Based on definition of our problem, factors that will influence our decision are:
The total number of crimes commited in each of the borough during the last year. The most common venues in each of the neighborhood in the safest borough selected. Following data sources will be needed to extract/generate the required information:
Part 1: Preprocessing a real world data set from Kaggle showing the London Crimes from 2008 to 2016: A dataset consisting of the crime statistics of each borough in London obtained from Kaggle Click here
Part 2: Scraping additional information of the different Boroughs in London from a Wikipedia page.: More information regarding the boroughs of London is scraped using the Pandas library
Part 3: Creating a new dataset of the Neighborhoods of the safest borough in London and generating their co-ordinates.: Co-ordinate of neighborhood will be obtained using Foursquare API
pandas
numpy
matplotlib
seaborn
sklearn
geopy
foursquare Api
When you open the jupyer File , all the links are provided for the Data.
There is a complete guide in notebook about the code