main.py

import pandas as pd
import matplotlib.pyplot as plt

# Load dataset
df = pd.read_csv("data/sales_data.csv")

# Convert Date column to datetime
df['Date'] = pd.to_datetime(df['Date'])

# Check missing values
df.dropna(inplace=True)

# Validation
if df.empty:
    raise ValueError("Dataset is empty after cleaning")

print("Dataset Loaded Successfully")
print(df.head())

# ------------------ ANALYSIS ------------------

# 1. Total sales by product
product_sales = df.groupby('Product')['Total_Sales'].sum()

# 2. Sales by region
region_sales = df.groupby('Region')['Total_Sales'].sum()

# 3. Monthly sales trend
df['Month'] = df['Date'].dt.month
monthly_sales = df.groupby('Month')['Total_Sales'].sum()

# ------------------ VISUALIZATION ------------------

# Bar Chart – Product Sales
plt.figure()
product_sales.plot(kind='bar')
plt.title("Total Sales by Product")
plt.xlabel("Product")
plt.ylabel("Total Sales")
plt.tight_layout()
plt.savefig("visualizations/product_sales.png")
plt.close()

# Line Chart – Monthly Sales Trend
plt.figure()
monthly_sales.plot(kind='line', marker='o')
plt.title("Monthly Sales Trend")
plt.xlabel("Month")
plt.ylabel("Total Sales")
plt.tight_layout()
plt.savefig("visualizations/monthly_sales.png")
plt.close()

# Pie Chart – Region-wise Sales
plt.figure()
region_sales.plot(kind='pie', autopct='%1.1f%%')
plt.title("Sales Distribution by Region")
plt.ylabel("")
plt.tight_layout()
plt.savefig("visualizations/region_sales.png")
plt.close()

print("Analysis & Visualizations Completed Successfully")