การเลือกข้อมูลจาก MultiIndex

การนำทางข้อมูลแบบลำดับชั้น

import pandas as pd
import numpy as np

# Setup: GDP data by country and year
df_flat = pd.DataFrame({
    'country': ['USA','USA','USA','UK','UK','UK','DE','DE','DE'],
    'year': [2021, 2022, 2023, 2021, 2022, 2023, 2021, 2022, 2023],
    'gdp_bn': [23000, 25000, 26000, 3000, 3100, 3200, 4100, 4200, 4350]
})
df = df_flat.set_index(['country', 'year']).sort_index()
print(df)

การเลือกตามระดับนอกด้วย .loc

import pandas as pd

df_flat = pd.DataFrame({
    'country': ['USA','USA','USA','UK','UK','UK'],
    'year': [2021, 2022, 2023, 2021, 2022, 2023],
    'gdp_bn': [23000, 25000, 26000, 3000, 3100, 3200]
})
df = df_flat.set_index(['country', 'year']).sort_index()

# Select all USA rows
usa = df.loc['USA']
print('All USA rows:')
print(usa)
print('\nRemaining index type:', usa.index.name)

การเลือกทูเพิลเฉพาะด้วย .loc

import pandas as pd

df_flat = pd.DataFrame({
    'country': ['USA','USA','USA','UK','UK','UK'],
    'year': [2021, 2022, 2023, 2021, 2022, 2023],
    'gdp_bn': [23000, 25000, 26000, 3000, 3100, 3200],
    'cpi': [3.2, 5.1, 4.8, 2.5, 3.4, 3.0]
})
df = df_flat.set_index(['country', 'year']).sort_index()

# Single row as Series
print('USA 2022 (Series):')
print(df.loc[('USA', 2022)])

# Single row as DataFrame
print('\nUSA 2022 (DataFrame):')
print(df.loc[[('USA', 2022)]])

การเลือกหลายแถวด้วยลิสต์ของทูเพิล

import pandas as pd

df_flat = pd.DataFrame({
    'country': ['USA','USA','UK','UK','DE','DE'],
    'year': [2022, 2023, 2022, 2023, 2022, 2023],
    'gdp_bn': [25000, 26000, 3100, 3200, 4200, 4350]
})
df = df_flat.set_index(['country', 'year']).sort_index()

# Select specific (country, year) combinations
subset = df.loc[[('USA', 2022), ('UK', 2023), ('DE', 2022)]]
print(subset)

การเลือกช่วงด้วย pd.IndexSlice

import pandas as pd
import numpy as np

years = [2021, 2022, 2023]
countries = ['DE', 'UK', 'USA']
mi = pd.MultiIndex.from_product([countries, years], names=['country', 'year'])
df = pd.DataFrame({'gdp': np.random.randint(3000, 26000, 9)}, index=mi)

idx = pd.IndexSlice

# Select UK and USA for years 2022 and 2023
subset = df.loc[idx['UK':'USA', 2022:2023], :]
print(subset)

การเข้าถึงส่วนตัดขวางด้วย .xs()

import pandas as pd
import numpy as np

countries = ['DE', 'UK', 'USA']
years = [2021, 2022, 2023]
mi = pd.MultiIndex.from_product([countries, years], names=['country', 'year'])
df = pd.DataFrame({'gdp': [4100,4200,4350, 3000,3100,3200, 23000,25000,26000]}, index=mi)

# All countries for year 2022 (inner level)
print('All data for year 2022:')
print(df.xs(2022, level='year'))

# All years for UK (outer level)
print('\nAll years for UK:')
print(df.xs('UK', level='country'))

การเข้าถึงคอลัมน์แบบ MultiIndex

import pandas as pd
import numpy as np

metrics = ['revenue', 'cost']
quarters = ['Q1', 'Q2', 'Q3', 'Q4']
cols = pd.MultiIndex.from_product([metrics, quarters], names=['metric', 'quarter'])
df = pd.DataFrame(
    np.random.randint(50, 200, (3, 8)),
    columns=cols,
    index=['USA', 'UK', 'DE']
)

# Access all revenue columns
print('Revenue columns:')
print(df['revenue'])

# Access a specific cell
print('\nUSA revenue Q1:', df.loc['USA', ('revenue', 'Q1')])

การเลือกระดับในจากคีย์ระดับนอกทั้งหมด

import pandas as pd
import numpy as np

countries = ['DE', 'UK', 'USA']
years = [2021, 2022, 2023]
mi = pd.MultiIndex.from_product([countries, years], names=['country', 'year'])
df = pd.DataFrame({'gdp': [4100,4200,4350, 3000,3100,3200, 23000,25000,26000]}, index=mi)

idx = pd.IndexSlice

# All countries for year 2022 (using IndexSlice)
all_2022 = df.loc[idx[:, 2022], :]
print('All countries in 2022:')
print(all_2022)

ข้อผิดพลาดที่พบบ่อยในการเลือกด้วย MultiIndex

import pandas as pd

# Unsorted MultiIndex slicing
tuples = [('B', 2), ('A', 1), ('B', 1), ('A', 2)]
mi = pd.MultiIndex.from_tuples(tuples, names=['letter', 'num'])
df = pd.DataFrame({'value': [10, 20, 30, 40]}, index=mi)

print('Is sorted:', df.index.is_monotonic_increasing)
# Sort before slicing
df = df.sort_index()
print('After sort:', df.index.is_monotonic_increasing)

idx = pd.IndexSlice
print('\nSlice A:')
print(df.loc[idx['A', :], :])

ตัวอย่างเชิงปฏิบัติ: การจัดทำรายงานรายไตรมาส

import pandas as pd
import numpy as np

regions = ['North', 'South', 'East', 'West']
quarters = ['Q1', 'Q2', 'Q3', 'Q4']
mi = pd.MultiIndex.from_product([regions, quarters], names=['region', 'quarter'])

np.random.seed(42)
df = pd.DataFrame({
    'sales': np.random.randint(200, 500, 16),
    'units': np.random.randint(50, 150, 16)
}, index=mi)

# Extract Q4 performance across all regions
q4 = df.xs('Q4', level='quarter')
print('Q4 Results by Region:')
print(q4)
print('\nQ4 Total Sales:', q4['sales'].sum())

การรวมการเลือกด้วย MultiIndex เข้ากับคอลัมน์

import pandas as pd
import numpy as np

countries = ['DE', 'UK', 'USA']
years = [2021, 2022, 2023]
mi = pd.MultiIndex.from_product([countries, years], names=['country', 'year'])
df = pd.DataFrame({
    'gdp': [4100,4200,4350, 3000,3100,3200, 23000,25000,26000],
    'inflation': [1.5, 2.1, 2.8, 2.0, 3.4, 2.9, 3.2, 5.1, 4.8],
    'unemployment': [5.0, 4.8, 4.5, 4.5, 4.2, 4.0, 3.8, 3.5, 3.3]
}, index=mi)

idx = pd.IndexSlice

# UK and USA, years 2022-2023, only gdp and inflation
result = df.loc[idx['UK':'USA', 2022:2023], ['gdp', 'inflation']]
print(result)

ตรวจสอบความเข้าใจอย่างรวดเร็ว

สรุปบทเรียน