Masego999/CRIME_STATS_ANALYSIS-

This project involved cleaning, processing, and analyzing South African crime complaint data to uncover trends, hotspots, and insights for actionable decision-making. Using Python (Pandas, Matplotlib, Seaborn) in a Jupyter Notebook, I handled missing values, converted data types, and reshaped the dataset to enable meaningful analysis. # CRIME_STATS_ANALYSIS- This project involved cleaning, processing, and analyzing South African crime complaint data to uncover trends, hotspots, and insights for actionable decision-making. Using Python (Pandas, Matplotlib, Seaborn) in a Jupyter Notebook, I handled missing values, converted data types, and reshaped the dataset to enable meaningful analysis. # Crime Data Analysis – South Africa This project analyzes South African crime complaints to identify trends and hotspots. ## Overview - Cleaned messy complaint data (missing values, incorrect types) - Categorized crime types - Aggregated data by district, province, station, and year - Created visualizations to support insights ## Tools - Python (Pandas, Matplotlib, Seaborn) - Jupyter Notebook ## Visualizations - Total crimes by Offence - Crimes by District and Province - Top 10 Most Frequent Offences - Station-level heatmap over Years ## Usage 1. Clone the repo 2. Open `notebooks/Crime_Analysis.ipynb` in Jupyter 3. Run cells to reproduce the analysis ## Insights - Certain districts and provinces are crime hotspots - The top 10 offences account for a majority of total cases - Stations with high counts require more policing resources