Homicide Data Observations: Guns and Family Trageties

Posted on Jul 30, 2018
The skills the author demoed here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.


Explore and visualize the general trends in the data on homicide incidences in US during 1980-2014 using ShinyApp: What's the demographic distribution of those crimes? How did the weapons used in the crime change over time? Were the perpetrators and victims totally strangers most of the time?

Welcome to my ShinyApp blog post! My project is based on the database of Homicide Reports in US, 1980-2014 provided by FBI and FOIA (Freedom of Information Act). It is part of the MAP (Murder Accountability Project) database, which is the most complete database of homicides in the US currently available. There are about 640,000 homicide records, including the time, location and the weapon used in each case, the gender, age, race and ethnicity information of victims and perpetrators, as well as the relationship between the victim and perpetrator. The dataset in csv version can be found onΒ Kaggle.

The goal of this ShinyApp is to explore the trends in the homicides cases in US in the past three decades, visualize the geographic distribution of the incidences, the age and gender of the victims and perpetrators, the weapon used by different age and gender groups, and above all, put insights into the relationships between the victim and perpetrator.


Homicide Data Observations: Guns and Family Trageties


The overall trend of the total number of homicide incidences in US was declining through 1980 to 2014, especially considering the fact that during this period of time, the populations in US had increased by about 40%. However, the number of homicide incidences around 1993 had reached a high peak, which was associated with the highest rate of civilian gun ownership in US. The big decline afterwards, however, remained to be a "mystery" that many different sociologist and economists had proposed various hypotheses to rationalize it. Meanwhile, the state wise numbers show that California had the most homicide incidences, followed by Texas, then New York.

Average Distrbution

Homicide Data Observations: Guns and Family Trageties

The average rate of unsolved homicide cases through 1980 to 2014 was about 30%. The yearly state-wise rate can be found using the slider bar. In the years near 2014, Illinois had the highest unsolved homicide rate, mainly due to gang-related shooting incidences in Chicago. Back to earlier years, high unsolved rate in California, New York and New Mexico were also indicators of active organized crimes.

For the following parts of the project, the data were all extracted from solved cases.

Homicide Data Observations: Guns and Family Trageties

Details - Age and Gender

The age distribution of overall count of the numbers of both victims and perpetrators had a big jump and reached peaks through late teen and early 20's. Over the years the percentage of victim and perpetrator under 18 years old was declining (from 6~7 % to about 5%), except the fact that around 1993 there was nearly 10% victims were under 18, and about 13% for prepetrators, resulting in a significent shift towards the younger side in the age distribution plot. The increase of young people's involvement is strongly associate with the 1993 homicide peak.

Meanwhile the gender groups did not show significent change over the years. About 67% homicide incidences were male killing male, and overall the perpetrators committed 90% of the crimes.

Homicide Data Observations: Guns and Family Trageties

Details - Weapon

The use of firearm, knife and blunt objects dominated the weapon used in US through 1980 to 2014, with a noticiable small portion of suffocation. About 70% of the homicide incidences had firearm as the murder weapon, with a high peak of about 75% around 1993.

The perpetrator group of male adults show almost identical distribution of weapon use over the year, mainly due to the fact that it was the dominant age/gender group shown above. The perpdetrator group of female adults shows totally different features. There was less firearm use and this portion was continuous dropping down below 50% after 2000. Instead there was relatively constant portion of knife use than male, followed by increasing portion of blunt objects, suffocation and explosive/fire.

The weapon use of young female perpetrators had strong fluctuations mainly because of the relatively small sample comparing to other groups. There also seemed to be a trend of increasing portion of firearm use in recent years.

For young male group, however, the plot shows a distinctive difference before and after 1993. The portions of all other weapon uses decreased, resulting in an alarming high rate of firearm use that maintained to be 80% without trace of dropping back. This number only reflects the weapon use in homicide, but it indicates the increasing role of guns in vast majority of crimes among young people. Other long-term gun problems could be rooted deeply inside those patterns.


The relationships between victims and perpetrators through 1980 to 2014 were combined into six big categories in the pie chart. Among 60% of the homicide cases the victims didn't know the perpetrators; 30% were acquaintances, and in the last 30% incidences both sides knew each other to some degree. In 25% of the crimes both sides were either family members or in close-relationship.

The details of the gender or role in the relationship can be selected from the choice box, with the corresponding table of numbers and relationship descriptions provided below the bar chart. Those are painful numbers to look at, considering all the family crisis going behind those numbers. The marital problem that ended up with homicide between husband and wife (with the majority of husband killing wife), for example, was the top two incidences.

The code of my ShinyApp can be found inΒ my GitHub account, and the application is also availabe inΒ my shinyapps.io account.


Useful references:

About Author

Xu Huang

Xu Huang got PhD in Computational Chemistry from University of Iowa and B.S. in Chemistry from Peking University. Her study includes developing & testing the computational code to improve the accuracy for the modeling of battery material &...
View all posts by Xu Huang >

Leave a Comment

No comments found.

View Posts by Categories

Our Recent Popular Posts

View Posts by Tags

#python #trainwithnycdsa 2019 2020 Revenue 3-points agriculture air quality airbnb airline alcohol Alex Baransky algorithm alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus ames dataset ames housing dataset apartment rent API Application artist aws bank loans beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep boston safety Bundles cake recipe California Cancer Research capstone car price Career Career Day citibike classic cars classpass clustering Coding Course Demo Course Report covid 19 credit credit card crime frequency crops D3.js data data analysis Data Analyst data analytics data for tripadvisor reviews data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization database Deep Learning Demo Day Discount disney dplyr drug data e-commerce economy employee employee burnout employer networking environment feature engineering Finance Financial Data Science fitness studio Flask flight delay gbm Get Hired ggplot2 googleVis H20 Hadoop hallmark holiday movie happiness healthcare frauds higgs boson Hiring hiring partner events Hiring Partners hotels housing housing data housing predictions housing price hy-vee Income Industry Experts Injuries Instructor Blog Instructor Interview insurance italki Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter las vegas airport lasso regression Lead Data Scienctist Lead Data Scientist leaflet league linear regression Logistic Regression machine learning Maps market matplotlib Medical Research Meet the team meetup methal health miami beach movie music Napoli NBA netflix Networking neural network Neural networks New Courses NHL nlp NYC NYC Data Science nyc data science academy NYC Open Data nyc property NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time performance phoenix pollutants Portfolio Development precision measurement prediction Prework Programming public safety PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R Data Analysis R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn seafood type Selenium sentiment analysis sentiment classification Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau teachers team team performance TensorFlow Testimonial tf-idf Top Data Science Bootcamp Top manufacturing companies Transfers tweets twitter videos visualization wallstreet wallstreetbets web scraping Weekend Course What to expect whiskey whiskeyadvocate wildfire word cloud word2vec XGBoost yelp youtube trending ZORI