import re

import re

# Sample dataset labels
labels = [
    "AI_Vision_Model",
    "AI_NLP_Model",
    "AI_Generative_Model",
    "ML_Regression_Model",
    "AI_Chatbot_System"
]

# Regular expression pattern to match labels
# ^AI_  -> Ensures the label starts with "AI_"
# .*    -> Matches any characters in between
# _Model$ -> Ensures the label ends with "_Model"
# re.search(pattern, label) -> Checks if each label matches the pattern.
pattern = r"^AI_.*_Model$"

# Checking each label against the pattern
for label in labels:
    if re.search(pattern, label):
        print(f"Match: {label}")
    else:
        print(f"No Match: {label}")

Match: AI_Vision_Model
Match: AI_NLP_Model
Match: AI_Generative_Model
No Match: ML_Regression_Model
No Match: AI_Chatbot_System

import re

# Sample AI-related text
text = "Machine Learning, Deep Learning, and AI are evolving rapidly."

# Regular expression pattern to find occurrences of "Learning"
pattern = r"\bLearning\b"  # \b ensures exact word match

# Extract all occurrences of the pattern
matches = re.findall(pattern, text)

print("Matches found:", matches)
### Output: Matches found: ['Learning', 'Learning']

Matches found: ['Learning', 'Learning']

import re

text = "Neural networks power modern AI models."

# Trying to find the word "Learning"
pattern = r"\bLearning\b"
matches = re.findall(pattern, text)

# Checking if any matches were found
if matches:
    print("Matches found:", matches)
else:
    print("No matches found.")

### Output: No matches found.

No matches found.

import re

# Sample dataset text
text = "AI models have 98% accuracy, and 87% of users prefer AI-based tools."

# Regular expression pattern to find the first number
pattern = r"\d+"

# Searching for the first number in the text
match = re.search(pattern, text)

if match:
    print("First number found:", match.group())  # Extract the matched number
else:
    print("No number found in the text.")

### Output: First number found: 98

First number found: 98

import re

# Sample text
text = "AI is powerful. It transforms industries! Can we keep up?"

# Regular expression pattern to split sentences using punctuation
pattern = r"[.!?]"

# Splitting the text
sentences = re.split(pattern, text)

# Removing empty strings from the list
sentences = [s.strip() for s in sentences if s.strip()]

print("Split sentences:", sentences)
### Output: Split sentences: ['AI is powerful', 'It transforms industries', 'Can we keep up']

Split sentences: ['AI is powerful', 'It transforms industries', 'Can we keep up']

text = "AI is evolving fast. New models emerge daily."

# Split only at the first punctuation mark
sentences = re.split(r"[.!?]", text, maxsplit=1)

print("Limited split:", sentences)
### Output: Limited split: ['AI is evolving fast', ' New models emerge daily.']

Limited split: ['AI is evolving fast', ' New models emerge daily.']

import re

# Sample AI-related text
text = "Deep Learning and AI models are advancing."

# Regular expression pattern to replace "AI" and "Deep Learning" with "ML"
pattern = r"(AI|Deep Learning)"

# Replacing occurrences with "ML"
updated_text = re.sub(pattern, "ML", text)

print("Updated text:", updated_text)
### Output: Updated text: ML and ML models are advancing.

Updated text: ML and ML models are advancing.

text = "AI is evolving. AI is everywhere."

# Replace only the first occurrence of "AI"
updated_text = re.sub(r"AI", "ML", text, count=1)

print("Updated text:", updated_text)
### Output: Updated text: ML is evolving. AI is everywhere.

