The instructions for the coding test are as follows:" Votee would like to conduct the…
- User
The instructions for the coding test are as follows:"
Votee would like to conduct the coding test in a recorded live session. The idea is to connect to an API that plays a Wordle-like puzzle. You can find the API documentation at the following link: https://wordle.votee.dev:8000/redoc
Developers are allowed to use any frameworks, IDEs, chatbots, LLMs, or other resources to write their program and showcase their skill set. However, if you take references from other open-source projects or tutorials, please ensure that proper credit is given. Plagiarism will not be tolerated, and it may affect the evaluation of your application.
Your task is to write a program that automatically guesses random words against the API, using the following command as an example: curl -v ‘https://wordle.votee.dev:8000/random?guess=theft&seed=1234'" If I run curl -v ‘https://wordle.votee.dev:8000/random?guess=theft&seed=1234 in the terminal, the output: StatusCode : 200 StatusDescription : OK Content : [{"slot":0,"guess":"t","result":"correct"},{"slot":1,"guess":"h","result":"correct"},{"slot":2,"guess":"e","result":"correct"}, {"slot":3,"guess":"f","result":"correct"},{"slot":4,"guess":"t","result":... RawContent : HTTP/1.1 200 OK Content-Length: 211 Content-Type: application/json Date: Sun, 26 May 2024 08:27:33 GMT Server: uvicorn
[{"slot":0,"guess":"t","result":"correct"},{"slot":1,"guess":"h","result":...Forms : {} Headers : {[Content-Length, 211], [Content-Type, application/json], [Date, Sun, 26 May 2024 08:27:33 GMT], [Server, uvicorn]} Images : {} InputFields : {} Links : {} ParsedHtml : mshtml.HTMLDocumentClass RawContentLength : 211
My code to guess the words automatically and calculate the mean guess number of 100 words: "import requests import json
Load the word list
with open("/content/gdrive/MyDrive/wordle_guesses.txt", 'r') as file: word_list = [line.strip() for line in file.readlines()]
API base URL
base_url = 'https://wordle.votee.dev:8000/random'
def make_guess(guess, seed): response = requests.get(f"{base_url}?guess={guess}&seed={seed}") if response.status_code == 200: return response.json() else: print("Failed to make a guess.") return None
def filter_word_list(word_list, feedback): new_word_list = word_list[:] for feedback_item in feedback: slot = feedback_item['slot'] guess = feedback_item['guess'] result = feedback_item['result']
if result == 'correct': new_word_list = [word for word in new_word_list if word[slot] == guess] elif result == 'present': new_word_list = [word for word in new_word_list if guess in word and word[slot] != guess] elif result == 'absent': new_word_list = [word for word in new_word_list if guess not in word] return new_word_listdef solve_puzzle(seed): attempts = 0 current_word_list = word_list while attempts < 6: if not current_word_list: # Check if the list is empty print("No more words left to guess. Exiting.") return None
guess = current_word_list[0] # Initially, guess the first word in the list print(f"Attempt {attempts + 1}: Guessing '{guess}'...") feedback = make_guess(guess, seed) if feedback: print(f"Feedback: {json.dumps(feedback, indent=2)}") if all(item['result'] == 'correct' for item in feedback): print(f"Solved with guess: {guess}") return attempts + 1 current_word_list = filter_word_list(current_word_list, feedback) else: print("Error: No feedback received. Exiting.") return None attempts += 1 print("Failed to solve the puzzle within 6 attempts.") return Nonedef test_all_seeds(seeds): total_guesses = 0 for seed in seeds: print(f"Testing seed: {seed}") guesses = solve_puzzle(seed) if guesses is not None: total_guesses += guesses else: print(f"Could not solve puzzle for seed: {seed}")
mean_guesses = total_guesses / len(seeds) print(f"Mean number of guesses: {mean_guesses}")Example usage with a list of seeds
seeds = [1234, 2345, 3456, 4567] # This should be a list of seeds you want to test test_all_seeds(seeds)" Help me to make the loop faster, since it is too slow, can you make all guesses of the word at same time?
- Assistant
Sure, performing guesses sequentially and depending on real-time HTTP requests can indeed be slow. To make the loop faster, you can leverage asynchronous requests. This way, you can make multiple HTTP requests simultaneously, which can greatly speed up the process.
