def code(): # CONVERT THE REDD DATASET TO NILMTK'S HDF5 FORMAT from nilmtk.dataset_converters import convert_redd convert_redd('/data/REDD/low_freq', '/data/REDD/redd.h5') # IMPORT HDF5 FORMAT INTO NILMTK from nilmtk import DataSet redd = DataSet('/data/REDD/redd.h5')
import os import sys import nilmtk from nilmtk import DataSet from nilmtk.dataset_converters import convert_redd from nilmtk.utils import print_dict, dict_to_html if os.sep == "/": convert_redd("../data/low_freq", "../data/redd.5h") else: convert_redd( r'C:\Users\job heersink\Desktop\Projects\AS-NALM\data\low_freq', r"C:\Users\job heersink\Desktop\Projects\AS-NALM\data\redd.5h")
# -*- coding: utf-8 -*- """ Created on Wed Mar 21 15:12:35 2018 @author: Raymond """ from nilmtk.dataset_converters import convert_redd convert_redd('data/low_freq', 'redd.h5', format='HDF')
from pathlib import Path from nilmtk import DataSet from nilm_models.gru.grudisaggregator import GRUDisaggregator from nilmtk.dataset_converters import convert_redd import tensorflow as tf print("Num GPUs Available: ", len(tf.config.experimental.list_physical_devices('GPU'))) cwd = Path.cwd() dataset_path = '..\\..\\experiments\\data\\low_freq' full_path = cwd.joinpath(dataset_path) if not Path(r'..\\..\\experiments\\data\\redd.h5').exists(): convert_redd(str(full_path), r'..\\..\\experiments\\data\\redd.h5') redd = DataSet(r'..\\..\\experiments\\data\\redd.h5') redd.set_window(end="30-4-2011") #Use data only until 4/30/2011 train_elec = redd.buildings[1].elec train_mains = train_elec.mains().all_meters()[ 0] # The aggregated meter that provides the input train_meter = train_elec.submeters()['fridge'] gru = GRUDisaggregator() if not Path("model-redd5.h5").exists(): gru.train(train_mains, train_meter, epochs=5, sample_period=1) gru.export_model("model-redd5.h5") else: gru.import_model("model-redd5.h5")
from nilmtk.dataset_converters import convert_redd, convert_eco #convert redd and eco to h5 convert_redd('/net/linse8/no_backup_01/s1183/data/low_freq', '/net/linse8/no_backup_01/s1183/data/redd.h5') convert_eco('/net/linse8/no_backup_01/s1183/data/eco', '/net/linse8/no_backup_01/s1183/data/eco.h5')
#Este projeto treina usando todas as casas e usando o método from __future__ import print_function, division import time from matplotlib import rcParams import matplotlib.pyplot as plt import pandas as pd import numpy as np from six import iteritems from nilmtk import DataSet, TimeFrame, MeterGroup, HDFDataStore from nilmtk.legacy.disaggregate import CombinatorialOptimisation, FHMM import nilmtk.utils import time from datetime import datetime from nilmtk.dataset_converters import convert_redd convert_redd(r'low_freq', 'redd.h5') #Carrega os dados na memória train = DataSet('redd.h5') test = DataSet('redd.h5') #Enumera todas as casas buildings = [ i for i in range(6)] # The dates are interpreted by Pandas, prefer using ISO dates (yyyy-mm-dd) train.set_window(end="2011-04-30") test.set_window(start="2011-04-30") #Vetor que guarda os dados de todas as casas train_elec = [None for i in range(6)] test_elec = [None for i in range(6)]
from nilmtk.dataset import DataSet from nilmtk.dataset_converters import convert_redd #convert data from redd into a .hdf file for future loading convert_redd("C:/NILM/Data/REDD/low_freq/","C:/NILM/Data/Output/redd.h5")
from nilmtk.dataset_converters import convert_redd from pathlib import Path print(Path.cwd()) cwd = Path.cwd() dataset_path = 'data\\low_freq' full_path = cwd.joinpath(dataset_path) if not Path(r'data\\redd.h5').exists(): convert_redd(str(full_path), r'data\\redd.h5') from nilmtk import DataSet from nilmtk.utils import print_dict redd = DataSet(r'data\\redd.h5') print_dict(redd.metadata) elec = redd.buildings[1].elec print("\n All data from building 1 ----- \n") print(elec) fridge = elec['fridge'] print("\n All columns available for a fridge from Building 1 ----- \n") print(fridge.available_columns()) df = next(fridge.load()) print("\n Df Head ----- \n") print(df.head())
from nilmtk.dataset_converters import convert_redd convert_redd('C:\\Users\\dl50129\\Desktop\\nilmtk\\data\\REDD\\low_freq', r'C:\\Users\\dl50129\\Desktop\\nilmtk\\data\\redd.h5', format='HDF') convert_redd('C:\\Users\\dl50129\\Desktop\\nilmtk\\data\\REDD\\low_freq', r'C:\\Users\\dl50129\\Desktop\\nilmtk\\data\\redd_csv', format='CSV')
