تنضيف البيانات

import pandas as pd
from io import StringIO

raw = StringIO("""name,city,age,spent
Ahmed , cairo,28,"1,200 EGP"
Sara,GIZA,,850 EGP
Omar,Cairo ,35,"2,500 EGP"
Sara,GIZA,,850 EGP
Laila,alexandria,240,400 EGP
Youssef,,31,""")

df = pd.read_csv(raw)
print(df)

import pandas as pd
from io import StringIO

raw = StringIO("""name,city,age,spent
Ahmed , cairo,28,"1,200 EGP"
Sara,GIZA,,850 EGP
Omar,Cairo ,35,"2,500 EGP"
Sara,GIZA,,850 EGP
Laila,alexandria,240,400 EGP
Youssef,,31,""")
df = pd.read_csv(raw)

print("Duplicates:", df.duplicated().sum())
df = df.drop_duplicates()
print("Rows now:", len(df))

import pandas as pd
from io import StringIO

raw = StringIO("""name,city,age,spent
Ahmed , cairo,28,"1,200 EGP"
Sara,GIZA,,850 EGP
Omar,Cairo ,35,"2,500 EGP"
Laila,alexandria,240,400 EGP
Youssef,,31,""")
df = pd.read_csv(raw)

# .str gives you string methods for a whole column
df["name"] = df["name"].str.strip()
df["city"] = df["city"].str.strip().str.title()

# "1,200 EGP" -> 1200.0
df["spent"] = (df["spent"].str.replace(" EGP", "")
                          .str.replace(",", "")
                          .astype(float))
print(df)
print(df.dtypes["spent"])

import pandas as pd
import numpy as np

df = pd.DataFrame({
    "name": ["Ahmed", "Sara", "Omar", "Laila", "Youssef"],
    "city": ["Cairo", "Giza", "Cairo", "Alexandria", None],
    "age": [28, np.nan, 35, 240, 31],
    "spent": [1200, 850, 2500, 400, np.nan],
})

print(df.isna().sum())                         # missing per column

df["age"] = df["age"].fillna(df["age"].median())   # fill with median
df["city"] = df["city"].fillna("Unknown")
df = df.dropna(subset=["spent"])               # drop rows missing 'spent'
print(df)

import pandas as pd

df = pd.DataFrame({
    "name": ["Ahmed", "Sara", "Omar", "Laila"],
    "age": [28, 31, 35, 240],
})

valid = df["age"].between(10, 100)
print(df[~valid])                    # ~ means NOT -> show invalid rows

df.loc[~valid, "age"] = pd.NA        # mark as missing, decide later
print(df)