aboutsummaryrefslogtreecommitdiff
path: root/notebooks/raw_data_exploration.ipynb
diff options
context:
space:
mode:
authorChristian Cleberg <hello@cleberg.net>2024-01-23 16:16:25 -0600
committerChristian Cleberg <hello@cleberg.net>2024-01-23 16:16:25 -0600
commitce1c40b7dfccf62e4434795bf46dae27d1678a99 (patch)
tree8b61c2a8d3a4f9feb1f4bb783cfeae53f5956012 /notebooks/raw_data_exploration.ipynb
downloadomaha-incidents-ce1c40b7dfccf62e4434795bf46dae27d1678a99.tar.gz
omaha-incidents-ce1c40b7dfccf62e4434795bf46dae27d1678a99.tar.bz2
omaha-incidents-ce1c40b7dfccf62e4434795bf46dae27d1678a99.zip
initial commit
Diffstat (limited to 'notebooks/raw_data_exploration.ipynb')
-rw-r--r--notebooks/raw_data_exploration.ipynb99
1 files changed, 99 insertions, 0 deletions
diff --git a/notebooks/raw_data_exploration.ipynb b/notebooks/raw_data_exploration.ipynb
new file mode 100644
index 0000000..46c3a43
--- /dev/null
+++ b/notebooks/raw_data_exploration.ipynb
@@ -0,0 +1,99 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Omaha Incidents"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Prerequisites\n",
+ "\n",
+ "You must download the data from the URL below first.\n",
+ "\n",
+ "https://police.cityofomaha.org/crime-information/incident-data-download"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Data Exploration\n",
+ "\n",
+ "Let's explore the data a little bit to see what kind of analysis and visualizations we want to implement."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# import data\n",
+ "df = pd.read_csv(\"../raw_data/Incidents_2015.csv\")\n",
+ "\n",
+ "# test to see what the dataframe looks like\n",
+ "df.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# !pip install \"matplotlib\"\n",
+ "import numpy\n",
+ "import matplotlib\n",
+ "%matplotlib inline"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# test plotting by sorting & plotting top 5 crime categories\n",
+ "s = df.value_counts(subset=[\"Statute/Ordinance Description\"])\n",
+ "t = s.nlargest(5)\n",
+ "t.head()\n",
+ "t.plot(kind=\"bar\", title=\"Top 5 Incident Categories\")"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "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": "3.11.7"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}