analysis.py

import pandas as pd

df = pd.read_csv("Superstore.csv", encoding="latin1")

print("Total Sales:")
print(df["Sales"].sum())

print("\nTotal Profit:")
print(df["Profit"].sum())

print("\nAverage Sales:")
print(df["Sales"].mean())

print("\nAverage Profit:")
print(df["Profit"].mean())

category_sales = df.groupby("Category")["Sales"].sum()

print("\nCategory Wise Sales:")
print(category_sales)

category_profit = df.groupby("Category")["Profit"].sum()

print("\nCategory Wise Profit:")
print(category_profit)

top_products = df.groupby(
    "Product Name"
)["Sales"].sum()

print("\nTop 10 Products")

print(
    top_products.sort_values(
        ascending=False
    ).head(10)
)
print(df.columns)

import matplotlib.pyplot as plt

category_sales.plot(kind="bar")

plt.title("Category Wise Sales")
plt.xlabel("Category")
plt.ylabel("Sales")

plt.savefig("images/category_sales.png")

plt.show()

plt.figure()

category_profit.plot(kind="bar")

plt.title("Category Wise Profit")
plt.xlabel("Category")
plt.ylabel("Profit")

plt.savefig("images/profit_analysis.png")

plt.show()

plt.figure(figsize=(10,5))

top_products.sort_values(
    ascending=False
).head(10).plot(kind="bar")

plt.title("Top 10 Products")
plt.xlabel("Products")
plt.ylabel("Sales")

plt.savefig("images/top_products.png")

plt.show()
df["Order Date"] = pd.to_datetime(df["Order Date"])

df["Month"] = df["Order Date"].dt.to_period("M")

monthly_sales = df.groupby(
    "Month"
)["Sales"].sum()
plt.figure(figsize=(12,5))

monthly_sales.plot(
    kind="line",
    marker="o"
)

plt.title("Monthly Sales Trend")
plt.xlabel("Month")
plt.ylabel("Sales")

plt.savefig("images/monthly_sales_trend.png")

plt.show()

plt.figure(figsize=(8,5))

plt.scatter(
    df["Sales"],
    df["Profit"]
)

plt.title("Sales vs Profit")
plt.xlabel("Sales")
plt.ylabel("Profit")

plt.savefig("images/sales_vs_profit.png")

plt.show()