Updated text: ML is evolving. AI is everywhere.

import re

# Sample text
text = "Natural Language Processing (NLP) and Deep Learning are part of AI."

# Regular expression pattern to find "AI"
pattern = r"AI"

# Searching for the first occurrence of "AI"
match = re.search(pattern, text)

# Printing the Match Object
print("Match Object:", match)  # Output: <re.Match object; span=(64, 66), match='AI'>

Match Object: <re.Match object; span=(64, 66), match='AI'>

import re

# Sample text
text = "Machine Learning and AI are transforming industries."

# Searching for "AI"
match = re.search(r"AI", text)

if match:
    print("Match Position (Start, End):", match.span())  # Output: (21, 23)
### Output: Match Position (Start, End): (21, 23)

Match Position (Start, End): (21, 23)

import re

# Sample text
text = "Data Science and AI are shaping the future."

# Searching for "AI"
match = re.search(r"AI", text)

if match:
    print("Original String:", match.string)
### Output: Original String: Data Science and AI are shaping the future.

Original String: Data Science and AI are shaping the future.

import re

# Sample text
text = "Generative AI is revolutionizing content creation."

# Searching for "AI"
match = re.search(r"AI", text)

if match:
    print("Matched Text:", match.group())  # Output: AI
### Output: Matched Text: AI

Matched Text: AI

import re

text = "AI is changing the world of technology."

# Using match() – Only matches if "AI" is at the beginning
match_start = re.match(r"AI", text)
print("match() result:", match_start)  # Output: <re.Match object; span=(0, 2), match='AI'>

# Using search() – Matches "AI" anywhere in the string
match_anywhere = re.search(r"AI", text)
print("search() result:", match_anywhere)  # Output: <re.Match object; span=(0, 2), match='AI'>

match() result: <re.Match object; span=(0, 2), match='AI'>
search() result: <re.Match object; span=(0, 2), match='AI'>

import re

text = "Intensity Coding and AI Learning"

# Find all letters from 'a' to 'm'
matches = re.findall("[a-m]", text)

print("Matched characters:", matches)
### Output: Matched characters: ['e', 'i', 'd', 'i', 'g', 'a', 'd', 'e', 'a', 'i', 'g']

Matched characters: ['e', 'i', 'd', 'i', 'g', 'a', 'd', 'e', 'a', 'i', 'g']

import re

text = "The AI model achieved 99% accuracy with 5000 training samples."

# Find all digits in the text
matches = re.findall("\d", text)

print("Matched digits:", matches)
# Output:
# Matched digits: ['9', '9', '5', '0', '0', '0']

Matched digits: ['9', '9', '5', '0', '0', '0']

import re

text = "Intensity Insight AI Int99ity In56ity"

# Match pattern: "In" followed by any two characters, then "ity"
matches = re.findall("In..ity", text)

print("Matched words:", matches)
### Output: Matched words: ['In56ity']

Matched words: ['In56ity']

import re

text = "Intensity Coding is a platform for AI and ML tutorials"

# Check if text starts with "Intensity"
if re.findall("^Intensity", text):
    print("Text starts with 'Intensity'.")

# Check if text ends with "Coding"
if re.findall("Coding$", text):
    print("Text ends with 'Coding'.")
else:
    print("No match found.")
## Output
# Text starts with 'Intensity'.
# No match found.

Text starts with 'Intensity'.
No match found.

import re

text = "Intensity Insight AI Int99ity Inity"

# Match 'In' followed by 0 or more characters before 'ity'
# Non-greedy match: makes sure it stops at the first possible "ity"
matches_star = re.findall("In.*?ity", text)

# Match 'In' followed by 1 or more characters before 'ity'
# Non-greedy match: makes sure it stops at the first possible "ity"
matches_plus = re.findall("In.+?ity", text)

# Match 'In' followed by 0 or 1 character before 'ity'
matches_question = re.findall("In.?ity", text)

print("Matches (*):", matches_star)
print("Matches (+):", matches_plus)
print("Matches (?):", matches_question)
### Output:
# Matches (*): ['Intensity', 'Insight AI Int99ity', 'Inity']
# Matches (+): ['Intensity', 'Insight AI Int99ity']
# Matches (?): ['Inity']

Matches (*): ['Intensity', 'Insight AI Int99ity', 'Inity']
Matches (+): ['Intensity', 'Insight AI Int99ity']
Matches (?): ['Inity']

import re

text = "Intensity In55ity Int99ity Int888ity"

# Match 'In' followed by exactly 2 characters before 'ity'
matches = re.findall("In.{2}ity", text)

print("Matched words:", matches)
### Output
# Matched words: ['In55ity']

Matched words: ['In55ity']

import re

text = "Intensity Coding focuses on AI and ML concepts."

