{ "cells": [ { "cell_type": "markdown", "id": "4a6ab9a2-28a2-445d-8512-a0dc8d1b54e9", "metadata": {}, "source": [ "# Code Commenter\n", "\n", "The requirement: use an LLM to generate docstring and comments for Python code\n", "\n", "This is my week 4 day 5 project. \n", "\n", "Note: I used gpt to find out the most effective system and user prompt (very effective). I also decided not to use the open source models due to inference api costs with HF" ] }, { "cell_type": "code", "execution_count": 1, "id": "e610bf56-a46e-4aff-8de1-ab49d62b1ad3", "metadata": {}, "outputs": [], "source": [ "# imports\n", "\n", "import os\n", "import io\n", "import sys\n", "import json\n", "import requests\n", "from dotenv import load_dotenv\n", "from openai import OpenAI\n", "import google.generativeai\n", "import anthropic\n", "from IPython.display import Markdown, display, update_display\n", "import gradio as gr\n", "import subprocess" ] }, { "cell_type": "code", "execution_count": 2, "id": "4f672e1c-87e9-4865-b760-370fa605e614", "metadata": {}, "outputs": [], "source": [ "# environment\n", "\n", "load_dotenv()\n", "os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY', 'your-key-if-not-using-env')\n", "os.environ['ANTHROPIC_API_KEY'] = os.getenv('ANTHROPIC_API_KEY', 'your-key-if-not-using-env')\n", "google_api_key = os.getenv('GOOGLE_API_KEY')\n" ] }, { "cell_type": "code", "execution_count": 3, "id": "8aa149ed-9298-4d69-8fe2-8f5de0f667da", "metadata": {}, "outputs": [], "source": [ "# initialize\n", "\n", "openai = OpenAI()\n", "claude = anthropic.Anthropic()\n", "google.generativeai.configure()\n", "\n", "OPENAI_MODEL = \"gpt-4o\"\n", "CLAUDE_MODEL = \"claude-3-5-sonnet-20240620\"\n", "GOOGLE_MODEL = \"gemini-1.5-pro\"" ] }, { "cell_type": "code", "execution_count": 4, "id": "6896636f-923e-4a2c-9d6c-fac07828a201", "metadata": {}, "outputs": [], "source": [ "system_message = \"You are a Python code assistant. Your task is to analyze Python code and generate high-quality, concise comments and docstrings. Follow these guidelines:\"\n", "system_message += \"Docstrings: Add a docstring for every function, class, and module. Describe the purpose of the function/class, its parameters, and its return value. Keep the description concise but informative, using proper Python docstring conventions (e.g., Google, NumPy, or reStructuredText format).\"\n", "system_message += \"Inline Comments: Add inline comments only where necessary to clarify complex logic, important steps, or non-obvious behavior. Avoid commenting on obvious operations like x += 1 unless it involves a nuanced concept. Keep comments short, clear, and relevant.\"\n", "system_message += \"General Instructions: Maintain consistency in style and tone. Use technical terminology where appropriate, but ensure clarity for someone with intermediate Python knowledge. Do not over-explain or add redundant comments for self-explanatory code. Follow PEP 257 and PEP 8 standards for style and formatting.\"\n" ] }, { "cell_type": "code", "execution_count": 5, "id": "8e7b3546-57aa-4c29-bc5d-f211970d04eb", "metadata": {}, "outputs": [], "source": [ "def user_prompt_for(python):\n", " user_prompt = \"Analyze the following Python code and enhance it by adding high-quality, concise docstrings and comments. \"\n", " user_prompt += \"Ensure all functions, classes, and modules have appropriate docstrings describing their purpose, parameters, and return values. \"\n", " user_prompt += \"Add inline comments only for complex or non-obvious parts of the code. \"\n", " user_prompt += \"Follow Python's PEP 257 and PEP 8 standards for documentation and formatting. \"\n", " user_prompt += \"Do not modify the code itself; only add annotations.\\n\\n\"\n", " user_prompt += python\n", " return user_prompt\n" ] }, { "cell_type": "code", "execution_count": 6, "id": "c6190659-f54c-4951-bef4-4960f8e51cc4", "metadata": {}, "outputs": [], "source": [ "def messages_for(python):\n", " return [\n", " {\"role\": \"system\", \"content\": system_message},\n", " {\"role\": \"user\", \"content\": user_prompt_for(python)}\n", " ]" ] }, { "cell_type": "code", "execution_count": 7, "id": "a1cbb778-fa57-43de-b04b-ed523f396c38", "metadata": {}, "outputs": [], "source": [ "pi = \"\"\"\n", "import time\n", "\n", "def calculate(iterations, param1, param2):\n", " result = 1.0\n", " for i in range(1, iterations+1):\n", " j = i * param1 - param2\n", " result -= (1/j)\n", " j = i * param1 + param2\n", " result += (1/j)\n", " return result\n", "\n", "start_time = time.time()\n", "result = calculate(100_000_000, 4, 1) * 4\n", "end_time = time.time()\n", "\n", "print(f\"Result: {result:.12f}\")\n", "print(f\"Execution Time: {(end_time - start_time):.6f} seconds\")\n", "\"\"\"" ] }, { "cell_type": "code", "execution_count": 8, "id": "c3b497b3-f569-420e-b92e-fb0f49957ce0", "metadata": {}, "outputs": [], "source": [ "python_hard = \"\"\"# Be careful to support large number sizes\n", "\n", "def lcg(seed, a=1664525, c=1013904223, m=2**32):\n", " value = seed\n", " while True:\n", " value = (a * value + c) % m\n", " yield value\n", " \n", "def max_subarray_sum(n, seed, min_val, max_val):\n", " lcg_gen = lcg(seed)\n", " random_numbers = [next(lcg_gen) % (max_val - min_val + 1) + min_val for _ in range(n)]\n", " max_sum = float('-inf')\n", " for i in range(n):\n", " current_sum = 0\n", " for j in range(i, n):\n", " current_sum += random_numbers[j]\n", " if current_sum > max_sum:\n", " max_sum = current_sum\n", " return max_sum\n", "\n", "def total_max_subarray_sum(n, initial_seed, min_val, max_val):\n", " total_sum = 0\n", " lcg_gen = lcg(initial_seed)\n", " for _ in range(20):\n", " seed = next(lcg_gen)\n", " total_sum += max_subarray_sum(n, seed, min_val, max_val)\n", " return total_sum\n", "\n", "# Parameters\n", "n = 10000 # Number of random numbers\n", "initial_seed = 42 # Initial seed for the LCG\n", "min_val = -10 # Minimum value of random numbers\n", "max_val = 10 # Maximum value of random numbers\n", "\n", "# Timing the function\n", "import time\n", "start_time = time.time()\n", "result = total_max_subarray_sum(n, initial_seed, min_val, max_val)\n", "end_time = time.time()\n", "\n", "print(\"Total Maximum Subarray Sum (20 runs):\", result)\n", "print(\"Execution Time: {:.6f} seconds\".format(end_time - start_time))\n", "\"\"\"" ] }, { "cell_type": "code", "execution_count": 9, "id": "0be9f47d-5213-4700-b0e2-d444c7c738c0", "metadata": {}, "outputs": [], "source": [ "def stream_gpt(python): \n", " stream = openai.chat.completions.create(model=OPENAI_MODEL, messages=messages_for(python), stream=True)\n", " reply = \"\"\n", " for chunk in stream:\n", " fragment = chunk.choices[0].delta.content or \"\"\n", " reply += fragment\n", " yield reply.replace('```python\\n','').replace('```','')" ] }, { "cell_type": "code", "execution_count": 10, "id": "8669f56b-8314-4582-a167-78842caea131", "metadata": {}, "outputs": [], "source": [ "def stream_claude(python):\n", " result = claude.messages.stream(\n", " model=CLAUDE_MODEL,\n", " max_tokens=2000,\n", " system=system_message,\n", " messages=[{\"role\": \"user\", \"content\": user_prompt_for(python)}],\n", " )\n", " reply = \"\"\n", " with result as stream:\n", " for text in stream.text_stream:\n", " reply += text\n", " yield reply.replace('```python\\n','').replace('```','')" ] }, { "cell_type": "code", "execution_count": 11, "id": "25f8d215-67a8-4179-8834-0e1da5a7dd32", "metadata": {}, "outputs": [], "source": [ "def stream_google(python):\n", " # Initialize empty reply string\n", " reply = \"\"\n", " \n", " # The API for Gemini has a slightly different structure\n", " gemini = google.generativeai.GenerativeModel(\n", " model_name=GOOGLE_MODEL,\n", " system_instruction=system_message\n", " )\n", " \n", " response = gemini.generate_content(\n", " user_prompt_for(python),\n", " stream=True\n", " )\n", " \n", " # Process the stream\n", " for chunk in response:\n", " # Extract text from the chunk\n", " if chunk.text:\n", " reply += chunk.text\n", " yield reply.replace('```python\\n','').replace('```','')" ] }, { "cell_type": "code", "execution_count": 12, "id": "2f1ae8f5-16c8-40a0-aa18-63b617df078d", "metadata": {}, "outputs": [], "source": [ "def optimize(python, model):\n", " if model==\"GPT\":\n", " result = stream_gpt(python)\n", " elif model==\"Claude\":\n", " result = stream_claude(python)\n", " elif model==\"Gemini\":\n", " result = stream_google(python)\n", " else:\n", " raise ValueError(\"Unknown model\")\n", " for stream_so_far in result:\n", " yield stream_so_far " ] }, { "cell_type": "code", "execution_count": 13, "id": "43a6b5f5-5d7c-4511-9d0c-21640070b3cf", "metadata": {}, "outputs": [], "source": [ "def execute_python(code):\n", " try:\n", " output = io.StringIO()\n", " sys.stdout = output\n", " exec(code)\n", " finally:\n", " sys.stdout = sys.__stdout__\n", " return output.getvalue()" ] }, { "cell_type": "code", "execution_count": 14, "id": "f35b0602-84f9-4ed6-aa35-87be4290ed24", "metadata": {}, "outputs": [], "source": [ "css = \"\"\"\n", ".python {background-color: #306998;}\n", ".cpp {background-color: #050;}\n", "\"\"\"" ] }, { "cell_type": "code", "execution_count": 15, "id": "62488014-d34c-4de8-ba72-9516e05e9dde", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "* Running on local URL: http://127.0.0.1:7860\n", "\n", "To create a public link, set `share=True` in `launch()`.\n" ] }, { "data": { "text/html": [ "
" ], "text/plain": [ "