from nilmtk.dataset import DataSet from nilmtk.dataset_converters import convert_redd #convert data from redd into a .hdf file for future loading convert_redd("C:/NILM/Data_Sets/low_freq/","C:/NILM/Data_Sets/redd_data.h5")
from nilmtk.dataset import DataSet from nilmtk.dataset_converters import convert_redd #convert data from redd into a .hdf file for future loading convert_redd("C:/NILM/Data/REDD/low_freq/", "C:/NILM/Data/Output/redd.h5")
from nilmtk.dataset_converters import convert_redd from pathlib import Path from nilmtk import DataSet from nilm_models.dae.daedisaggregator import DAEDisaggregator import tensorflow as tf print("Num GPUs Available: ", len(tf.config.experimental.list_physical_devices('GPU'))) cwd = Path.cwd() dataset_path = '..\\experiments\\data\\low_freq' raw_data = cwd.joinpath(dataset_path).resolve() nilmtk_h5_path = Path(r'..\\experiments\\data\\redd.h5').resolve() if not nilmtk_h5_path.exists(): convert_redd(str(raw_data), nilmtk_h5_path) dae = DAEDisaggregator(256) #if not Path('model-redd100.h5').exists(): redd = DataSet(nilmtk_h5_path) redd.set_window(end="30-4-2011") #Use data only until 4/30/2011 train_elec = redd.buildings[1].elec train_mains = train_elec.mains().all_meters()[ 0] # The aggregated meter that provides the input train_meter = train_elec.submeters()[ 'fridge'] # The microwave meter that is used as a training target if not Path("model-redd100.h5").exists():
from bokeh.palettes import brewer from bokeh.io import output_file, show from bokeh.plotting import figure from bokeh.embed import components from flask import Flask, render_template # # 데이터 컨버터 (return : DataSet) # # --- # In[ ]: # 데이터 컨버트 # .dat ==> .h5 convert_redd('C:\\Users\\dlsrk\\Desktop\\nilm\\low_freq', 'C:\\Users\\dlsrk\\Desktop\\nilm\\data\\redd.h5') # .h5 데이터(컨버트된) read # redd = DataSet('C:\\Users\\Kim-Taesu\\Documents\\nilm\\data\\redd.h5') redd = DataSet('C:\\Users\\dlsrk\\Desktop\\nilm\\data\\redd.h5') # date load 함수 def getData(inputPath, convertOutputPath): convert_redd(inputPath, convertOutputPath) return DataSet(convertOutputPath) # # 시각화 데이터 준비 # # ---
dataset_directory = Path.cwd() / 'data' / nd if dataset_directory.exists(): break dataset_directory_str = str(dataset_directory) datastore_file = dataset_directory / ('%s.h5' % (dataset_name.lower())) datastore_file_str = str(datastore_file) # If the datastore does not exist (data not converted yet, load it) if not datastore_file.exists(): if dataset_name.startswith('sortd'): ntkdsc.convert_sortd(dataset_directory_str, datastore_file_str) elif dataset_name.startswith('fortum'): ntkdsc.convert_fortum(dataset_directory_str, datastore_file_str) elif dataset_name == 'eco': ntkdsc.convert_eco(dataset_directory_str, datastore_file_str, 'CET') elif dataset_name == 'redd': ntkdsc.convert_redd(dataset_directory_str, datastore_file_str) # Then load the dataset into memory dataset = DataSet(datastore_file_str) # print basic info of the dataset) print('\n\n%s\n#### DATASET %s\n' % ('#' * 80, dataset_name)) print('\n== dataset.metadata') print(dataset.metadata) ## Exploring dataset for bkey in dataset.buildings: building = dataset.buildings[bkey] elec = building.elec print('\n== elec.meters') print(elec.meters) print('\n== elec.appliances')
def getData(inputPath, convertOutputPath): convert_redd(inputPath, convertOutputPath) return DataSet(convertOutputPath)
from six import iteritems from nilmtk.dataset_converters import convert_redd from nilmtk import DataSet from nilmtk import global_meter_group from const import * from utils import number_list_duplicates def main(): # if not isfile(REDD_FILE): # convert raw data into hd5 file <<<<<<< HEAD convert_redd(join(REDD_DIR, 'low_freq'), REDD_FILE) ======= convert_redd(join(REDD_DIR, 'low_freq'), REDD_FILE) >>>>>>> aef264f3ffe1171080a897c5ccc7ad180010cc49 redd = DataSet(REDD_FILE) # iterate over each building for id in range(1,7): # parse all building data and generate dataframe elec = redd.buildings[id].elec mains = next(elec.mains().load(sample_period=SAMPLE_PERIOD)) # iterate over meters and gather time series meter_dict = {} for i, chunk in enumerate(elec.mains().load(sample_period=SAMPLE_PERIOD)):
def convert_dataset(self, folder, destination_file): #convert_greend(folder, destination_file) convert_redd(folder, destination_file)