# Search for 'AI' or 'ML'
matches = re.findall("AI|ML", text)

if matches:
    print("Match found:", matches)
else:
    print("No match found.")

### Output
#Match found: ['AI', 'ML']

Match found: ['AI', 'ML']

import re

text = "Intensity Coding"
# Find occurrences of 'a', 'g', or 'n'
matches = re.findall("[agn]", text)

print(matches)  # Output: ['n', 'n', 'n', 'g']

['n', 'n', 'n', 'g']

text = "Intensity Coding"
# Find lowercase letters between 'a' and 'n'
matches = re.findall("[a-n]", text)

print(matches)  # Output: ['n', 'e', 'n', 'i', 'd', 'i', 'n', 'g']

['n', 'e', 'n', 'i', 'd', 'i', 'n', 'g']

text = "Intensity Coding"
# Find characters that are NOT 'a', 'g', or 'n'
matches = re.findall("[^agn]", text)

print(matches)  # Output: ['I', 't', 'e', 's', 'i', 't', 'y', ' ', 'C', 'o', 'd', 'i']

['I', 't', 'e', 's', 'i', 't', 'y', ' ', 'C', 'o', 'd', 'i']

text = "Intensity Coding was founded in 2023."
# Find occurrences of '0', '1', '2', or '3'
matches = re.findall("[0123]", text)

print(matches)  # Output: ['2', '0', '2', '3']

['2', '0', '2', '3']

text = "AI models have been trained on 500,000+ datasets."
# Find all digits (0-9)
matches = re.findall("[0-9]", text)

print(matches)  # Output: ['5', '0', '0', '0', '0', '0']

['5', '0', '0', '0', '0', '0']

text = "Training started at 09:45 AM."
# Find two-digit numbers between 00 and 59
matches = re.findall("[0-5][0-9]", text)

print(matches)  # Output: ['09', '45']

['09', '45']

text = "NLP and Computer Vision are AI fields."
# Find all alphabetic characters
matches = re.findall("[a-zA-Z]", text)

print(matches)
# Output: ['N', 'L', 'P', 'a', 'n', 'd', 'C', 'o', 'm', 'p', 'u', 't', 'e', 'r', 'V', 'i', 's', 'i', 'o', 'n', 'a', 'r', 'e', 'A', 'I', 'f', 'i', 'e', 'l', 'd', 's']

['N', 'L', 'P', 'a', 'n', 'd', 'C', 'o', 'm', 'p', 'u', 't', 'e', 'r', 'V', 'i', 's', 'i', 'o', 'n', 'a', 'r', 'e', 'A', 'I', 'f', 'i', 'e', 'l', 'd', 's']

import re

text = "The accuracy increased by +7% after tuning."
# Find occurrences of the '+' character
# In a set [], special characters like + lose their special meaning
# So, "[+]" will match the literal '+' character in the string
matches = re.findall("[+]", text)

print(matches)
# Output: ['+']

['+']

import re

text = "Intensity Coding provides AI tutorials."
# Check if the string starts with 'Intensity'
matches = re.findall("\AIntensity", text)

print(matches)
# Output: ['Intensity']

if matches:
    print("Yes, the string starts with 'Intensity'!")
else:
    print("No match found.")
# Output: Yes, the string starts with 'Intensity'!

