feat(Label_Ecoder):Support of Label Encoder in Multi Target Task

Feature Added

Signed-off-by: Trishala Ahalpara <[email protected]>

sapientml_core/templates/model_templates/model.py.jinja

@@ -22,21 +22,34 @@ model = {{ model_name }}({{ silent }}random_state=random_state_model, {{ params
 from sklearn.multioutput import MultiOutputRegressor
 
 model = MultiOutputRegressor(model)
+
 {% elif is_multioutput_classification %}
 from sklearn.multioutput import MultiOutputClassifier
 
 model = MultiOutputClassifier(model)
 {% endif %}
 {% set xgbclassifier = "XGBClassifier" %}
-{% if model_name == xgbclassifier %}
+{% if pipeline.task.target_columns|length == 1 %}
+
 from sklearn.preprocessing import LabelEncoder
 
-label_encoder = LabelEncoder()
-target_train = pd.DataFrame(label_encoder.fit_transform(target_train), columns=TARGET_COLUMNS)
-{% endif %}
-{% if pipeline.task.target_columns|length == 1 %}
+if target_train.select_dtypes(include=['object']).columns.any():
+        str_columns = target_train.select_dtypes(include=['object']).columns
+        label_encoder= LabelEncoder()
+        for col in str_columns:
+                target_train[col] = label_encoder.fit_transform(target_train[col])
+                target_test[col] = label_encoder.transform(target_test[col])
+
 model.fit(feature_train, target_train.values.ravel())
 {% else %}
+
+from sklearn.preprocessing import LabelEncoder
+if target_train.select_dtypes(include=['object']).columns.any():
+        str_columns = target_train.select_dtypes(include=['object']).columns
+        label_encoder= LabelEncoder()
+        for col in str_columns:
+                target_train[col] = label_encoder.fit_transform(target_train[col])
+                target_test[col] = label_encoder.transform(target_test[col])
 model.fit(feature_train, target_train)
 {% endif %}
 y_pred = model.predict(feature_test)
@@ -45,4 +58,4 @@ y_pred = model.classes_[np.argmax(y_pred, axis=1)].reshape(-1, 1)
 {% endif %}
 {% if model_name == xgbclassifier and (not pipeline.adaptation_metric.startswith("MAP_")) and (not pipeline.adaptation_metric == "LogLoss") and (pipeline.adaptation_metric not in metric_needing_predict_proba) %}
 y_pred = label_encoder.inverse_transform(y_pred).reshape(-1, 1)
-{% endif %}
+{% endif %}

sapientml_core/templates/model_templates/model_train.py.jinja

@@ -17,25 +17,47 @@ model = {{ model_name }}(random_state=random_state_model, {{ params }})
 from sklearn.multioutput import MultiOutputRegressor
 
 model = MultiOutputRegressor(model)
+
 {% elif is_multioutput_classification %}
 from sklearn.multioutput import MultiOutputClassifier
 
 model = MultiOutputClassifier(model)
 {% endif %}
+
 {% set xgbclassifier = "XGBClassifier" %}
-{% if model_name == xgbclassifier %}
+
+{% if pipeline.task.target_columns|length == 1 %}
 from sklearn.preprocessing import LabelEncoder
+flag=0
+if target_train.select_dtypes(include=['object']).columns.any():
+   str_columns = target_train.select_dtypes(include=['object']).columns
+   label_encoder= LabelEncoder()
+   flag=1
+   for col in str_columns:
+       target_train[col] = label_encoder.fit_transform(target_train[col])
 
-label_encoder = LabelEncoder()
-target_train = pd.DataFrame(label_encoder.fit_transform(target_train), columns=TARGET_COLUMNS)
-with open('target_LabelEncoder.pkl', 'wb') as f:
-    pickle.dump(label_encoder, f)
+if flag==1:
+    with open('target_LabelEncoder.pkl', 'wb') as f:
+        pickle.dump(label_encoder, f)
+    flag=0
 
-{% endif %}
-{% if pipeline.task.target_columns|length == 1 %}
 model.fit(feature_train, target_train.values.ravel())
 {% else %}
+from sklearn.preprocessing import LabelEncoder
+flag=0
+if target_train.select_dtypes(include=['object']).columns.any():
+   str_columns = target_train.select_dtypes(include=['object']).columns
+   label_encoder= LabelEncoder()
+   flag=1
+   for col in str_columns:
+       target_train[col] = label_encoder.fit_transform(target_train[col])
+
+if flag==1:
+    with open('target_LabelEncoder.pkl', 'wb') as f:
+        pickle.dump(label_encoder, f)
+    flag=0
+
 model.fit(feature_train, target_train)
 {% endif %}
 with open('model.pkl', 'wb') as f:
-    pickle.dump(model, f)
+    pickle.dump(model, f)

sapientml_core/templates/other_templates/evaluation.py.jinja

@@ -22,11 +22,24 @@ for i, col in enumerate(target_test.columns):
     one_acc = accuracy_score(target_test[col], y_pred[:, i:i+1])
     __accs.append(one_acc)
 print(f"RESULT: Accuracy : {str(sum(__accs)/len(__accs))}")
-{% elif pipeline.adaptation_metric == macros.Metric.F1.value %}
+
+{% elif (pipeline.adaptation_metric == macros.Metric.F1.value) and (not pipeline.is_multi_class_multi_targets) %}
 from sklearn import metrics
 
 f1 = metrics.f1_score(target_test, y_pred, average='macro')
 print('RESULT: F1 Score: ' + str(f1))
+
+{% elif pipeline.adaptation_metric == macros.Metric.F1.value and (pipeline.is_multi_class_multi_targets)%}
+from sklearn import metrics
+f1_scores = []
+
+for i, col in enumerate(target_test.columns):
+    one_f1 = metrics.f1_score(target_test[col], y_pred[:, i:i+1], average='macro')
+    f1_scores.append(one_f1)
+
+average_f1 = sum(f1_scores) / len(f1_scores)
+print(f"RESULT: Average F1 score: {average_f1}")
+
 {% elif pipeline.adaptation_metric == macros.Metric.R2.value %}
 from sklearn import metrics
 
@@ -123,4 +136,4 @@ from sklearn import metrics
 
 f1 = metrics.f1_score(target_test, y_pred, average='macro')
 print('RESULT: F1 Score: ' + str(f1))
-{% endif %}
+{% endif %}