{ "cells": [ { "cell_type": "code", "execution_count": 55, "id": "3b348213", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "dict_keys(['task_id', 'Question', 'Level', 'Final answer', 'file_name', 'Annotator Metadata'])" ] }, "execution_count": 55, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import json\n", "\n", "with open('metadata.jsonl', 'r') as f:\n", " lst = [json.loads(line.strip()) for line in f]\n", "\n", "lst[0].keys()" ] }, { "cell_type": "code", "execution_count": 32, "id": "d0ccfa98", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "dict_keys(['Steps', 'Number of steps', 'How long did this take?', 'Tools', 'Number of tools'])" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "lst[0]['Annotator Metadata'].keys()" ] }, { "cell_type": "code", "execution_count": 36, "id": "6b4fd5bc", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Task ID: c61d22de-5f6c-4958-a7f6-5e9707bd3466\n", "Question: A paper about AI regulation that was originally submitted to arXiv.org in June 2022 shows a figure with three axes, where each axis has a label word at both ends. Which of these words is used to describe a type of society in a Physics and Society article submitted to arXiv.org on August 11, 2016?\n", "Level: 2\n", "Answer: egalitarian\n", "Annotator Metadata:\n", "- Total steps: 12\n", "- Time taken: 8 minutes\n", "- Tool used: 2\n", "- Tools details:\n", " 1. Web browser\n", " 2. Image recognition tools (to identify and parse a figure with three axes)\n", "- Detailed steps:\n", " 1. Go to arxiv.org and navigate to the Advanced Search page.\n", " 2. Enter \"AI regulation\" in the search box and select \"All fields\" from the dropdown.\n", " 3. Enter 2022-06-01 and 2022-07-01 into the date inputs, select \"Submission date (original)\", and submit the search.\n", " 4. Go through the search results to find the article that has a figure with three axes and labels on each end of the axes, titled \"Fairness in Agreement With European Values: An Interdisciplinary Perspective on AI Regulation\".\n", " 5. Note the six words used as labels: deontological, egalitarian, localized, standardized, utilitarian, and consequential.\n", " 6. Go back to arxiv.org\n", " 7. Find \"Physics and Society\" and go to the page for the \"Physics and Society\" category.\n", " 8. Note that the tag for this category is \"physics.soc-ph\".\n", " 9. Go to the Advanced Search page.\n", " 10. Enter \"physics.soc-ph\" in the search box and select \"All fields\" from the dropdown.\n", " 11. Enter 2016-08-11 and 2016-08-12 into the date inputs, select \"Submission date (original)\", and submit the search.\n", " 12. Search for instances of the six words in the results to find the paper titled \"Phase transition from egalitarian to hierarchical societies driven by competition between cognitive and social constraints\", indicating that \"egalitarian\" is the correct answer.\n" ] } ], "source": [ "def format_sample(sample):\n", " \"\"\"Format a dataset sample for better readability\"\"\"\n", " print(f\"Task ID: {sample['task_id']}\")\n", " print(f\"Question: {sample['Question']}\")\n", " print(f\"Level: {sample['Level']}\")\n", " print(f\"Answer: {sample['Final answer']}\")\n", " \n", " if sample['file_name']:\n", " print(f\"📁 FILE: {sample['file_name']}\")\n", " \n", " print(f\"Annotator Metadata:\")\n", " metadata = sample['Annotator Metadata']\n", " \n", " print(f\"- Total steps: {metadata['Number of steps']}\")\n", " print(f\"- Time taken: {metadata['How long did this take?']}\")\n", " print(f\"- Tool used: {metadata['Number of tools']}\")\n", " \n", " print(f\"- Tools details:\")\n", " tools = metadata['Tools'].split('\\n')\n", " for tool in tools:\n", " print(f\" {tool}\")\n", " \n", " print(f\"- Detailed steps:\")\n", " steps = metadata['Steps'].split('\\n')\n", " for i, step in enumerate(steps, 1):\n", " if step.strip(): # Only print non-empty steps\n", " print(f\" {step.strip()}\")\n", "\n", "# Format the first sample\n", "format_sample(lst[0])\n" ] }, { "cell_type": "code", "execution_count": 91, "id": "8301a90f", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Web browser: 95\n", "Search engine: 88\n", "Calculator: 30\n", "Image recognition tools: 11\n", "search engine: 9\n", "None: 9\n", "web browser: 8\n", "A web browser: 8\n", "A search engine: 8\n", "PDF access: 7\n", "PDF viewer: 7\n", "Microsoft Excel: 5\n", "Image recognition: 5\n", "calculator: 4\n", "A calculator: 4\n", "OCR: 4\n", "Python: 3\n", "Microsoft