app

app.py

@@ -3,6 +3,12 @@ import pandas as pd
 from sklearn.preprocessing import LabelEncoder
 from sklearn.feature_selection import mutual_info_classif
 from sklearn.feature_selection import chi2
+from sklearn import metrics
+from sklearn.ensemble import AdaBoostClassifier
+from aif360.datasets import BinaryLabelDataset
+from aif360.metrics import BinaryLabelDatasetMetric
+from aif360.algorithms.preprocessing.reweighing import Reweighing
+from sklearn.metrics import classification_report
 
 def data_description(action_type):
     df = pd.read_csv('emp_experience_data.csv')
@@ -34,9 +40,56 @@ def data_description(action_type):
         for score, fname in sorted(zip(feature_scores, col_values), reverse=True)[:10]:
             data.append([fname, score])
         return data
+    if action_type == "AdaBoost Classifier":
+        data_selected = data_encoded[['EmployeeExperience', 'HealthBenefitsSatisfaction', 'SalarySatisfaction', 'Designation', 'HealthConscious',
+                        'EmployeeFeedbackSentiments', 'Education', 'Gender', 'HoursOfTrainingAttendedLastYear', 'InternalJobMovement', 'Attrition']]
+
+        input_data = data_selected.drop(['Attrition'], axis=1)
+        target_data = data_selected[['Attrition']]
+        input_data = data_selected[0:150]
+        validation_data = data_selected[150:198]
+        validation_input_data = validation_data.drop(['Attrition'], axis=1)
+        validation_target_data = validation_data[['Attrition']]
+        test_data = data_selected[198:]
+        test_input_data = test_data.drop(['Attrition'], axis=1)
+        test_target_data = test_data[['Attrition']]
+        privileged_groups = [{'Gender': 0}]
+        unprivileged_groups = [{'Gender': 1}]
+        favorable_label = 0 
+        unfavorable_label = 1
+        BM_dataset = BinaryLabelDataset(favorable_label=favorable_label,
+                                        unfavorable_label=unfavorable_label,
+                                        df=input_data,
+                                        label_names=['Attrition'],
+                                        protected_attribute_names=['Gender'],
+                                        unprivileged_protected_attributes=unprivileged_groups)
+        metric_orig_train = BinaryLabelDatasetMetric(BM_dataset, unprivileged_groups=unprivileged_groups,  privileged_groups=privileged_groups)
+        RW = Reweighing(unprivileged_groups=unprivileged_groups,
+                    privileged_groups=privileged_groups)
+        RW.fit(BM_dataset)
+        train_tf_dataset = RW.transform(BM_dataset)
+        metric_orig_train = BinaryLabelDatasetMetric(train_tf_dataset, 
+                                                    unprivileged_groups=unprivileged_groups,
+                                                    privileged_groups=privileged_groups)
+
+        print("Difference in mean outcomes between unprivileged and privileged groups = %f"% metric_orig_train.mean_difference())
+
+        estimator = [100]
+        for i in estimator:
+            cls = AdaBoostClassifier(n_estimators=i)
+            cls.fit(train_tf_dataset.features, train_tf_dataset.labels,sample_weight=train_tf_dataset.instance_weights)
+
+            predicted_output = cls.predict(train_tf_dataset.features)
+            accuracy = metrics.accuracy_score(train_tf_dataset.labels, predicted_output)
+            report = classification_report(train_tf_dataset.labels, predicted_output)
+            df_train = pd.DataFrame(report).transpose()
+            predicted_output = cls.predict(validation_input_data)
+            accuracy = metrics.accuracy_score(validation_target_data, predicted_output)
+            report_pred = classification_report(validation_target_data, predicted_output)
+            df_pred = pd.DataFrame(report_pred).transpose()
 
 inputs = [
-        gr.Dropdown(["Input Data", "Target Data", "Feature Selection By Mutual Information", "Feature Selection By Chi Square"], label="Develop Data Models")
+        gr.Dropdown(["Input Data", "Target Data", "Feature Selection By Mutual Information", "Feature Selection By Chi Square", "AdaBoost Classifier"], label="Develop Data Models")
     ]
 
 outputs = [gr.DataFrame()]

requirements.txt

@@ -1,2 +1,4 @@
 cufflinks
-sklearn
+sklearn
+aif360
+'aif360[AdversarialDebiasing]'