simonepreite / DigitalTwinSample

Mini DigitalTwin

DIGITALTWIN WEBSERVER

START SERVER

sudo pip install virtualenv
git clone https://github.com/simonepreite/DataHow.git
cd DataHow
virtualenv --python python3 .venv
source .venv/bin/activate
pip install -r requirements.txt
export FLASK_APP=server.py
flask run

Use the tool by running in a browser

http://localhost:5000

or, to use the old interface

http://localhost:5000/old

REGRESSION MODEL

python regression.py
python regression2.py

NOTE: please read the Usage advertise inside the files before execute them

model.sav is generated by regression.py In the regression.py it is only used the input to train the model and make a prediction of the Product Concentration.

The regression2.py does not save a model, it uses also a different approach.
The input information are used to train 3 different model which are used to predict the values of Ammonium, Lactate and Viable cell (offline).
After trained the models are used to predict these values which are used to train the final Regression model that predict the Product concentration.

Requirements

click==7.1.2
et-xmlfile==1.1.0
Flask==1.1.2
Flask-Cors==3.0.10
itsdangerous==1.1.0
Jinja2==2.11.3
joblib==1.0.1
MarkupSafe==1.1.1
matplotlib==3.4.2
numpy==1.20.3
openpyxl==3.0.7
pandas==1.2.4
python-dateutil==2.8.1
pytz==2021.1
scikit-learn==0.24.2
scipy==1.6.3
six==1.15.0
sklearn
threadpoolctl==2.1.0
Werkzeug==1.0.1