stack และ unstack กับ MultiIndex

บทนำเกี่ยวกับ stack และ unstack

stack(): จากคอลัมน์เป็นแถว

import pandas as pd

df = pd.DataFrame({
    'Math': [85, 90, 78],
    'Science': [92, 88, 95]
}, index=['Alice', 'Bob', 'Carol'])

print(df)
#        Math  Science
# Alice    85       92
# Bob      90       88
# Carol    78       95

stacked = df.stack()
print(stacked)
# Alice    Math       85
#          Science    92
# Bob      Math       90
#          Science    88
# Carol    Math       78
#          Science    95
# dtype: int64

unstack(): จากแถวเป็นคอลัมน์

stacked = df.stack()
print(type(stacked))  # Series with MultiIndex

# Restore the original wide format
df_restored = stacked.unstack()
print(df_restored)
#        Math  Science
# Alice    85       92
# Bob      90       88
# Carol    78       95

# Identical to the original df!

การเลือกระดับที่จะใช้กับ stack

# MultiIndex columns
arrays = [['Math', 'Math', 'Science', 'Science'],
          ['Q1', 'Q2', 'Q1', 'Q2']]
multi_cols = pd.MultiIndex.from_arrays(arrays, names=['subject', 'quarter'])

df_multi = pd.DataFrame([[85, 90, 92, 88], [78, 80, 95, 91]],
                        index=['Alice', 'Bob'], columns=multi_cols)

# Stack the 'quarter' level (innermost, level=-1)
print(df_multi.stack(level='quarter').head())

unstack() กับระดับแถวที่ระบุ

# GroupBy produces MultiIndex rows
df2 = pd.DataFrame({
    'region': ['East', 'East', 'West', 'West'],
    'product': ['A', 'B', 'A', 'B'],
    'sales': [100, 150, 120, 200]
})

# MultiIndex result from groupby
multi = df2.groupby(['region', 'product'])['sales'].sum()
print(multi)

# Unstack the product level into columns
wide = multi.unstack('product')
print(wide)
# product    A    B
# region
# East     100  150
# West     120  200

การจัดการค่าที่หายไปใน stack/unstack

# Incomplete data: West has no product B
df3 = df2[df2['product'] != 'B'].copy()
multi3 = df3.groupby(['region', 'product'])['sales'].sum()

wide3 = multi3.unstack('product', fill_value=0)
print(wide3)
# product    A    B
# region
# East     100    0  <- B filled with 0 instead of NaN
# West     120    0

stack() แล้วคำนวณกับแถว

# Normalise each column by its column mean using stack/compute/unstack
normalised = (
    df.stack()
      .groupby(level=1)
      .transform(lambda s: (s - s.mean()) / s.std())
      .unstack()
)
print(normalised.round(2))
#        Math  Science
# Alice  0.0     0.39
# Bob    1.13   -1.09
# Carol -1.13    0.71

stack() สำหรับการสร้างกราฟ

# Prepare data for line plot using stack
long = df.stack().reset_index()
long.columns = ['student', 'subject', 'score']
print(long)
#   student  subject  score
# 0   Alice     Math     85
# 1   Alice  Science     92
# ...

# Ready for: sns.barplot(data=long, x='student', y='score', hue='subject')

swaplevel() สำหรับจัดลำดับดัชนีใหม่

stacked = df.stack()  # MultiIndex: (student, subject)
swapped = stacked.swaplevel()  # MultiIndex: (subject, student)
swapped = swapped.sort_index()
print(swapped)
# subject  student
# Math     Alice      85
#          Bob        90
#          Carol      78
# Science  Alice      92
#          Bob        88
#          Carol      95

ควรใช้ stack, melt หรือ pivot เมื่อใด

# Decision guide (comment, not executable standalone):
# MultiIndex columns -> want fewer levels: use stack()
# Flat wide -> need long format for plotting/ML: use melt()
# Long -> need wide summary table: use pivot_table()
# Wide -> back to long: use melt() or stack()

# Example: stack when you have pivot_table output (MultiIndex cols)
tbl = df2.groupby(['region', 'product'])['sales'].sum().unstack()
long_again = tbl.stack().rename('sales').reset_index()
print(long_again)

สรุปเชิงปฏิบัติ: สรุปจำง่ายเรื่องการปรับรูป

# stack/unstack cycle
df_wide = df.copy()             # wide format
df_long = df_wide.stack()       # long via stack
df_wide2 = df_long.unstack()    # back to wide

# melt/pivot cycle
df_melted = df_wide.melt(id_vars=[])    # wide -> long
# df_pivoted = df_melted.pivot(...)     # long -> wide

print('Original shape:  ', df_wide.shape)
print('After stack:     ', df_long.shape)
print('After unstack:   ', df_wide2.shape)

ตรวจสอบความเข้าใจ

สรุปบทเรียน