Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added Pecan Dataport converter #855

Open
wants to merge 28 commits into
base: 0.3.x
Choose a base branch
from
Open

Added Pecan Dataport converter #855

wants to merge 28 commits into from

Conversation

daniprec
Copy link

Current dataport downloader works only with the full license of the Pecan Dataport. There exists, however, a free sample of the dataset that cannot be downloaded nor converted with the current nilmtk library.

This dataport converter is able to load the sample Pecan Dataport dataset, and convert it to hdf5 nilmtk format.

rajat-tech-002 and others added 28 commits June 26, 2019 19:40
Currently it works for Homes A, B and C
Added the corrected API as requested by Paulo
NOTE: This is a work in progress, the new API is not fully integrated yet
Adding  SMART* Dataset converter interface 
(Note: still incomplete)
...after the changes to the environment files.
The default tests, the notebooks and some of the converters were tested -- no issues so far.
Closes #802
The tests were not entirely valid before since they assumed the order after converting to set. The new from_list preserves the input order.
Related to #233
* Use git tag as version for Travis builds
* Tweak setup.py logic
* Mention the automated builds in the docs
Modules, tests, notebooks and README.md were updated.
Changes from @Rithwikksvr:
* Added the baseline algorithms supported by the API to the repository.
* Added the baseline algorithms supported for the API
* Converted Tabs to Spaces
- remove `six` and `__future__` usage (we don't support Python 2.7 anymore)
- `disaggregate/mean.py`: `load_model` should open the file in read mode
- remove fixed seeds (most times without effect)
- rename the class `FHMM_EXACT` to `FHMMExact`
- some formatting (will be revisited later)
I added the metrics R2 Score, Normalized Disaggregation Error (NDE) and Normalized Error in Assigned Power (NEP).
added 3 metrics to the API
Update link to Numpy docstring style guide
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

8 participants