import gradio as gr
import pandas as pd
import joblib

model = joblib.load('decision_tree.pkl')

def onehot(df, column):
    df = df.copy()
    dummies = pd.get_dummies(df[column], prefix='type')
    df = pd.concat([df,dummies], axis=1)
    df = df.drop(column, axis=1)
    return df


def dataframe(file_obj):
    df = pd.read_csv(file_obj.name)
    df = onehot(df, column='type')

    #if the 'type' column doesn't have value 'CASH_OUT' then add a column 'type_CASH_OUT' with value 0
    if 'type_CASH_OUT' not in df.columns:
        df['type_CASH_OUT'] = 0
    #if the 'type' column doesn't have value 'TRANSFER' then add a column 'type_TRANSFER' with value 0
    if 'type_TRANSFER' not in df.columns:
        df['type_TRANSFER'] = 0
    #if the 'type' column doesn't have value 'PAYMENT' then add a column 'type_PAYMENT' with value 0
    if 'type_PAYMENT' not in df.columns:
        df['type_PAYMENT'] = 0
    #if the 'type' column doesn't have value 'DEBIT' then add a column 'type_DEBIT' with value 0
    if 'type_DEBIT' not in df.columns:
        df['type_DEBIT'] = 0
    #if the 'type' column doesn't have value 'PAYMENT' then add a column 'type_PAYMENT' with value 0
    if 'type_PAYMENT' not in df.columns:
        df['type_PAYMENT'] = 0
    
    df = df.drop(['nameOrig','nameDest','isFraud'], axis=1)
    print(df.shape)
    y_pred = model.predict(df)
    
    pred_df = pd.DataFrame(y_pred, columns = ['predictedFraud'])
    #append the predictions to the original dataframe
    df_original = pd.read_csv(file_obj.name)
    pred_df = pd.concat([df_original, pred_df], axis=1)
    print(type(pred_df))
    print(pred_df.shape)
#     clr = classification_report(y_test, y_pred, target_names=['Not Fraud','Fraud'])
#     return 'Classification Report:\n'+ clr
    return pred_df

file = gr.components.File(file_count="single", type="file", label="Fisierul CSV cu tranzactii", optional=False)
y_pred_df = gr.components.Dataframe(max_rows=20, max_cols=None, overflow_row_behaviour="paginate", type="pandas", label="predictedFraud - Predictii bazate pe modelul de clasificare /n isFraud - Etichetele reale")
tree_structure = gr.Image("https://imgur.com/a/dTj0c7X", label="Structura arborelui de decizie")
interface_csv = gr.Interface(
                            fn=dataframe, 
                            inputs=file, 
                            outputs=y_pred_df,
                            title="Fraud Detection - EXPERT SYSTEM",
                            description="Sistem expert bazat pe un model de clasificare pentru detectarea fraudelor in tranzactii bancare",
                            )

interface_csv.launch(inline=False)