Spaces:
Sleeping
Sleeping
| import json | |
| import random | |
| # ========================== | |
| # CODING & DEVELOPER DATA CREATOR | |
| # ========================== | |
| coding_examples = [ | |
| ("Write a Python function to reverse a string.", | |
| "def reverse_string(s):\n return s[::-1]"), | |
| ("Explain what a class is in Python.", | |
| "A class is a blueprint for creating objects. It defines attributes and methods that its objects will have."), | |
| ("Fix this Python error: TypeError: 'int' object is not iterable.", | |
| "You are likely trying to loop over an integer. Use range() or convert it to an iterable."), | |
| ("Write a JavaScript function to check if a number is even.", | |
| "function isEven(num) {\n return num % 2 === 0;\n}"), | |
| ("Explain how async/await works in JavaScript.", | |
| "Async/await allows asynchronous code to be written in a synchronous style using Promises under the hood."), | |
| ("Write a simple React component that shows 'Hello World'.", | |
| "function HelloWorld() {\n return <h1>Hello World</h1>;\n}\nexport default HelloWorld;"), | |
| ("Explain what Big O notation is.", | |
| "Big O notation describes how the runtime or space requirements of an algorithm grow relative to the input size."), | |
| ("Create a function in C++ that returns the factorial of a number.", | |
| "int factorial(int n) {\n return (n <= 1) ? 1 : n * factorial(n - 1);\n}"), | |
| ("Explain what an API is.", | |
| "An API (Application Programming Interface) allows two systems to communicate by exposing data or functions programmatically."), | |
| ("Write a SQL query to select all users older than 25.", | |
| "SELECT * FROM users WHERE age > 25;"), | |
| ("Explain what recursion is.", | |
| "Recursion is when a function calls itself to solve smaller instances of a problem."), | |
| ("Write a Python program to check if a string is a palindrome.", | |
| "def is_palindrome(s):\n s = s.lower().replace(' ', '')\n return s == s[::-1]"), | |
| ("Explain what a REST API is.", | |
| "A REST API uses HTTP methods (GET, POST, PUT, DELETE) to manage resources identified by URLs."), | |
| ("Write a JavaScript program to fetch data from an API.", | |
| "fetch('https://api.example.com/data')\n .then(res => res.json())\n .then(data => console.log(data));"), | |
| ("Explain the difference between == and === in JavaScript.", | |
| "== compares values with type coercion, while === compares both value and type."), | |
| ("Write a Python decorator that logs function calls.", | |
| "def log_calls(func):\n def wrapper(*args, **kwargs):\n print(f'Calling {func.__name__}')\n return func(*args, **kwargs)\n return wrapper"), | |
| ("Explain what machine learning is.", | |
| "Machine learning is a branch of AI where algorithms learn patterns from data to make predictions or decisions without being explicitly programmed."), | |
| ("Write a Python list comprehension to get squares of numbers from 1 to 10.", | |
| "[x**2 for x in range(1, 11)]"), | |
| ("Explain the difference between list and tuple in Python.", | |
| "A list is mutable (can be changed), while a tuple is immutable (cannot be changed)."), | |
| ("Explain how Git works.", | |
| "Git is a version control system that tracks changes in code and allows collaboration through commits and branches.") | |
| ] | |
| # ========================== | |
| # GENERATE EXTENDED DATASET | |
| # ========================== | |
| dataset = [] | |
| for _ in range(1000): # Generate 1000 examples | |
| instruction, response = random.choice(coding_examples) | |
| dataset.append({ | |
| "category": "coding", | |
| "instruction": instruction, | |
| "response": response | |
| }) | |
| # ========================== | |
| # SAVE TO JSONL | |
| # ========================== | |
| output_file = "coding_ai_dataset.jsonl" | |
| with open(output_file, "w", encoding="utf-8") as f: | |
| for ex in dataset: | |
| f.write(json.dumps(ex, ensure_ascii=False) + "\n") | |
| print(f"✅ Created {len(dataset)} coding & dev examples.") | |
| print(f"📄 Saved as {output_file}") | |