ترتيب القيم

ما هو الترتيب؟

import pandas as pd

df = pd.DataFrame({
    'player': ['Alice', 'Bob', 'Carol', 'Dave', 'Eve'],
    'score': [88, 72, 95, 72, 85]
})

df['rank'] = df['score'].rank()
print(df)
#    player  score  rank
# 0   Alice     88   4.0
# 1     Bob     72   1.5   <- tied with Dave
# 2   Carol     95   5.0
# 3    Dave     72   1.5   <- tied with Bob
# 4     Eve     85   3.0

الترتيب التصاعدي مقابل التنازلي

import pandas as pd

df = pd.DataFrame({'score': [70, 95, 85, 60, 90]})

# Rank 1 = highest score
df['competition_rank'] = df['score'].rank(ascending=False)
print(df)
#    score  competition_rank
# 0     70               4.0
# 1     95               1.0
# 2     85               3.0
# 3     60               5.0
# 4     90               2.0

طرق كسر التعادل

import pandas as pd

s = pd.Series([10, 20, 20, 30])

print('average:', s.rank(method='average').tolist())  # [1.0, 2.5, 2.5, 4.0]
print('min:    ', s.rank(method='min').tolist())      # [1.0, 2.0, 2.0, 4.0]
print('max:    ', s.rank(method='max').tolist())      # [1.0, 3.0, 3.0, 4.0]
print('first:  ', s.rank(method='first').tolist())    # [1.0, 2.0, 3.0, 4.0]
print('dense:  ', s.rank(method='dense').tolist())    # [1.0, 2.0, 2.0, 3.0]

الترتيب الكثيف: بلا فجوات بعد التعادل

import pandas as pd

df = pd.DataFrame({
    'name': ['A', 'B', 'C', 'D', 'E'],
    'score': [100, 80, 80, 60, 60]
})

df['dense_rank'] = df['score'].rank(method='dense', ascending=False).astype(int)
print(df)
#   name  score  dense_rank
# 0    A    100           1
# 1    B     80           2
# 2    C     80           2  <- same score, same rank
# 3    D     60           3  <- next rank is 3, not 4
# 4    E     60           3

ترتيب المئينات باستخدام pct=True

import pandas as pd

df = pd.DataFrame({'score': [50, 70, 80, 90, 100]})

df['percentile'] = df['score'].rank(pct=True)
print(df)
#    score  percentile
# 0     50         0.2
# 1     70         0.4
# 2     80         0.6
# 3     90         0.8
# 4    100         1.0

الترتيب داخل المجموعات

import pandas as pd

df = pd.DataFrame({
    'dept': ['Eng', 'Eng', 'HR', 'HR', 'Eng'],
    'name': ['Alice', 'Bob', 'Carol', 'Dave', 'Eve'],
    'salary': [90000, 70000, 55000, 65000, 80000]
})

df['dept_rank'] = df.groupby('dept')['salary'].rank(
    method='dense', ascending=False
).astype(int)
print(df.sort_values(['dept', 'dept_rank']))
#    dept   name  salary  dept_rank
# 0   Eng  Alice   90000          1
# 4   Eng    Eve   80000          2
# 1   Eng    Bob   70000          3
# 3    HR   Dave   65000          1
# 2    HR  Carol   55000          2

pd.cut() للفئات متساوية العرض

import pandas as pd

df = pd.DataFrame({'age': [5, 15, 25, 35, 45, 55, 65, 75]})

df['age_group'] = pd.cut(df['age'], bins=[0, 18, 35, 60, 100],
                          labels=['Child', 'Young Adult', 'Middle Age', 'Senior'])
print(df)
#    age    age_group
# 0    5        Child
# 1   15        Child
# 2   25  Young Adult
# 3   35  Young Adult
# 4   45   Middle Age
# 5   55   Middle Age
# 6   65       Senior
# 7   75       Senior

pd.qcut() للفئات متساوية التكرار

import pandas as pd
import numpy as np

np.random.seed(0)
df = pd.DataFrame({'score': np.random.randint(40, 100, 20)})

# Split into 4 equal-frequency quartiles
df['quartile'] = pd.qcut(df['score'], q=4, labels=['Q1', 'Q2', 'Q3', 'Q4'])
print(df['quartile'].value_counts().sort_index())
# Q1    5
# Q2    5
# Q3    5
# Q4    5

cut() مقابل qcut() — الفروق الأساسية

import pandas as pd
import numpy as np

np.random.seed(0)
# Skewed distribution: most values near 0
skewed = pd.Series(np.random.exponential(scale=5, size=100).round())

# cut with equal width: many empty or tiny upper bins
cut_counts = pd.cut(skewed, bins=4).value_counts().sort_index()
print('cut():', cut_counts.values)

# qcut with equal frequency: always 25 per group
qcut_counts = pd.qcut(skewed, q=4).value_counts().sort_index()
print('qcut():', qcut_counts.values)

إضافة رقم الترتيب كعمود

import pandas as pd

df = pd.DataFrame({
    'team': ['Falcons', 'Eagles', 'Hawks', 'Owls'],
    'wins': [12, 9, 12, 7]
})

leaderboard = (
    df
    .sort_values('wins', ascending=False)
    .reset_index(drop=True)
)
leaderboard.index = leaderboard.index + 1
leaderboard.index.name = 'place'
print(leaderboard)

الترتيب كميزة لتعلّم الآلة

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'income': [30000, 50000, 70000, 1_000_000]  # outlier at 1M
})

# Add rank as a feature
df['income_rank'] = df['income'].rank(pct=True)
print(df)
#      income  income_rank
# 0    30000         0.25
# 1    50000         0.50
# 2    70000         0.75
# 3  1000000         1.00
# The outlier has rank 1.0 — extreme but not disproportionate

تحقق سريع

مراجعة الدرس