การเรียงลำดับตามดัชนี

ทำความเข้าใจดัชนีของ DataFrame

import pandas as pd

df = pd.DataFrame(
    {'value': [10, 20, 30]},
    index=['C', 'A', 'B']  # out-of-order alphabetic index
)
print(df)
#    value
# C     10
# A     20
# B     30

sort_index() — จากน้อยไปมาก

import pandas as pd

df = pd.DataFrame(
    {'temp': [22.5, 19.0, 25.1, 18.3]},
    index=pd.to_datetime(['2024-03-01', '2024-01-15', '2024-06-10', '2024-01-01'])
)

sorted_df = df.sort_index()
print(sorted_df)
#             temp
# 2024-01-01  18.3
# 2024-01-15  19.0
# 2024-03-01  22.5
# 2024-06-10  25.1

sort_index() จากมากไปน้อย

import pandas as pd

df = pd.DataFrame(
    {'price': [100, 110, 105, 115]},
    index=pd.to_datetime(['2024-01', '2024-02', '2024-03', '2024-04'])
)

# Most recent first
print(df.sort_index(ascending=False))
#             price
# 2024-04-30    115
# 2024-03-31    105
# 2024-02-29    110
# 2024-01-31    100

การเรียงป้ายกำกับคอลัมน์ด้วย axis=1

import pandas as pd

df = pd.DataFrame({
    'zebra': [1], 'apple': [2], 'mango': [3], 'banana': [4]
})

print('Before:', df.columns.tolist())
# ['zebra', 'apple', 'mango', 'banana']

sorted_cols = df.sort_index(axis=1)
print('After:', sorted_cols.columns.tolist())
# ['apple', 'banana', 'mango', 'zebra']

ดัชนีที่เรียงลำดับแล้วเร็วขึ้นเมื่อใด

import pandas as pd
import numpy as np

idx = pd.to_datetime(['2024-03-01', '2024-01-15', '2024-06-10'])
df = pd.DataFrame({'v': [1, 2, 3]}, index=idx)

print('Sorted?', df.index.is_monotonic_increasing)  # False

df = df.sort_index()
print('Sorted?', df.index.is_monotonic_increasing)  # True

# Now slicing is efficient
print(df.loc['2024-01':'2024-03'])

sort_index() กับ MultiIndex

import pandas as pd

arrays = [
    ['B', 'B', 'A', 'A'],
    ['two', 'one', 'two', 'one']
]
idx = pd.MultiIndex.from_arrays(arrays, names=['first', 'second'])
df = pd.DataFrame({'value': [10, 20, 30, 40]}, index=idx)

print(df.sort_index())
#               value
# first second
# A     one       40
#       two       30
# B     one       20
#       two       10

การเรียงลำดับเพียงระดับเดียวของ MultiIndex

import pandas as pd

df = pd.DataFrame({
    'sales': [300, 100, 200, 400, 150, 250]
}, index=pd.MultiIndex.from_tuples([
    ('Eng', 'Dave'), ('Eng', 'Alice'), ('Eng', 'Bob'),
    ('HR', 'Zoe'), ('HR', 'Carol'), ('HR', 'Eve')
], names=['dept', 'name']))

# Sort only the 'name' level alphabetically within each dept
print(df.sort_index(level='name'))
#              sales
# dept name
# Eng  Alice    100
#      Bob      200
#      Dave     300
# HR   Carol    150
#      Eve      250
#      Zoe      400

ความแตกต่างระหว่าง sort_index() และ sort_values()

import pandas as pd

df = pd.DataFrame(
    {'value': [30, 10, 20]},
    index=['C', 'A', 'B']
)

# sort_index: sorted by row label A, B, C
print(df.sort_index())
#    value
# A     10
# B     20
# C     30

# sort_values: sorted by data value 10, 20, 30
print(df.sort_values('value'))
#    value
# A     10
# B     20
# C     30
# (same here because values happen to match alphabetical label order!)

การคืนลำดับเดิมหลังการดำเนินการ

import pandas as pd

df = pd.DataFrame({'x': [10, 20, 30, 40, 50]})

# Shuffle (random sample)
shuffled = df.sample(frac=1, random_state=42)
print('Shuffled index:', shuffled.index.tolist())
# e.g. [2, 4, 0, 1, 3]

# Restore original order by sorting the index
restored = shuffled.sort_index()
print('Restored index:', restored.index.tolist())
# [0, 1, 2, 3, 4]

sort_index() กับ na_position

import pandas as pd
import numpy as np

df = pd.DataFrame(
    {'v': [1, 2, 3, 4]},
    index=['B', None, 'A', 'C']
)

print(df.sort_index(na_position='last'))
#      v
# A    3
# B    1
# C    4
# NaN  2

การวัดประโยชน์ด้านประสิทธิภาพ

import pandas as pd
import numpy as np

np.random.seed(0)
random_dates = pd.to_datetime(
    pd.Timestamp('2020-01-01').value + np.random.randint(0, 1_000_000_000_000_000, size=100_000),
    unit='ns'
)
df = pd.DataFrame({'val': np.random.randn(100_000)}, index=random_dates)

# Without sort: O(n) scan
import timeit
t1 = timeit.timeit(lambda: df.loc['2022-01':'2022-06'], number=100)

df_sorted = df.sort_index()
t2 = timeit.timeit(lambda: df_sorted.loc['2022-01':'2022-06'], number=100)

print(f'Unsorted: {t1:.3f}s, Sorted: {t2:.3f}s, Speedup: {t1/t2:.1f}x')

ตรวจสอบความเข้าใจ

สรุปบทเรียน