Add additional unittest for TargetEncoder

Author: MatthiasRoelsPython

cobra/evaluation/plotting_utils.py

@@ -7,7 +7,8 @@
 
 
 def plot_univariate_predictor_quality(df_auc: pd.DataFrame,
-                                      dim: tuple=(12, 8)):
+                                      dim: tuple=(12, 8),
+                                      path: str=None):
     """Plot univariate quality of the predictors
 
     Parameters
@@ -18,6 +19,8 @@ def plot_univariate_predictor_quality(df_auc: pd.DataFrame,
         criteria
     dim : tuple, optional
         tuple with width and lentgh of the plot
+    path : str, optional
+        path to store the figure
     """
 
     df = (df_auc[df_auc["preselection"]]
@@ -41,6 +44,9 @@ def plot_univariate_predictor_quality(df_auc: pd.DataFrame,
         # Remove white lines from the second axis
         ax.grid(False)
 
+        if path is not None:
+            plt.savefig(path, format="png", dpi=300, bbox_inches="tight")
+
         plt.show()
 
 
@@ -70,6 +76,7 @@ def plot_correlation_matrix(df_corr: pd.DataFrame,
 
 def plot_performance_curves(model_performance: pd.DataFrame,
                             dim: tuple=(12, 8),
+                            path: str=None,
                             colors: dict={"train": "#0099bf",
                                           "selection": "#ff9500",
                                           "validation": "#8064a2"}):
@@ -83,6 +90,8 @@ def plot_performance_curves(model_performance: pd.DataFrame,
         in the forward feature selection
     dim : tuple, optional
         tuple with width and lentgh of the plot
+    path : str, optional
+        path to store the figure
     """
     highest_auc = np.round(max(max(model_performance['train_performance']),
                                max(model_performance['selection_performance']),
@@ -113,6 +122,10 @@ def plot_performance_curves(model_performance: pd.DataFrame,
         fig.suptitle('Performance curves - forward feature selection',
                      fontsize=20)
         plt.ylabel('Model performance')
+
+        if path is not None:
+            plt.savefig(path, format="png", dpi=300, bbox_inches="tight")
+
         plt.show()
 
 

tests/preprocessing/test_target_encoder.py

@@ -90,7 +90,7 @@ def test_target_encoder_fit_column(self):
                            'target': [1, 1, 0, 0, 1, 0, 0, 0, 1, 1]})
 
         encoder = TargetEncoder()
-        encoder._global_mean = 0.0
+        encoder._global_mean = 0.5
         actual = encoder._fit_column(X=df.variable, y=df.target)
 
         expected = pd.Series(data=[0.333333, 0.50000, 0.666667],
@@ -164,6 +164,33 @@ def test_target_encoder_transform(self):
         pd.testing.assert_frame_equal(actual, expected,
                                       check_less_precise=5)
 
+    def test_target_encoder_transform_new_category(self):
+
+        df = pd.DataFrame({'variable': ['positive', 'positive', 'negative',
+                                        'neutral', 'negative', 'positive',
+                                        'negative', 'neutral', 'neutral',
+                                        'neutral'],
+                           'target': [1, 1, 0, 0, 1, 0, 0, 0, 1, 1]})
+
+        df_appended = df.append({"variable": "new", "target": 1},
+                                ignore_index=True)
+
+        # inputs of TargetEncoder will be of dtype category
+        df["variable"] = df["variable"].astype("category")
+        df_appended["variable"] = df_appended["variable"].astype("category")
+
+        expected = df_appended.copy()
+        expected["variable_enc"] = [0.666667, 0.666667, 0.333333, 0.50000,
+                                    0.333333, 0.666667, 0.333333, 0.50000,
+                                    0.50000, 0.50000, 0.333333]
+
+        encoder = TargetEncoder(imputation_strategy="min")
+        encoder.fit(data=df, column_names=["variable"], target_column="target")
+        actual = encoder.transform(data=df_appended, column_names=["variable"])
+
+        pd.testing.assert_frame_equal(actual, expected,
+                                      check_less_precise=5)
+
     # Tests for _clean_column_name
     def test_target_encoder_clean_column_name(self):