Spaces:
Runtime error
Runtime error
File size: 5,568 Bytes
1753801 8f429ae 1753801 8a3702d 174521f 1753801 bee3f66 1753801 49cb2d6 1753801 8f429ae 1753801 8f429ae 1753801 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 |
import gradio as gr
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')
pd.options.display.max_columns = 25
pd.options.display.max_rows = 10
data_encoded = df.copy(deep=True)
categorical_column = ['Attrition', 'Gender', 'BusinessTravel', 'Education', 'EmployeeExperience', 'EmployeeFeedbackSentiments', 'Designation',
'SalarySatisfaction', 'HealthBenefitsSatisfaction', 'UHGDiscountProgramUsage', 'HealthConscious', 'CareerPathSatisfaction', 'Region']
label_encoding = LabelEncoder()
for col in categorical_column:
data_encoded[col] = label_encoding.fit_transform(data_encoded[col])
input_data = data_encoded.drop(['Attrition'], axis=1)
target_data = data_encoded[['Attrition']]
col_values = list(input_data.columns.values)
if action_type == "Input Data":
return input_data.head()
if action_type == "Target Data":
return target_data.head()
if action_type == "Feature Selection By Mutual Information":
feature_scores = mutual_info_classif(input_data, target_data)
data = [["Feature", "Mutual Information (0: independent, 1: dependent)"]]
for score, fname in sorted(zip(feature_scores, col_values), reverse=True)[:10]:
data.append([fname, score])
return data
if action_type == "Feature Selection By Chi Square":
feature_scores = chi2(input_data, target_data)[0]
data = [["Feature", "Chi-Square (Frequency Distribution)"]]
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", "AdaBoost Classifier"], label="Develop Data Models")
]
outputs = [gr.DataFrame()]
demo = gr.Interface(
fn = data_description,
inputs = inputs,
outputs = outputs,
title="Employee-Experience: Model Development",
allow_flagging=False
)
if __name__ == "__main__":
demo.launch() |