MAINT: updates for Python 3.9 (#233)

Author: gregcaporaso

q2_sample_classifier/classify.py

@@ -83,7 +83,7 @@ def metatable(ctx,
             raise ValueError('Missing samples in metadata: %r' %
                              table_ids.difference(metadata_ids))
         else:
-            metadata = metadata.loc[sample_ids]
+            metadata = metadata.loc[list(sample_ids)]
         if len(sample_ids) < len(table_ids):
             tab = tab.filter(
                 ids_to_keep=sample_ids, axis='sample', inplace=False)

q2_sample_classifier/tests/test_actions.py

@@ -59,7 +59,7 @@ def test_action_split_table(self):
         self.assertEqual(y_train.name, 'bugs')
 
         # test if complete target column is covered
-        y_all = y_train.append(y_test).sort_index()
+        y_all = pd.concat([y_train, y_test]).sort_index()
         y_all.index.name = 'SampleID'
         pdt.assert_series_equal(y_all, self.md._series)
 

q2_sample_classifier/tests/test_estimators.py

@@ -117,7 +117,7 @@ def _load_cmc(md_fp, column):
             index_col=0, names=['feature', 'importance'])
         self.exp_pred = pd.read_csv(
             self.get_data_path('predictions.tsv'), sep='\t', header=0,
-            index_col=0, squeeze=True)
+            index_col=0).squeeze('columns')
         index = pd.Index(['A', 'B', 'C', 'D'], name='id')
         self.table_percnorm = qiime2.Artifact.import_data(
             FeatureTable[PercentileNormalized], pd.DataFrame(
@@ -135,7 +135,7 @@ def test_extract_features(self):
         dv = DictVectorizer()
         dv.fit(dicts)
         features = table.ids('observation')
-        self.assertEqual(set(dv.get_feature_names()), set(features))
+        self.assertEqual(set(dv.get_feature_names_out()), set(features))
         self.assertEqual(len(dicts), len(table.ids()))
         for dict_row, (table_row, _, _) in zip(dicts, table.iter()):
             for feature, count in zip(features, table_row):
@@ -398,7 +398,7 @@ def test_train_adaboost_decision_tree(self):
             parameter_tuning=True, classification=True,
             missing_samples='ignore', base_estimator="DecisionTree")
         self.assertEqual(type(abe.named_steps.est), AdaBoostClassifier)
-        self.assertEqual(type(abe.named_steps.est.base_estimator),
+        self.assertEqual(type(abe.named_steps.est.estimator),
                          DecisionTreeClassifier)
 
     def test_train_adaboost_extra_trees(self):
@@ -408,7 +408,7 @@ def test_train_adaboost_extra_trees(self):
             parameter_tuning=True, classification=True,
             missing_samples='ignore', base_estimator="ExtraTrees")
         self.assertEqual(type(abe.named_steps.est), AdaBoostClassifier)
-        self.assertEqual(type(abe.named_steps.est.base_estimator),
+        self.assertEqual(type(abe.named_steps.est.estimator),
                          ExtraTreeClassifier)
 
     # test some invalid inputs/edge cases
@@ -504,7 +504,7 @@ def test_predict_classifications(self):
             ls_pred_classes = prob.columns.tolist()
             ls_correct_range = [col for col in ls_pred_classes if
                                 prob[col].between(
-                                    0, 1, inclusive=True).all()]
+                                    0, 1, inclusive="both").all()]
             self.assertEqual(len(ls_correct_range), prob.shape[1],
                              msg='Predicted probabilities of class {}'
                              'are not in range [0,1]'.format(

q2_sample_classifier/tests/test_types_formats_transformers.py

@@ -85,7 +85,7 @@ def test_pd_series_to_boolean_format(self):
                         name='outlier', index=exp_index)
         obs = transformer(exp)
         obs = pd.read_csv(str(obs), sep='\t', header=0, index_col=0,
-                          squeeze=True)
+                          ).squeeze('columns')
         self.assertEqual(sorted(exp), sorted(obs))
 
     def test_boolean_format_to_pd_series(self):
@@ -152,7 +152,7 @@ def test_pd_series_to_Predictions_format(self):
                         name='prediction', index=['a', 'b', 'c', 'd'])
         obs = transformer(exp)
         obs = pd.read_csv(str(obs), sep='\t', header=0, index_col=0,
-                          squeeze=True)
+                          ).squeeze('columns')
         pdt.assert_series_equal(obs, exp)
 