['Intensity']
Yes, the string starts with 'Intensity'!

text = "AI is revolutionizing technology."
# Check if 'AI' is at the start of a word
matches = re.findall(r"\bAI", text)

print(matches)  # Output: ['AI']

if matches:
    print("Yes, 'AI' appears at the beginning of a word!")
else:
    print("No match found.")

# Output: Yes, 'AI' appears at the beginning of a word!

['AI']
Yes, 'AI' appears at the beginning of a word!

import re

text = "The latest advancements in AI are impressive."
# Check if 'AI' is at the end of a word
matches = re.findall(r"AI\b", text)

print(matches)
# Output: ['AI']

if matches:
    print("Yes, 'AI' appears at the end of a word!")
else:
    print("No match found.")

# Output:
# Yes, 'AI' appears at the end of a word!

['AI']
Yes, 'AI' appears at the end of a word!

text = "Brainpower is essential in AI research."
# Check if 'ain' appears inside a word (not at the beginning or end)
matches = re.findall(r"\Bain", text)

print(matches)
# Output: ['ain']

if matches:
    print("Yes, 'ain' appears inside a word!")
else:
    print("No match found.")
# Output: Yes, 'ain' appears inside a word!

['ain']
Yes, 'ain' appears inside a word!

text = "The accuracy improved by 98%."
# Find all numeric digits
matches = re.findall("\d", text)

print(matches)  # Output: ['9', '8']

if matches:
    print("Yes, the string contains digits!")
else:
    print("No match found.")
# Output: Yes, the string contains digits!

['9', '8']
Yes, the string contains digits!

text = "ML models reached 99% accuracy."
# Find all non-digit characters
matches = re.findall("\D", text)

print(matches)
# Output: ['M', 'L', ' ', 'm', 'o', 'd', 'e', 'l', 's', ' ', 'r', 'e', 'a', 'c', 'h', 'e', 'd', ' ', '%', ' ', 'a', 'c', 'c', 'u', 'r', 'a', 'c', 'y', '.']

if matches:
    print("Yes, the string contains non-digit characters!")
else:
    print("No match found.")

# Output:
# Yes, the string contains non-digit characters!

['M', 'L', ' ', 'm', 'o', 'd', 'e', 'l', 's', ' ', 'r', 'e', 'a', 'c', 'h', 'e', 'd', ' ', '%', ' ', 'a', 'c', 'c', 'u', 'r', 'a', 'c', 'y', '.']
Yes, the string contains non-digit characters!

text = "Deep Learning improves AI performance."
# Find all whitespace characters
matches = re.findall("\s", text)

print(matches)
# Output: [' ', ' ', ' ', ' ']

if matches:
    print("Yes, the string contains whitespace characters!")
else:
    print("No match found.")

# Output:
# Yes, the string contains whitespace characters!

[' ', ' ', ' ', ' ']
Yes, the string contains whitespace characters!

text = "AI models are evolving!"
# Find all non-whitespace characters
matches = re.findall("\S", text)

print(matches)
# Output: ['A', 'I', 'm', 'o', 'd', 'e', 'l', 's', 'a', 'r', 'e', 'e', 'v', 'o', 'l', 'v', 'i', 'n', 'g', '!']

if matches:
    print("Yes, the string contains non-whitespace characters!")
else:
    print("No match found.")

# Output:
# Yes, the string contains non-whitespace characters!

['A', 'I', 'm', 'o', 'd', 'e', 'l', 's', 'a', 'r', 'e', 'e', 'v', 'o', 'l', 'v', 'i', 'n', 'g', '!']
Yes, the string contains non-whitespace characters!

text = "AI_2025 is the future of automation."
# Find all word characters
matches = re.findall("\w", text)

print(matches)
# Output: ['A', 'I', '_', '2', '0', '2', '5', 'i', 's', 't', 'h', 'e', 'f', 'u', 't', 'u', 'r', 'e', 'o', 'f', 'a', 'u', 't', 'o', 'm', 'a', 't', 'i', 'o', 'n']

if matches:
    print("Yes, the string contains word characters!")
else:
    print("No match found.")

