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

sns.set(style="whitegrid")

data = {
    "OrderID": [1001, 1002, 1003, 1004, 1005, 1006],
    "Product": ["Laptop", "Mouse", "Keyboard", "Monitor", "Laptop", "Mouse"],
    "Category": ["Electronics", "Accessories", "Accessories", "Electronics", "Electronics", "Accessories"],
    "Price": [70000, 500, 1500, 12000, 72000, 550],
    "Quantity": [1, 2, 1, 2, 1, 3],
    "Date": pd.to_datetime(["2023-01-10", "2023-01-10", "2023-01-11", "2023-01-12", "2023-01-12", "2023-01-13"])
}
df = pd.DataFrame(data)
df

df["Revenue"] = df["Price"] * df["Quantity"]
df

df.describe()

revenue_by_product = df.groupby("Product")["Revenue"].sum().sort_values(ascending=False)
revenue_by_product

Product
Laptop      142000
Monitor      24000
Mouse         2650
Keyboard      1500
Name: Revenue, dtype: int64

revenue_by_product.plot(kind='bar', color='orange', figsize=(8,4))
plt.title("Revenue by Product")
plt.ylabel("Revenue in ₹")
plt.show()

daily_revenue = df.groupby("Date")["Revenue"].sum()
daily_revenue

Date
2023-01-10    71000
2023-01-11     1500
2023-01-12    96000
2023-01-13     1650
Name: Revenue, dtype: int64

daily_revenue.plot(marker='o', linestyle='--', color='green')
plt.title("Daily Revenue Trend")
plt.xlabel("Date")
plt.ylabel("Revenue in ₹")
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

category_revenue = df.groupby("Category")["Revenue"].sum()
category_revenue

Category
Accessories      4150
Electronics    166000
Name: Revenue, dtype: int64

category_revenue.plot.pie(autopct='%1.1f%%', startangle=90, figsize=(5,5))
plt.title("Revenue Share by Category")
plt.ylabel("")
plt.show()

df["Discount"] = [0, 50, 0, 1000, 0, 30]  # Simulate discounts
df["NetRevenue"] = df["Revenue"] - df["Discount"]
df

df[["Revenue", "NetRevenue"]].sum()

Revenue       170150
NetRevenue    169070
dtype: int64

df.loc[df["Revenue"].idxmax()]

OrderID                      1005
Product                    Laptop
Category              Electronics
Price                       72000
Quantity                        1
Date          2023-01-12 00:00:00
Revenue                     72000
Discount                        0
NetRevenue                  72000
Name: 4, dtype: object

plt.hist(df["Revenue"], bins=5, color="skyblue", edgecolor="black")
plt.title("Revenue Distribution")
plt.xlabel("Revenue")
plt.ylabel("Frequency")
plt.show()

correlation = df[["Price", "Quantity", "Revenue", "Discount", "NetRevenue"]].corr()
sns.heatmap(correlation, annot=True, cmap="YlGnBu")
plt.title("Sales Data Correlation Matrix")
plt.show()

summary = df.groupby("Product")[["Quantity", "Revenue", "Discount", "NetRevenue"]].sum()
summary