Skip to content

Analysis of Bangalore City, India on neighborhood(venues,location...) Data to find the best locations to open a fitness centre using Foursquare APIs and K-Means Clustering method.

Notifications You must be signed in to change notification settings

utkarshchoubeycs/IBM-Data-Science-Capstone

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 

Repository files navigation

IBM DATA SCIENCE APPLIED CAPSTONE PROJECT


                                                 Screenshot             Screenshot


Premium Fitness Centre Location Recommender (Bangalore)

Analysis of Bangalore City, India on neighborhood(venues,location...) Data to find the best locations to open a fitness centre using Foursquare APIs and K-Means Clustering method.


PROBLEM :
The problem at hand is to find an optimal location for a fitness centre. Specifically, this project will be targeted to stakeholders interested in opening a Premium Fitness Centre or a Franchise Gym in Bangalore, India. Finding a suitable location for gym in major cities like Bangalore proves to be a daunting task. Various factors such as over-saturation or no demand ,for the gym/fitness centre that the customer wants to open, effect the success or failure of the centre. Hence, prospective investors can bolster their decisions using the descriptive and predictive capabilities of data science.
SOLUTION APPROACH :
We need to find locations (Neighbourhood) that have a potentially unfulfilled demand for a Premium Fitness Centre like Golds, Cult, Icon Fitness…etc. Also, we need locations that have a relatively higher Average Income and population. We would also prefer location as close to popular city Neighbourhood, assuming the first two conditions are met. We will use our data science powers to generate a few most promising neighbourhoods based on this criteria. Advantages of each area will then be clearly Expressed so that best possible final location can be chosen by stakeholders.

Check out this Jupyter Notebook to solve this problem and understand different aspects of DATA SCIENCE.

👉🏻https://jp-tok.dataplatform.cloud.ibm.com/analytics/notebooks/v2/c5147560-ca2a-4726-925f-5aea7cd99c22/view?access_token=eb5c6b30f99de3504a9a3f8b628a27755c161831a164267f9e002c869f5524b6

Technologies used :-

  • IBM Cloud Watson Studio
  • Jupyter notebook
  • Foursquare API
  • Language : Python 3

Packages/Libraries used :-

  • numpy - (to handle data in a vectorized manner)
  • pandas - (for data analysis)
  • json - (to handle JSON files)
  • Nominatim(geopy.geocoders) - (to convert an address into latitude and longitude values)
  • requests - (to handle requests)
  • json_normalize(pandas.io.json) - (to tranform JSON file into a pandas dataframe)
  • Matplotlib and associated plotting modules - (for visualisation)
  • seaborn - (for visualisation)
  • KMeans(sklearn.cluster) - (for K-means clusteing)
  • folium - (for Map visualisation)

The dataset used in this project is taken from https://kaggle.com

About

Analysis of Bangalore City, India on neighborhood(venues,location...) Data to find the best locations to open a fitness centre using Foursquare APIs and K-Means Clustering method.

Topics

Resources

Stars

Watchers

Forks