
 ])
 def test_explain_linear(newsgroups_train, clf):
     docs, y, target_names = newsgroups_train
@@ -89,10 +89,10 @@ def test_explain_linear(newsgroups_train, clf):
 
 
 @pytest.mark.parametrize(['clf'], [
-    [LogisticRegression()],
-    [LogisticRegression(fit_intercept=False)],
+    [LogisticRegression(random_state=42)],
+    [LogisticRegression(random_state=42, fit_intercept=False)],
     [SGDClassifier(random_state=42)],
-    [LinearSVC()],
+    [LinearSVC(random_state=42)],
 ])
 def test_explain_linear_hashed(newsgroups_train, clf):
     docs, y, target_names = newsgroups_train
@@ -160,7 +160,7 @@ def top_pos_neg(classes, key, class_name):
 def test_explain_linear_tuple_top(newsgroups_train):
     docs, y, target_names = newsgroups_train
     vec = TfidfVectorizer()
-    clf = LogisticRegression()
+    clf = LogisticRegression(random_state=42)
 
     X = vec.fit_transform(docs)
     clf.fit(X, y)
@@ -213,7 +213,7 @@ def test_explain_random_forest(newsgroups_train, clf):
 
 
 def test_explain_empty(newsgroups_train):
-    clf = LogisticRegression(C=0.01, penalty='l1')
+    clf = LogisticRegression(C=0.01, penalty='l1', random_state=42)
     docs, y, target_names = newsgroups_train
     vec = TfidfVectorizer()
 
@@ -242,7 +242,7 @@ def test_unsupported():
     [RidgeCV()],
     [SGDRegressor(random_state=42)],
     [LinearRegression()],
-    [LinearSVR()],
+    [LinearSVR(random_state=42)],
 ])
 def test_explain_linear_regression(boston_train, clf):
     X, y, feature_names = boston_train

diff --git a/tests/test_sklearn_vectorizers.py b/tests/test_sklearn_vectorizers.py
@@ -87,7 +87,7 @@ def _without_weighted_spans(res):
 
 
 def test_explain_linear_dense():
-    clf = LogisticRegression()
+    clf = LogisticRegression(random_state=42)
     data = [{'day': 'mon', 'moon': 'full'},
             {'day': 'tue', 'moon': 'rising'},
             {'day': 'tue', 'moon': 'rising'},