flake8

docs/source/conf.py

@@ -220,11 +220,11 @@
 # A dictionary with options for the search language support, empty by default.
 # 'ja' uses this config value.
 # 'zh' user can custom change `jieba` dictionary path.
-#html_search_options = {'type': 'default'}
+# html_search_options = {'type': 'default'}
 
 # The name of a javascript file (relative to the configuration directory) that
 # implements a search results scorer. If empty, the default will be used.
-#html_search_scorer = 'scorer.js'
+# html_search_scorer = 'scorer.js'
 
 # Output file base name for HTML help builder.
 htmlhelp_basename = 'sklearn-evaluationdoc'

docs/source/nbs/train.py

@@ -43,7 +43,10 @@
 list(d['feature_names'])
 # -
 
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
+X_train, X_test, y_train, y_test = train_test_split(X,
+                                                    y,
+                                                    test_size=0.33,
+                                                    random_state=42)
 
 model = class_(**params)
 

examples/roc.py

@@ -19,4 +19,4 @@
 y_true = y_test
 
 plot.roc(y_true, y_score)
-plt.show()
+plt.show()

examples/simple.py

@@ -6,18 +6,24 @@
 import matplotlib.pyplot as plt
 
 from matplotlib import style
+
 style.use('seaborn-dark')
 
 # Import some data to play with
-data = datasets.make_classification(1000, 10, n_informative=5, class_sep=0.7, n_classes=8)
+data = datasets.make_classification(1000,
+                                    10,
+                                    n_informative=5,
+                                    class_sep=0.7,
+                                    n_classes=8)
 X = data[0]
 y = data[1]
 
 # shuffle and split training and test sets
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.5,
+X_train, X_test, y_train, y_test = train_test_split(X,
+                                                    y,
+                                                    test_size=.5,
                                                     random_state=0)
 
-
 est = RandomForestClassifier()
 est.fit(X_train, y_train)
 y_pred = est.predict(X_test)

setup.cfg

@@ -2,4 +2,4 @@
 description-file = README.md
 
 [flake8]
-exclude = .nox, .git, build
+exclude = .nox, .git, build, .ipynb_checkpoints, docs/source/conf.py

src/sklearn_evaluation/compute.py

@@ -42,7 +42,7 @@ def feature_importances(data, top_n=None, feature_names=None):
         sub_imp = np.array([e.feature_importances_ for e in data.estimators_])
         # calculate std
         std = np.std(sub_imp, axis=0)
-    except AttributeError:
+    except Exception:
         std = None
 
     # get the number of features

src/sklearn_evaluation/nb/NotebookCollection.py

@@ -25,7 +25,7 @@ class NotebookCollection(Mapping):
     """Compare output from a collection of notebooks
 
     To access output, notebooks must tag the cells (one tag per cell). For
-    instructions on tagging cells, `see this <https://jupyterbook.org/advanced/advanced.html#how-should-i-add-cell-tags-and-metadata-to-my-notebooks>`_.
+    instructions on tagging cells, `see this <https://jupyterbook.org/advanced/advanced.html#how-should-i-add-cell-tags-and-metadata-to-my-notebooks>`_. # noqa
 
     :doc:`Click here <../user_guide/NotebookCollection>` to see the user guide.
 

src/sklearn_evaluation/nb/NotebookIntrospector.py

@@ -77,7 +77,7 @@ class NotebookIntrospector(Mapping):
     """Retrieve output from a notebook file with tagged cells.
 
     For instructions on tagging cells,
-    `see this <https://jupyterbook.org/advanced/advanced.html#how-should-i-add-cell-tags-and-metadata-to-my-notebooks>`_.
+    `see this <https://jupyterbook.org/advanced/advanced.html#how-should-i-add-cell-tags-and-metadata-to-my-notebooks>`_. # noqa
 
     Notes
     -----

src/sklearn_evaluation/plot/classification.py

@@ -11,8 +11,12 @@
 from ..util import is_column_vector, is_row_vector, default_heatmap
 
 
-def confusion_matrix(y_true, y_pred, target_names=None, normalize=False,
-                     cmap=None, ax=None):
+def confusion_matrix(y_true,
+                     y_pred,
+                     target_names=None,
+                     normalize=False,
+                     cmap=None,
+                     ax=None):
     """
     Plot confustion matrix.
 
