import streamlit as st
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, LabelEncoder
from sklearn.feature_selection import SelectKBest, f_classif
from sklearn.impute import SimpleImputer
from imblearn.over_sampling import SMOTE
from sklearn.metrics import accuracy_score, classification_report

# Import ML Models
from sklearn.neighbors import KNeighborsClassifier, KNeighborsRegressor
from sklearn.svm import SVC, SVR
from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
from sklearn.linear_model import Perceptron

# Sidebar UI
st.sidebar.title("AI Code Generator 🧠")
st.sidebar.markdown("Generate AI models instantly!")

# Model Selection
model_options = ["KNN", "SVM", "Random Forest", "Decision Tree", "Perceptron"]
model = st.sidebar.selectbox("Choose a Model:", model_options)

# Task Selection
task_options = ["Classification", "Regression"]
task = st.sidebar.selectbox("Choose a Task:", task_options)

# Problem Selection based on Task and Model
problems = {
    "Classification": {
        "KNN": ["Spam Detection", "Disease Prediction"],
        "SVM": ["Image Recognition", "Text Classification"],
        "Random Forest": ["Fraud Detection", "Customer Segmentation"],
        "Decision Tree": ["Loan Approval", "Churn Prediction"],
        "Perceptron": ["Handwritten Digit Recognition", "Sentiment Analysis"]
    },
    "Regression": {
        "KNN": ["House Price Prediction", "Stock Prediction"],
        "SVM": ["Sales Forecasting", "Stock Market Trends"],
        "Random Forest": ["Energy Consumption", "Patient Survival Prediction"],
        "Decision Tree": ["House Price Estimation", "Revenue Prediction"],
        "Perceptron": ["Weather Forecasting", "Traffic Flow Prediction"]
    }
}

problem = st.sidebar.selectbox("Choose a Problem:", problems[task][model])

# Dataset Selection (User selects a pre-existing fake dataset)
dataset_mapping = {
    "Spam Detection": "datasets/spam_detection.csv",
    "Disease Prediction": "datasets/disease_prediction.csv",
    "Fraud Detection": "datasets/fraud_detection.csv",
    "House Price Prediction": "datasets/house_price.csv",
    "Sales Forecasting": "datasets/sales_forecasting.csv",
}

dataset_path = dataset_mapping.get(problem, "datasets/spam_detection.csv")
df = pd.read_csv(dataset_path)

# Display dataset
st.subheader("Sample Dataset")
st.write(df.head())

# Preprocessing Steps
st.subheader("📌 Preprocessing Steps")
st.markdown("""
- ✅ Handle Missing Values  
- ✅ Encoding Categorical Variables  
- ✅ Feature Scaling  
- ✅ Feature Selection  
- ✅ Handling Imbalanced Data using **SMOTE**
""")

# Handle missing values
imputer = SimpleImputer(strategy='mean')
df = df.apply(lambda col: imputer.fit_transform(col.values.reshape(-1, 1)).flatten() if col.dtypes == 'float64' else col)

# Encoding categorical variables
label_encoders = {}
for col in df.select_dtypes(include=['object']).columns:
    label_encoders[col] = LabelEncoder()
    df[col] = label_encoders[col].fit_transform(df[col])

# Split Data
X = df.iloc[:, :-1]  # Features
y = df.iloc[:, -1]   # Target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Feature Scaling
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Feature Selection
selector = SelectKBest(score_func=f_classif, k=5)
X_train = selector.fit_transform(X_train, y_train)
X_test = selector.transform(X_test)

# Handle imbalanced data
if task == "Classification":
    smote = SMOTE()
    X_train, y_train = smote.fit_resample(X_train, y_train)

# Model Initialization
model_mapping = {
    "KNN": KNeighborsClassifier() if task == "Classification" else KNeighborsRegressor(),
    "SVM": SVC() if task == "Classification" else SVR(),
    "Random Forest": RandomForestClassifier() if task == "Classification" else RandomForestRegressor(),
    "Decision Tree": DecisionTreeClassifier() if task == "Classification" else DecisionTreeRegressor(),
    "Perceptron": Perceptron() if task == "Classification" else Perceptron()
}

model_instance = model_mapping[model]

# Train Model
model_instance.fit(X_train, y_train)
y_pred = model_instance.predict(X_test)

# Evaluation Metrics
st.subheader("📊 Model Evaluation")
if task == "Classification":
    accuracy = accuracy_score(y_test, y_pred)
    report = classification_report(y_test, y_pred)
    st.write(f"**Accuracy:** {accuracy:.2f}")
    st.text(report)
else:
    st.write("Regression evaluation metrics will be added soon!")

# Visualization
st.subheader("📈 Data Visualization")
plt.figure(figsize=(8, 5))
sns.heatmap(df.corr(), annot=True, cmap="coolwarm")
st.pyplot(plt)

# Download Code
st.download_button("🐍 Download Python Code (.py)", "ai_model.py")
st.download_button("📓 Download Notebook (.ipynb)", "ai_model.ipynb")
st.markdown("[🚀 Open in Colab](https://colab.research.google.com/)")

st.success("Code generated! Download and do magic! ✨")