README.md 1.87 KB
Newer Older
José Hugo Elsas's avatar
José Hugo Elsas committed
1
2
# Active Learning Loading Case Selection

José Hugo Elsas's avatar
José Hugo Elsas committed
3
4
5
6
7
Accessory repository for the paper "Active Learning Loading Case Selection" including notebooks and data necessary to reproduce all results of the paper. 

# Included Files : 

## Notebooks 
8
9
10
  - Spreadsheet aggregation.ipynb
  - Single-Target random and active learning for loading case selection.ipynb
  - Multi-Target random and active
José Hugo Elsas's avatar
José Hugo Elsas committed
11
12

## Data Files 
13
14
15
16
17
18
   Case definition files constitute the data necessary to characterize a loading case, and therefore run the simulation. Each loading case requires definition of a current and a wave. The cases.csv defines the pair (current,wave) to which correspond each loading case. 
   
   currents.csv contains the parameters that characterize each current, which is the 2D velocity vector for each water depth, and waves.csv contains the parameters for the JONSWAP wave model for each wave. cardinal_directions.csv is an auxiliary file used to convert data from currents.csv file to more ameanable format. 

   config0.csv , config1.csv ... config5.csv are the files containing the results of the simulations, i.e. Axial tension and DNVUF201 CLC, for 6 different riser configurations. The results are for each of the loading cases listed in the cases.csv file and are, ultimately, the target for the machine learning model. 

José Hugo Elsas's avatar
José Hugo Elsas committed
19
   ### Case definition
20
21
22
23
24
25
26
27
   - cases.csv
   - cardinal_directions.csv
   - currents.csv
   - waves.csv
   - config0..5

   The resulting data of the analysis is stored in different folders for convenience. 

José Hugo Elsas's avatar
José Hugo Elsas committed
28
   ### Results data
29
30
31
32
33
34
   - data/ : processed deviation measures for ML predictions
   - plots/ : plotted graphs analyzing data/ files
   - results/ : case-by-case data of ML prediction

   Intermediary files are produced by Spreadsheet aggregation notebook, which format the data in features ameanable to machine learning processing. 

José Hugo Elsas's avatar
José Hugo Elsas committed
35
   ### Intermediary files
36
37
   - cases_full.csv
   - cases_full.xlsx