# Output:
# Yes, the string contains word characters!

['A', 'I', '_', '2', '0', '2', '5', 'i', 's', 't', 'h', 'e', 'f', 'u', 't', 'u', 'r', 'e', 'o', 'f', 'a', 'u', 't', 'o', 'm', 'a', 't', 'i', 'o', 'n']
Yes, the string contains word characters!

import re

text = "AI-powered tools: fast, reliable & scalable!"
# Find all non-word characters (!, ?, whitespace, etc.)
matches = re.findall("\W", text)

print(matches)
# Output: ['-', ' ', ':', ' ', ',', ' ', ' ', '&', ' ', '!']

if matches:
    print("Yes, the string contains non-word characters!")
else:
    print("No match found.")

# Output:
# Yes, the string contains non-word characters!

['-', ' ', ':', ' ', ',', ' ', ' ', '&', ' ', '!']
Yes, the string contains non-word characters!

import re

text = "Machine Learning is the future of AI."
# Check if the string ends with 'AI.'
matches = re.findall("AI\Z", text)

print(matches)
# Output: []

if matches:
    print("Yes, the string ends with 'AI'!")
else:
    print("No match found.")

# Output:
# []
# No match found.

[]
No match found.

# Let's modify the text to make it match
text2 = "The future of AI"
matches2 = re.findall("AI\Z", text2)

print(matches2)
# Output: ['AI']

if matches2:
    print("Yes, the string ends with 'AI'!")
else:
    print("No match found.")

# Output:
# Yes, the string ends with 'AI'!

['AI']
Yes, the string ends with 'AI'!

Function	Description
`findall()`	Returns a list of all matches in a string.
`search()`	Returns a Match object for the first match found.
`split()`	Splits a string at each match and returns a list.
`sub()`	Replaces occurrences of a pattern with a specified string.

Function	Behavior
`match()`	Checks for a match only at the beginning of the string.
`search()`	Checks for a match anywhere in the string.

Set Pattern	Description
`[agn]`	Matches any occurrence of 'a', 'g', or 'n'.
`[a-n]`	Matches any lowercase letter between 'a' and 'n'.
`[^agn]`	Matches any character except 'a', 'g', or 'n'.
`[0123]`	Matches any occurrence of '0', '1', '2', or '3'.
`[0-9]`	Matches any digit from '0' to '9'.
`[0-5][0-9]`	Matches any two-digit number between '00' and '59'.
`[a-zA-Z]`	Matches any lowercase or uppercase letter from 'a' to 'z'.
`[+]`	Matches the literal `+` character. Special characters inside sets lose their special meaning.

Character	Description	Example
`\A`	Matches the start of the string.	`\AThe`
`\b`	Matches the start or end of a word (word boundary).	`r"\bAI"` or `r"AI\b"`
`\B`	Matches characters inside a word (not at the start or end).	`r"\BAI"`
`\d`	Matches any digit (`0-9`).	`"\d"`
`\D`	Matches any non-digit.	`"\D"`
`\s`	Matches any whitespace (space, tab, newline).	`"\s"`
`\S`	Matches any non-whitespace character.	`"\S"`
`\w`	Matches word characters (`a-z`, `A-Z`, `0-9`, `_`).	`"\w"`
`\W`	Matches non-word characters (`!`, `?`, whitespace, etc.).	`"\W"`
`\Z`	Matches the end of the string.	`"coding\Z"`

Python Regular Expressions (RegEx)

