def train_arima_model(data_train, date_init, date_fin, op_red, type_day, transform='decompose-Fourier'
, type_decompose='additive', n_decompose=1, n_coeff_fourier=4, filter_decompose=None):
num_cluster = data_train.name
data_train = np.array(data_train)[~np.isnan(np.array(data_train))]
type_model = 'arima'
if transform == 'decompose-Fourier' or transform == 'decompose-Fourier-log':
print('n_decompose: ', n_decompose, 'n_coeff_fourier: ', n_coeff_fourier)
forecast_seasonal, trend_residual, n_diffs, periods_decompose, m_f, k_f = get_transform_model(data_train, transform=transform
, type_decompose=type_decompose
, n_decompose=n_decompose
, n_coeff_fourier=n_coeff_fourier)
pipeline_trend_residual = Pipeline([
('fourier', ppc.FourierFeaturizer(m=m_f, k=k_f))
, ("model", pm.AutoARIMA(d=n_diffs, seasonal=False, trace=True, error_action='ignore'
, maxiter=30, max_p=4, max_q=4, suppress_warnings=True, with_intercept=True))])
print('\t\t\t training model...')
pipeline_trend_residual.fit(trend_residual)
print(pipeline_trend_residual.summary())
# aic_model = pipeline_trend_residual.steps[-1][1].model_.aic()
print('\t\t\t saving model...')
save_model_dir(pipeline_trend_residual, transform, num_cluster, op_red, type_day, type_model, date_init
, date_fin, periods_decompose, str(n_decompose), type_decompose)
print('\t\t\t finish save model...')
elif transform == 'Fourier':
n_diffs, m_f, k_f = get_transform_model(data_train, transform=transform, n_coeff_fourier=n_coeff_fourier)
pipeline = Pipeline([
('fourier', ppc.FourierFeaturizer(m=m_f, k=k_f))
, ("model", pm.AutoARIMA(d=n_diffs, seasonal=False, trace=True, error_action='ignore'
, maxiter=30, max_p=4, max_q=4, suppress_warnings=True, with_intercept=True))])
pipeline.fit(data_train)
save_model_dir(pipeline, transform, num_cluster, op_red, type_day, type_model, date_init, date_fin)
elif transform == 'decompose':
forecast_seasonal, trend_residual, n_diffs, ns_diffs, periods_decompose, m_f = get_transform_model(data_train
, transform=transform
, type_decompose=type_decompose
, n_decompose=n_decompose)
pipeline_trend_residual = Pipeline(
[("model", pm.AutoARIMA(d=n_diffs, D=ns_diffs, seasonal=True, m=m_f, trace=True, error_action='ignore'
, maxiter=30, max_p=4, max_q=4, suppress_warnings=True, with_intercept=True))])
pipeline_trend_residual.fit(trend_residual)
save_model_dir(pipeline_trend_residual, transform, num_cluster, op_red, type_day, type_model, date_init
, date_fin, periods_decompose, str(n_decompose), type_decompose)
elif transform == 'normal':
n_diffs, ns_diffs, m_f = get_transform_model(data_train, transform=transform)
pipeline = Pipeline(
[("model", pm.AutoARIMA(d=n_diffs, D=ns_diffs, seasonal=True, m=m_f, trace=True, error_action='ignore'
, maxiter=30, max_p=4, max_q=4, suppress_warnings=True, with_intercept=True))])
pipeline.fit(data_train)
save_model_dir(pipeline, transform, num_cluster, op_red, type_day, type_model, date_init, date_fin)
else:
raise ValueError('invalid variable transform {}.'.format(transform))
vector_rmse_train.append(vector_combinaciones.iloc[0, 4])
vector_rmse_test.append(vector_combinaciones.iloc[0, 3])
algoritmo.append('Holt_winters')
vector_serie.append(vector[s])
##########################################################33
########## MODELO AUTOARIMA
errores_proceso_ar = []
try:
# Let's create a pipeline with multiple stages... the Wineind dataset is
# seasonal, so we'll include a FourierFeaturizer so we can fit it without
# seasonality
pipe = pipeline.Pipeline([
("fourier", ppc.FourierFeaturizer(
m=5)), #modela la estacionalidad con periodicidad 5
(
"arima",
arima.AutoARIMA(
stepwise=True,
trace=1,
error_action="ignore",
seasonal=False, # because we use Fourier
suppress_warnings=True))
])
pipe.fit(train_arima)
print("Model fit:")
print(pipe)
# We can compute predictions the same way we would on a normal ARIMA object:
# Author: Taylor Smith <*****@*****.**>
import numpy as np
import pmdarima as pm
from pmdarima import pipeline, preprocessing as ppc, arima
from matplotlib import pyplot as plt
# Load the data and split it into separate pieces
data = pm.datasets.load_wineind()
train, test = data[:150], data[150:]
# Let's create a pipeline with multiple stages... the Wineind dataset is
# seasonal, so we'll include a FourierFeaturizer so we can fit it without
# seasonality
pipe = pipeline.Pipeline([
("fourier", ppc.FourierFeaturizer(m=12, k=4)),
("arima", arima.AutoARIMA(stepwise=True, trace=1, error_action="ignore",
seasonal=False, # because we use Fourier
transparams=False,
suppress_warnings=True))
])
pipe.fit(train)
print("Model fit:")
print(pipe)
