andras/great-ai
andras/great-ai
Watch
1
0
Fork
You've already forked great-ai
 0
Code Issues Pull requests 2 Projects Releases 4 Packages 1 Wiki Activity Actions
great-ai/docs/surveys/surveys.ipynb
Andras Schmelczer cf61b38b45
All checks were successful
Publish documentation to great-ai.schmelczer.dev / publish (push) Successful in 1m10s
Details
Check / Lint, format & type checks (push) Successful in 1m55s
Details
Check / Test on Python 3.12 (push) Successful in 3m8s
Details
Check / Test on Python 3.13 (push) Successful in 2m32s
Details
Check / Notebooks on Python 3.12 (push) Successful in 8m49s
Details
Check / Notebooks on Python 3.13 (push) Successful in 7m53s
Details
Rerender
2026-10-28 22:53:24 +00:00

1438 lines
185 KiB
Text
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"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 figures are saved in the working directory.\n"
],
"metadata": {}
},
{
"id": "ba5f79ca",
"cell_type": "code",
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:18.858795Z",
"iopub.status.busy": "2026-10-28T22:48:18.858521Z",
"iopub.status.idle": "2026-10-28T22:48:18.863019Z",
"shell.execute_reply": "2026-10-28T22:48:18.862079Z"
}
},
"execution_count": 1,
"source": [
"from docs.notebook_support import SURVEY_DIR"
],
"outputs": []
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:18.864150Z",
"iopub.status.busy": "2026-10-28T22:48:18.864063Z",
"iopub.status.idle": "2026-10-28T22:48:19.025770Z",
"shell.execute_reply": "2026-10-28T22:48:19.025432Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>How many years of software engineering experience do you have?</th>\n",
" <th>How many years of data science experience do you have?</th>\n",
" <th>Write reusable scripts for data cleaning and merging</th>\n",
" <th>Make datasets available on shared infrastructure</th>\n",
" <th>Use versioning for data, model, configurations and training scripts</th>\n",
" <th>Continuously monitor the behaviour of deployed models</th>\n",
" <th>Log production predictions with the model’s version and input data</th>\n",
" <th>Store models in a single format for ease of use</th>\n",
" <th>Equip with web interface, package image, provide REST API</th>\n",
" <th>Provide simple API for serving batch and real-time requests</th>\n",
" <th>Integration with existing data infrastructure</th>\n",
" <th>Querying, visualising and understanding metrics and event logging</th>\n",
" <th>Allow experimentation with the inference code</th>\n",
" <th>Keep the model’s API and documentation together</th>\n",
" <th>Parallelise feature extraction</th>\n",
" <th>Cache predictions</th>\n",
" <th>Async support for top-down chaining models</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>Strongly agree</td>\n",
" <td>Agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Strongly agree</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>6</td>\n",
" <td>2</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Agree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Agree</td>\n",
" <td>Agree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly disagree</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Agree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" <td>Agree</td>\n",
" <td>Agree</td>\n",
" <td>Disagree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Agree</td>\n",
" <td>Not applicable</td>\n",
" <td>Not applicable</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Agree</td>\n",
" <td>Disagree</td>\n",
" <td>Agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Not applicable</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Agree</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>7</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Not applicable</td>\n",
" <td>Not applicable</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Not applicable</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Agree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Not applicable</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>Disagree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Agree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Not applicable</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly agree</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>Disagree</td>\n",
