This project aims to analyze disaster data from appen to build a model for an API that classifies disaster messages.
There are three components you'll need to complete for this project.
In a Python script, process_data.py
, i did a data cleaning pipeline that:
- Loads the
messages
andcategories
datasets - Merges the two datasets
- Cleans the data
- Stores it in a SQLite database
In a Python script, train_classifier.py
, i did 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
- Modify file paths for database and model
- Add data visualizations using Plotly in the web app.
The project graded based on the following:
- Use of Git and Github
- Strong documentation
- Clean and modular code
-
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 https://0.0.0.0:3001/