@@ -57,10 +61,10 @@ def confusion_matrix(y_true, y_pred, target_names=None, normalize=False,
     expected_len = len(values)
 
     if target_names and (expected_len != len(target_names)):
-        raise ValueError(('Data cointains {} different values, but target'
-                         ' names contains {} values.'.format(expected_len,
-                                                             len(target_names)
-                                                             )))
+        raise ValueError(
+            ('Data cointains {} different values, but target'
+             ' names contains {} values.'.format(expected_len,
+                                                 len(target_names))))
 
     # if the user didn't pass target_names, create generic ones
     if not target_names:
@@ -86,9 +90,12 @@ def confusion_matrix(y_true, y_pred, target_names=None, normalize=False,
     for (y, x), v in np.ndenumerate(cm):
         try:
             label = '{:.2}'.format(v)
-        except:
+        except Exception:
             label = v
-        ax.text(x, y, label, horizontalalignment='center',
+        ax.text(x,
+                y,
+                label,
+                horizontalalignment='center',
                 verticalalignment='center')
 
     if cmap is None:
@@ -117,8 +124,11 @@ def confusion_matrix(y_true, y_pred, target_names=None, normalize=False,
 
 
 # http://scikit-learn.org/stable/auto_examples/ensemble/plot_forest_importances.html
-def feature_importances(data, top_n=None, feature_names=None,
-                        orientation='horizontal', ax=None):
+def feature_importances(data,
+                        top_n=None,
+                        feature_names=None,
+                        orientation='horizontal',
+                        ax=None):
     """
     Get and order feature importances from a scikit-learn model
     or from an array-like structure. If data is a scikit-learn model with
@@ -156,7 +166,9 @@ def feature_importances(data, top_n=None, feature_names=None,
     # If no feature_names is provided, assign numbers
     res = compute.feature_importances(data, top_n, feature_names)
 
-    ax = bar.plot(res.importance, orientation, res.feature_name,
+    ax = bar.plot(res.importance,
+                  orientation,
+                  res.feature_name,
                   error=None if not hasattr(res, 'std_') else res.std_)
     ax.set_title("Feature importances")
     return ax

src/sklearn_evaluation/training/__init__.py

@@ -3,4 +3,4 @@
 """
 from sklearn_evaluation.training.selector import DataSelector
 
-__all__ = ['DataSelector']
+__all__ = ['DataSelector']

src/sklearn_evaluation/util.py

@@ -116,8 +116,8 @@ def _mapping_to_tuple_pairs(d):
     return tuple(product(*t))
 
 
-def _flatten_list(l):
-    return [item for sublist in l for item in sublist]
+def _flatten_list(elements):
+    return [item for sublist in elements for item in sublist]
 
 
 def truncate_colormap(cmap, minval=0.0, maxval=1.0, n=100):

tests/test_metrics.py

@@ -1,13 +1,11 @@
 from unittest import TestCase
-from sklearn_evaluation.metrics import (precision_at, labels_at,
-                                        tp_at, fp_at)
+from sklearn_evaluation.metrics import (precision_at, labels_at, tp_at, fp_at)
 
 import numpy as np
 from numpy import nan
 
 
 class Test_precision_at(TestCase):
-
     def test_perfect_precision(self):
         labels = np.array([1, 1, 1, 1, 1, 0, 0, 0, 0, 0])
         scores = np.array([100, 90, 80, 70, 60, 50, 40, 30, 20, 10])
@@ -18,8 +16,10 @@ def test_perfect_precision(self):
     def test_perfect_precision_with_nas(self):
         labels = np.array([1, nan, 1, 1, 1, nan, 0, 0, 0, 0])
         scores = np.array([100, 90, 80, 70, 60, 50, 40, 30, 20, 10])
-        prec, cutoff = precision_at(
-            labels, scores, top_proportion=0.10, ignore_nas=True)
+        prec, cutoff = precision_at(labels,
+                                    scores,
+                                    top_proportion=0.10,
+                                    ignore_nas=True)
         self.assertEqual(prec, 1.0)
         self.assertEqual(cutoff, 100)
 
@@ -33,42 +33,57 @@ def test_baseline_precision(self):
     def test_baseline_precision_with_nas(self):
         labels = np.array([nan, 1, nan, 1, 1, nan, nan, 0, 0, 0])
         scores = np.array([100, 90, 80, 70, 60, 50, 40, 30, 20, 10])
-        prec, cutoff = precision_at(
-            labels, scores, top_proportion=1.0, ignore_nas=True)
+        prec, cutoff = precision_at(labels,
+                                    scores,
+                                    top_proportion=1.0,
+                                    ignore_nas=True)
         self.assertEqual(prec, 0.5)
         self.assertEqual(cutoff, 10)
 
     def test_proportion_less_than_zero(self):
         self.assertRaises(ValueError, precision_at, [1], [0], -0.1)
 
     def test_proportion_more_than_one(self):
-        self.assertRaises(ValueError, precision_at, [1], [0], top_proportion=1.1)
+        self.assertRaises(ValueError,
+                          precision_at, [1], [0],
+                          top_proportion=1.1)
 
 
 class Test_labels_at(TestCase):
-
     def test_no_labels_at_1(self):
         y_true = np.array([nan, nan, nan, nan, nan, nan, nan, nan, nan, nan])
         y_score = np.random.rand(1, 10)
-        labels = labels_at(y_true, y_score, top_proportion=0.01, normalize=False)
+        labels = labels_at(y_true,
+                           y_score,
+                           top_proportion=0.01,
+                           normalize=False)
         self.assertEqual(labels, 0)
 