" <td>Neither agree nor disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Agree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Agree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Not applicable</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Strongly disagree</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Agree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Disagree</td>\n",
" <td>Strongly disagree</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Agree</td>\n",
" <td>Agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly disagree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Not applicable</td>\n",
" <td>Agree</td>\n",
" <td>Agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Strongly agree</td>\n",
" <td>Agree</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" How many years of software engineering experience do you have? \\\n",
"0 3 \n",
"1 6 \n",
"2 1 \n",
"3 3 \n",
"4 1 \n",
"5 6 \n",
"6 2 \n",
"7 1 \n",
"8 0 \n",
"9 7 \n",
"\n",
" How many years of data science experience do you have? \\\n",
"0 1 \n",
"1 2 \n",
"2 5 \n",
"3 3 \n",
"4 7 \n",
"5 0 \n",
"6 2 \n",
"7 2 \n",
"8 1 \n",
"9 1 \n",
"\n",
" Write reusable scripts for data cleaning and merging \\\n",
"0 Strongly agree \n",
"1 Neither agree nor disagree \n",
"2 Strongly disagree \n",
"3 Agree \n",
"4 Neither agree nor disagree \n",
"5 Strongly agree \n",
"6 Disagree \n",
"7 Disagree \n",
"8 Strongly disagree \n",
"9 Strongly agree \n",
"\n",
" Make datasets available on shared infrastructure \\\n",
"0 Agree \n",
"1 Agree \n",
"2 Disagree \n",
"3 Agree \n",
"4 Disagree \n",
"5 Strongly agree \n",
"6 Neither agree nor disagree \n",
"7 Neither agree nor disagree \n",
"8 Disagree \n",
"9 Strongly agree \n",
"\n",
" Use versioning for data, model, configurations and training scripts \\\n",
"0 Strongly agree \n",
"1 Neither agree nor disagree \n",
"2 Disagree \n",
"3 Disagree \n",
"4 Neither agree nor disagree \n",
"5 Agree \n",
"6 Agree \n",
"7 Disagree \n",
"8 Strongly disagree \n",
"9 Agree \n",
"\n",
" Continuously monitor the behaviour of deployed models \\\n",
"0 Neither agree nor disagree \n",
"1 Agree \n",
"2 Strongly disagree \n",
"3 Neither agree nor disagree \n",
"4 Disagree \n",
"5 Neither agree nor disagree \n",
"6 Strongly agree \n",
"7 Agree \n",
"8 Disagree \n",
"9 Strongly agree \n",
"\n",
" Log production predictions with the model’s version and input data \\\n",
"0 Strongly agree \n",
"1 Agree \n",
"2 Disagree \n",
"3 Agree \n",
"4 Strongly disagree \n",
"5 Agree \n",
"6 Neither agree nor disagree \n",
"7 Disagree \n",
"8 Strongly disagree \n",
"9 Agree \n",
"\n",
" Store models in a single format for ease of use \\\n",
"0 Strongly agree \n",
"1 Neither agree nor disagree \n",
"2 Strongly disagree \n",
"3 Not applicable \n",
"4 Not applicable \n",
"5 Strongly agree \n",
"6 Disagree \n",
"7 Strongly disagree \n",
"8 Disagree \n",
"9 Agree \n",
"\n",
" Equip with web interface, package image, provide REST API \\\n",
"0 Strongly agree \n",
"1 Disagree \n",
"2 Strongly disagree \n",
"3 Not applicable \n",
"4 Not applicable \n",
"5 Agree \n",
"6 Strongly agree \n",
"7 Strongly agree \n",
"8 Agree \n",
"9 Strongly agree \n",
"\n",
" Provide simple API for serving batch and real-time requests \\\n",
"0 Strongly agree \n",
"1 Strongly disagree \n",
"2 Neither agree nor disagree \n",
"3 Neither agree nor disagree \n",
"4 Disagree \n",
"5 Strongly agree \n",
"6 Disagree \n",
"7 Strongly agree \n",
"8 Strongly disagree \n",
"9 Strongly disagree \n",
"\n",
" Integration with existing data infrastructure \\\n",
"0 Strongly agree \n",
"1 Disagree \n",
"2 Strongly disagree \n",
"3 Agree \n",
"4 Strongly disagree \n",
"5 Agree \n",
"6 Disagree \n",
"7 Strongly disagree \n",
"8 Disagree \n",
"9 Strongly agree \n",
"\n",
" Querying, visualising and understanding metrics and event logging \\\n",
"0 Strongly agree \n",
"1 Strongly disagree \n",
"2 Disagree \n",
"3 Disagree \n",
"4 Disagree \n",
"5 Strongly agree \n",
"6 Agree \n",
"7 Disagree \n",
"8 Strongly disagree \n",
"9 Not applicable \n",
"\n",
" Allow experimentation with the inference code \\\n",
"0 Strongly agree \n",
"1 Disagree \n",
"2 Neither agree nor disagree \n",
"3 Agree \n",
"4 Disagree \n",
"5 Disagree \n",
