jnsll / laprediction Goto Github PK
View Code? Open in Web Editor NEWLoop Aggregation Prediction
Loop Aggregation Prediction
There are two cases to use the data for the prediction:
The code should be changed to make the scripts use the files corresponding to the related case thanks to an option.
Scripts to change:
At the moment, the permeability value has been fixed at 86.4 m/d. So in all the names of folders/models/etc, the string contains "Permeability_86.4"
.
It now should be adapted to "permeability" + str(permeability)
.
/!\ What's more, there is an issue with the location where the maps (depth, amp, etc) are stored. At the moment, they are all stored in the model_time_0_geo_0_thick_1_K_86.4_Sy_0.1_Step1_site1_Chronicle0
folder. The depth map that is not linked to specific values of the initial reference simulation (K=86.4) should not be stored inside that folder. Especially, now that, for example, the folder for the reference simulation with permeability=8.64 does not exist. The depth map is only using the topology values from the reference simulation but those are identical for all the simulations.
vulnerabilityMaps.py
: lines 34, 96, 106.Some scripts used for concatenating data from the simulations (exec_time, H ind, etc) are located in the Modflops project and should be present in this project instead.
Scripts :
Save the numbers of the subcatchs of each site. It will enable some computations (e.g., loops) to be done for the exact number of subcatchs and not more than that.
It can be stored as a python object (pickled dictionary?) or in a file (csv to be opened as a pandas dataframe ?).
At the moment, there are several helpers.py
files. Actually, there is one in every subfolder of src
. A common helpers.py
file should be used instead. It will prevent having some mismatch between the different files.
In every script calling helpers.py
, the path to the helpers
folder should be added with something like this:
sys.path.append(os.path.join(os.path.dirname(__file__), '..', 'helpers'))
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.