     def test_no_labels_at_50(self):
         y_true = np.array([nan, nan, nan, nan, nan, nan, nan, nan, nan, nan])
         y_score = np.random.rand(1, 10)
-        labels = labels_at(y_true, y_score, top_proportion=0.5, normalize=False)
+        labels = labels_at(y_true,
+                           y_score,
+                           top_proportion=0.5,
+                           normalize=False)
         self.assertEqual(labels, 0)
 
     def test_no_labels_at_100(self):
         y_true = np.array([nan, nan, nan, nan, nan, nan, nan, nan, nan, nan])
         y_score = np.random.rand(1, 10)
-        labels = labels_at(y_true, y_score, top_proportion=1.0, normalize=False)
+        labels = labels_at(y_true,
+                           y_score,
+                           top_proportion=1.0,
+                           normalize=False)
         self.assertEqual(labels, 0)
 
     def test_one_label_at_10(self):
         y_true = np.array([1, nan, nan, nan, nan, nan, nan, nan, nan, nan])
         y_score = np.array([1.0, 0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1])
-        labels = labels_at(y_true, y_score, top_proportion=0.1, normalize=False)
+        labels = labels_at(y_true,
+                           y_score,
+                           top_proportion=0.1,
+                           normalize=False)
         self.assertEqual(labels, 1)
 
     def test_one_label_at_10_norm(self):
@@ -80,19 +95,28 @@ def test_one_label_at_10_norm(self):
     def test_one_label_at_50(self):
         y_true = np.array([1, nan, nan, nan, nan, nan, nan, nan, nan, nan])
         y_score = np.array([1.0, 0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1])
-        labels = labels_at(y_true, y_score, top_proportion=0.5, normalize=False)
+        labels = labels_at(y_true,
+                           y_score,
+                           top_proportion=0.5,
+                           normalize=False)
         self.assertEqual(labels, 1)
 
     def test_one_label_at_100(self):
         y_true = np.array([1, nan, nan, nan, nan, nan, nan, nan, nan, nan])
         y_score = np.array([1.0, 0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1])
-        labels = labels_at(y_true, y_score, top_proportion=1.0, normalize=False)
+        labels = labels_at(y_true,
+                           y_score,
+                           top_proportion=1.0,
+                           normalize=False)
         self.assertEqual(labels, 1)
 
     def test_60_labels_at_60(self):
         y_true = np.array([1, 1, 1, 1, 1, 1, nan, nan, nan, nan])
         y_score = np.array([1.0, 0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1])
-        labels = labels_at(y_true, y_score, top_proportion=0.6, normalize=False)
+        labels = labels_at(y_true,
+                           y_score,
+                           top_proportion=0.6,
+                           normalize=False)
         self.assertEqual(labels, 6)
 
     def test_60_labels_at_60_norm(self):
@@ -104,7 +128,10 @@ def test_60_labels_at_60_norm(self):
     def test_60_labels_at_60_mixed_values(self):
         y_true = np.array([1, 0, 0, 1, 0, 1, nan, nan, nan, nan])
         y_score = np.array([1.0, 0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1])
-        labels = labels_at(y_true, y_score, top_proportion=0.6, normalize=False)
+        labels = labels_at(y_true,
+                           y_score,
+                           top_proportion=0.6,
+                           normalize=False)
         self.assertEqual(labels, 6)
 
     def test_60_labels_at_60_norm_mixed_values(self):
@@ -116,7 +143,10 @@ def test_60_labels_at_60_norm_mixed_values(self):
     def test_60_labels_at_30(self):
         y_true = np.array([1, 1, 1, 1, 1, 1, nan, nan, nan, nan])
         y_score = np.array([1.0, 0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1])
-        labels = labels_at(y_true, y_score, top_proportion=0.3, normalize=False)
+        labels = labels_at(y_true,
+                           y_score,
+                           top_proportion=0.3,
+                           normalize=False)
         self.assertEqual(labels, 3)
 
     def test_60_labels_at_30_norm(self):
@@ -133,7 +163,6 @@ def test_proportion_more_than_one(self):
 
 
 class Test_tp_at(TestCase):
-
     def test_with_nas(self):
         y_true = np.array([1, nan, 1, 1, 1, 1, 1, 1, 1, nan])
         y_score = np.array([1.0, 0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1])
@@ -196,7 +225,6 @@ def test_proportion_more_than_one(self):
 
 
 class Test_fp_at(TestCase):
-
     def test_with_nas(self):
         y_true = np.array([0, nan, 1, 1, 1, 1, 1, 1, 1, nan])
         y_score = np.array([1.0, 0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1])