Crime Data Analysis Project

Project Overview

This project analyzes crime trends in Ireland using two datasets crime_data_set1(source1) and crime_data_set2(source2). The data has been processed, cleaned, and joined using Azure Data Factory, resulting in a consolidated dataset named today.csv(sink). The analysis aims to provide actionable insights into crime patterns, distribution, and hotspots across Ireland.

---

Goals and Implemented Logics

1. Yearly Crime Trends in Ireland

Analyzed yearly changes in crime rates across Ireland.

2. Top Offense Types in Ireland

Most common types of offenses committed in Ireland and their frequency.

3. Crime Distribution across Counties

Crimes across different counties to highlight areas of concern.

4. Nearest Crime Location Station from End User

Mapped crime locations to the nearest Garda police stations to provide location-based insights.

5. Highest Crime Areas in Dublin

=Dublin with the highest crime rates.

7. Most Common Crime in Ireland

Most frequently occurring crime type across Ireland.

8. Top 10 Counties for Theft and Related Offenses in Ireland

Ranked the top counties for theft and related offenses regional trends.

9. Crime Offenses in Maynooth

specific crime types and their occurrences in Maynooth.

---

Tools and Architecture

1. Azure Data Factory

• Data Sources: source1 and source2
• Data Processing: Merging, cleaning, and pushing data using transformations (e.g., derived columns, joins).
• Sink: Pushed processed data into PostgreSQL for further querying and storage.

2. Azure Databricks

• Used for advanced data cleaning, filtering, and transformations before visualizations.

3. PostgreSQL

• Stored the cleaned data for efficient querying and further analysis.

4. QGIS

• Visualized crime data on maps to conduct spatial analysis and identify hotspots.

5. Power BI

• Created interactive dashboards and data visualizations for deeper insights into crime patterns.
• Power BI Report Click

---

Files in the Repository

1. crime_data_set1.csv: Raw dataset 1 containing crime records.
2. crime_data_set2.csv: Raw dataset 2 containing additional crime records.
3. today.csv: Processed dataset resulting from the merging and cleaning of the two raw datasets.
4. README.md: Documentation for the project.

---

How to Use

1. Clone the repository:

   git clone <repository-url>

2. Load the today.csv file into your preferred analysis tool (e.g., Python, PostgreSQL, QGIS, or Power BI).

3. Use the SQL scripts or Python notebooks provided (if applicable) to replicate the analyses.

4. Visualize data using QGIS or Power BI for geospatial and interactive insights.

---

Insights Derived

• Temporal crime trends to inform policymaking and resource allocation.
• Identification of crime-prone areas for targeted interventions.
• Insights into specific crime categories and their geographical prevalence.

---

Future Work

• Automate the workflow using Azure Data Factory pipelines for real-time data updates.
• Expand the analysis to include additional crime-related datasets.
• Incorporate predictive analytics for crime forecasting.