New predictions
Required inputs
Robert_example_test.csv: CSV file with data to use as the external test set. The full CSV file can be found in the "Examples" folder of the ROBERT repository or downloaded here:
Name |
Target_values |
x1 |
x2 |
x3 |
x4 |
x5 |
x6 |
x7 |
x8 |
x9 |
x10 |
x11 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
38 |
1.854766065 |
12 |
110.9270401 |
70.8240401 |
Csub-H |
89.87553406 |
49.77253406 |
1 |
0 |
0 |
0 |
1 |
39 |
2.034511341 |
11.7 |
110.6553116 |
70.25231158 |
Csub-Csub |
78.65235138 |
55.53135138 |
1 |
0 |
0 |
0 |
1 |
... |
||||||||||||
45 |
0.329517076 |
-101.6 |
115.2292938 |
-38.47370618 |
Csub-O |
70.45233154 |
-65.96866846 |
0 |
2 |
1 |
3 |
3 |
46 |
1.902644865 |
4.29 |
110.7536316 |
62.94063159 |
Csub-H |
89.6808548 |
41.8678548 |
2 |
0 |
0 |
0 |
2 |
Executing the job
Instructions:
Run the Full workflow from CSV workflow from the Examples.
Download the Robert_example_test.csv file specified in Required inputs and paste it in the same working folder.
Go to the working folder in your terminal (using the "cd" command, i.e.
cd C:/Users/test_robert).Activate the conda environment where ROBERT was installed (
conda activate robert).Run the following command line:
python -m robert --predict --csv_test Robert_example_test.csv
Note
The --csv_test option can be used as part of end-to-end workflows. For example, this option can be added to the "Full workflow from CSV" example:
python -m robert --names Name --y Target_values --csv_name Robert_example.csv --csv_test Robert_example_test.csv
Options used:
--predict: only runs the PREDICT module.--names Name: Name of the column containing the names of the datapoints. This feature allows to print the names of the outlier points (if any).--csv_test Robert_example_test.csv: CSV with the external test set.
Execution time and versions
Time: ~10 sec
System: 8 processors (11th Gen Intel(R) Core(TM) i7-1165G7 @ 2.80GHz) using 16.0 GB RAM memory
ROBERT version: 2.0.1
scikit-learn-intelex version: 2025.2.0
Results
Two CSV files called Robert_example_test_NN_No_PFI and Robert_example_test_NN_PFI should be created inside the PREDICT folder. The two files contain the predictions from the two different Neural Network (NN) models, with and without PFI filtering, obtained in the Full workflow example.
The CSV files can be visualized here: (No PFI), (PFI)
If you want to tabulate your results inside a report PDF, run this command line:
python -m robert --report
The PDF file can be visualized here: 
The predictions are sorted at the end of the PDF report (including both the No_PFI and the PFI models):