"6 Neither agree nor disagree \n",
"7 Agree \n",
"8 Disagree \n",
"9 Agree \n",
"\n",
" Keep the model’s API and documentation together \\\n",
"0 Strongly agree \n",
"1 Strongly disagree \n",
"2 Agree \n",
"3 Strongly agree \n",
"4 Neither agree nor disagree \n",
"5 Strongly agree \n",
"6 Neither agree nor disagree \n",
"7 Strongly disagree \n",
"8 Strongly disagree \n",
"9 Agree \n",
"\n",
" Parallelise feature extraction Cache predictions \\\n",
"0 Strongly agree Neither agree nor disagree \n",
"1 Disagree Strongly agree \n",
"2 Strongly disagree Strongly disagree \n",
"3 Not applicable Neither agree nor disagree \n",
"4 Strongly disagree Strongly agree \n",
"5 Agree Strongly agree \n",
"6 Not applicable Disagree \n",
"7 Not applicable Strongly disagree \n",
"8 Disagree Disagree \n",
"9 Strongly agree Strongly agree \n",
"\n",
" Async support for top-down chaining models \n",
"0 Strongly agree \n",
"1 Strongly disagree \n",
"2 Disagree \n",
"3 Agree \n",
"4 Not applicable \n",
"5 Not applicable \n",
"6 Strongly agree \n",
"7 Strongly disagree \n",
"8 Strongly disagree \n",
"9 Agree "
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"\n",
"best_practices = pd.read_csv(SURVEY_DIR / \"Best practices assessment.csv\")\n",
"best_practices"
],
"id": "cell-2"
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:19.026577Z",
"iopub.status.busy": "2026-10-28T22:48:19.026513Z",
"iopub.status.idle": "2026-10-28T22:48:19.029777Z",
"shell.execute_reply": "2026-10-28T22:48:19.029465Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"(np.float64(2.5), np.float64(2.0))"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"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": 4,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:19.030529Z",
"iopub.status.busy": "2026-10-28T22:48:19.030475Z",
"iopub.status.idle": "2026-10-28T22:48:19.521482Z",
"shell.execute_reply": "2026-10-28T22:48:19.521094Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"PearsonRResult(statistic=np.float64(-0.5440527060340572), pvalue=np.float64(0.10399880919437816))"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"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": 5,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:19.522297Z",
"iopub.status.busy": "2026-10-28T22:48:19.522214Z",
"iopub.status.idle": "2026-10-28T22:48:19.650855Z",
"shell.execute_reply": "2026-10-28T22:48:19.650524Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.5157738095238095\n"
]
},
{
"data": {
"text/plain": [
"PearsonRResult(statistic=np.float64(0.6722543326178703), pvalue=np.float64(0.033211248815547774))"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 1400x1000 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"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(\"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": 6,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:19.651678Z",
"iopub.status.busy": "2026-10-28T22:48:19.651609Z",
"iopub.status.idle": "2026-10-28T22:48:19.655040Z",
"shell.execute_reply": "2026-10-28T22:48:19.654690Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>I believe the use of GreatAI improves the quality of AI deployments.</th>\n",
" <th>I believe the use of GreatAI would increase my productivity.</th>\n",
" <th>I believe the use of GreatAI can lead to robust and trustworthy deployments.</th>\n",
" <th>Overall, I found GreatAI useful when working with AI.</th>\n",
" <th>I found the GreatAI easy to learn.</th>\n",
" <th>I found it is easy to employ GreatAI in practice.</th>\n",
" <th>I found it is easy to integrate GreatAI into an existing project.</th>\n",
" <th>Overall, I found GreatAI easy to use.</th>\n",
" <th>Assuming GreatAI is applicable to my task, I predict that I will use it on a regular basis in the future.</th>\n",
" <th>Overall, I intend to use the GreatAI in my personal or professional projects.</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>6</td>\n",
" <td>7</td>\n",
" <td>5</td>\n",
" <td>6</td>\n",
" <td>7</td>\n",
" <td>6</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>5</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>6</td>\n",
" <td>7</td>\n",
" <td>6</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>6</td>\n",
" <td>7</td>\n",
" <td>6</td>\n",
