Installation

Obtaining the package, virtual environment

NOTE: This software has only been tested on the ALICE ML machine for the moment. It might run in other environments but the setup does only explain how to use it on this particular machine.

Change to a directory where you want to place the TPCwithDNN package. In there, type

git clone https://github.com/AliceO2Group/TPCwithDNN.git

and you will find a new directory TPCwithDNN.

As we use RootInteractive that depends on AliRoot, you need to build AliRoot and enter its environment:

alienv enter AliRoot/latest

To keep the python environment clean, we will use a virtual environment for the software setup. Dealing with that is handled by TPCwithDNN/load.sh and there are 3 scenarios when you type

source load.sh # This you can actually source from anywhere

1. If the environment has not been created yet, sourcing will create and enter it.
2. Being inside the environment, sourcing it again will leave the environment.
3. Outside of the environment, source load.sh --recreate will delete and re-install it.

Installation

From inside the virtual environment, change to $CLONE_TOP_DIR/TPCwithDNN where you can find setup.py. To install the package with all its dependencies, run

pip install -e .
pip install root_pandas # Installed separately as it depends on machine-specific ROOT

Now, you are good to go and you can run the code! Type:

cd tpcwithdnn/
python steer_analysis.py

You can define which step of the analysis you want to run by configuring the database:

vim default.yaml

The parameters of the ML analysis can be configured here:

vim database_parameters_DNN_fluctuations.yml