In this project there is a web application where an emergency worker can insert a new message and obtain classification results in several categories. The web application will also display visualizations of the data.
Third project developed on the Udacity platform in the Data Scientist Nanodegree program, and also the first challenge proposed on the Kaggle platform.
The project is divided into three major blocks:
Loading of message and category data sets Merge the two data sets Data cleaning Storage in an SQLite database
Loading data from the SQLite database Dividing the dataset into training and testing sets Creating a word processing and machine learning pipeline Training and adjusting a model using GridSearchCV Presentation of the results in the test set Exporting the final model as a pickle file
Data visualizations using Plotly in the web application + Flask Web.
-
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
- To run ETL pipeline that cleans data and stores in database
-
Run the following command in the app's directory to run your web app.
python run.py
-
Go to http://0.0.0.0:3001/