From ed714e64547ed8768395382d09bd965580105f32 Mon Sep 17 00:00:00 2001
From: Mirko Birbaumer <mirko.birbaumer@hslu.ch>
Date: Mon, 14 Oct 2024 07:17:12 +0000
Subject: [PATCH] renamed notebooks
---
notebooks/Model Comparison/MC_2_2.ipynb | 289 ++++++++++++++++++
.../pymc3_beta_posterior_predictive.ipynb | 172 -----------
2 files changed, 289 insertions(+), 172 deletions(-)
create mode 100644 notebooks/Model Comparison/MC_2_2.ipynb
delete mode 100644 notebooks/Model Comparison/pymc3_beta_posterior_predictive.ipynb
diff --git a/notebooks/Model Comparison/MC_2_2.ipynb b/notebooks/Model Comparison/MC_2_2.ipynb
new file mode 100644
index 0000000..2c0b985
--- /dev/null
+++ b/notebooks/Model Comparison/MC_2_2.ipynb
@@ -0,0 +1,289 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "WARNING (pytensor.tensor.blas): Using NumPy C-API based implementation for BLAS functions.\n"
+ ]
+ }
+ ],
+ "source": [
+ "%matplotlib inline\n",
+ "import pymc as pm\n",
+ "import matplotlib.pyplot as plt\n",
+ "import scipy.stats as st\n",
+ "import arviz as az\n",
+ "#import metropolis_commands as mc\n",
+ "import numpy as np\n",
+ "import warnings\n",
+ "warnings.filterwarnings(\"ignore\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Auto-assigning NUTS sampler...\n",
+ "Initializing NUTS using jitter+adapt_diag...\n",
+ "Multiprocess sampling (4 chains in 4 jobs)\n",
+ "NUTS: [theta]\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+ ],
+ "text/plain": []
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Sampling 4 chains for 1_000 tune and 1_000 draw iterations (4_000 + 4_000 draws total) took 3 seconds.\n"
+ ]
+ }
+ ],
+ "source": [
+ "trials = 20\n",
+ "head = 4 \n",
+ "\n",
+ "data = np.zeros(trials)\n",
+ "data[np.arange(head)] = 1\n",
+ "\n",
+ "alph = 5\n",
+ "bet = 2\n",
+ "\n",
+ "with pm.Model() as model:\n",
+ " theta = pm.Beta('theta', alpha=alph, beta=bet)\n",
+ " y = pm.Bernoulli('y', p=theta, observed=data)\n",
+ " trace = pm.sample()\n",
+ " "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Sampling: [y]\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+ ],
+ "text/plain": []
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/plain": [
+ "<Axes: xlabel='y'>"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 1200x400 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "pm.sample_posterior_predictive(trace, model=model, extend_inferencedata=True, random_seed=123)\n",
+ "az.plot_ppc(trace, num_pp_samples=100, figsize=(12, 4), colors=[\"C1\", \"C0\", \"C1\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {
+ "tags": []
+ },
+ "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>mean</th>\n",
+ " <th>sd</th>\n",
+ " <th>hdi_2.5%</th>\n",
+ " <th>hdi_97.5%</th>\n",
+ " <th>mcse_mean</th>\n",
+ " <th>mcse_sd</th>\n",
+ " <th>ess_bulk</th>\n",
+ " <th>ess_tail</th>\n",
+ " <th>r_hat</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>theta</th>\n",
+ " <td>0.335</td>\n",
+ " <td>0.09</td>\n",
+ " <td>0.16</td>\n",
+ " <td>0.512</td>\n",
+ " <td>0.002</td>\n",
+ " <td>0.002</td>\n",
+ " <td>1655.0</td>\n",
+ " <td>2971.0</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " mean sd hdi_2.5% hdi_97.5% mcse_mean mcse_sd ess_bulk \\\n",
+ "theta 0.335 0.09 0.16 0.512 0.002 0.002 1655.0 \n",
+ "\n",
+ " ess_tail r_hat \n",
+ "theta 2971.0 1.0 "
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "az.summary(trace, hdi_prob=.95)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<Axes: title={'center': 'theta'}>"
+ ]
+ },
+ "execution_count": 9,
+ "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": [
+ "az.plot_posterior(trace, hdi_prob=.95, point_estimate=\"mode\")"
+ ]
+ }
+ ],
+ "metadata": {
+ "hide_input": false,
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "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": "3.10.11"
+ },
+ "varInspector": {
+ "cols": {
+ "lenName": 16,
+ "lenType": 16,
+ "lenVar": 40
+ },
+ "kernels_config": {
+ "python": {
+ "delete_cmd_postfix": "",
+ "delete_cmd_prefix": "del ",
+ "library": "var_list.py",
+ "varRefreshCmd": "print(var_dic_list())"
+ },
+ "r": {
+ "delete_cmd_postfix": ") ",
+ "delete_cmd_prefix": "rm(",
+ "library": "var_list.r",
+ "varRefreshCmd": "cat(var_dic_list()) "
+ }
+ },
+ "types_to_exclude": [
+ "module",
+ "function",
+ "builtin_function_or_method",
+ "instance",
+ "_Feature"
+ ],
+ "window_display": false
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/notebooks/Model Comparison/pymc3_beta_posterior_predictive.ipynb b/notebooks/Model Comparison/pymc3_beta_posterior_predictive.ipynb
deleted file mode 100644
index 15e16aa..0000000
--- a/notebooks/Model Comparison/pymc3_beta_posterior_predictive.ipynb
+++ /dev/null
@@ -1,172 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {
- "tags": []
- },
- "outputs": [],
- "source": [
- "%matplotlib inline\n",
- "import pymc as pm\n",
- "import matplotlib.pyplot as plt\n",
- "import scipy.stats as st\n",
- "import arviz as az\n",
