{
 "cells": [
  {
   "id": "7af82b40",
   "cell_type": "markdown",
   "source": [
    "## Local setup\n",
    "\n",
    "Use Python 3.12 or 3.13 and install this checkout with `uv pip install --editable '.[notebooks]'`.\n",
    "See **Run notebooks locally** in the repository README for the kernel, execution order,\n",
    "and full-data options. Generated artifacts stay under `.cache/notebooks/`.\n"
   ],
   "metadata": {}
  },
  {
   "id": "ba5f79ca",
   "cell_type": "code",
   "metadata": {},
   "execution_count": null,
   "source": [
    "import os\n",
    "import sys\n",
    "from pathlib import Path\n",
    "\n",
    "# Works when opened from the repository root or any notebook directory.\n",
    "_start = Path(globals().get(\"__file__\", Path.cwd())).resolve()\n",
    "ROOT = next(\n",
    "    p\n",
    "    for p in [_start, *_start.parents]\n",
    "    if (p / \"pyproject.toml\").is_file() and (p / \"great_ai\").is_dir()\n",
    ")\n",
    "sys.path.insert(0, str(ROOT / \"docs\"))\n",
    "from notebook_support import setup_notebook, mag_lines\n",
    "\n",
    "FULL_RUN = os.environ.get(\"GREAT_AI_NOTEBOOK_FULL\") == \"1\"\n",
    "WORK_DIR = setup_notebook(ROOT, \"surveys\")\n",
    "DATA_DIR = ROOT / \"docs/tutorial/data\""
   ],
   "outputs": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "SURVEY_DIR = ROOT / \"docs/surveys\"\n",
    "best_practices = pd.read_csv(SURVEY_DIR / \"Best practices assessment.csv\")\n",
    "best_practices"
   ],
   "id": "cell-2"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "m = {\n",
    "    \"Strongly agree\": 4 / 4,\n",
    "    \"Agree\": 3 / 4,\n",
    "    \"Neither agree nor disagree\": 2 / 4,\n",
    "    \"Disagree\": 1 / 4,\n",
    "    \"Strongly disagree\": 0 / 4,\n",
    "}\n",
    "\n",
    "best_practices_dicts = [v.to_dict() for _, v in best_practices.iterrows()]\n",
    "\n",
    "best_practice_score_ds = []\n",
    "best_practice_score_se = []\n",
    "\n",
    "for d in best_practices_dicts:\n",
    "    ds_experience = int(d[\"How many years of data science experience do you have?\"])\n",
    "    del d[\"How many years of data science experience do you have?\"]\n",
    "\n",
    "    se_experience = int(\n",
    "        d[\"How many years of software engineering experience do you have?\"]\n",
    "    )\n",
    "    del d[\"How many years of software engineering experience do you have?\"]\n",
    "\n",
    "    scores = [m[v] for v in d.values() if v != \"Not applicable\"]\n",
    "    score = sum(scores) / len(scores)\n",
    "    best_practice_score_ds.append((ds_experience, score))\n",
    "    best_practice_score_se.append((se_experience, score))\n",
    "\n",
    "best_practices[\n",
    "    \"How many years of software engineering experience do you have?\"\n",
    "].median(), best_practices[\n",
    "    \"How many years of data science experience do you have?\"\n",
    "].median()"
   ],
   "id": "cell-3"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "from scipy import stats\n",
    "\n",
    "best_practice_score_ds = sorted(best_practice_score_ds)\n",
    "plt.scatter(\n",
    "    [x for x, y in best_practice_score_ds], [y for x, y in best_practice_score_ds]\n",
    ")\n",
    "stats.pearsonr(\n",
    "    [x for x, y in best_practice_score_ds], [y for x, y in best_practice_score_ds]\n",
    ")"
   ],
   "id": "cell-4"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "\n",
    "best_practice_score_se = sorted(best_practice_score_se)\n",
    "\n",
    "%matplotlib inline\n",
    "plt.rcParams[\"figure.facecolor\"] = \"white\"\n",
    "plt.rcParams[\"font.size\"] = 24\n",
    "plt.rcParams[\"figure.figsize\"] = (14, 10)\n",
    "\n",
    "X = [x for x, y in best_practice_score_se]\n",
    "Y = [y for x, y in best_practice_score_se]\n",
    "\n",
    "print(sum(Y) / len(Y))\n",
    "sc = plt.scatter(X, Y, c=\"black\", s=[x * 50 for x, y in best_practice_score_ds])\n",