" <td>7</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>6</td>\n",
" <td>7</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>7</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>7</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>6</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>3</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>5</td>\n",
" <td>7</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" <td>5</td>\n",
" <td>6</td>\n",
" <td>5</td>\n",
" <td>6</td>\n",
" <td>7</td>\n",
" <td>7</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" I believe the use of GreatAI improves the quality of AI deployments. \\\n",
"0 7 \n",
"1 7 \n",
"2 4 \n",
"3 6 \n",
"4 7 \n",
"5 6 \n",
"6 6 \n",
"7 7 \n",
"8 4 \n",
"9 7 \n",
"\n",
" I believe the use of GreatAI would increase my productivity. \\\n",
"0 7 \n",
"1 7 \n",
"2 4 \n",
"3 7 \n",
"4 7 \n",
"5 6 \n",
"6 6 \n",
"7 6 \n",
"8 5 \n",
"9 7 \n",
"\n",
" I believe the use of GreatAI can lead to robust and trustworthy deployments. \\\n",
"0 7 \n",
"1 6 \n",
"2 5 \n",
"3 6 \n",
"4 6 \n",
"5 6 \n",
"6 6 \n",
"7 6 \n",
"8 5 \n",
"9 7 \n",
"\n",
" Overall, I found GreatAI useful when working with AI. \\\n",
"0 7 \n",
"1 7 \n",
"2 6 \n",
"3 7 \n",
"4 7 \n",
"5 6 \n",
"6 4 \n",
"7 6 \n",
"8 5 \n",
"9 7 \n",
"\n",
" I found the GreatAI easy to learn. \\\n",
"0 7 \n",
"1 5 \n",
"2 6 \n",
"3 7 \n",
"4 4 \n",
"5 6 \n",
"6 5 \n",
"7 4 \n",
"8 7 \n",
"9 5 \n",
"\n",
" I found it is easy to employ GreatAI in practice. \\\n",
"0 7 \n",
"1 6 \n",
"2 5 \n",
"3 6 \n",
"4 5 \n",
"5 6 \n",
"6 7 \n",
"7 5 \n",
"8 2 \n",
"9 6 \n",
"\n",
" I found it is easy to integrate GreatAI into an existing project. \\\n",
"0 7 \n",
"1 7 \n",
"2 4 \n",
"3 7 \n",
"4 5 \n",
"5 6 \n",
"6 6 \n",
"7 3 \n",
"8 3 \n",
"9 5 \n",
"\n",
" Overall, I found GreatAI easy to use. \\\n",
"0 7 \n",
"1 6 \n",
"2 4 \n",
"3 6 \n",
"4 5 \n",
"5 6 \n",
"6 6 \n",
"7 5 \n",
"8 3 \n",
"9 6 \n",
"\n",
" Assuming GreatAI is applicable to my task, I predict that I will use it on a regular basis in the future. \\\n",
"0 7 \n",
"1 7 \n",
"2 5 \n",
"3 7 \n",
"4 6 \n",
"5 6 \n",
"6 7 \n",
"7 5 \n",
"8 3 \n",
"9 7 \n",
"\n",
" Overall, I intend to use the GreatAI in my personal or professional projects. \n",
"0 7 \n",
"1 7 \n",
"2 4 \n",
"3 6 \n",
"4 6 \n",
"5 6 \n",
"6 7 \n",
"7 6 \n",
"8 3 \n",
"9 7 "
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tam = pd.read_csv(SURVEY_DIR / \"Technology acceptance model questionnaire.csv\")\n",
"tam"
],
"id": "cell-6"
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:19.655753Z",
"iopub.status.busy": "2026-10-28T22:48:19.655703Z",
"iopub.status.idle": "2026-10-28T22:48:19.743362Z",
"shell.execute_reply": "2026-10-28T22:48:19.742922Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"(np.float64(0.8813771517996869), array([0.688, 0.967]))"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"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": 8,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:19.744161Z",
"iopub.status.busy": "2026-10-28T22:48:19.744099Z",
"iopub.status.idle": "2026-10-28T22:48:19.747071Z",
"shell.execute_reply": "2026-10-28T22:48:19.746708Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"(np.float64(0.7729220222793487), array([0.403, 0.937]))"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"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": 9,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:19.747745Z",
"iopub.status.busy": "2026-10-28T22:48:19.747691Z",
"iopub.status.idle": "2026-10-28T22:48:19.750388Z",
"shell.execute_reply": "2026-10-28T22:48:19.749996Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"(np.float64(0.9538950715421306), array([0.814, 0.989]))"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"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": 10,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:19.750990Z",
"iopub.status.busy": "2026-10-28T22:48:19.750941Z",
"iopub.status.idle": "2026-10-28T22:48:19.754251Z",
"shell.execute_reply": "2026-10-28T22:48:19.753978Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>pu</th>\n",
" <th>peou</th>\n",
" <th>itu</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>7.00</td>\n",
" <td>7.00</td>\n",
" <td>7.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>6.75</td>\n",
