You have to install the required packages using pip
:
pip install -r requirements.txt
The application additionally needs the following NLTK data packages:
punkt
- Punkt Tokenizer Models
For installation instructions please visit http://www.nltk.org/data.html.
python cli.py [options]
-t / --provider-type DATA_PROVIDER_TYPE
The type of the specified data provider, which supplies the status updates.-c / --classifier-type CLASSIFIER_TYPE
The type of the classifier to be trained. (currently onlydecision_tree
)
--dataset-path FILE_PATH
The path of the CSV dataset, which contains the status updates.
--twitter-user TWITTER_USER_ID
The id of the twitter user, whose status updates should be analyzed.
-n / --experiments-count NUMBER_OF_EXPERIMENTS
The number of experiments to run. (default: 10)
./run_app_dev.sh