การแปลงชนิดด้วย astype()

บทนำสู่ astype()

import pandas as pd

df = pd.DataFrame({'age': ['25', '30', '35']})
print('Before:', df['age'].dtype)  # object

df['age'] = df['age'].astype(int)
print('After:', df['age'].dtype)   # int64
print(df['age'] + 1)               # [26, 31, 36] — arithmetic now works

การแปลงเป็นชนิดตัวเลข

import pandas as pd

df = pd.DataFrame({'price': ['10.5', '20.0', 'N/A', '30.5']})

# astype would crash on 'N/A'
# price_float = df['price'].astype(float)  # ValueError!

# pd.to_numeric with errors='coerce' is safer
df['price_float'] = pd.to_numeric(df['price'], errors='coerce')
print(df)
#   price  price_float
# 0  10.5         10.5
# 1  20.0         20.0
# 2   N/A          NaN
# 3  30.5         30.5

การแปลงเป็นสตริง (object)

import pandas as pd

df = pd.DataFrame({'id': [1, 2, 3], 'region': ['E', 'W', 'N']})

# Concatenate id and region into a composite key
df['key'] = df['id'].astype(str) + '_' + df['region']
print(df)
#    id region  key
# 0   1      E  1_E
# 1   2      W  2_W
# 2   3      N  3_N

การแปลงเป็นบูลีน

import pandas as pd

df = pd.DataFrame({
    'active_int': [1, 0, 1, 0],
    'active_str': ['Yes', 'No', 'Yes', 'No']
})

# Integer to bool
df['active_bool'] = df['active_int'].astype(bool)

# String to bool via mapping
df['active_bool2'] = df['active_str'].map({'Yes': True, 'No': False})

print(df[['active_bool', 'active_bool2']])
#    active_bool  active_bool2
# 0         True          True
# 1        False         False

การลดขนาดชนิดข้อมูลตัวเลข

import pandas as pd
import numpy as np

df = pd.DataFrame({'count': np.random.randint(0, 200, 1_000_000)})

print('int64 bytes:', df['count'].nbytes)   # 8,000,000

df['count_int16'] = df['count'].astype('int16')  # max 32767, fits 0-200
print('int16 bytes:', df['count_int16'].nbytes)  # 2,000,000

# Or let Pandas choose the smallest type automatically
df['count_auto'] = pd.to_numeric(df['count'], downcast='integer')
print('auto dtype:', df['count_auto'].dtype)

การแปลง DataFrame ทั้งหมดด้วย astype(dict)

import pandas as pd

df = pd.DataFrame({
    'age': ['25', '30'],
    'salary': ['50000', '70000'],
    'is_manager': ['1', '0']
})

df = df.astype({
    'age': 'int32',
    'salary': 'float64',
    'is_manager': 'bool'
})
print(df.dtypes)
# age           int32
# salary      float64
# is_manager     bool

การจัดการข้อผิดพลาดใน astype()

import pandas as pd

# Clean then cast pattern
df = pd.DataFrame({'price': ['$1,200', '$800', '$450']})

# Step 1: remove non-numeric characters
df['price_clean'] = (
    df['price']
    .str.replace('$', '', regex=False)
    .str.replace(',', '', regex=False)
)
# Step 2: safe cast
df['price_num'] = df['price_clean'].astype(float)
print(df)
#      price price_clean  price_num
# 0  $1,200        1200     1200.0
# 1    $800         800      800.0
# 2    $450         450      450.0

การแปลงเป็น Pandas StringDtype

import pandas as pd

df = pd.DataFrame({'name': ['Alice', None, 'Carol']})

# Convert to the modern string dtype
df['name'] = df['name'].astype('string')
print(df['name'].dtype)   # string
print(df['name'].isna())  # proper NA detection
# 0    False
# 1     True
# 2    False

ความเสี่ยงจากค่าล้นเมื่อ ลดขนาดชนิดข้อมูล

import pandas as pd
import numpy as np

df = pd.DataFrame({'value': [100, 200, 300, 127, 128]})

# int8 range: -128 to 127
df['value_i8'] = df['value'].astype('int8')
print(df)
#    value  value_i8
# 0    100       100
# 1    200       -56   <- overflow! 200-256 = -56
# 2    300        44   <- overflow! 300-256 = 44
# 3    127       127
# 4    128      -128   <- overflow!

# Always check range first
print(df['value'].max())  # 300 > 127 — int8 is UNSAFE here

การตรวจสอบการแปลงด้วยแผนผังชนิดข้อมูล

import pandas as pd

df = pd.DataFrame({
    'user_id': [1, 2, 3],
    'amount': [10.5, 20.0, 30.5],
    'active': [True, False, True]
})

expected = {'user_id': 'int64', 'amount': 'float64', 'active': 'bool'}

for col, dtype in expected.items():
    assert str(df[col].dtype) == dtype, (
        f'{col}: expected {dtype}, got {df[col].dtype}'
    )
print('Schema validation passed')

ตัวอย่างกระบวนการแปลงข้อมูลทั้งหมด

import pandas as pd

raw = pd.DataFrame({
    'user_id': ['101', '102', '103'],
    'revenue': ['$1,200', '$800', '$2,500'],
    'active': ['Yes', 'No', 'Yes']
})

df = (
    raw
    .assign(
        user_id=raw['user_id'].astype('int32'),
        revenue=pd.to_numeric(
            raw['revenue'].str.replace('[$,]', '', regex=True)
        ),
        active=raw['active'].map({'Yes': True, 'No': False})
    )
)
print(df.dtypes)
# user_id      int32
# revenue    float64
# active        bool

ตรวจสอบความเข้าใจ

สรุปบทเรียน