#1. Importing Lib

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
import gradio as gr

#2. Data Preprocessing

df=pd.read_csv("mail_data.csv")

df.loc[df["Category"]=="spam","Category",]=0
df.loc[df["Category"]=="ham","Category",]=1

# Spliting Data into xand y

x=df["Message"]
y=df["Category"]

#3. Modeling Part

x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=0)

# Features extractions using TfidfVectorizer
feature_extraction=TfidfVectorizer(min_df=1,stop_words="english",lowercase=True)

x_train_features = feature_extraction.fit_transform(x_train)
x_test_features  =  feature_extraction.transform(x_test)

y_train = y_train.astype("int")
y_test = y_test.astype("int")



model=LogisticRegression()
# Trains the model only at Train data features
model.fit(x_train_features,y_train)

x_predict=model.predict(x_train_features)
x_accuracy=accuracy_score(x_predict,y_train)

y_predict=model.predict(x_test_features)
y_accuracy=accuracy_score(y_predict,y_test)

#4. UI For Model

# Function to predict whether the email is spam or ham
def classify_email(email_text):
    # Transform the input email text using the same vectorizer used during training
    input_data_features = feature_extraction.transform([email_text])

    # Predict using the trained model
    prediction = model.predict(input_data_features)

    # Return the result based on the prediction
    if prediction[0] == 0:
        return "Your email is Spam"
    else:
        return "Your email is Ham"

# Create a Gradio interface for user input
interface = gr.Interface(
    fn=classify_email,  # Function to be called when user interacts
    inputs=gr.Textbox(label="Enter your email text here", placeholder="Type your email...", lines=5),
    outputs=gr.Textbox(label="Prediction"),
    live=True  # Live prediction update
)

# Launch the interface
interface.launch()