{
"cells": [
{
"cell_type": "markdown",
"id": "078900c6-d71d-44f0-9e76-cc5ce66f0ca9",
"metadata": {},
"source": [
"# Logistic regression: exploring bootstrapping\n",
"\n",
"Exploring different boostrapping idea:\n",
"\n",
"* non-parametric with minimal constraint (no empty group)\n",
"* stratified non-parametric\n",
"* comparing with MLE asymptotic approx"
]
},
{
"cell_type": "markdown",
"id": "e18cec5e",
"metadata": {},
"source": [
"## Common"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "3b351af7",
"metadata": {},
"outputs": [],
"source": [
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"import scipy\n",
"\n",
"import pandas as pd\n",
"import seaborn as sns\n",
"import os\n",
"\n",
"from sklearn import linear_model\n",
"\n",
"# our libs\n",
"import data_utils\n",
"import logit_utils\n",
"\n",
"# testing multivariate normal\n",
"import pingouin as pg\n",
"import mvn"
]
},
{
"cell_type": "markdown",
"id": "e0de7f02-942b-42ff-874c-3c0e2ac1e0dc",
"metadata": {},
"source": [
"## Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3373f87f",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"results_path = \"./results\"\n",
"if not os.path.exists(results_path): os.makedirs(results_path)\n",
"\n",
"data_path = \"../../data/\"\n",
"suv_filename = os.path.join(data_path, \"suv_percentilesSLOthenUWM.mat\")\n",
"flags_filename = os.path.join(data_path,\"flags_combined.mat\")\n",
"normal_range_filename = os.path.join(data_path, \"normal_range.mat\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "811d990d",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"\"\"\"\n",
"Loading all data\n",
"\"\"\"\n",
"suv_dict = scipy.io.loadmat(suv_filename)\n",
"flags_dict = scipy.io.loadmat(flags_filename)\n",
"normal_range_dict = scipy.io.loadmat(normal_range_filename)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "4a292c31",
"metadata": {},
"outputs": [],
"source": [
"# get data\n",
"perc = 95\n",
"organ = \"lung\"\n",
"x, y = data_utils.get_data(organ, perc, suv_dict, flags_dict)"
]
},
{
"cell_type": "markdown",
"id": "35e9bb7b-5a50-4cae-9af4-261c11453dd4",
"metadata": {},
"source": [
"## Fit\n",
"\n",
"Ref: logistic regression documentation\n",
"* https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
"* https://stats.stackexchange.com/questions/186830/what-is-scikit-learns-logisticregression-minimizing"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "239ae789",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"pars = array([-11.68319035, 5.68708926])\n"
]
}
],
"source": [
"# fits\n",
"logr = linear_model.LogisticRegression(penalty = None)\n",
"pars = logit_utils.logit_poly_fit(logr, x, y, degree = 1)\n",
"print(f\"{pars = }\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "9cf6fec1",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"cov_pars = array([[12.31854544, -6.71118734],\n",
" [-6.71118734, 3.81820749]])\n"
]
}
],
"source": [
"# asymptotic covariance matrix of parameters\n",
"cov_pars = logit_utils.logit_poly_cov(x, pars)\n",
"print(f\"{cov_pars = }\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2359d3c1",
"metadata": {},
"outputs": [],
"source": [
"# defining twosided probabilities\n",
"alpha = 0.05 # significance level\n",
"probs = [alpha/2, 1 - alpha/2]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "4ba4d5d4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"pars_CI = array([[-18.5622299 , 1.85727375],\n",
" [ -4.80415081, 9.51690477]])\n"
]
}
],
"source": [
"# CI of params (assuming asymptotic distr of parameters)\n",
"pars_CI = logit_utils.logit_poly_pars_quantiles_normal(probs, pars, cov_pars)\n",
"print(f\"{pars_CI = }\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "96acc3ab",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.microsoft.datawrangler.viewer.v0+json": {
"columns": [
{
"name": "index",
"rawType": "object",
"type": "string"
},
{
"name": "value",
"rawType": "float64",
"type": "float"
},
{
"name": "LCL",
"rawType": "float64",
"type": "float"
},
{
"name": "UCL",
"rawType": "float64",
"type": "float"
}
],
"ref": "0aa78a15-d75a-46c7-b90f-b46c53f128d8",
"rows": [
[
"b0",
"-11.683190353932442",
"-18.562229897321515",
"-4.804150810543373"
],
[
"b1",
"5.687089258005262",
"1.8572737464039784",
"9.516904769606544"
]
],
"shape": {
"columns": 3,
"rows": 2
}
},
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" value | \n",
" LCL | \n",
" UCL | \n",
"
\n",
" \n",
" \n",
" \n",
" | b0 | \n",
" -11.683190 | \n",
" -18.562230 | \n",
" -4.804151 | \n",
"
\n",
" \n",
" | b1 | \n",
" 5.687089 | \n",
" 1.857274 | \n",
" 9.516905 | \n",
"
\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" n | \n",
" k | \n",
" dof | \n",
" LLF | \n",
" AIC | \n",
" BIC | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 58 | \n",
" 2 | \n",
" 56 | \n",
" -7.394196 | \n",
" 18.788392 | \n",
" 22.909278 | \n",
"
\n",
" \n",
"
\n",
"