pytest updates

pca/examples.py

@@ -10,7 +10,7 @@
 # Fit transform
 results = model.fit_transform(df)
 
-model.biplot(s=15, fontsize=0)
+model.biplot(s=20, fontsize=0, labels=None)
 
 # %% issue 54
 # https://github.com/erdogant/pca/issues/54
@@ -216,7 +216,7 @@
 # All available markers
 markers = np.array(['.', 'o', 'v', '^', '<', '>', '8', 's', 'p', '*', 'h', 'H', 'D', 'd', 'P', 'X'])
 # Create colors
-cmap = plt.cm.get_cmap('tab20c', len(markers))
+cmap = plt.get_cmap('tab20c', len(markers))
 # Generate random integers
 random_integers = np.random.randint(0, len(markers), size=X.shape[0])
 # Draw markers

pca/tests/test_pca.py

@@ -42,7 +42,7 @@ def test_specifying(self):
         combinations=list(combinations)
 
         # Init
-        model = pca(verbose=0)
+        model = pca(verbose=None)
         # Fit
         model.fit_transform(X)
         # Make plot with blue arrows and text
@@ -215,7 +215,7 @@ def test_correct_ordering_features_in_biplot(self):
     def test_for_new_outliers_after_transformation(self):
         # Generate dataset
         np.random.seed(42)
-        n_total = 10000
+        n_total = 1000
         train_ratio = 0.8
         n_features = 10
         my_array = np.random.randint(low=1, high=10, size=(n_total, n_features))
@@ -231,7 +231,7 @@ def test_for_new_outliers_after_transformation(self):
         # Inference: mapping of data into space.
         PC_test = model.transform(X=X_test[features])
         # Compute new outliers
-        scores, _ = model.compute_outliers(PC=PC_test, n_std=3, verbose=3) 
+        scores, _ = model.compute_outliers(PC=PC_test, n_std=3, verbose=3)
 
         assert model.results.get('outliers_params', None) is not None
         assert scores.shape[0]==X_test.shape[0]