أساسيات Pandas

order_id,date,city,category,product,qty,price,rating
1001,2026-01-05,Cairo,Electronics,Headphones,1,1200,4.5
1002,2026-01-07,Giza,Fashion,T-shirt,3,250,4.0
1003,2026-01-12,Alexandria,Home,Blender,1,1800,3.5
1004,2026-02-02,Cairo,Fashion,Sneakers,1,2200,5.0
1005,2026-02-10,Cairo,Electronics,Power Bank,2,650,4.0
1006,2026-02-15,Mansoura,Home,Kettle,1,900,
1007,2026-03-01,Giza,Electronics,Smart Watch,1,3500,4.5
1008,2026-03-08,Alexandria,Fashion,Jacket,1,1600,3.0
1009,2026-03-20,Cairo,Home,Air Fryer,1,4200,5.0
1010,2026-04-02,Giza,Fashion,T-shirt,2,250,4.5
1011,2026-04-11,Mansoura,Electronics,Headphones,1,1200,4.0
1012,2026-04-25,Cairo,Electronics,Laptop Stand,2,850,3.5

import pandas as pd

pd.set_option("display.max_columns", None)   # show all columns
pd.set_option("display.width", 200)          # don't wrap wide tables
df = pd.read_csv("orders.csv")

print(df.shape)          # (rows, columns)
print(df.head(3))        # first 3 rows

import pandas as pd

df = pd.read_csv("orders.csv")
df.info()                # column types + how many non-missing values

import pandas as pd

df = pd.read_csv("orders.csv")
print(df[["qty", "price", "rating"]].describe().round(1))   # quick statistics

import pandas as pd

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

print(df["city"].unique().tolist())         # unique values of one column
print(df[["product", "price"]].head(2))     # several columns -> DataFrame (note [[ ]])

print(df.loc[0, "product"])       # loc  -> by label (row index, column name)
print(df.iloc[-1, 4])             # iloc -> by position (last row, 5th column)

import pandas as pd

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

cairo_big = df[(df["city"] == "Cairo") & (df["price"] > 1000)]
print(cairo_big[["order_id", "product", "price"]])

print(df[df["category"].isin(["Home", "Fashion"])].shape[0], "orders")