Python Regular Expressions (RegEx)¶

Introduction to Regular Expressions¶

Why Use RegEx?¶

Python's re Module¶

RegEx Functions¶

1. findall() – Extracting All Matches¶

Handling No Matches¶

2. search() – Finding the First Match¶

3. split() – Splitting Text Based on a Pattern¶

Limiting the Number of Splits¶

4. sub() – Replacing Text Using a Pattern¶

Limiting the Number of Replacements¶

RegEx Match Object¶

Why Use Match Objects?¶

Using search() to Get a Match Object¶

Match Object Methods¶

1. .span() – Get Start and End Position of the Match¶

2. .string – Get the Original Search String¶

3. .group() – Get the Matched Text¶

Difference Between match() and search()¶

RegEx Metacharacters¶

Common Metacharacters in RegEx¶

Metacharacters in Action (Code Examples)¶

1. [] – Match Specific Character Sets¶

2. \d – Find Digits in Text¶

3. . – Match Any Character Except Newline¶

4. ^ and $ – Match Start and End of String¶

5. *, +, ? – Match Repeating Characters¶

6. {} – Match Exact Number of Characters¶

7. | – Match Either Condition¶

RegEx Sets¶

Common Set Patterns in Regular Expressions¶

Examples Using Regular Expression Sets¶

1. Matching Specific Characters ([agn])¶

2. Matching Characters in a Range ([a-n])¶

3. Matching Characters Except Certain Ones ([^agn])¶

4. Finding Specific Digits ([0123])¶

5. Finding Any Numeric Digit ([0-9])¶

6. Matching Two-Digit Numbers (Range 00-59)¶

7. Finding Uppercase and Lowercase Letters ([a-zA-Z])¶

8. Finding Special Characters ([+])¶

RegEx Special Sequences¶

Common Special Sequences in RegEx¶

Examples Using Special Sequences¶

1. Checking if a String Starts with a Specific Word (\A)¶

2. Finding a Word at the Start or End (\b)¶

3. Finding a Word Inside, but Not at the Boundary (\B)¶

4. Finding Digits (\d)¶

5. Finding Non-Digit Characters (\D)¶

6. Finding Whitespaces (\s)¶

7. Finding Non-Whitespace Characters (\S)¶

8. Finding Word Characters (\w)¶

9. Finding Non-Word Characters (\W)¶

10. Checking if a String Ends with a Specific Word (\Z)¶

Contact Form

Python's `re` Module¶

Using `search()` to Get a Match Object¶

1. `.span()` – Get Start and End Position of the Match¶

2. `.string` – Get the Original Search String¶

3. `.group()` – Get the Matched Text¶

Difference Between `match()` and `search()`¶

1. `[]` – Match Specific Character Sets¶

2. `\d` – Find Digits in Text¶

3. `.` – Match Any Character Except Newline¶

4. `^` and `$` – Match Start and End of String¶

**5. `*`, `+`, `?` – Match Repeating Characters**¶

6. `{}` – Match Exact Number of Characters¶

7. `|` – Match Either Condition¶

1. Matching Specific Characters (`[agn]`)¶

2. Matching Characters in a Range (`[a-n]`)¶

3. Matching Characters Except Certain Ones (`[^agn]`)¶

4. Finding Specific Digits (`[0123]`)¶

5. Finding Any Numeric Digit (`[0-9]`)¶

6. Matching Two-Digit Numbers (Range `00-59`)¶

7. Finding Uppercase and Lowercase Letters (`[a-zA-Z]`)¶

8. Finding Special Characters (`[+]`)¶

1. Checking if a String Starts with a Specific Word (`\A`)¶

2. Finding a Word at the Start or End (`\b`)¶

3. Finding a Word Inside, but Not at the Boundary (`\B`)¶

4. Finding Digits (`\d`)¶

5. Finding Non-Digit Characters (`\D`)¶

6. Finding Whitespaces (`\s`)¶

7. Finding Non-Whitespace Characters (`\S`)¶

8. Finding Word Characters (`\w`)¶

9. Finding Non-Word Characters (`\W`)¶

10. Checking if a String Ends with a Specific Word (`\Z`)¶