Merge pull request #4 from o19s/add_book_related_notebooks

Still need some work, but at least got them in

Author: epugh

README.md

@@ -27,7 +27,7 @@ Browse to http://localhost:8000 and you should see the Jupyterlite interface.
 
 ## Development 2
 
-1. Run the docker task, and make the jupyter-lite-build.tgz.
+1. Run `docker run -it --rm -e TARGET_DIR=/dist -v "$(pwd)":/dist $(docker build -q .)` producing the jupyter-lite-build.tgz.
 1. Unzip it into the ./notebooks
 1. `rm -rf public/notebooks` in Quepid
 1. Make sure Quepid's docker-compose.override.yml has a line similar to `- /Users/epugh/Documents/projects/quepid-jupyterlite/notebooks:/srv/app/public/notebooks`

jupyterlite/files/README.md

@@ -7,6 +7,9 @@ The example notebooks are stored under ./examples.  Feel free to run them, but p
 * `./examples/Scoring Comparison.ipynb` is an example of measuring relevance score change.
 * `./examples/Jaccard and RBO Comparison.ipynb` is an example of comparing query result sets to each other.
 
+* `./examples/Multiple Raters Analysis.ipynb` looks at how judge compare in rating.
+* `./examples/Fleiss Kappa.ipynb` calculates a specific measurement of rater agreement.
+
 These notebooks use data from the Haystack Rating Party.
 
 

jupyterlite/files/examples/Fleiss Kappa.ipynb

@@ -0,0 +1,160 @@
+{
+  "metadata": {
+    "kernelspec": {
+      "name": "python",
+      "display_name": "Python (Pyodide)",
+      "language": "python"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "python",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.8"
+    }
+  },
+  "nbformat_minor": 5,
+  "nbformat": 4,
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "source": "# Fleiss' Kappa \nTo understand how much your raters what?  Scott, need some text!\n\nPlease copy this example and customize it for your own purposes!",
+      "metadata": {},
+      "id": "bd7e4efa-eb00-451e-984d-ed6646d8e25f"
+    },
+    {
+      "cell_type": "markdown",
+      "source": "## Imports",
+      "metadata": {},
+      "id": "e3412382"
+    },
+    {
+      "cell_type": "code",
+      "source": "import pandas as pd\nfrom js import fetch\nimport json\n\nfrom collections import defaultdict\nfrom statsmodels.stats.inter_rater import aggregate_raters\nfrom statsmodels.stats.inter_rater import fleiss_kappa\nfrom IPython.display import display, Markdown",
+      "metadata": {
+        "trusted": true
+      },
+      "execution_count": 1,
+      "outputs": [],
+      "id": "4972936a"
+    },
+    {
+      "cell_type": "markdown",
+      "source": "## Step 0: Configuration",
+      "metadata": {},
+      "id": "6da26c5e"
+    },
+    {
+      "cell_type": "code",
+      "source": "QUEPID_BOOK_NUM = 25\n\n# Not needed if running within Quepid JupyterLite\n# QUEPID_API_TOKEN = \"\"",
+      "metadata": {
+        "trusted": true
+      },
+      "execution_count": 3,
+      "outputs": [],
+      "id": "71803a49-4065-4adf-a69e-cb0fe2d00f22"
+    },
+    {
+      "cell_type": "markdown",
+      "source": "## Step 1: Download the Quepid Book",
+      "metadata": {},
+      "id": "420416df-9e6a-41b4-987b-7a03c9dd38b3"
+    },
+    {
+      "cell_type": "code",
+      "source": "# Generic GET call to a JSON endpoint \nasync def get_json(url):\n    resp = await fetch(url)\n    resp_text = await resp.text()\n    return json.loads(resp_text)\n\n",
+      "metadata": {
+        "trusted": true
+      },
+      "execution_count": 4,
+      "outputs": [],
+      "id": "31193536-98eb-4b46-ab98-af04ee07c6d3"
+    },
+    {
+      "cell_type": "code",
+      "source": "data = await get_json(f'/api/export/books/{QUEPID_BOOK_NUM}')",
+      "metadata": {
+        "trusted": true
+      },
+      "execution_count": 5,
+      "outputs": [],
+      "id": "8fef6231-daa8-467f-ac57-13a144e8a356"
+    },
+    {
+      "cell_type": "markdown",
+      "source": "## Step 2: Extract and Prepare Data",
+      "metadata": {},
+      "id": "79d985ad-cd11-44a9-a7e1-0851bc99aef3"
+    },
+    {
+      "cell_type": "code",
+      "source": "# Initialize a list to hold the tuples of (doc_id, rating, count)\nratings_data = []\n\n# Iterate through each query-doc pair\nfor pair in data['query_doc_pairs']:\n    # Initialize a dictionary to count the ratings for this pair\n    ratings_count = defaultdict(int)\n    \n    # Extract judgements and count the ratings\n    for judgement in pair['judgements']:\n        rating = judgement['rating']\n        ratings_count[rating] += 1\n\n    # Append the counts to the ratings_data list\n    for rating, count in ratings_count.items():\n        ratings_data.append((pair['doc_id'], rating, count))\n",
+      "metadata": {
+        "trusted": true
+      },
+      "execution_count": 6,
+      "outputs": [],
+      "id": "9a8561fd-2dbf-477e-9ac1-4df6d5ebdc91"
+    },
+    {
+      "cell_type": "markdown",
+      "source": "## Step 3: Aggregate Raters' Data",
+      "metadata": {},
+      "id": "caf5632b-132a-4e1b-80fe-c8c5ab7f2f3a"
+    },
+    {
+      "cell_type": "code",
+      "source": "# Convert ratings_data to a DataFrame\ndf = pd.DataFrame(ratings_data, columns=['doc_id', 'rating', 'count'])\n\n# Use crosstab to create a contingency table\ndata_crosstab = pd.crosstab(index=df['doc_id'], columns=df['rating'], values=df['count'], aggfunc='sum')\n\n# Drop any rows missing judgements\ndata_crosstab = data_crosstab.dropna(how='any')\n\n# Convert the DataFrame to the format expected by aggregate_raters\ndata_for_aggregation = data_crosstab.values\n\n# Aggregate the raters' data\ntable, _ = aggregate_raters(data_for_aggregation)",
+      "metadata": {
+        "trusted": true
+      },
+      "execution_count": 7,
+      "outputs": [],
+      "id": "a7598308-129b-4628-ad3a-fc3d703f8205"
+    },
+    {
+      "cell_type": "markdown",
+      "source": "## Step 4: Compute Fleiss' Kappa",
+      "metadata": {},
+      "id": "25c79fbc"
+    },
+    {
+      "cell_type": "code",
+      "source": "kappa = fleiss_kappa(table, method='fleiss')\ndisplay(Markdown(f\"## Fleiss' Kappa: {kappa:.4f}\"))",
+      "metadata": {
+        "trusted": true
+      },
+      "execution_count": 8,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": "<IPython.core.display.Markdown object>",
+            "text/markdown": "## Fleiss' Kappa: -0.3333"
+          },
+          "metadata": {}
+        }
+      ],
+      "id": "25a613f9"
+    },
+    {
+      "cell_type": "markdown",
+      "source": "_This notebook was last updated 17-FEB-2024_",
+      "metadata": {},
+      "id": "5704579e-2321-4629-8de0-6608b428e2b6"
+    },
+    {
+      "cell_type": "code",
+      "source": "",
+      "metadata": {},
+      "execution_count": null,
+      "outputs": [],
+      "id": "7203f6cc-c068-4f75-a59a-1f49c5555319"
+    }
+  ]
+}