Skip to content

Latest commit

 

History

History
54 lines (35 loc) · 2.35 KB

README.md

File metadata and controls

54 lines (35 loc) · 2.35 KB

Table of Contents

  1. Installation
  2. Project Motivation
  3. File Descriptions
  4. Instructions
  5. Screenshots
  6. Licensing, Authors, and Acknowledgements

Installation

libraries needed by this project are provided by the Anaconda distribution of Python. The code should run with no issues using Python versions 3.*.

Project Motivation

This project build a web app to classify information on twitter according to its purpose and send the information to the appropriate aid agencies during a disaster event.

A machine learning model is trained to classify information into different categories using dataset of Figure Eight - Multilingual Disaster Response Messages.

File Descriptions

notebook folder contain ETL pipeline and ML pipeline notebook

data folder contain data and process_data.py file which is an ETL-pipeline for cleaning, transforming and storing the data from CSV-files

models folder contain train_classifier.py which train and build a ML model for classify messages. The output is a pickle file containing the fitted model.

app folder contain html template and run.py file to run and render web app.

img folder contain screen shot of the web app

Instructions

Run process_data.py

python data/process_data.py data/messages.csv data/categories.csv data/DisasterResponse.db

Run train_classifier.py

python models/train_classifier.py data/DisasterResponse.db models/classifier.pkl

Run the web app

  1. Save the app folder in the current working directory.
  2. Run the following command in the app directory: python run.py
  3. Go to http://0.0.0.0:3001/

Screenshots

App Front Page Screenshot 1

App Results Page Screenshot 2

Licensing, Authors, Acknowledgements

This app was completed as part of the Udacity Data Scientist Nanodegree. Code templates and data were provided by Udacity. The data was originally sourced by Udacity from Figure Eight.