Comments (6)
It was a pippin issue! SNN looks good now!
from supernnova.
ok I lied there's still something weird
from supernnova.
we're fitting about 50% of the PS1-spectroscopically confirmed SNIa as CC. Pretty similar for SDSS. Is this normal?
from supernnova.
Newest update: Using the --plot_file
command for run.py appears to prevent SNN from generating any plots.
We were working in /scratch/midway2/rkessler/PIPPIN_OUTPUT/PANOPTICON-DATA/3_CLAS/SNNTEST_PS_DATAPS1_SNNTEST_PS_PS1+MVCC/
previously, and ran job_plot.slurm around 20:00 EST.
The location that these should have been plotted in,
/scratch/midway2/rkessler/PIPPIN_OUTPUT/PANOPTICON-DATA/3_CLAS/SNNTEST_PS_DATAPS1_SNNTEST_PS_PS1+MVCC/dump/lightcurves/SNNTEST_PS_PS1+MVCC/early_prediction/
only contains files that were created 6 hours before, at 14:00 EST!
There's no error message in /scratch/midway2/rkessler/PIPPIN_OUTPUT/PANOPTICON-DATA/3_CLAS/SNNTEST_PS_DATAPS1_SNNTEST_PS_PS1+MVCC/output.log
So I'm not sure what's happening!
from supernnova.
Having a similar but separate issue for the spec sample. We couldn't get the plot_file working, as above, so we tried to run SNN on the spec sample as analogue to see the plots. Unfortunately, we're getting a strange error when running
/scratch/midway2/rkessler/PIPPIN_OUTPUT/MV_PS1_SDSS/3_CLAS/SNNTEST_PS_DATAPS1_SNNTEST_PS_PS1+MVCC/job_plot.slurm
which is detailed in /scratch/midway2/rkessler/PIPPIN_OUTPUT/MV_PS1_SDSS/3_CLAS/SNNTEST_PS_DATAPS1_SNNTEST_PS_PS1+MVCC/output.log -
^[[32m[Computing splits] ^[[0m
List files []
^[[32m[Data processing] ^[[0m<0s
Traceback (most recent call last):
File "run.py", line 210, in
raise e
File "run.py", line 44, in
make_dataset.make_dataset(settings)
File "/project2/rkessler/PRODUCTS/miniconda/envs/snn_gpu/lib/python3.6/contextlib.py", line 52, in inner
return func(*args, **kwds)
File "/project2/rkessler/PRODUCTS/classifiers/supernnova/supernnova/data/make_dataset.py", line 814, in make_dataset
build_traintestval_splits(settings)
File "/project2/rkessler/PRODUCTS/classifiers/supernnova/supernnova/data/make_dataset.py", line 96, in build_traintestval_splits
df_photo = pd.concat(list_df)
File "/project2/rkessler/PRODUCTS/miniconda/envs/snn_gpu/lib/python3.6/site-packages/pandas/core/reshape/concat.py", line 225, in concat
copy=copy, sort=sort)
File "/project2/rkessler/PRODUCTS/miniconda/envs/snn_gpu/lib/python3.6/site-packages/pandas/core/reshape/concat.py", line 259, in init
raise ValueError('No objects to concatenate')
ValueError: No objects to concatenate
This seems to be arising from the photo_window_files, but I haven't been able to figure out what the problem is
from supernnova.
.txt format is not supported with SuperNNova, only .FITS (SNANA format) or .csv (Plasticc format)
from supernnova.
Related Issues (20)
- SNANA FLT changed for BAND
- problem reading sntypes
- Warning when empty files are given
- Unusual results for PS1 Data HOT 2
- AttributeError: 'ExperimentSettings' object has no attribute 'sntype_var' HOT 3
- Pip update
- redshift_label and --zspe/zpho
- Database
- Pickle format change
- Confusion matrix labels
- Input from spark dataframe
- Photo window not supported with csv
- redshift_label support csv + additional_train_var for validation
- clean up cli_args
- Documentation: on the fly
- [on the fly] fill automatically columns not used HOT 1
- access above path exists HOT 1
- Cyclic speeding
- read GENTYPE map from sim-readme
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from supernnova.