    "plt.ylabel(\"Ratio of implemented deployment best practices\")\n",
    "plt.xlabel(\"Years of professional software engineering experience\")\n",
    "\n",
    "\n",
    "def best_fit(X, Y):\n",
    "    xbar = sum(X) / len(X)\n",
    "    ybar = sum(Y) / len(Y)\n",
    "    n = len(X)\n",
    "\n",
    "    numer = sum([xi * yi for xi, yi in zip(X, Y)]) - n * xbar * ybar\n",
    "    denum = sum([xi**2 for xi in X]) - n * xbar**2\n",
    "\n",
    "    b = numer / denum\n",
    "    a = ybar - b * xbar\n",
    "    return a, b\n",
    "\n",
    "\n",
    "a, b = best_fit(X, Y)\n",
    "yfit = [a + b * xi for xi in X]\n",
    "plt.plot(X, yfit, \"b\", label=\"Best fit\")\n",
    "plt.legend(\n",
    "    sc.legend_elements(\"sizes\", num=5)[0],\n",
    "    [\n",
    "        re.sub(r\"[^\\d]*(\\d+)[^\\d]*\", lambda v: f\"{int(v.group(1)) // 40} years (DS)\", t)\n",
    "        for t in sc.legend_elements(\"sizes\", num=5)[1]\n",
    "    ],\n",
    ")\n",
    "plt.tight_layout()\n",
    "\n",
    "plt.savefig(WORK_DIR / \"best-practices.png\", dpi=150)\n",
    "\n",
    "stats.pearsonr(\n",
    "    [x for x, y in best_practice_score_se], [y for x, y in best_practice_score_se]\n",
    ")"
   ],
   "id": "cell-5"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "tam = pd.read_csv(SURVEY_DIR / \"Technology acceptance model questionnaire.csv\")\n",
    "tam"
   ],
   "id": "cell-6"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pingouin\n",
    "\n",
    "pu = [\n",
    "    \"I believe the use of GreatAI improves the quality of AI deployments.\",\n",
    "    \"I believe the use of GreatAI would increase my productivity.\",\n",
    "    \"I believe the use of GreatAI can lead to robust and trustworthy deployments.\",\n",
    "    \"Overall, I found GreatAI useful when working with AI.\",\n",
    "]\n",
    "pingouin.cronbach_alpha(tam[pu])"
   ],
   "id": "cell-7"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "peou = [\n",
    "    \"I found the GreatAI easy to learn.\",\n",
    "    \"I found it is easy to employ GreatAI in practice.\",\n",
    "    \"I found it is easy to integrate GreatAI into an existing project.\",\n",
    "    \"Overall, I found GreatAI easy to use.\",\n",
    "]\n",
    "pingouin.cronbach_alpha(tam[peou])"
   ],
   "id": "cell-8"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "itu = [\n",
    "    \"Assuming GreatAI is applicable to my task, I predict that I will use it on a regular basis in the future.\",\n",
    "    \"Overall, I intend to use the GreatAI in my personal or professional projects.\",\n",
    "]\n",
    "pingouin.cronbach_alpha(tam[itu])"
   ],
   "id": "cell-9"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "tam[\"pu\"] = tam[pu].mean(axis=1)\n",
    "tam[\"peou\"] = tam[peou].mean(axis=1)\n",
    "tam[\"itu\"] = tam[itu].mean(axis=1)\n",
    "tam[[\"pu\", \"peou\", \"itu\"]]"
   ],
   "id": "cell-10"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "tam[[\"pu\", \"peou\", \"itu\"]].mean()"
   ],
   "id": "cell-11"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "tam[[\"pu\", \"peou\", \"itu\"]].median()"
   ],
   "id": "cell-12"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "tam[[\"pu\", \"peou\", \"itu\"]].std()"
   ],
   "id": "cell-13"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "stats.pearsonr(tam[\"peou\"], tam[\"pu\"])"
   ],
   "id": "cell-14"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "stats.pearsonr(tam[\"peou\"], tam[\"itu\"])"
   ],
   "id": "cell-15"
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "stats.pearsonr(tam[\"pu\"], tam[\"itu\"])"
   ],
   "id": "cell-16"
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "GreatAI (local)",
   "language": "python",
   "name": "great-ai-local"
  },
  "language_info": {
   "name": "python",
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}