diff --git a/examples/generalized_linear_models/GLM-out-of-sample-predictions.ipynb b/examples/generalized_linear_models/GLM-out-of-sample-predictions.ipynb
index e7f2bee1b..2307aea8c 100644
--- a/examples/generalized_linear_models/GLM-out-of-sample-predictions.ipynb
+++ b/examples/generalized_linear_models/GLM-out-of-sample-predictions.ipynb
@@ -4,61 +4,50 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "# GLM in PyMC3: Out-Of-Sample Predictions\n",
+ "(GLM-out-of-sample-predictions)=\n",
+ "# Out-Of-Sample Predictions\n",
"\n",
- "In this notebook I explore the [glm](https://docs.pymc.io/api/glm.html) module of [PyMC3](https://docs.pymc.io/). I am particularly interested in the model definition using [patsy](https://patsy.readthedocs.io/en/latest/) formulas, as it makes the model evaluation loop faster (easier to include features and/or interactions). There are many good resources on this subject, but most of them evaluate the model in-sample. For many applications we require doing predictions on out-of-sample data. This experiment was motivated by the discussion of the thread [\"Out of sample\" predictions with the GLM sub-module](https://discourse.pymc.io/t/out-of-sample-predictions-with-the-glm-sub-module/773) on the (great!) forum [discourse.pymc.io/](https://discourse.pymc.io/), thank you all for your input!\n",
- "\n",
- "**Resources**\n",
- "\n",
- "\n",
- "- [PyMC3 Docs: Example Notebooks](https://docs.pymc.io/nb_examples/index.html)\n",
- " \n",
- " - In particular check [GLM: Logistic Regression](https://docs.pymc.io/notebooks/GLM-logistic.html)\n",
- "\n",
- "- [Bambi](https://bambinos.github.io/bambi/), a more complete implementation of the GLM submodule which also allows for mixed-effects models.\n",
- "\n",
- "- [Bayesian Analysis with Python (Second edition) - Chapter 4](https://github.com/aloctavodia/BAP/blob/master/code/Chp4/04_Generalizing_linear_models.ipynb)\n",
- "- [Statistical Rethinking](https://xcelab.net/rm/statistical-rethinking/)"
+ ":::{post} June, 2022\n",
+ ":tags: generalized linear model, logistic regression, out of sample predictions, patsy\n",
+ ":category: beginner\n",
+ ":::"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
- "## Prepare Notebook"
+ "For many applications we require doing predictions on out-of-sample data. This experiment was motivated by the discussion of the thread [\"Out of sample\" predictions with the GLM sub-module](https://discourse.pymc.io/t/out-of-sample-predictions-with-the-glm-sub-module/773) on the (great!) forum [discourse.pymc.io/](https://discourse.pymc.io/), thank you all for your input! But note that this GLM sub-module was deprecated in favour of [`bambi`](https://github.com/bambinos/bambi). But this notebook implements a 'raw' PyMC model."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "WARNING (theano.tensor.blas): Using NumPy C-API based implementation for BLAS functions.\n"
- ]
- }
- ],
+ "outputs": [],
"source": [
+ "import arviz as az\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"import pandas as pd\n",
- "import seaborn as sns\n",
- "\n",
- "sns.set_style(style=\"darkgrid\", rc={\"axes.facecolor\": \".9\", \"grid.color\": \".8\"})\n",
- "sns.set_palette(palette=\"deep\")\n",
- "sns_c = sns.color_palette(palette=\"deep\")\n",
- "\n",
- "import arviz as az\n",
"import patsy\n",
- "import pymc3 as pm\n",
- "\n",
- "from pymc3 import glm\n",
+ "import pymc as pm\n",
