مشروع: تحليل استكشافي (EDA)

import pandas as pd

df = pd.read_csv("orders.csv")

# --- 1. Clean ---
df["date"] = pd.to_datetime(df["date"])
df["rating"] = df["rating"].fillna(df["rating"].median())
df["revenue"] = df["qty"] * df["price"]
df["month"] = df["date"].dt.to_period("M")

# --- 2. Ask questions ---
print("Total revenue:", f"{df['revenue'].sum():,} EGP")
print("Average order:", f"{df['revenue'].mean():,.0f} EGP")

print("\nRevenue share by category:")
share = df.groupby("category")["revenue"].sum() / df["revenue"].sum()
print((share * 100).round(1).sort_values(ascending=False))

print("\nMonthly trend:")
print(df.groupby("month")["revenue"].sum())

print("\nBest rated category:")
print(df.groupby("category")["rating"].mean().round(2).idxmax())

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv("orders.csv")
df["date"] = pd.to_datetime(df["date"])
df["revenue"] = df["qty"] * df["price"]

fig, axes = plt.subplots(1, 2, figsize=(10, 3.6))   # two charts side by side

monthly = df.groupby(df["date"].dt.strftime("%b"), sort=False)["revenue"].sum()
axes[0].bar(monthly.index, monthly.values, color="#3776AB")
axes[0].set_title("Revenue per month")

by_cat = df.groupby("category")["revenue"].sum()
axes[1].pie(by_cat.values, labels=by_cat.index, autopct="%1.0f%%",
            colors=["#3776AB", "#FFD43B", "#9BB8D3"])
axes[1].set_title("Revenue share")

plt.tight_layout()
plt.show()