import gradio as gr
import pandas as pd
from sklearn.preprocessing import LabelEncoder

def data_description(desc_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()

    if desc_type == "Display Data":
        return df.head()
    if desc_type == "Describe Data":
        df_copy = df.copy(deep=True)
        data_desc = df_copy.describe()
        data_desc.insert(0, "Description", ["count", "mean", "std", "min", "25%", "50%", "75%", "max"], True)
        return data_desc
    if desc_type == "Display Encoding":
        data = [["Feature", "Mapping"]]
        for col in categorical_column:
            data_encoded[col] = label_encoding.fit_transform(data_encoded[col])
            le_name_mapping = dict(zip(label_encoding.classes_, label_encoding.transform(label_encoding.classes_)))
            data.append([col, str(le_name_mapping)])
        return data
    if desc_type == "Display Encoded Data":
        for col in categorical_column:
            data_encoded[col] = label_encoding.fit_transform(data_encoded[col])
        return data_encoded.head()

inputs = [
        gr.Dropdown(["Display Data", "Describe Data", "Display Encoding", "Display Encoded Data"], label="Perform Data Actions")
    ]

outputs = [gr.DataFrame()]

demo = gr.Interface(
    fn = data_description,
    inputs = inputs,
    outputs = outputs,
    title="Employee-Experience: Data Description",
    allow_flagging=False
)

if __name__ == "__main__":
    demo.launch()