การกำหนดและรีเซ็ตดัชนี

ดัชนีของ DataFrame คืออะไร

import pandas as pd

df = pd.DataFrame({
    'date': ['2024-01-01', '2024-01-02', '2024-01-03'],
    'sales': [100, 200, 150]
})
print('Default index:', df.index.tolist())  # [0, 1, 2]
print(df)

set_index() — ยกระดับคอลัมน์เป็นดัชนี

import pandas as pd

df = pd.DataFrame({
    'date': ['2024-01-01', '2024-01-02', '2024-01-03'],
    'sales': [100, 200, 150]
})

df = df.set_index('date')
print(df)
#             sales
# date
# 2024-01-01    100
# 2024-01-02    200
# 2024-01-03    150

print(df.index)  # Index(['2024-01-01', ...], dtype='object', name='date')

การเลือกแถวด้วยดัชนีแบบกำหนดเอง

import pandas as pd

df = pd.DataFrame({
    'product': ['A', 'B', 'C'],
    'price': [10, 20, 30],
    'stock': [100, 50, 75]
})
df = df.set_index('product')

# Access row by label
print(df.loc['B'])
# price    20
# stock    50
# Name: B, dtype: int64

set_index() กับหลายคอลัมน์ — MultiIndex

import pandas as pd

df = pd.DataFrame({
    'region': ['East', 'East', 'West', 'West'],
    'year': [2023, 2024, 2023, 2024],
    'revenue': [100, 150, 200, 220]
})

df = df.set_index(['region', 'year'])
print(df)
#              revenue
# region year
# East   2023      100
#        2024      150
# West   2023      200
#        2024      220

print(df.loc[('East', 2024)])  # revenue = 150

พารามิเตอร์ drop= ใน set_index()

import pandas as pd

df = pd.DataFrame({'id': [1, 2, 3], 'value': [10, 20, 30]})

# Keep 'id' as both index and column
df_with_both = df.set_index('id', drop=False)
print(df_with_both)
#     id  value
# id
# 1    1     10
# 2    2     20
# 3    3     30

reset_index() — ย้ายดัชนีกลับไปเป็นคอลัมน์

import pandas as pd

df = pd.DataFrame({'sales': [100, 200]}, index=['East', 'West'])
df.index.name = 'region'

reset = df.reset_index()
print(reset)
#   region  sales
# 0   East    100
# 1   West    200

print(reset.index.tolist())  # [0, 1] — default RangeIndex restored

reset_index(drop=True)

import pandas as pd

df = pd.DataFrame({'x': [10, 20, 30, 40, 50]})
filtered = df[df['x'] > 15]
print('Filtered index:', filtered.index.tolist())  # [1, 2, 3, 4]

# Drop the old index — don't move it to a column
clean = filtered.reset_index(drop=True)
print('Clean index:', clean.index.tolist())  # [0, 1, 2, 3]

reset_index() หลัง groupby

import pandas as pd

df = pd.DataFrame({
    'dept': ['Eng', 'HR', 'Eng', 'Sales', 'HR'],
    'salary': [90000, 50000, 80000, 70000, 55000]
})

# After groupby, dept becomes the index
agg = df.groupby('dept')['salary'].mean()
print(type(agg), agg.index.tolist())
# dept is the index

# Reset makes dept a regular column again
result = agg.reset_index()
result.columns = ['dept', 'avg_salary']
print(result)

rename_axis() สำหรับชื่อดัชนี

import pandas as pd

df = pd.DataFrame({'sales': [100, 200, 300]}, index=['A', 'B', 'C'])
print(df.index.name)  # None

# Name the index
df = df.rename_axis('region')
print(df)
#         sales
# region
# A         100
# B         200
# C         300

การจัดดัชนีใหม่เพื่อเติมช่องว่าง

import pandas as pd

df = pd.DataFrame({
    'month': ['Jan', 'Mar', 'Jun'],
    'revenue': [100, 200, 300]
}).set_index('month')

all_months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun']
complete = df.reindex(all_months)
print(complete)
#       revenue
# Jan     100.0
# Feb       NaN   <- filled with NaN
# Mar     200.0
# Apr       NaN
# May       NaN
# Jun     300.0

MultiIndex reset_index และการเลือกระดับ

import pandas as pd

df = pd.DataFrame(
    {'revenue': [100, 150, 200, 220]},
    index=pd.MultiIndex.from_tuples(
        [('East', 2023), ('East', 2024), ('West', 2023), ('West', 2024)],
        names=['region', 'year']
    )
)

# Reset only the 'year' level, keep 'region' as index
df2 = df.reset_index(level='year')
print(df2)
#         year  revenue
# region
# East    2023      100
# East    2024      150
# West    2023      200
# West    2024      220

ตรวจสอบความเข้าใจ

สรุปบทเรียน