- "#import metropolis_commands as mc\n",
- "import numpy as np\n",
- "import warnings\n",
- "warnings.filterwarnings(\"ignore\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "metadata": {
- "tags": []
- },
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "Auto-assigning NUTS sampler...\n",
- "Initializing NUTS using jitter+adapt_diag...\n",
- "Multiprocess sampling (4 chains in 4 jobs)\n",
- "NUTS: [theta]\n"
- ]
- },
- {
- "data": {
- "text/html": [
- "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
- ],
- "text/plain": []
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "Sampling 4 chains for 1_000 tune and 1_000 draw iterations (4_000 + 4_000 draws total) took 3 seconds.\n"
- ]
- }
- ],
- "source": [
- "trials = 20\n",
- "head = 4 \n",
- "\n",
- "data = np.zeros(trials)\n",
- "data[np.arange(head)] = 1\n",
- "\n",
- "alph = 5\n",
- "bet = 2\n",
- "\n",
- "with pm.Model() as our_first_model:\n",
- " theta = pm.Beta('theta', alpha=alph, beta=bet)\n",
- " y = pm.Bernoulli('y', p=theta, observed=data)\n",
- " trace = pm.sample()\n",
- " "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "metadata": {
- "tags": []
- },
- "outputs": [
- {
- "ename": "AttributeError",
- "evalue": "'int' object has no attribute 'potentials'",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[0;32mIn[4], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m y_ppc_t \u001b[38;5;241m=\u001b[39m \u001b[43mpm\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msample_posterior_predictive\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtrace\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m100\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mour_first_model\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2\u001b[0m y_pred_t \u001b[38;5;241m=\u001b[39m az\u001b[38;5;241m.\u001b[39mfrom_pymc(trace\u001b[38;5;241m=\u001b[39mtrace, posterior_predictive\u001b[38;5;241m=\u001b[39my_ppc_t)\n\u001b[1;32m 3\u001b[0m ay \u001b[38;5;241m=\u001b[39m az\u001b[38;5;241m.\u001b[39mplot_ppc(y_pred_t, figsize\u001b[38;5;241m=\u001b[39m(\u001b[38;5;241m12\u001b[39m, \u001b[38;5;241m6\u001b[39m), mean\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n",
- "File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymc/sampling/forward.py:807\u001b[0m, in \u001b[0;36msample_posterior_predictive\u001b[0;34m(trace, model, var_names, sample_dims, random_seed, progressbar, progressbar_theme, return_inferencedata, extend_inferencedata, predictions, idata_kwargs, compile_kwargs)\u001b[0m\n\u001b[1;32m 803\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m samples \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 805\u001b[0m model \u001b[38;5;241m=\u001b[39m modelcontext(model)\n\u001b[0;32m--> 807\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpotentials\u001b[49m:\n\u001b[1;32m 808\u001b[0m warnings\u001b[38;5;241m.\u001b[39mwarn(\n\u001b[1;32m 809\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThe effect of Potentials on other parameters is ignored during posterior predictive sampling. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 810\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThis is likely to lead to invalid or biased predictive samples.\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 811\u001b[0m \u001b[38;5;167;01mUserWarning\u001b[39;00m,\n\u001b[1;32m 812\u001b[0m stacklevel\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m2\u001b[39m,\n\u001b[1;32m 813\u001b[0m )\n\u001b[1;32m 815\u001b[0m constant_coords \u001b[38;5;241m=\u001b[39m get_constant_coords(trace_coords, model)\n",
- "\u001b[0;31mAttributeError\u001b[0m: 'int' object has no attribute 'potentials'"
- ]
- }
- ],
- "source": [
- "y_ppc_t = pm.sample_posterior_predictive(trace, 100, our_first_model)\n",
- "y_pred_t = az.from_pymc(trace=trace, posterior_predictive=y_ppc_t)\n",
- "ay = az.plot_ppc(y_pred_t, figsize=(12, 6), mean=False)\n",
- "ay[0].legend(fontsize=15)\n",
- "plt.xlim(40, 70)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "az.summary(trace, hdi_prob=.95)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "az.plot_posterior(trace, hdi_prob=.95, point_estimate=\"mode\")"
- ]
- }
- ],
- "metadata": {
- "hide_input": false,
- "kernelspec": {
- "display_name": "Python 3 (ipykernel)",
- "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": "3.10.11"
- },
- "varInspector": {
- "cols": {
- "lenName": 16,
- "lenType": 16,
- "lenVar": 40
- },
- "kernels_config": {
- "python": {
- "delete_cmd_postfix": "",
- "delete_cmd_prefix": "del ",
- "library": "var_list.py",
- "varRefreshCmd": "print(var_dic_list())"
- },
- "r": {
- "delete_cmd_postfix": ") ",
- "delete_cmd_prefix": "rm(",
- "library": "var_list.r",
- "varRefreshCmd": "cat(var_dic_list()) "
- }
- },
- "types_to_exclude": [
- "module",
- "function",
- "builtin_function_or_method",
- "instance",
- "_Feature"
- ],
- "window_display": false
- }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}
--
GitLab