ML Based Holiday Trip Planner Algorithms

• Project Description:

  • Idea behind this project is to develop a Ml based holiday trip planner for creating complete plan of my upcoming trip without any kind of human help.In this project I have used the datasets available on the internet especially on sites like "www.kaggle.com" to predict the best route and price of transportation and also predicted the best hotels at that particular location .
  • For this project I have used various libraries like sklearn,which contains a lot of efficient tools for machine learning and statistical modeling including classification, regression, clustering and dimensionality reduction.Also I have used plotly Python library which is an interactive, open-source plotting library that supports over 40 unique chart types covering a wide range of statistical, financial, geographic, scientific, and 3-dimensional use-cases.Along with that I have also used other libraries like pandas,numpy,nltk etc for other basic operations.
  • To make it more interactive or user friendly we can colaborate this Ml models with the other website/application platforms like Flask,etc.

• Objectives:

  • To predict the best route and prices of the transportation from available datasets to reach the desired destination.
  • To predict best hotels with prices based on the previous available data
  • To select suitable Ml models for the above predictions
  • To provide the best and suitable trip plan based on the previous plans selected by the customers/users.

• Steps to run

  • Installation of required libraries

  ! pip install scikit-learn
  ! pip install chart_studio
  ! pip install pyLDAvis
  ! pip install matplotlib
  ! pip install nltk
  ! pip install tensorflow
  

  • Navigate to the folder

  $ cd /[directory]
  

  • Clone the github repository

  $ git clone https://github.com/omkulkarni01/ML-Based-Holiday-Trip-Planner-Algorithms.git
  

  Click to get datasets!

  • Datasets

    • Data_Train.xlsx
    • Seattle_hotels.csv
    • Test_set.xlsx

• Few output graphs:

  • 
  • 

• Resources: