##########################################################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:
forecast_arima = pipe.predict(n_periods=int(len(test)))
rmse_test_arima = mean_squared_error(test_arima,
forecast_arima,
squared=False)
def draw_(province, isDaily):
# 模型训练
model = arima.AutoARIMA(
start_p=0,
max_p=4,
d=None,
start_q=0,
max_q=1,
start_P=0,
max_P=1,
D=None,
start_Q=0,
max_Q=1,
m=7,
seasonal=True,
test="kpss",
trace=True,
error_action="ignore",
suppress_warnings=True,
stepwise=True,
)
if isDaily:
data = df[province].diff().dropna()
model.fit(data)
else:
data = df[province]
model.fit(data)
# 模型验证
train, test = train_test_split(data, train_size=0.8)
pred_test = model.predict_in_sample(start=train.shape[0], dynamic=False)
validating = pd.Series(pred_test, index=test.index)
r2 = r2_score(test, pred_test)
# 开始预测
pred, pred_ci = model.predict(n_periods=14, return_conf_int=True)
idx = pd.date_range(data.index.max() + pd.Timedelta("1D"),
periods=14,
freq="D")
forecasting = pd.Series(pred, index=idx)
# 绘图呈现
plt.figure(figsize=(24, 6))
plt.plot(data.index, data, label="Actual Value", color="blue")
plt.plot(validating.index, validating, label="Check Value", color="orange")
plt.plot(forecasting.index,
forecasting,
label="Predict Value",
color="red")
# plt.fill_between(forecasting.index, pred_ci[:, 0], pred_ci[:, 1], color="black", alpha=.25)
plt.legend()
plt.ticklabel_format(style="plain", axis="y")
# plt.rcParams["font.sans-serif"] = ["Microsoft YaHei"]
if isDaily:
plt.title(
f"Daily Confirmed Cases Forecasting - {province}\nARIMA {model.model_.order}x{model.model_.seasonal_order} (R2 = {r2:.6f})"
)
plt.savefig(
os.path.join("figures",
f"covid-{adjust_name(province)}-daily.svg"),
bbox_inches="tight",
)
plt.close()
else:
plt.title(
f"Accumulative Confirmed Cases Forecasting - {province}\nARIMA {model.model_.order}x{model.model_.seasonal_order} (R2 = {r2:.6f})"
)
plt.savefig(
os.path.join("figures", f"covid-{adjust_name(province)}.svg"),
bbox_inches="tight",
)
plt.close()
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)
#paramsSS = thissarimaSS.get_params([0])
#sos = paramsSS.get('seasonal_order')
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)
# Here's what the featurizer will create for us:
date_feat = preprocessing.DateFeaturizer(
column_name="date", # the name of the date feature in the exog matrix
with_day_of_week=True,
with_day_of_month=True)
_, X_train_feats = date_feat.fit_transform(y_train, X_train)
print("Head of generated exog features:\n%s" % repr(X_train_feats.head()))
# We can plug this exog featurizer into a pipeline:
pipe = pipeline.Pipeline([
('date', date_feat),
('arima', arima.AutoARIMA(d=n_diffs,
trace=3,
stepwise=True,
suppress_warnings=True,
seasonal=False))
])
pipe.fit(y_train, X_train)
# Plot our forecasts
forecasts = pipe.predict(exogenous=X_test)
fig = plt.figure(figsize=(16, 8))
ax = fig.add_subplot(1, 1, 1)
n_train = y_train.shape[0]
x = np.arange(n_train + forecasts.shape[0])