def manaus(start='1983-01-31', end='1995-01-31', p=4, q=4):
"""
Plot the ARMA(p,q) model of the River Negro height
data using statsmodels built-in ARMA class.
Parameters:
start (str): the data at which to begin forecasting
end (str): the date at which to stop forecasting
p (int): max_ar parameter
q (int): max_ma parameter
Return:
aic_min_order (tuple): optimal order based on AIC
bic_min_order (tuple): optimal order based on BIC
"""
# Get dataset
raw = pydata('manaus')
# Make DateTimeIndex
manaus = pd.DataFrame(raw.values,
index=pd.date_range('1903-01', '1993-01', freq='M'))
manaus = manaus.drop(0, axis=1)
# Reset column names
manaus.columns = ['Water Level']
#Selecting the best order
order = order_select(manaus.values,
max_ar=p,
max_ma=q,
ic=['aic', 'bic'],
fit_kw={'method': 'mle'})
aic = order['aic_min_order']
bic = order['bic_min_order']
#The Mle models
model = ARMA(manaus, aic).fit(method='mle')
fig, ax = plt.subplots(figsize=(13, 7))
fig = model.plot_predict(start=start, end=end, ax=ax)
#The Aic plot
ax.set_title('Manaus Dataset AIC')
ax.set_xlabel('Year')
ax.set_ylabel('Water Level')
plt.show()
model = ARMA(manaus, bic).fit(method='mle')
fig, ax = plt.subplots(figsize=(13, 7))
fig = model.plot_predict(start=start, end=end, ax=ax)
#The BIC plot
ax.set_title('Manaus Dataset BIC')
ax.set_xlabel('Year')
ax.set_ylabel('Water Level')
plt.show()
return aic, bic
df.dropna(inplace=True)
##df['Date'] = pd.to_datetime(df['Date'])
LocalTransmission = df['LocalTransmission'].astype('int32')
#print (df.head())
print(df.index)
result = ARMA(df, order=(0, 1)).fit(disp=False)
print(result.summary())
#print(result.params)
predictions = result.predict(start="2020-03-01", end="2020-05-01")
#accuracy = result.score()
print(predictions)
##accuracy = result.score()
#print (accuracy)
result.plot_predict(start="2020-03-01", end="2020-05-01")
plt.suptitle('Prediction for postive cases in Egypt \n Algorithm used: MA',
fontsize=12)
plt.show()
##def mean_forecast_error(y, yhat):
## return y.sub(yhat).mean()
def mean_forecast_error(LocalTransmission, predictions):
return mean(sum(LocalTransmission, predictions))
mean_forecast_error(LocalTransmission, predictions)
y_pred_ar = ar.predict(start=90, end=99)
y_pred_ma = ma.predict(start=90, end=99)
y_pred_arma = arma.predict(start=90, end=99)
print("MSE AR: {:.2f}".format(0.1 *
np.sum(np.power(y_test - y_pred_ar, 2))))
print("MSE MA: {:.2f}".format(0.1 *
np.sum(np.power(y_test - y_pred_ma, 2))))
print("MSE ARMA: {:.2f}".format(0.1 *
np.sum(np.power(y_test - y_pred_arma, 2))))
# Show the results for AR and MA
fig, ax = plt.subplots(2, 1, figsize=(18, 20), sharex=True)
ax[0].plot(y_test, linewidth=1.0, color="r", label="Data")
ar.plot_predict(start=90, end=99, plot_insample=False, ax=ax[0])
ax[1].plot(y_test, linewidth=1.0, color="r", label="Data")
ma.plot_predict(start=90, end=99, plot_insample=False, ax=ax[1])
ax[0].set_title("AR(15) prediction", fontsize=16)
ax[1].set_title("MA(15) prediction", fontsize=16)
ax[1].set_xlabel("Time", fontsize=16)
ax[0].set_ylabel("Measure", fontsize=16)
ax[1].set_ylabel("Measure", fontsize=16)
ax[0].legend(fontsize=16)
ax[1].legend(fontsize=16)
plt.show()
# Show the result for ARMA
model = ARIMA(arima202, (2, 0, 2)).fit()
print model.summary()
model.resid.plot()
plot_acf(model.resid,lags=100)
plt.show
df.ExplosivityIndexMax.diff(1).autocorr(1) #-0.46688
df.ExplosivityIndexMax.diff(1).plot()
plt.show()
#predictions of explosivity of volcanic eruptions
model.plot_predict(1, 35) #ok for up to (1,35) (1,40 onwards returns error)
#(1,30) shows 1960 - 2003
model.plot_predict(10, 30) #1979-1995
model.plot_predict(10, 35) #1981-2003
fig, ax = plt.subplots()
ax = df['1960'].plot(ax=ax)
fig = model.plot_predict(1, 35, ax=ax, plot_insample=False)
#the predictive model doesn't seem to work. No error!
#TODO - to do the code for splitting the data for training / test set
df.head()
#result_trend.k_trend 有常数时是1,没有常数时是0
#result_trend.llf 对数似然函数值
#result_trend.maparams MA参数值
#result_trend.nobs 拟合所用观察数
#result_trend.params 模型的参数,顺序是趋势系数,k_exog外生系数,ar系数,ma系数。
#应该使用params来查看结果更好些
#result_trend.pvalues 系数的p值,基于的是z统计量
#result_trend.resid 模型残差
#result_trend.sigma2 残差的方差
#4.模型拟合度检验
#(1)残差的白噪声检验
output3 = acorr_ljungbox(result_trend.resid,
boxpierce=True,
lags=[6, 12],
return_df=True)
print(output3)
#(2)模型参数的显著性检验
print(result_trend.pvalues) #这个结果貌似与R的不太一致
fig, ax = plt.subplots()
ax = data.loc['1950':].plot(ax=ax)
result_trend.plot_predict('2009',
'2012',
dynamic=True,
ax=ax,
plot_insample=False)
plt.show()
plt.show
#one big negative outlier
#arima (2,0,2)
from statsmodels.tsa.arima_model import ARIMA
model = ARIMA(SO2_eruption[['SO2Mass']], (2, 0, 2)).fit()
print model.summary()
model.resid.plot()
plot_acf(model.resid,lags=50)
plt.show #this time the autocorelation has no negative "outlier"
#predicting with arima(2,0,2)
model.plot_predict(1, 10)
#don't understand why this returns error as compared to volcano explosivity and earthquake magnitude
ig, ax = plt.subplots()
ax = SO2_eruption['2015'].plot(ax=ax)
fig = model.plot_predict(1, 50, ax=ax, plot_insample=False)
predictions = model.predict(
'2012-01-05',
'2016-03-30',
dynamic=True,
)
mean_absolute_error(test, predictions)
model.summary()
model.resid.plot() plot_acf(model.resid,lags=50) plt.show #seems like arma(1,0) is sufficient given little fluctuations in autocorrelation values after 3 #TODO - to do the code for splitting the data for training / test set df.head() n = len(df.mag) train = df.mag[:int(.75*n)] test = df.mag[int(.75*n):] import statsmodels.api as sm from sklearn.metrics import mean_absolute_error model = sm.tsa.ARMA(train, (1, 0)).fit() model.plot_predict(1,35) #The max is (1,35) 40 and above returns error. This is only for two months' worth of quakes in 1960 (Jan-Feb) model.plot_predict(1,20) #For Jan 1960 only. fig, ax = plt.subplots() ax = df['1960'].plot(ax=ax) fig = model.plot_predict(1, 35, ax=ax, plot_insample=False) #whole of 1960 #Other years, the visualization doesn't seem to work