To achieve this, you can use the
aiohttplibrary along with Python'sasynciomodule. Below is an updated version of your code that makes the guesses asynchronously:-
First, you need to install
aiohttpif you haven't already:pip install aiohttp -
Here is the updated version of your code with asynchronous requests:
import aiohttp import asyncio import json # Load the word list with open("/content/gdrive/MyDrive/wordle_guesses.txt", 'r') as file: word_list = [line.strip() for line in file.readlines()] # API base URL base_url = 'https://wordle.votee.dev:8000/random' async def make_guess(session, guess, seed): async with session.get(f"{base_url}?guess={guess}&seed={seed}") as response: if response.status == 200: return await response.json() else: print("Failed to make a guess.") return None def filter_word_list(word_list, feedback): new_word_list = word_list[:] for feedback_item in feedback: slot = feedback_item['slot'] guess = feedback_item['guess'] result = feedback_item['result'] if result == 'correct': new_word_list = [word for word in new_word_list if word[slot] == guess] elif result == 'present': new_word_list = [word for word in new_word_list if guess in word and word[slot] != guess] elif result == 'absent': new_word_list = [word for word in new_word_list if guess not in word] return new_word_list async def solve_puzzle(session, seed): attempts = 0 current_word_list = word_list while attempts < 6: if not current_word_list: # Check if the list is empty print("No more words left to guess. Exiting.") return None guess = current_word_list[0] # Initially, guess the first word in the list print(f"Attempt {attempts + 1}: Guessing '{guess}'...") feedback = await make_guess(session, guess, seed) if feedback: print(f"Feedback: {json.dumps(feedback, indent=2)}") if all(item['result'] == 'correct' for item in feedback): print(f"Solved with guess: {guess}") return attempts + 1 current_word_list = filter_word_list(current_word_list, feedback) else: print("Error: No feedback received. Exiting.") return None attempts += 1 print("Failed to solve the puzzle within 6 attempts.") return None async def test_all_seeds(seeds): total_guesses = 0 async with aiohttp.ClientSession() as session: tasks = [solve_puzzle(session, seed) for seed in seeds] results = await asyncio.gather(*tasks) for guesses in results: if guesses is not None: total_guesses += guesses else: print(f"Could not solve puzzle for some seeds.") mean_guesses = total_guesses / len(seeds) print(f"Mean number of guesses: {mean_guesses}") # Example usage with a list of seeds seeds = [1234, 2345, 3456, 4567] # This should be a list of seeds you want to test # Run the async main method to test all seeds asyncio.run(test_all_seeds(seeds))This code leverages asynchronous HTTP requests to parallelize the guessing for multiple seeds, which should significantly speed up the execution time compared to making requests sequentially.
-
- User
RuntimeError Traceback (most recent call last) in <cell line: 84>() 82 83 # Run the async main method to test all seeds ---> 84 asyncio.run(test_all_seeds(seeds))
/usr/lib/python3.10/asyncio/runners.py in run(main, debug) 31 """ 32 if events._get_running_loop() is not None: ---> 33 raise RuntimeError( 34 "asyncio.run() cannot be called from a running event loop") 35
RuntimeError: asyncio.run() cannot be called from a running event loop
- Assistant
The
RuntimeError: asyncio.run() cannot be called from a running event looptypically occurs in environments like Jupyter notebooks, which already have a running event loop. To handle this, you need a workaround to execute your asynchronous code without running into this issue.One approach is to use
nest_asyncio, which allows you to nest calls toasyncio.runeven when an event loop is already running.Here is the updated code:
-
First, install the
nest_asynciopackage if you haven't already:pip install nest_asyncio -
Update your script to include the workaround:
import aiohttp import asyncio import json import nest_asyncio # Apply the nest_asyncio patch nest_asyncio.apply() # Load the word list with open("/content/gdrive/MyDrive/wordle_guesses.txt", 'r') as file: word_list = [line.strip() for line in file.readlines()] # API base URL base_url = 'https://wordle.votee.dev:8000/random' async def make_guess(session, guess, seed): async with session.get(f"{base_url}?guess={guess}&seed={seed}") as response: if response.status == 200: return await response.json() else: print("Failed to make a guess.") return None def filter_word_list(word_list, feedback): new_word_list = word_list[:] for feedback_item in feedback: slot = feedback_item['slot'] guess = feedback_item['guess'] result = feedback_item['result'] if result == 'correct': new_word_list = [word for word in new_word_list if word[slot] == guess] elif result == 'present': new_word_list = [word for word in new_word_list if guess in word and word[slot] != guess] elif result == 'absent': new_word_list = [word for word in new_word_list if guess not in word] return new_word_list async def solve_puzzle(session, seed): attempts = 0 current_word_list = word_list while attempts < 6: if not current_word_list: # Check if the list is empty print("No more words left to guess. Exiting.") return None guess = current_word_list[0] # Initially, guess the first word in the list print(f"Attempt {attempts + 1}: Guessing '{guess}'...") feedback = await make_guess(session, guess, seed) if feedback: print(f"Feedback: {json.dumps(feedback, indent=2)}") if all(item['result'] == 'correct' for item in feedback): print(f"Solved with guess: {guess}") return attempts + 1 current_word_list = filter_word_list(current_word_list, feedback) else: print("Error: No feedback received. Exiting.") return None attempts += 1 print("Failed to solve the puzzle within 6 attempts.") return None async def test_all_seeds(seeds): total_guesses = 0 async with aiohttp.ClientSession() as session: tasks = [solve_puzzle(session, seed) for seed in seeds] results = await asyncio.gather(*tasks) for guesses in results: if guesses is not None: total_guesses += guesses else: print(f"Could not solve puzzle for some seeds.") mean_guesses = total_guesses / len(seeds) print(f"Mean number of guesses: {mean_guesses}") # Example usage with a list of seeds seeds = [1234, 2345, 3456, 4567] # This should be a list of seeds you want to test # Run the async main method to test all seeds await test_all_seeds(seeds)By applying the
nest_asynciopatch, you enable callingawaitandasyncio.runfunctions inside an already running event loop, making it compatible with Jupyter notebooks and similar environments. -
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.