" <td>6.00</td>\n",
" <td>7.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.75</td>\n",
" <td>4.75</td>\n",
" <td>4.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>6.50</td>\n",
" <td>6.50</td>\n",
" <td>6.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>6.75</td>\n",
" <td>4.75</td>\n",
" <td>6.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>6.00</td>\n",
" <td>6.00</td>\n",
" <td>6.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>5.50</td>\n",
" <td>6.00</td>\n",
" <td>7.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>6.25</td>\n",
" <td>4.25</td>\n",
" <td>5.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>4.75</td>\n",
" <td>3.75</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>7.00</td>\n",
" <td>5.50</td>\n",
" <td>7.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" pu peou itu\n",
"0 7.00 7.00 7.0\n",
"1 6.75 6.00 7.0\n",
"2 4.75 4.75 4.5\n",
"3 6.50 6.50 6.5\n",
"4 6.75 4.75 6.0\n",
"5 6.00 6.00 6.0\n",
"6 5.50 6.00 7.0\n",
"7 6.25 4.25 5.5\n",
"8 4.75 3.75 3.0\n",
"9 7.00 5.50 7.0"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"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": 11,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:19.754873Z",
"iopub.status.busy": "2026-10-28T22:48:19.754824Z",
"iopub.status.idle": "2026-10-28T22:48:19.756966Z",
"shell.execute_reply": "2026-10-28T22:48:19.756639Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"pu 6.125\n",
"peou 5.450\n",
"itu 5.950\n",
"dtype: float64"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tam[[\"pu\", \"peou\", \"itu\"]].mean()"
],
"id": "cell-11"
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:19.757577Z",
"iopub.status.busy": "2026-10-28T22:48:19.757526Z",
"iopub.status.idle": "2026-10-28T22:48:19.759604Z",
"shell.execute_reply": "2026-10-28T22:48:19.759243Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"pu 6.375\n",
"peou 5.750\n",
"itu 6.250\n",
"dtype: float64"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tam[[\"pu\", \"peou\", \"itu\"]].median()"
],
"id": "cell-12"
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:19.760166Z",
"iopub.status.busy": "2026-10-28T22:48:19.760119Z",
"iopub.status.idle": "2026-10-28T22:48:19.762217Z",
"shell.execute_reply": "2026-10-28T22:48:19.761889Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"pu 0.859990\n",
"peou 1.039498\n",
"itu 1.321825\n",
"dtype: float64"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tam[[\"pu\", \"peou\", \"itu\"]].std()"
],
"id": "cell-13"
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:19.762756Z",
"iopub.status.busy": "2026-10-28T22:48:19.762714Z",
"iopub.status.idle": "2026-10-28T22:48:19.764568Z",
"shell.execute_reply": "2026-10-28T22:48:19.764260Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"PearsonRResult(statistic=np.float64(0.5515422017785757), pvalue=np.float64(0.09838124227663884))"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"stats.pearsonr(tam[\"peou\"], tam[\"pu\"])"
],
"id": "cell-14"
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:19.765159Z",
"iopub.status.busy": "2026-10-28T22:48:19.765111Z",
"iopub.status.idle": "2026-10-28T22:48:19.766812Z",
"shell.execute_reply": "2026-10-28T22:48:19.766534Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"PearsonRResult(statistic=np.float64(0.8066270322592025), pvalue=np.float64(0.004809023073122994))"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"stats.pearsonr(tam[\"peou\"], tam[\"itu\"])"
],
"id": "cell-15"
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:19.767398Z",
"iopub.status.busy": "2026-10-28T22:48:19.767356Z",
"iopub.status.idle": "2026-10-28T22:48:19.769008Z",
"shell.execute_reply": "2026-10-28T22:48:19.768714Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"PearsonRResult(statistic=np.float64(0.7880605510627579), pvalue=np.float64(0.006774486564715021))"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"stats.pearsonr(tam[\"pu\"], tam[\"itu\"])"
],
"id": "cell-16"
}
],
"metadata": {
"kernelspec": {
"display_name": "GreatAI (local)",
"language": "python",
"name": "great-ai-local"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.5"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in a new issue View git blame Copy permalink