     def test_pd_series_to_Predictions_format_allow_nans(self):
@@ -161,7 +161,7 @@ def test_pd_series_to_Predictions_format_allow_nans(self):
                         name='prediction', index=['a', 'b', 'c', 'd'])
         obs = transformer(exp)
         obs = pd.read_csv(str(obs), sep='\t', header=0, index_col=0,
-                          squeeze=True)
+                          ).squeeze('columns')
         pdt.assert_series_equal(obs, exp)
 
     def test_Predictions_format_to_pd_series(self):

q2_sample_classifier/utilities.py

@@ -239,7 +239,7 @@ def _rfecv_feature_selection(feature_data, targets, estimator,
     # Describe top features
     n_opt = rfecv.named_steps.est.n_features_
     importance = _extract_important_features(
-        rfecv.named_steps.dv.get_feature_names(),
+        rfecv.named_steps.dv.get_feature_names_out(),
         rfecv.named_steps.est.ranking_)
     importance = sort_importances(importance, ascending=True)[:n_opt]
 
@@ -249,16 +249,17 @@ def _rfecv_feature_selection(feature_data, targets, estimator,
 
 
 def _extract_rfe_scores(rfecv):
+    grid_scores_ = rfecv.cv_results_['mean_test_score']
     n_features = len(rfecv.ranking_)
     # If using fractional step, step = integer of fraction * n_features
     if rfecv.step < 1:
         rfecv.step = int(rfecv.step * n_features)
-    # Need to manually calculate x-axis, as rfecv.grid_scores_ are a 1-d array
+    # Need to manually calculate x-axis, grid_scores_ is a 1-d array
     x = [n_features - (n * rfecv.step)
-         for n in range(len(rfecv.grid_scores_)-1, -1, -1)]
+         for n in range(len(grid_scores_)-1, -1, -1)]
     if x[0] < 1:
         x[0] = 1
-    return pd.Series(rfecv.grid_scores_, index=x, name='Accuracy')
+    return pd.Series(grid_scores_, index=x, name='Accuracy')
 
 
 def nested_cross_validation(table, metadata, cv, random_state, n_jobs,
@@ -411,12 +412,12 @@ def _calculate_feature_importances(estimator):
     # feature_importances_ or coef_ to report feature importance/weights
     try:
         importances = _extract_important_features(
-            estimator.named_steps.dv.get_feature_names(),
+            estimator.named_steps.dv.get_feature_names_out(),
             estimator.named_steps.est.feature_importances_)
     # is there a better way to determine whether estimator has coef_ ?
     except AttributeError:
         importances = _extract_important_features(
-            estimator.named_steps.dv.get_feature_names(),
+            estimator.named_steps.dv.get_feature_names_out(),
             estimator.named_steps.est.coef_)
     return importances
 
@@ -718,7 +719,7 @@ def _mean_feature_importance(importances):
 def _null_feature_importance(table):
     feature_extractor = DictVectorizer()
     feature_extractor.fit(table)
-    imp = pd.DataFrame(index=feature_extractor.get_feature_names())
+    imp = pd.DataFrame(index=feature_extractor.get_feature_names_out())
     imp.index.name = "feature"
     imp["importance"] = 1
     return imp
@@ -827,8 +828,9 @@ def _train_adaboost_base_estimator(table, metadata, column, base_estimator,
 
     return Pipeline(
         [('dv', estimator.named_steps.dv),
-         ('est', adaboost_estimator(estimator.named_steps.est,
-                                    n_estimators, random_state=random_state))])
+         ('est', adaboost_estimator(estimator=estimator.named_steps.est,
+                                    n_estimators=n_estimators,
+                                    random_state=random_state))])
 
 
 def _disable_feature_selection(estimator, optimize_feature_selection):

q2_sample_classifier/visuals.py

@@ -167,9 +167,9 @@ def _plot_confusion_matrix(y_test, y_pred, classes, normalize, palette,
     predictions.loc["Overall Accuracy"] = ""
     predictions.loc["Baseline Accuracy"] = ""
     predictions.loc["Accuracy Ratio"] = ""
-    predictions.loc["Overall Accuracy"]["Overall Accuracy"] = accuracy
-    predictions.loc["Baseline Accuracy"]["Overall Accuracy"] = basline_accuracy
-    predictions.loc["Accuracy Ratio"]["Overall Accuracy"] = accuracy_ratio
+    predictions.loc["Overall Accuracy", "Overall Accuracy"] = accuracy
+    predictions.loc["Baseline Accuracy", "Overall Accuracy"] = basline_accuracy
+    predictions.loc["Accuracy Ratio", "Overall Accuracy"] = accuracy_ratio
 
     return predictions, confusion