# We can compute predictions the same way we would on a normal ARIMA object:
preds, conf_int = pipe.predict(n_periods=10, return_conf_int=True)
print("\nForecasts:")
print(preds)
# Author: Taylor Smith <*****@*****.**>
import numpy as np
import pmdarima as pm
from pmdarima import pipeline, preprocessing as ppc, arima
from matplotlib import pyplot as plt
# Load the data and split it into separate pieces
data = pm.datasets.load_wineind()
train, test = data[:150], data[150:]
# Let's create a pipeline with multiple stages... the Wineind dataset is
# seasonal, so we'll include a FourierFeaturizer so we can fit it without
# seasonality
pipe = pipeline.Pipeline([
("fourier", ppc.FourierFeaturizer(m=12)),
(
"arima",
arima.AutoARIMA(
stepwise=True,
trace=1,
error_action="ignore",
seasonal=False, # because we use Fourier
transparams=False,
suppress_warnings=True))
])
pipe.fit(train)
print("Model fit:")
print(pipe)
def Arima(df, dataset, months, var):
# if dataset=='iig_maitri' or dataset=='iig_bharati':
# data2=pd.read_csv('datasets/'+dataset+'.csv')
# # print(df)
# elif dataset=='dcwis':
# data2=pd.read_csv('datasets/'+dataset+'.csv', names=['obstime', 'tempr', 'ap', 'ws', 'rh', 'dew'])
df['obstime'] = pd.to_datetime(df['obstime'])
df = df.set_index('obstime')
data2 = df[var]
# print(data2)
# train2, test2= data2[:23423], data2[23423:]
# train =train2.resample('M').mean()
# ds_temp=df[var].resample('M').mean()
if var == 'rh':
data2 = data2[data2 > 10]
if var == 'ws':
data2 = data2[data2 >= 0]
if var == 'ap':
data2 = data2[data2 > -10]
data = data2.resample('M').mean()
# print(data)
# data.dropna(inplace=True)
# train.dropna(inplace=True)
# test.dropna(inplace=True)
# data['Date']=data.index.strftime('%B')
# data['Date']=data['Date']+' '+data.index.strftime('%Y')
# data.set_index('Date', inplace=True)
# datum=data
data.dropna(inplace=True)
# print(data.size)
ind = list()
for i in range(int(data.size)):
ind.append(i)
# print(data.Date)
# print(ind)
# Q1 = data.quantile(0.25)
# Q3 = data.quantile(0.75)
# IQR = Q3 - Q1
# # print(IQR)
# data = data[~((data < (Q1 - 1.5 * IQR)) |(data > (Q3 + 1.5 * IQR)))]
# data.shape
# Let's create a pipeline with multiple stages... the Wineind dataset is
# seasonal, so we'll include a FourierFeaturizer so we can fit it without
# seasonality
pipe = pipeline.Pipeline([
("fourier", ppc.FourierFeaturizer(m=12)),
(
"arima",
arima.AutoARIMA(
stepwise=True,
trace=1,
error_action="ignore",
seasonal=False, # because we use Fourier
transparams=False,
suppress_warnings=True))
])
pipe.fit(data)
# print("Model fit:")
# # print(pipe)
# months=12
dates = []
for year in range(2012, 2016 + int(months / 6)):
for month in range(1, 13):
dates.append(dt.datetime(year=year, month=month, day=28))
preds, conf_int = pipe.predict(n_periods=months, return_conf_int=True)
datum = data
data3 = data2.resample('M').mean()
# print(dates)
# print(data3[dt()'2012-01-31'])
# for i, j in zip(data3.index, range(data3.size)):
# if math.isnan(data3[i])==True:
# del dates[j]
# print(datum)
temp = np.append(data3, preds)
# dates=np.array(dates)
# print(np.array(dates).shape)
# # print
# print(temp.shape)
# plt.subplot(211)
plt.plot(dates[:temp.size], temp)
plt.plot(datum)
import matplotlib.pyplot as plt
data3 = pm.datasets.load_wineind()
train, test = data3[:150], data[150:]
lenSeq = 10000
subSamp = 40
f0SamplesSS = 10
f0Samples = 400
data.shape
data = data[:lenSeq]
dataSS = data[::subSamp]
with StepwiseContext(max_steps=2):
pipe = pipeline.Pipeline([
("fourier", ppc.FourierFeaturizer(m=f0Samples)),
("arima", arima.AutoARIMA(stepwise=True, maxiter=20, with_intercept = False, start_p=5, start_q=4, max_p= 6, max_q= 6, trace=1, error_action="ignore",
seasonal=False, # because we use Fourier
suppress_warnings=True))
])
pipe.fit(data)
yhat = pipe.predict(n_periods=1000)
#from pyramid.arima import auto_arima
#f0Samples = 10 # fs = 44100, f0 = 110 (A2), therefore f0 in samples is approx 400
#thissa = pm.auto_arima(train, error_action='ignore', seasonal=True, m=12)
#thissarimaSS = pm.auto_arima(dataSS, with_intercept = False, d = 0, D = 0, start_p=0, start_q=0,test='adf', max_p= 3, max_q= 3, m=f0SamplesSS,start_P=0, start_Q= 0, max_Q=3, max_P=3, trace=True,error_action='ignore', suppress_warnings=True)
#thissarimaS1 = pm.auto_arima(data, with_intercept = False, d = 0, D = 0, start_p=0, start_q=0,test='adf', max_p= 3, max_q= 3, m=f0Samples,start_P=0, start_Q= 0, max_Q=3, max_P=3, trace=True,error_action='ignore', suppress_warnings=True)
#thissarima = pm.auto_arima(data, with_intercept = False, d = 0, start_p=0, start_q=0,test='adf', max_p= 5, max_q= 5, seasonal=False, trace=True,error_action='ignore', suppress_warnings=True)