Since Jan. 1, 2015, The Washington Post has been compiling a database of every fatal shooting in the US by a police officer in the line of duty. This project aims to analyze this dataset along with additional datasets containing US census data on poverty rate, high school graduation rate, median household income, and racial demographics. This analysis will explore the relationships and insights that can be derived from these datasets using various data visualization libraries such as Matplotlib, Seaborn, and Plotly.
- Open the provided Google Colab notebook ('Fatal_Force_(start).ipynb') to visualize the analysis, to view ploty plots open the notebook in Google Colab.
The analysis utilizes a variety of graphs to provide insights into the dataset:
- Matplotlib Line Plot
- Matplotlib Bar Plot
- Plotly Stacked Bar Graph
- Plotly Donut Chart
- Seaborn Kernel Density Plot
- Seaborn FacetGrid
- Seaborn Regression Line Plot
The analysis yielded several significant results:
- Temporal Trends: Police shootings show variations over time, with some years exhibiting higher incidents than others.
- Racial Disparities: There are noticeable racial disparities in police shootings, with certain racial groups being disproportionately affected.
- Gender Analysis: The gender distribution of victims reveals interesting patterns in police shootings.
- Mental Health Impact: A proportion of victims were experiencing mental health crises at the time of the incidents.
- Dangerous Locations: Certain cities and states have a higher rate of police shootings compared to others.
- Armed vs. Unarmed: The analysis indicates how frequently victims were armed and how this correlates with their fate.
- Age Distribution: The age distribution of victims varies, with peaks at certain age ranges.
- Poverty and Shootings: There seems to be a relationship between poverty rates and the occurrence of police shootings.
These insights shed light on the complexities surrounding police shootings in the US and provide a starting point for further investigation and discussion.