main.py

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

data = pd.read_csv('data.csv')
print(data.columns)  # Should output Name, Age, Marks

class DataAnalyzer:
    def __init__(self, csv_path):
        self.df = pd.read_csv(csv_path)

    def calculate_average(self, column):
        avg = self.df[column].mean()
        print(f'Average for {column}: {avg:.2f}')
        return avg

    def plot_bar_chart(self, x_col, y_col):
        plt.figure(figsize=(8,5))
        plt.bar(self.df[x_col], self.df[y_col], color='skyblue')
        plt.xlabel(x_col)
        plt.ylabel(y_col)
        plt.title(f'Bar Chart of {y_col} vs {x_col}')
        plt.show()

    def plot_scatter(self, x_col, y_col):
        plt.figure(figsize=(8,5))
        plt.scatter(self.df[x_col], self.df[y_col], c='tomato', alpha=0.7)
        plt.xlabel(x_col)
        plt.ylabel(y_col)
        plt.title(f'Scatter Plot of {y_col} vs {x_col}')
        plt.show()

    def plot_heatmap(self):
        corr = data[['Age', 'Marks']].corr()   # Only numeric columns!
        sns.heatmap(corr, annot=True)
        plt.title('Correlation Heatmap')
        plt.show()
        # corr = self.df.corr()
        # plt.figure(figsize=(10,8))
        # sns.heatmap(corr, annot=True, cmap='viridis')
        # plt.title('Correlation Heatmap')
        # plt.show()

# Usage example
if __name__ == '__main__':
    analyzer = DataAnalyzer('data.csv')
    analyzer.calculate_average('Marks') # Replace with actual column name
    analyzer.plot_bar_chart('Name', 'Marks') # Replace with actual columns
    analyzer.plot_scatter('Age', 'Marks') # Replace with actual columns
    analyzer.plot_heatmap()