# )
# ensemble_optimization(
# root_path=root_path,
# station='zjs',
# decomposer='vmd',
# lev=11,
# variables=variables,
# orig_df=orig,
# pattern='one_model_'+str(lead)+'_ahead_hindcast_pacf',
# )
# ensemble_optimization(
# root_path=root_path,
# station='zjs',
# decomposer='vmd',
# lev=11,
# variables=variables,
# orig_df=orig,
# pattern='one_model_'+str(lead)+'_ahead_hindcast_pacf_mis',
# )
ensemble_optimization(
root_path=root_path,
station='zjs',
decomposer='vmd',
lev=11,
variables=variables,
orig_df=orig,
criterion='NMSE',
pattern='one_model_1_ahead_forecast_pacf_loss_nmse',
)
plt.show()
sys.path.append(root_path + '/tools/')
from plot_utils import plot_rela_pred, plot_history, plot_error_distribution, plot_subsignals_preds
from ensemble import ensemble_optimization
from metrics_ import PPTS
from variables import variables
orig = pd.read_excel(
root_path +
'/time_series/ZhangJiaShanDailyFlow1997-2014.xlsx')['DailyFlow']
for lead in [1, 3, 5, 7]:
ensemble_optimization(
root_path=root_path,
station='zjs',
decomposer='eemd',
lev=12,
variables=variables,
orig_df=orig,
pattern='multi_models_' + str(lead) + '_ahead_forecast_pacf',
)
ensemble_optimization(
root_path=root_path,
station='zjs',
decomposer='eemd',
lev=12,
variables=variables,
orig_df=orig,
pattern='one_model_' + str(lead) + '_ahead_forecast_pacf',
)
ensemble_optimization(
root_path=root_path,
import pandas as pd
import numpy as np
import math
import matplotlib.pyplot as plt
from sklearn.metrics import r2_score, mean_absolute_error, mean_squared_error, mean_squared_log_error
import os
root_path = os.path.os.path.dirname(os.path.abspath('__file__'))
# root_path = os.path.abspath(os.path.join(root_path, os.path.pardir))
# root_path = os.path.abspath(os.path.join(root_path, os.path.pardir))
print(10*'-'+' Root Path: {}'.format(root_path))
import sys
sys.path.append(root_path+'/tools/')
from plot_utils import plot_rela_pred,plot_history,plot_error_distribution,plot_subsignals_preds
from ensemble import ensemble_optimization
from metrics_ import PPTS
from variables import variables
orig = pd.read_excel(root_path+'/time_series/Test.xlsx')['DailyFlow']
ensemble_optimization(
root_path=root_path,
station='test',
decomposer='test',
lev=3,
variables=variables,
orig_df=orig,
pattern='multi_models_1_ahead_forecast',
)
# ensemble_optimization(
# root_path=root_path,
# station='yx',
# decomposer='wd',
# lev=lev,
# variables=variables,
# orig_df=orig,
# pattern='one_model_'+str(lead)+'_ahead_forecast_pacf',
# wavelet=wavelet,
# )
# ensemble_optimization(
# root_path=root_path,
# station='yx',
# decomposer='wd',
# lev=lev,
# variables=variables,
# orig_df=orig,
# pattern='one_model_'+str(lead)+'_ahead_forecast_pacf_mis',
# wavelet=wavelet,
# )
ensemble_optimization(
root_path=root_path,
station='yx',
decomposer='wd',
lev=lev,
variables=variables,
orig_df=orig,
pattern='one_model_' + str(lead) + '_ahead_hindcast_pacf_mis',
wavelet=wavelet,
)
import pandas as pd
import numpy as np
import math
import matplotlib.pyplot as plt
from sklearn.metrics import r2_score, mean_absolute_error, mean_squared_error, mean_squared_log_error
import os
root_path = os.path.os.path.dirname(os.path.abspath('__file__'))
# root_path = os.path.abspath(os.path.join(root_path, os.path.pardir))
# root_path = os.path.abspath(os.path.join(root_path, os.path.pardir))
print(10*'-'+' Root Path: {}'.format(root_path))
import sys
sys.path.append(root_path+'/tools/')
from plot_utils import plot_rela_pred,plot_history,plot_error_distribution,plot_subsignals_preds
from ensemble import ensemble_optimization
from metrics_ import PPTS
from variables import variables
orig = pd.read_excel(root_path+'/time_series/YangXianDailyFlow1997-2014.xlsx')['DailyFlow']
for leading_time in [1,3,5,7]:
ensemble_optimization(
root_path=root_path,
station='yx',
variables=variables,
orig_df=orig,
pattern=str(leading_time)+'_ahead',
)
import sys
sys.path.append(root_path + '/tools/')
from plot_utils import plot_rela_pred, plot_history, plot_error_distribution, plot_subsignals_preds
from ensemble import ensemble_optimization
from metrics_ import PPTS
from variables import variables
orig = pd.read_excel(
root_path + '/time_series/YangXianDailyFlow1997-2014.xlsx')['DailyFlow']
for lead in [1, 3, 5, 7]:
ensemble_optimization( #multi-models ensemble forecasting
root_path=root_path,
station='yx',
decomposer='eemd',
lev=12,
variables=variables,
orig_df=orig,
pattern='multi_models_' + str(lead) + '_ahead_forecast_pacf',
)
ensemble_optimization( #single-model forecasting
root_path=root_path,
station='yx',
decomposer='eemd',
lev=12,
variables=variables,
orig_df=orig,
pattern='one_model_' + str(lead) + '_ahead_forecast_pacf',
)
ensemble_optimization( #single-model forecasting with most influential subsignals
root_path=root_path,
for lead in [1,3,5,7]:
# ensemble_optimization(
# root_path=root_path,
# station='yx',
# decomposer='vmd',
# lev=9,
# variables=variables,
# orig_df=orig,
# pattern='multi_models_'+str(lead)+'_ahead_forecast_pacf',
# )
ensemble_optimization(
root_path=root_path,
station='yx',
decomposer='vmd',
lev=9,
variables=variables,
orig_df=orig,
pattern='one_model_'+str(lead)+'_ahead_forecast_pacf',
)
# ensemble_optimization(
# root_path=root_path,
# station='yx',
# decomposer='vmd',
# lev=9,
# variables=variables,
# orig_df=orig,
# pattern='one_model_'+str(lead)+'_ahead_forecast_pacf_mis',
# )
# ensemble_optimization(
# root_path=root_path,