{
"cells": [
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"# Learning Practice 2 for the University of Tulsa's QM-7063 Data Mining Course\n",
"# Dimension Reduction\n",
"# Professor: Dr. Abdulrashid, Spring 2023\n",
"# Noah L. Schrick - 1492657\n",
"\n",
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn.decomposition import PCA\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"## Read in Breakfast Cereal data\n",
"cereals_df = pd.read_csv('Cereals.csv')\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" mean | \n",
" median | \n",
" min | \n",
" max | \n",
" sd | \n",
"
\n",
" \n",
" \n",
" \n",
" | calories | \n",
" 106.883117 | \n",
" 110.00 | \n",
" 50.00 | \n",
" 160.0 | \n",
" 19.484119 | \n",
"
\n",
" \n",
" | sodium | \n",
" 159.675325 | \n",
" 180.00 | \n",
" 0.00 | \n",
" 320.0 | \n",
" 83.832295 | \n",
"
\n",
" \n",
" | protein | \n",
" 2.545455 | \n",
" 3.00 | \n",
" 1.00 | \n",
" 6.0 | \n",
" 1.094790 | \n",
"
\n",
" \n",
" | fat | \n",
" 1.012987 | \n",
" 1.00 | \n",
" 0.00 | \n",
" 5.0 | \n",
" 1.006473 | \n",
"
\n",
" \n",
" | fiber | \n",
" 2.151948 | \n",
" 2.00 | \n",
" 0.00 | \n",
" 14.0 | \n",
" 2.383364 | \n",
"
\n",
" \n",
" | carbo | \n",
" 14.802632 | \n",
" 14.50 | \n",
" 5.00 | \n",
" 23.0 | \n",
" 3.907326 | \n",
"
\n",
" \n",
" | sugars | \n",
" 7.026316 | \n",
" 7.00 | \n",
" 0.00 | \n",
" 15.0 | \n",
" 4.378656 | \n",
"
\n",
" \n",
" | potass | \n",
" 98.666667 | \n",
" 90.00 | \n",
" 15.00 | \n",
" 330.0 | \n",
" 70.410636 | \n",
"
\n",
" \n",
" | weight | \n",
" 1.029610 | \n",
" 1.00 | \n",
" 0.50 | \n",
" 1.5 | \n",
" 0.150477 | \n",
"
\n",
" \n",
" | cups | \n",
" 0.821039 | \n",
" 0.75 | \n",
" 0.25 | \n",
" 1.5 | \n",
" 0.232716 | \n",
"
\n",
" \n",
"
\n",
"