Regular expressions for text cleaning in NLP

Introduction

Regular expressions help find and fix messy parts in text. They make text ready for computers to understand.

Removing extra spaces or tabs from user comments.

Deleting special characters from product reviews.

Changing all letters to lowercase for fair comparison.

Extracting phone numbers or emails from messages.

Fixing inconsistent date formats in text data.

Syntax

NLP

import re

# Basic pattern matching
pattern = r'your_pattern_here'
text = 'your text here'

# Find all matches
matches = re.findall(pattern, text)

# Replace matches with new text
clean_text = re.sub(pattern, 'replacement', text)

r before quotes means raw string, so backslashes are treated correctly.

re.findall finds all parts matching the pattern.

Examples

This removes all exclamation marks, question marks, and periods from the text.

NLP

import re
text = 'Hello!!! How are you???'
clean_text = re.sub(r'[!?.]', '', text)
print(clean_text)

This finds phone numbers in the format 123-456-7890.

NLP

import re
text = 'Call me at 123-456-7890.'
phone = re.findall(r'\d{3}-\d{3}-\d{4}', text)
print(phone)

This replaces multiple spaces with one space and removes spaces at the ends.

NLP

import re
text = '  Lots   of   spaces  '
clean_text = re.sub(r'\s+', ' ', text).strip()
print(clean_text)

Sample Model

This program cleans text by removing punctuation, finding phone numbers, fixing spaces, and making all letters lowercase.

NLP

import re

# Sample messy text
text = "Hello!!! This is a sample text... Visit us at www.example.com or call 555-123-4567."

# Step 1: Remove punctuation
text_no_punct = re.sub(r'[!?.]', '', text)

# Step 2: Find phone numbers
phones = re.findall(r'\d{3}-\d{3}-\d{4}', text_no_punct)

# Step 3: Replace multiple spaces with one
clean_text = re.sub(r'\s+', ' ', text_no_punct).strip()

# Step 4: Lowercase all text
final_text = clean_text.lower()

print('Cleaned Text:', final_text)
print('Phone Numbers Found:', phones)

Important Notes

Regular expressions can be tricky at first; test patterns on small text samples.

Use raw strings (r'pattern') to avoid errors with backslashes.

Cleaning text well helps machine learning models understand data better.

Summary

Regular expressions find and fix patterns in text easily.

They help remove unwanted characters and extract useful info.

Using them improves text quality for machine learning tasks.

Practice

1. What is the main purpose of using regular expressions in text cleaning for NLP?

easy

A. To find and remove unwanted patterns or characters in text

B. To train machine learning models directly

C. To store large datasets efficiently

D. To visualize text data with graphs

Solution

1. Step 1: Understand the role of regular expressions

   Regular expressions are used to identify patterns in text, such as unwanted characters or specific sequences.

2. Step 2: Connect to text cleaning

   Text cleaning involves removing or replacing unwanted parts of text to prepare it for analysis or modeling.

3. Final Answer:

   To find and remove unwanted patterns or characters in text -> Option A

4. Quick Check:

   Regular expressions clean text by pattern matching [OK]

Hint: Regular expressions = pattern search and replace in text [OK]

Common Mistakes:

• Confusing regex with model training
• Thinking regex stores data
• Assuming regex creates visualizations

2. Which of the following is the correct Python syntax to import the regular expression module?

easy

A. from regex import *

B. import regex

C. import re

D. import regular_expression

Solution

1. Step 1: Recall Python's regex module name

   Python's built-in module for regular expressions is named 're'.

2. Step 2: Check syntax correctness

   The correct import statement is 'import re' to use regex functions.

3. Final Answer:

   import re -> Option C

4. Quick Check:

   Python regex module = re [OK]

Hint: Remember: Python regex module is 're' not 'regex' [OK]

Common Mistakes:

• Using 'import regex' which is not standard
• Trying to import non-existent modules
• Confusing module names with function names

3. What will be the output of this Python code snippet?

import re
text = "Hello, World! 123"
cleaned = re.sub(r'[^a-zA-Z ]', '', text)
print(cleaned)

medium

A. Hello World

B. Hello World 123

C. Hello, World!

D. HelloWorld123

Solution

1. Step 1: Understand the regex pattern used

   The pattern '[^a-zA-Z ]' means any character NOT a letter (a-z or A-Z) or space.

2. Step 2: Apply re.sub to remove unwanted characters

   All characters except letters and spaces are removed, so commas, exclamation marks, and digits are deleted.

3. Final Answer:

   Hello World -> Option A

4. Quick Check:

   Regex removes non-letters/spaces = 'Hello World ' [OK]

Hint: [^...] means NOT those characters, so it removes digits and punctuation [OK]

Common Mistakes:

• Thinking digits remain after substitution
• Confusing character classes with ranges
• Ignoring spaces in the pattern

4. Identify the error in this regex code snippet for removing digits from text:

import re
text = "Price: 100 dollars"
cleaned = re.sub(r'\d', '', text)
print(cleaned)

medium

A. The pattern '\d' should be '\D' to remove digits

B. The backslash in '\d' is not escaped properly

C. The re.sub function is used incorrectly

D. The code will run correctly and remove digits

Solution

1. Step 1: Check regex pattern correctness

   The pattern r'\d' correctly matches digits (0-9).

2. Step 2: Verify code syntax and function usage

   The code uses raw string r'\d' which properly escapes the backslash, so digits are removed as intended.

3. Final Answer:

   The code will run correctly and remove digits -> Option D

4. Quick Check:

   r'\d' matches digits; re.sub removes them correctly [OK]

Hint: In raw strings, r'\d' matches digits; no extra escaping needed [OK]

Common Mistakes:

• Thinking '\d' needs double escaping outside raw strings
• Confusing '\d' with '\D' (non-digit)
• Assuming re.sub syntax is wrong

5. You want to clean a text dataset by removing all URLs and extra spaces. Which regex pattern and code snippet correctly achieves this in Python?

import re
text = "Visit https://example.com now!  Enjoy!"
cleaned = re.sub(_____, ' ', text)
cleaned = re.sub(r'\s+', ' ', cleaned).strip()
print(cleaned)

hard

A. r'http://[a-z]+'

B. r'https?://\S+'

C. r'www\.[a-z]+\.com'

D. r'https?://[a-z]+'

Solution

1. Step 1: Identify a regex pattern that matches URLs

   The pattern 'https?://' matches 'http://' or 'https://', and '\S+' matches non-space characters following it, capturing full URLs.

2. Step 2: Understand the code's cleaning steps

   First, URLs are replaced by a space, then multiple spaces are reduced to one, and leading/trailing spaces removed.

3. Final Answer:

   r'https?://\S+' -> Option B

4. Quick Check:

   Use 'https?://\S+' to remove URLs effectively [OK]

Hint: Use 'https?://' plus '\S+' to match full URLs [OK]

Common Mistakes:

• Using too narrow patterns missing https or full URL
• Not removing extra spaces after substitution
• Using patterns that match only partial URLs