ชนิดข้อมูลแบบหมวดหมู่

ชนิดข้อมูล Categorical คืออะไร

import pandas as pd

df = pd.DataFrame({
    'region': ['North', 'South', 'East', 'North', 'East', 'South'] * 1000
})

# Without Categorical: object dtype stores every string
print('object dtype memory:', df['region'].memory_usage(deep=True))

# With Categorical: only stores 3 unique values + integer codes
df['region_cat'] = df['region'].astype('category')
print('category dtype memory:', df['region_cat'].memory_usage(deep=True))

การสร้าง Categorical Series

import pandas as pd

s = pd.Series(['low', 'high', 'med', 'high', 'low'])
s_cat = s.astype('category')

print(s_cat.cat.categories)  # Index(['high', 'low', 'med'], dtype='object')
print(s_cat.cat.codes)       # integer codes per row
# 0    1
# 1    0
# 2    2
# 3    0
# 4    1

การประหยัดหน่วยความจำด้วย Categorical

import pandas as pd
import numpy as np

n = 1_000_000
statuses = np.random.choice(['active', 'inactive', 'pending'], size=n)
df = pd.DataFrame({'status': statuses})

object_mem = df['status'].memory_usage(deep=True) / 1e6
df['status'] = df['status'].astype('category')
cat_mem = df['status'].memory_usage(deep=True) / 1e6

print(f'Object dtype:    {object_mem:.1f} MB')
print(f'Category dtype:  {cat_mem:.1f} MB')
print(f'Reduction:       {object_mem/cat_mem:.1f}x')

Categorical แบบมีลำดับสำหรับการจัดอันดับ

import pandas as pd

df = pd.DataFrame({
    'priority': ['high', 'low', 'medium', 'high', 'low']
})

priority_type = pd.CategoricalDtype(
    categories=['low', 'medium', 'high'],
    ordered=True
)
df['priority'] = df['priority'].astype(priority_type)

# Comparison now works correctly
print(df['priority'] >= 'medium')
# 0     True
# 1    False
# 2     True
# 3     True
# 4    False

การเรียงลำดับ Categorical แบบมีลำดับ

import pandas as pd

df = pd.DataFrame({
    'severity': pd.Categorical(
        ['high', 'low', 'medium', 'low', 'high'],
        categories=['low', 'medium', 'high'],
        ordered=True
    ),
    'count': [5, 20, 8, 15, 3]
})

# sort_values respects the categorical order
print(df.sort_values('severity')[['severity', 'count']])
#   severity  count
# 1      low     20
# 3      low     15
# 2   medium      8
# 0     high      5
# 4     high      3

ความเร็วของ GroupBy ด้วย Categorical

import pandas as pd
import numpy as np

np.random.seed(0)
df = pd.DataFrame({
    'region': pd.Categorical(
        np.random.choice(['North', 'South', 'East', 'West'], 10),
        categories=['North', 'South', 'East', 'West']
    ),
    'sales': np.random.randint(100, 1000, 10)
})

# observed=False shows ALL categories even empty ones
print(df.groupby('region', observed=False)['sales'].sum())

การเพิ่มและลบหมวดหมู่

import pandas as pd

s = pd.Categorical(['a', 'b', 'a'], categories=['a', 'b', 'c'])
s = pd.Series(s)

print(s.cat.categories)  # Index(['a', 'b', 'c'], dtype='object')
print(s.value_counts())  # a:2, b:1, c:0

# Remove unused category 'c'
s = s.cat.remove_unused_categories()
print(s.cat.categories)  # Index(['a', 'b'], dtype='object')

การเปลี่ยนชื่อป้ายกำกับหมวดหมู่

import pandas as pd

s = pd.Series(pd.Categorical(['M', 'F', 'M', 'F'], categories=['M', 'F']))

# Rename using a dict
s = s.cat.rename_categories({'M': 'Male', 'F': 'Female'})
print(s)
# 0      Male
# 1    Female
# 2      Male
# 3    Female
print(s.cat.categories)  # Index(['Male', 'Female'], dtype='object')

กรณีที่ไม่ควรใช้ Categorical

import pandas as pd
import numpy as np

df = pd.DataFrame({'user_id': range(1_000_000)})

# High-cardinality: every value is unique — don't use Categorical
object_mem = df['user_id'].astype(str).memory_usage(deep=True) / 1e6
cat_mem = df['user_id'].astype(str).astype('category').memory_usage(deep=True) / 1e6

print(f'String: {object_mem:.1f} MB')
print(f'Category: {cat_mem:.1f} MB')
# Category is WORSE for high-cardinality data!

Categorical ในตาราง Pivot และ Groupby

import pandas as pd

df = pd.DataFrame({
    'quarter': pd.Categorical(
        ['Q1', 'Q1', 'Q3'],
        categories=['Q1', 'Q2', 'Q3', 'Q4']
    ),
    'revenue': [100, 200, 300]
})

# observed=False includes Q2 and Q4 even though they have no rows
result = df.groupby('quarter', observed=False)['revenue'].sum()
print(result)
# quarter
# Q1    300
# Q2      0
# Q3    300
# Q4      0

Categorical และการเรียนรู้ของเครื่อง

import pandas as pd

df = pd.DataFrame({
    'colour': pd.Categorical(['red', 'blue', 'green', 'red'])
})

# One-hot encode for unordered categories
one_hot = pd.get_dummies(df['colour'], prefix='colour')
print(one_hot)
#    colour_blue  colour_green  colour_red
# 0            0             0           1
# 1            1             0           0
# 2            0             1           0
# 3            0             0           1

ตรวจสอบความเข้าใจ

สรุปบทเรียน