noah/QM-7063-Learning-Practice-9
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Data pre-processing work

Browse Source
This commit is contained in:
Noah L. Schrick 2023-04-01 20:30:24 -05:00
parent 57d398b6bc
commit 3555a14f54
1 changed files with 44 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
Schrick-Noah_Learning-Practice-9.ipynb
View File

@ -14,11 +14,20 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 6,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# Imports" "# Imports\n",
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"from sklearn import preprocessing\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"\n",
"%matplotlib inline"
] ]
}, },
{ {
@ -32,11 +41,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 5,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# a" "# a\n",
"accidents_df = pd.read_csv('accidentsFull.csv')\n",
"accidents_df = accidents_df.apply(pd.to_numeric) # convert all columns of DataFrame\n"
] ]
}, },
{ {
@ -50,11 +61,21 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 7,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# b." "# b.\n",
"## Normalize\n",
"scaler = preprocessing.StandardScaler()\n",
"\n",
"accident_cols = accidents_df.columns.values.tolist()\n",
"\n",
"scaler.fit(accidents_df[accident_cols]) # Note the use of an array of column names\n",
"\n",
"# Transform the full dataset\n",
"accidentsNorm = pd.DataFrame(scaler.transform(accidents_df[accident_cols]), \n",
" columns=accident_cols)"
] ]
}, },
{ {
@ -72,7 +93,8 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# c." "# c.\n",
"trainData, validData = train_test_split(accidentsNorm, test_size=0.4, random_state=26)"
] ]
}, },
{ {
@ -149,8 +171,22 @@
} }
], ],
"metadata": { "metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": { "language_info": {
"name": "python" "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 "orig_nbformat": 4
}, },