+ "import seaborn as sns\n",
"\n",
- "plt.rcParams[\"figure.figsize\"] = [7, 6]\n",
- "plt.rcParams[\"figure.dpi\"] = 100"
+ "from scipy.special import expit as inverse_logit\n",
+ "from sklearn.metrics import RocCurveDisplay, accuracy_score, auc, roc_curve\n",
+ "from sklearn.model_selection import train_test_split"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "RANDOM_SEED = 8927\n",
+ "rng = np.random.default_rng(RANDOM_SEED)\n",
+ "az.style.use(\"arviz-darkgrid\")"
]
},
{
@@ -72,7 +61,7 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 3,
"metadata": {},
"outputs": [
{
@@ -104,32 +93,32 @@
" \n",
" \n",
" 0 \n",
- " 0.993428 \n",
- " -2.521768 \n",
+ " -0.445284 \n",
+ " 1.381325 \n",
" 0 \n",
" \n",
" \n",
" 1 \n",
- " -0.276529 \n",
- " 1.835724 \n",
- " 0 \n",
+ " 2.651317 \n",
+ " 0.800736 \n",
+ " 1 \n",
" \n",
" \n",
" 2 \n",
- " 1.295377 \n",
- " 4.244312 \n",
- " 1 \n",
+ " -1.141940 \n",
+ " -0.128204 \n",
+ " 0 \n",
" \n",
" \n",
" 3 \n",
- " 3.046060 \n",
- " 2.064931 \n",
- " 1 \n",
+ " 1.336498 \n",
+ " -0.931965 \n",
+ " 0 \n",
" \n",
" \n",
" 4 \n",
- " -0.468307 \n",
- " -3.038740 \n",
+ " 2.290762 \n",
+ " 3.400222 \n",
" 1 \n",
" \n",
" \n",
@@ -138,39 +127,34 @@
],
"text/plain": [
" x1 x2 y\n",
- "0 0.993428 -2.521768 0\n",
- "1 -0.276529 1.835724 0\n",
- "2 1.295377 4.244312 1\n",
- "3 3.046060 2.064931 1\n",
- "4 -0.468307 -3.038740 1"
+ "0 -0.445284 1.381325 0\n",
+ "1 2.651317 0.800736 1\n",
+ "2 -1.141940 -0.128204 0\n",
+ "3 1.336498 -0.931965 0\n",
+ "4 2.290762 3.400222 1"
]
},
- "execution_count": 2,
+ "execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "SEED = 42\n",
- "np.random.seed(SEED)\n",
- "\n",
- "# Number of data points.\n",
+ "# Number of data points\n",
"n = 250\n",
- "# Create features.\n",
- "x1 = np.random.normal(loc=0.0, scale=2.0, size=n)\n",
- "x2 = np.random.normal(loc=0.0, scale=2.0, size=n)\n",
- "epsilon = np.random.normal(loc=0.0, scale=0.5, size=n)\n",
- "# Define target variable.\n",
+ "# Create features\n",
+ "x1 = rng.normal(loc=0.0, scale=2.0, size=n)\n",
+ "x2 = rng.normal(loc=0.0, scale=2.0, size=n)\n",
+ "# Define target variable\n",
"intercept = -0.5\n",
"beta_x1 = 1\n",
"beta_x2 = -1\n",
"beta_interaction = 2\n",
"z = intercept + beta_x1 * x1 + beta_x2 * x2 + beta_interaction * x1 * x2\n",
- "p = 1 / (1 + np.exp(-z))\n",
- "y = np.random.binomial(n=1, p=p, size=n)\n",
- "\n",
+ "p = inverse_logit(z)\n",
+ "# note binimial with n=1 is equal to a bernoulli\n",
+ "y = rng.binomial(n=1, p=p, size=n)\n",
"df = pd.DataFrame(dict(x1=x1, x2=x2, y=y))\n",
- "\n",
"df.head()"
]
},
@@ -183,3207 +167,22 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 4,
"metadata": {},
"outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Users/benjamv/opt/anaconda3/envs/pymc-dev-py39/lib/python3.9/site-packages/seaborn/axisgrid.py:64: UserWarning: This figure was using constrained_layout, but that is incompatible with subplots_adjust and/or tight_layout; disabling constrained_layout.\n",
+ " self.fig.tight_layout(*args, **kwargs)\n"
+ ]
+ },
{
"data": {
- "image/png": "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\n",
- "image/svg+xml": [
- "\n",
- "\n",
- "\n",
- "\n",
- " \n",
- " \n",
- " \n",
- " \n",
- " 2021-03-02T16:30:47.727416 \n",
- " image/svg+xml \n",
- " \n",
- " \n",
- " Matplotlib v3.3.4, https://matplotlib.org/ \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- " \n",
- "