https://github.com/londheshubham153/disaster-response-pipelines
A machine learning pipeline to categorize emergency messages based on the needs communicated by the sender.
https://github.com/londheshubham153/disaster-response-pipelines
Last synced: 9 days ago
JSON representation
A machine learning pipeline to categorize emergency messages based on the needs communicated by the sender.
- Host: GitHub
- URL: https://github.com/londheshubham153/disaster-response-pipelines
- Owner: LondheShubham153
- Created: 2020-05-13T03:49:22.000Z (almost 5 years ago)
- Default Branch: master
- Last Pushed: 2020-05-14T08:05:38.000Z (almost 5 years ago)
- Last Synced: 2025-04-01T19:17:42.002Z (29 days ago)
- Language: Jupyter Notebook
- Size: 2.39 MB
- Stars: 3
- Watchers: 2
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Disaster-Response-Pipelines
## Required libraries
- nltk 3.3.0
- numpy 1.15.2
- pandas 0.23.4
- scikit-learn 0.20.0
- sqlalchemy 1.2.12
## Motivation
In this project, It will provide disaster responses to analyze data from [Figure Eight](https://www.figure-eight.com/) to build a model for an API that classifies disaster messages.
This project will include a web app where an emergency worker can input a new message and get classification results in several categories. The web app will also display visualizations of the data.
Below are a few screenshots of the web app.
## Files
- ETL Pipeline Preparation.ipynb: Description for workspace/data/process_data.py
- ML Pipeline Preparation.ipynb: Description for workspace/model/train_classifier.py
- workspace/data/process_data.py: A data cleaning pipeline that:
- Loads the messages and categories datasets
- Merges the two datasets
- Cleans the data
- Stores it in a SQLite database
- workspace/model/train_classifier.py: A machine learning pipeline that:
- Loads data from the SQLite database
- Splits the dataset into training and test sets
- Builds a text processing and machine learning pipeline
- Trains and tunes a model using GridSearchCV
- Outputs results on the test set
- Exports the final model as a pickle file
## Acknowledgements
I wish to thank [Figure Eight](https://www.figure-eight.com/) for dataset, and thank [Udacity](https://www.udacity.com/) for advice and review.