การจับคู่รูปแบบด้วย Regex

เหตุใดจึงใช้ Regex ใน Pandas

import pandas as pd

df = pd.DataFrame({
    'text': ['Order #12345 placed', 'No order', 'Ref #67890 paid', 'Refund for #11111']
})

# Find rows that contain an order number (# followed by 5 digits)
has_order = df['text'].str.contains(r'#\d{5}', regex=True)
print(df[has_order])
#                  text
# 0  Order #12345 placed
# 2    Ref #67890 paid
# 3  Refund for #11111

ใช้ .str.contains() ร่วมกับ Regex

import pandas as pd

df = pd.DataFrame({
    'code': ['US-001', 'UK-042', 'DE-18', 'FR-', 'us-003']
})

# Valid format: two uppercase letters, hyphen, 3 digits
valid = df['code'].str.contains(r'^[A-Z]{2}-\d{3}$', regex=True)
print(df['code'][valid].tolist())
# ['US-001', 'UK-042']

.str.match() สำหรับการจับคู่ที่มีจุดยึด

import pandas as pd

df = pd.DataFrame({'id': ['ORD001', 'ORD002', 'RET003', 'ORDXYZ']})

# Match rows whose ID starts with 'ORD' followed by digits
orders = df['id'].str.match(r'ORD\d+')
print(df[orders])
#        id
# 0  ORD001
# 1  ORD002

# match() is anchored at start, so 'ORDXYZ' (XYZ not digits) is excluded

ใช้ .str.extract() สำหรับกลุ่มที่จับ

import pandas as pd

df = pd.DataFrame({
    'notes': ['Shipped on 2024-01-15', 'Delivered on 2024-03-20', 'Pending', 'Shipped on 2024-07-04']
})

# Extract the date (YYYY-MM-DD) from the notes column
dates = df['notes'].str.extract(r'(\d{4}-\d{2}-\d{2})')
df['shipped_date'] = dates[0]
print(df[['notes', 'shipped_date']])
#                     notes shipped_date
# 0   Shipped on 2024-01-15   2024-01-15
# 1  Delivered on 2024-03-20   2024-03-20
# 2                  Pending          NaN
# 3   Shipped on 2024-07-04   2024-07-04

กลุ่มที่จับแบบมีชื่อ

import pandas as pd

df = pd.DataFrame({
    'entry': ['Alice (25, Engineer)', 'Bob (30, Manager)', 'Carol (28, Analyst)']
})

# Named capturing groups
extracted = df['entry'].str.extract(
    r'(?P<name>\w+) \((?P<age>\d+), (?P<role>\w+)\)'
)
print(extracted)
#     name age      role
# 0  Alice  25  Engineer
# 1    Bob  30   Manager
# 2  Carol  28   Analyst

ใช้ .str.extractall() เพื่อจับคู่หลายรายการ

import pandas as pd

df = pd.DataFrame({
    'text': ['Call 555-1234 or 555-5678', 'Contact 800-9000', 'No numbers']
})

# Extract all phone patterns
all_phones = df['text'].str.extractall(r'(\d{3}-\d{4})')
print(all_phones)
#              0
#   match
# 0 0      555-1234
#   1      555-5678
# 1 0      800-9000

ใช้ .str.findall() เพื่อสร้างรายการผลการจับคู่

import pandas as pd

df = pd.DataFrame({
    'text': ['Buy 3 items for $10 each', 'Save $5 on 2 products', 'No deal']
})

# Find all dollar amounts
df['prices'] = df['text'].str.findall(r'\$\d+')
df['price_count'] = df['prices'].str.len()

print(df[['text', 'prices', 'price_count']])
#                         text  prices  price_count
# 0  Buy 3 items for $10 each   [$10]            1
# 1  Save $5 on 2 products      [$5]            1
# 2                   No deal      []            0

การจับคู่โดยไม่คำนึงถึงตัวพิมพ์ด้วย re.IGNORECASE

import pandas as pd
import re

df = pd.DataFrame({
    'skill': ['Python', 'JAVA', 'javascript', 'PyThOn developer', 'SQL']
})

# Case-insensitive search for python
mask = df['skill'].str.contains('python', flags=re.IGNORECASE, regex=True)
print(df[mask])
#               skill
# 0            Python
# 3  PyThOn developer

การตรวจสอบรูปแบบด้วยการจับคู่ทั้งสตริง

import pandas as pd

df = pd.DataFrame({
    'email': ['alice@example.com', 'bob_at_work', 'carol@test', 'dave@org.co']
})

# Simple email validation: word@word.word
valid_email = df['email'].str.fullmatch(r'[\w.+-]+@[\w-]+\.[\w.]+')
print(df[valid_email])
#                email
# 0  alice@example.com
# 3        dave@org.co

การแทนที่ด้วยการอ้างอิงย้อนกลับของ Regex

import pandas as pd

df = pd.DataFrame({'phone': ['(555) 123-4567', '(800) 555-0199', '(212) 867-5309']})

# Reformat to 555-123-4567
df['phone_clean'] = df['phone'].str.replace(
    r'\((\d{3})\) (\d{3})-(\d{4})',
    r'\1-\2-\3',
    regex=True
)
print(df)
#             phone phone_clean
# 0  (555) 123-4567  555-123-4567
# 1  (800) 555-0199  800-555-0199
# 2  (212) 867-5309  212-867-5309

การสร้างตัวแยกข้อมูลโดยใช้ Regex

import pandas as pd

df = pd.DataFrame({
    'note': [
        'SKU:A001 price:$49.99 in stock',
        'SKU:B202 price:$12.50 low stock',
        'No SKU available'
    ]
})

extracted = df['note'].str.extract(
    r'SKU:(?P<sku>\w+).*price:\$(?P<price>[\d.]+)'
)
print(extracted)
#     sku  price
# 0  A001  49.99
# 1  B202  12.50
# 2   NaN    NaN

ตรวจสอบความเข้าใจอย่างรวดเร็ว

สรุปบทเรียน