import os
import tkinter as tk
from tkinter import filedialog, messagebox
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans

# Function to read and load a CSV file
def load_csv_file():
    filename = filedialog.askopenfilename(filetypes=[("CSV files", "*.csv")])
    if filename:
        try:
            data = pd.read_csv(filename)
            return data
        except Exception as e:
            messagebox.showerror("Error", f"Failed to load the file: {e}")
            return None
    else:
        return None

# Function to show basic statistics of the dataset
def show_statistics(data):
    if data is not None:
        stats = data.describe().transpose()
        messagebox.showinfo("Data Statistics", stats.to_string())
    else:
        messagebox.showerror("Error", "No data loaded.")

# Function to plot a histogram for numerical columns
def plot_histogram(data):
    if data is not None:
        numeric_cols = data.select_dtypes(include=np.number).columns
        if len(numeric_cols) == 0:
            messagebox.showwarning("No Numeric Data", "No numeric columns found in the dataset.")
            return
        for col in numeric_cols:
            plt.figure(figsize=(10, 6))
            data[col].hist(bins=20, color='skyblue', edgecolor='black')
            plt.title(f"Histogram of {col}")
            plt.xlabel(col)
            plt.ylabel('Frequency')
            plt.show()
    else:
        messagebox.showerror("Error", "No data loaded.")

# Function to perform KMeans clustering
def perform_kmeans(data):
    if data is not None:
        numeric_cols = data.select_dtypes(include=np.number).columns
        if len(numeric_cols) < 2:
            messagebox.showwarning("Insufficient Data", "Need at least two numeric columns for clustering.")
            return
        try:
            X = data[numeric_cols].values
            kmeans = KMeans(n_clusters=3)
            kmeans.fit(X)
            data['Cluster'] = kmeans.labels_
            plt.figure(figsize=(10, 6))
            plt.scatter(data[numeric_cols[0]], data[numeric_cols[1]], c=data['Cluster'], cmap='viridis')
            plt.title('KMeans Clustering')
            plt.xlabel(numeric_cols[0])
            plt.ylabel(numeric_cols[1])
            plt.show()
        except Exception as e:
            messagebox.showerror("Error", f"Failed to perform KMeans clustering: {e}")
    else:
        messagebox.showerror("Error", "No data loaded.")

# Function to save the modified data to a new CSV file
def save_data(data):
    if data is not None:
        save_path = filedialog.asksaveasfilename(defaultextension=".csv", filetypes=[("CSV files", "*.csv")])
        if save_path:
            try:
                data.to_csv(save_path, index=False)
                messagebox.showinfo("Success", f"Data saved successfully to {save_path}")
            except Exception as e:
                messagebox.showerror("Error", f"Failed to save the file: {e}")
        else:
            messagebox.showwarning("Save Cancelled", "Save operation was cancelled.")
    else:
        messagebox.showerror("Error", "No data to save.")

# Main GUI window class
class DataAnalysisApp:
    def __init__(self, root):
        self.root = root
        self.root.title("Data Analysis Tool")
        self.root.geometry("400x300")
        
        self.data = None
        
        # Buttons
        self.load_button = tk.Button(root, text="Load CSV", command=self.load_data)
        self.load_button.pack(pady=10)
        
        self.stats_button = tk.Button(root, text="Show Stats", command=self.show_statistics)
        self.stats_button.pack(pady=10)
        
        self.hist_button = tk.Button(root, text="Plot Histogram", command=self.plot_histogram)
        self.hist_button.pack(pady=10)
        
        self.kmeans_button = tk.Button(root, text="Perform KMeans", command=self.perform_kmeans)
        self.kmeans_button.pack(pady=10)
        
        self.save_button = tk.Button(root, text="Save Data", command=self.save_data)
        self.save_button.pack(pady=10)
    def load_data(self):
        self.data = load_csv_file()
        if self.data is not None:
            messagebox.showinfo("File Loaded", "CSV file loaded successfully.")
    
    def show_statistics(self):
        show_statistics(self.data)
    
    def plot_histogram(self):
        plot_histogram(self.data)
    
    def perform_kmeans(self):
        perform_kmeans(self.data)
    
    def save_data(self):
        save_data(self.data)

# Running the application
if __name__ == "__main__":
    root = tk.Tk()
    app = DataAnalysisApp(root)
    root.mainloop()