Original article was published on Deep Learning on Medium
So each row consists of 13 features:
1. IncidntNum: Incident Number
2. Category: Category of crime or incident
3. Descript: Description of the crime or incident
4. DayOfWeek: The day of the week on which the incident occurred
5. Date: The Date on which the incident occurred
6. Time: The time of day on which the incident occurred
7. PdDistrict: The police department district
8. Resolution: The resolution of the crime in terms of whether the perpetrator was arrested or not.
9. Address: The closest address to where the incident took place
10. X: The longitude value of the crime location
11. Y: The latitude value of the crime location
12. Location: A tuple of the latitude and the longitude values
13. PdId: The police department ID
Let’s find out how many entries there are in our dataset.
So the dataframe consists of 150,500 crimes, which took place in the year 2016. In order to reduce the computational cost.
Let’s just work with the first 100 incidents in this dataset.
# get the first 100 crimes in the df_incidents dataframe
limit = 100
df_incidents = df_incidents.iloc[0:limit, :]
Now that we reduced the data a little bit, let’s visualize where these crimes took place in the city of San Francisco. We will use the default style and we will initialize the zoom level to 12.
# San Francisco latitude and longitude values
latitude = 37.77
longitude = -122.42# create map and display it
sanfran_map = folium.Map(location=[latitude, longitude], zoom_start=12)# display the map of San Francisco