175 lines
4.5 KiB
Plaintext
175 lines
4.5 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Learning Practice 10 for the University of Tulsa's QM-7063 Data Mining Course\n",
|
|
"# Evaluating Predictive Performance\n",
|
|
"# Professor: Dr. Abdulrashid, Spring 2023\n",
|
|
"# Noah L. Schrick - 1492657"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Imports"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pandas as pd"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Problem 5.7 \n",
|
|
"Table 5.7 shows a small set of predictive model validation results for a classification\n",
|
|
"model, with both actual values and propensities.\n",
|
|
"\n",
|
|
"| Propensity of 1 | Actual |\n",
|
|
"|-----------------|-----------------|\n",
|
|
"| 0.03 | 0 |\n",
|
|
"| 0.52 | 0 |\n",
|
|
"| 0.38 | 0 |\n",
|
|
"| 0.82 | 1 |\n",
|
|
"| 0.33 | 0 |\n",
|
|
"| 0.42 | 0 |\n",
|
|
"| 0.55 | 1 |\n",
|
|
"| 0.59 | 0 |\n",
|
|
"| 0.09 | 0 |\n",
|
|
"| 0.21 | 0 |\n",
|
|
"| 0.43 | 0 |\n",
|
|
"| 0.04 | 0 |\n",
|
|
"| 0.08 | 0 |\n",
|
|
"| 0.13 | 0 |\n",
|
|
"| 0.01 | 0 |\n",
|
|
"| 0.79 | 1 |\n",
|
|
"| 0.42 | 0 |\n",
|
|
"| 0.29 | 0 |\n",
|
|
"| 0.08 | 0 |\n",
|
|
"| 0.02 | 0 |"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# a.\n",
|
|
"Calculate error rates, sensitivity, and specificity using cutoffs of 0.25, 0.5, and 0.75."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
" Propensity of 1 Actual\n",
|
|
"0 0.03 0\n",
|
|
"1 0.52 0\n",
|
|
"2 0.38 0\n",
|
|
"3 0.82 1\n",
|
|
"4 0.33 0\n",
|
|
"5 0.42 0\n",
|
|
"6 0.55 1\n",
|
|
"7 0.59 0\n",
|
|
"8 0.09 0\n",
|
|
"9 0.21 0\n",
|
|
"10 0.43 0\n",
|
|
"11 0.04 0\n",
|
|
"12 0.08 0\n",
|
|
"13 0.13 0\n",
|
|
"14 0.01 0\n",
|
|
"15 0.79 1\n",
|
|
"16 0.42 0\n",
|
|
"17 0.29 0\n",
|
|
"18 0.08 0\n",
|
|
"19 0.02 0\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"data = [\n",
|
|
" [0.03, 0],\n",
|
|
" [0.52, 0],\n",
|
|
" [0.38, 0], \n",
|
|
" [0.82, 1], \n",
|
|
" [0.33, 0], \n",
|
|
" [0.42, 0], \n",
|
|
" [0.55, 1], \n",
|
|
" [0.59, 0], \n",
|
|
" [0.09, 0], \n",
|
|
" [0.21, 0], \n",
|
|
" [0.43, 0], \n",
|
|
" [0.04, 0], \n",
|
|
" [0.08, 0], \n",
|
|
" [0.13, 0], \n",
|
|
" [0.01, 0], \n",
|
|
" [0.79, 1], \n",
|
|
" [0.42, 0], \n",
|
|
" [0.29, 0], \n",
|
|
" [0.08, 0],\n",
|
|
" [0.02, 0]\n",
|
|
" ]\n",
|
|
"\n",
|
|
"table = pd.DataFrame(data, columns = ['Propensity of 1', 'Actual'])\n",
|
|
"print(table)"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# b.\n",
|
|
"Create a decile lift chart."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"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": "3.10.10"
|
|
},
|
|
"orig_nbformat": 4
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|