Document loading and parsing in Prompt Engineering / GenAI - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the output of this document parsing code?

Consider the following code that loads and parses a JSON document string. What will be the value of parsed_data after running this code?

Prompt Engineering / GenAI

import json
json_string = '{"name": "Alice", "age": 30, "skills": ["Python", "ML"]}'
parsed_data = json.loads(json_string)

A {'name': 'Alice', 'age': 30, 'skills': ['Python', 'ML']}

B {"name": "Alice", "age": 30, "skills": ["Python", "ML"]}

C {'name': "Alice", 'age': 30, 'skills': ["Python", "ML"]}

D {"name": 'Alice', "age": 30, "skills": ['Python', 'ML']}

💡 Hint

Remember that json.loads converts JSON strings into Python dictionaries with single quotes.

The json.loads function converts the JSON string into a Python dictionary. Python dictionaries use single quotes for string keys and values when printed.

🧠 Conceptual

intermediate

Which format is best for loading structured text documents for ML?

You want to load a large collection of structured text documents for machine learning. Which document format is most suitable for easy parsing and extracting fields?

A Binary files with custom encoding

B Plain text files with no structure

C Encrypted PDF files

D CSV files with columns for each field

💡 Hint

Think about formats that clearly separate data fields for easy extraction.

CSV files organize data in rows and columns, making it easy to parse and extract fields for ML tasks.

❓ Metrics

advanced

How to measure parsing success rate on a document dataset?

You have a dataset of 1000 documents to parse. Your parser successfully extracts data from 920 documents without errors. What is the parsing success rate?

A 100%

B 8%

C 92%

D 90%

💡 Hint

Success rate = (number of successful parses / total documents) * 100

Parsing success rate is the percentage of documents parsed without errors: (920/1000)*100 = 92%.

🔧 Debug

advanced

Why does this XML parsing code raise an error?

This code tries to parse an XML document but raises an error. What is the cause?

Prompt Engineering / GenAI

import xml.etree.ElementTree as ET
xml_string = '<root><item>Value</item></root>'
root = ET.parse(xml_string)

A ET.parse expects a file path or file object, not a string of XML content

B The XML string is malformed and missing closing tags

C ET.parse cannot parse XML with nested tags

D The xml.etree.ElementTree module is not imported correctly

💡 Hint

Check the expected input type for ET.parse.

ET.parse expects a filename or file object, not a string containing XML data. To parse a string, use ET.fromstring instead.

❓ Model Choice

expert

Which model is best for extracting structured data from scanned document images?

You have scanned images of invoices and want to extract structured fields like date, total, and vendor name. Which AI model type is best suited for this task?

A Convolutional Neural Network (CNN) for image classification

B Optical Character Recognition (OCR) combined with Named Entity Recognition (NER)

C Generative Adversarial Network (GAN) for image generation

D Recurrent Neural Network (RNN) for time series prediction

💡 Hint

Think about models that convert images to text and then extract information.

OCR converts images to text, and NER extracts structured fields from text, making this combination ideal for scanned document data extraction.