Skip to content

Latest commit

 

History

History
42 lines (31 loc) · 1.43 KB

README.md

File metadata and controls

42 lines (31 loc) · 1.43 KB

Disaster Response Pipeline Project

Introduction

This code base contain the pipeline to process messages encountered during disaster and classify them using RandomForest into one of the 36 categories that will define the response or help to be sent.

Pipeline

The messages are processed using the following:

  1. Tokenise (Lemmatisation)
  2. CountVectoriser
  3. TF-IDF
  4. MultiOutputClassifier using RandomForest

Files

The project is organised as follows:

  1. data Contains the csv file of messages and their categories classification as csv files. It also has process_data.py which reads the csv file and prepares the data for the model.

  2. model Contains the train_classifier.py that has the logic to setup, train and evaluate the model using data from data folder

  3. app This is the flask app to interact with the model. (by Udacity)

How to run this:

  1. Run the following commands in the project's root directory to set up your database and model.

    • To run ETL pipeline that cleans data and stores in database python data/process_data.py data/disaster_messages.csv data/disaster_categories.csv data/DisasterResponse.db
    • To run ML pipeline that trains classifier and saves python models/train_classifier.py data/DisasterResponse.db models/classifier.pkl

  2. Run the following command in the app's directory to run your web app. python run.py

  3. Go to http://0.0.0.0:3001/