loneharoon / gsp_energy_disaggregator Goto Github PK

Hi,

I have a problem with compiling using Python 3.7 on PyCharm 2018.3.4 x64.
Compiling stop at step 3 of 6> generates full power series of appliances and display following error:
File "C:/Users/hacke/PycharmProjects/GSP_Disagregator/gsp_disaggregator.py", line 72, in <module> power_series, appliance_signatures = gsp.generate_appliance_powerseries(appliance_pairs, delta_p) File "C:\Users\hacke\PycharmProjects\GSP_Disagregator\gsp_support.py", line 194, in generate_appliance_powerseries powerval = interpolate_values(final) if sum(np.isnan(final)) else final TypeError: ufunc 'isnan' not supported for the input types, and the inputs could not be safely coerced to any supported types according to the casting rule ''safe''

Thanks for response

Could you please provide the source of the demo data?
Is it real measured data?

Hello,

I am trying to get the disaggregation results with REFIT and REDD files, as the authors did on the article. You have output_disaggr.csv and signature_database_labelled.csv, which are two labelled disaggregated files, and REDD and REFIT data have aggregated files and dissaggregated files which are equivalent to output_disaggr.csv (ground truth). How can I generate/obtain the equivalen signature_database_labelled.csv to REDD and REFIT data?

I have plotted the sum of the dis-aggregated 15 loads obtained in gsp_result data frame. The actual aggregated data is also plotted to compare the results with the actual data. There appears to be a big difference between the actual aggregate power and the result obtained using your code. Can you verify?

File "gsp_disaggregator.py", line 71, in
power_series, appliance_signatures = gsp.generate_appliance_powerseries(appliance_pairs, delta_p)
File "/home/qzx/nilm/gsp_support.py", line 210, in generate_appliance_powerseries
power_series[i] = pd.DataFrame({'timestamp':timeseq,'power':powerseq})
File "/home/qzx/.local/lib/python3.8/site-packages/pandas/core/frame.py", line 709, in init
mgr = dict_to_mgr(data, index, columns, dtype=dtype, copy=copy, typ=manager)
File "/home/qzx/.local/lib/python3.8/site-packages/pandas/core/internals/construction.py", line 481, in dict_to_mgr
return arrays_to_mgr(arrays, columns, index, dtype=dtype, typ=typ, consolidate=copy)
File "/home/qzx/.local/lib/python3.8/site-packages/pandas/core/internals/construction.py", line 115, in arrays_to_mgr
index = _extract_index(arrays)
File "/home/qzx/.local/lib/python3.8/site-packages/pandas/core/internals/construction.py", line 655, in _extract_index
raise ValueError("All arrays must be of the same length")
ValueError: All arrays must be of the same length

Hi

When I execute the gsp_disagreggator.py file, I've got the following error on the 64 line:

LinAlgError: SVD did not converge

What can it be?

Hi @loneharoon,
I'd like to give your implementation a try, but there is not demo data file.

csvfile = "./demo_data.csv"
Would you include this file pls?

Thank you.
Best,

I keep getting this issue when I run the gsp_disaggregator.py.
A[pd.isnull(A)] = np.interp(x, xp, fp), This is where the error is pointed it is line 314 in gsp_support.py in interpolate function.
Please guide I'm unable to resolve the error

Hi,

I am new in this area and thank you so much to upload the python code of GSP based NILM! And I really want to have a successful run of your code!

However I have some problem when running the code with the function DWT and fastDWT
" dist = (s1[i] - s2[j]) ** 2
TypeError: unsupported operand type(s) for -: 'function' and 'int'". Could you please help me with that?

I got the following error while i would like to run the code as it is.

also help me in implementing the same algorithm to the public available datasets like REDD,UKDALE

1 of 6> reading data
Traceback (most recent call last):
File "gsp_disaggregator.py", line 62, in
event = [i for i in range(0, len(delta_p)) if (delta_p[i] > T_Positive or delta_p[i] < T_Negative) ]
File "gsp_disaggregator.py", line 62, in
event = [i for i in range(0, len(delta_p)) if (delta_p[i] > T_Positive or delta_p[i] < T_Negative) ]
TypeError: '>' not supported between instances of 'tuple' and 'int'