Text cleaning pipeline in Data Analysis Python - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of basic text cleaning with lowercasing and punctuation removal

What is the output of this Python code that cleans a text by making it lowercase and removing punctuation?

Data Analysis Python

import string
text = "Hello, World! Welcome to Data Science."
cleaned = ''.join(ch for ch in text.lower() if ch not in string.punctuation)
print(cleaned)

A hello world welcome to data science

B Hello World Welcome to Data Science

C hello, world! welcome to data science.

D HELLO WORLD WELCOME TO DATA SCIENCE

💡 Hint

Think about what happens when you convert text to lowercase and remove punctuation characters.

The code converts the text to lowercase and removes all punctuation characters, resulting in a clean string with only lowercase letters and spaces.

❓ data_output

intermediate

Result of tokenizing and removing stopwords from text

Given the following code that tokenizes text and removes common stopwords, what is the resulting list?

Data Analysis Python

text = "Data science is fun and exciting"
stopwords = {'is', 'and'}
tokens = text.lower().split()
filtered = [word for word in tokens if word not in stopwords]
print(filtered)

A ['data', 'science', 'is', 'fun', 'and', 'exciting']

B ['Data', 'science', 'fun', 'exciting']

C ['data', 'science', 'fun', 'exciting']

D ['data', 'science', 'fun', 'and', 'exciting']

💡 Hint

Stopwords are removed after converting all words to lowercase.

The code splits the text into lowercase words, then removes the stopwords 'is' and 'and', leaving only the meaningful words.

🔧 Debug

advanced

Identify the error in this text cleaning function

What error does this code raise when trying to clean text by removing digits and extra spaces?

Data Analysis Python

def clean_text(text):
    import re
    text = re.sub(r'\d+', '', text)
    text = re.sub(r'\s+', ' ', text).strip()
    return text

print(clean_text('Data 123 science 456'))

A No error, output: 'Data science'

B SyntaxError: invalid syntax

C AttributeError: 'str' object has no attribute 'sub'

D TypeError: 'builtin_function_or_method' object is not callable

💡 Hint

Check how the strip method is used in the code.

The strip method is referenced without parentheses, so it is a method object, not called. Trying to use it as a string causes a TypeError.

❓ visualization

advanced

Visualizing word frequency after cleaning text

Which option shows the correct bar chart output for the word frequencies after cleaning and tokenizing the text?

Data Analysis Python

import matplotlib.pyplot as plt
from collections import Counter
text = "Data science is fun. Data science is exciting."
words = [w.lower().strip('.!') for w in text.split()]
counter = Counter(words)
plt.bar(counter.keys(), counter.values())
plt.show()

A Bar chart with words ['data', 'science', 'is', 'fun', 'exciting'] and counts [1, 1, 1, 1, 1]

B Bar chart with words ['data', 'science', 'is', 'fun', 'exciting'] and counts [2, 2, 2, 1, 1]

C Bar chart with words ['Data', 'science', 'is', 'fun', 'exciting'] and counts [2, 2, 2, 1, 1]

D Bar chart with words ['data', 'science', 'fun', 'exciting'] and counts [2, 2, 1, 1]

💡 Hint

Check how words are lowercased and punctuation is stripped before counting.

The code lowercases words and removes punctuation, then counts each word's frequency correctly, resulting in counts 2 for 'data', 'science', 'is' and 1 for 'fun', 'exciting'.

🚀 Application

expert

Predict the output of a complex text cleaning pipeline

Given this pipeline that removes URLs, lowercases, removes stopwords, and lemmatizes, what is the final list of words?

Data Analysis Python

import re
from nltk.stem import WordNetLemmatizer
text = "Visit https://example.com for data science tutorials! Data scientists love data."
text = re.sub(r'https?://\S+', '', text)
text = text.lower()
stopwords = {'for', 'is', 'the', 'and', 'a', 'of'}
words = text.split()
words = [w for w in words if w not in stopwords]
lemmatizer = WordNetLemmatizer()
words = [lemmatizer.lemmatize(w) for w in words]
print(words)

A ['visit', 'data', 'science', 'tutorial', 'data', 'scientist', 'love', 'data']

B ['visit', 'data', 'science', 'tutorials', 'data', 'scientists', 'love', 'data']

C ['visit', 'data', 'science', 'tutorials!', 'data', 'scientist', 'love', 'data.']

D ['visit', 'data', 'science', 'tutorial', 'data', 'scientists', 'love', 'data']

💡 Hint

Remember lemmatizer converts plurals to singular and removes punctuation only if stripped before lemmatization.

URLs are removed, text lowercased, stopwords removed, then lemmatizer converts 'tutorials' to 'tutorial' and 'scientists' to 'scientist'. Punctuation remains on 'tutorials!' and 'data.' if not stripped, so option A is correct because punctuation is removed by split and lemmatizer output.