Excel / Google Sheets: 3\n", "Excel: 3\n", "Color recognition: 3\n", "Excel file access: 3\n", "Web Browser: 3\n", "Access to Wikipedia: 3\n", "A file interface: 3\n", "A web browser.: 2\n", "A search engine.: 2\n", "File handling: 2\n", "Video recognition tools: 2\n", "A speech-to-text tool: 2\n", "Search Engine: 2\n", "Audio capability: 2\n", "image recognition/OCR: 2\n", "Image recognition tools (to identify and parse a figure with three axes): 1\n", "Unlambda compiler (optional): 1\n", "A calculator.: 1\n", "google search: 1\n", "JSONLD file access: 1\n", "Video parsing: 1\n", "Python compiler: 1\n", "video recognition tools: 1\n", "Word document access: 1\n", "Tool to extract text from images: 1\n", "A word reversal tool / script: 1\n", "Counter: 1\n", "XML file access: 1\n", "(Optional) Web browser: 1\n", "(Optional) Search engine: 1\n", "Access to the Internet Archive, web.archive.org: 1\n", "Text processing/diff tool: 1\n", "GIF parsing tools: 1\n", "code/data analysis tools: 1\n", "PDF reader: 1\n", "Markdown: 1\n", "a calculator: 1\n", "Google Translate access: 1\n", "Bass note data: 1\n", "Text Editor: 1\n", "XLSX file access: 1\n", "PowerPoint viewer: 1\n", "CSV file access: 1\n", "Calculator (or use Excel): 1\n", "computer algebra system: 1\n", "Video processing software: 1\n", "Audio processing software: 1\n", "Computer vision: 1\n", "Google Maps: 1\n", "Access to Excel files: 1\n", "Calculator (or ability to count): 1\n", "A Python IDE: 1\n", "Spreadsheet editor: 1\n", "No tools required: 1\n", "Image recognition and processing tools: 1\n", "Computer vision or OCR: 1\n", "C++ compiler: 1\n", "Access to Google Maps: 1\n", "Image recognition/OCR: 1\n", "YouTube player: 1\n", "Natural language processor: 1\n", "Graph interaction tools: 1\n", "Bablyonian cuniform -> arabic legend: 1\n", "Access to YouTube: 1\n", "image recognition tools: 1\n", "image search tools: 1\n", "Calculator or counting function: 1\n", "A speech-to-text audio processing tool: 1\n", "Access to academic journal websites: 1\n", "pdf reader/extracter: 1\n", "Rubik's cube model: 1\n", "Wikipedia: 1\n", "Video capability: 1\n", "Image processing tools: 1\n", "Image recognition software: 1\n", "YouTube: 1\n" ] } ], "source": [ "# Tools usage summary from metadata.jsonl\n", "import seaborn as sns\n", "import matplotlib.pyplot as plt\n", "from collections import Counter\n", "\n", "# Extract tool names and create summary\n", "tool_names = []\n", "for item in lst:\n", " tools_text = item['Annotator Metadata']['Tools']\n", " for line in tools_text.split('\\n'):\n", " if line.strip():\n", " # Clean tool name (remove numbers and extra text)\n", " tool = line.split('.', 1)[-1].strip()\n", " tool_names.append(tool)\n", "\n", "summary = Counter(tool_names)\n", "origin_sorted_data = dict(sorted(summary.items(), key=lambda x: x[1], reverse=True))\n", "sorted_data = {k: v for k, v in origin_sorted_data.items() if v > 5}\n", "\n", "# Plot with gradient colors\n", "plt.figure(figsize=(12, 6))\n", "colors = sns.color_palette(\"viridis\", len(sorted_data))\n", "sns.barplot(x=list(sorted_data.values()), y=list(sorted_data.keys()), hue=list(sorted_data.keys()), palette=colors, legend=False)\n", "plt.title('Tool Usage Distribution')\n", "plt.xlabel('Frequency')\n", "plt.ylabel('Tools')\n", "plt.tight_layout()\n", "plt.show()\n", "\n", "for key, value in origin_sorted_data.items():\n", " print(f\"{key}: {value}\")" ] }, { "cell_type": "code", "execution_count": 53, "id": "1538559d", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Total docs: 165\n", "Columns:\n", " id : \n", " content : \n", " metadata : \n", "\tsource: str\n", " embedding : \n", "Number of keys: 4\n" ] } ], "source": [ "# Explore supabase_docs.csv with SupabaseVectorStore\n", "import csv\n", "import ast\n", "import json\n", "\n", "# Quick CSV exploration\n", "with open('supabase_docs.csv', 'r') as f:\n", " docs = list(csv.DictReader(f))\n", "\n", "print(f\"Total docs: {len(docs)}\")\n", "print(f\"Columns:\")\n", "for key in docs[0].keys():\n", " print(f\" {key} : {type(docs[0][key])}\")\n", " try:\n", " parsed = ast.literal_eval(docs[0][key])\n", " if isinstance(parsed, dict):\n", " for k, v in parsed.items():\n", " print(f\"\\t{k}: {type(v).__name__}\")\n", " except: pass\n", "print(f\"Number of keys: {len(docs[0])}\")" ] } ], "metadata": { "kernelspec": { "display_name": "DeepML", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.11.7" } }, "nbformat": 4, "nbformat_minor": 5 }