From 3555a14f54e0799952716a869d1633dfb442ad16 Mon Sep 17 00:00:00 2001
From: noah <noah@theschricks.com>
Date: Sat, 1 Apr 2023 20:30:24 -0500
Subject: [PATCH] Data pre-processing work

---
 Schrick-Noah_Learning-Practice-9.ipynb | 52 ++++++++++++++++++++++----
 1 file changed, 44 insertions(+), 8 deletions(-)

diff --git a/Schrick-Noah_Learning-Practice-9.ipynb b/Schrick-Noah_Learning-Practice-9.ipynb
index 6f64da5..03a1508 100644
--- a/Schrick-Noah_Learning-Practice-9.ipynb
+++ b/Schrick-Noah_Learning-Practice-9.ipynb
@@ -14,11 +14,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "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",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "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",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "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": {},
    "outputs": [],
    "source": [
-    "# c."
+    "# c.\n",
+    "trainData, validData = train_test_split(accidentsNorm, test_size=0.4, random_state=26)"
    ]
   },
   {
@@ -149,8 +171,22 @@
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
   "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
  },