时间序列DEMO

2019独角兽企业重金招聘Python工程师标准>>>

#!/usr/bin/env python
from __future__ import print_function
import numpy as np
from scipy import stats
import pandas as pd
import matplotlib
matplotlib.style.use('ggplot')
import matplotlib.pyplot as plt
import statsmodels.api as sm
from statsmodels.graphics.api import qqplot
print(sm.datasets.sunspots.NOTE)

dta = sm.datasets.sunspots.load_pandas().data

dta.index = pd.Index(sm.tsa.datetools.dates_from_range('1700', '2008'))
del dta["YEAR"]

dta.plot(figsize=(12,8));   ###一定记得加分号，要不然后面的图片显示不了


fig = plt.figure(figsize=(12,8))
ax1 = fig.add_subplot(211)
fig = sm.graphics.tsa.plot_acf(dta.values.squeeze(), lags=40, ax=ax1)
ax2 = fig.add_subplot(212)
fig = sm.graphics.tsa.plot_pacf(dta, lags=40, ax=ax2)

arma_mod20 = sm.tsa.ARMA(dta, (2,0)).fit()
print(arma_mod20.params)
print(arma_mod20.aic, arma_mod20.bic, arma_mod20.hqic)


arma_mod30 = sm.tsa.ARMA(dta, (3,0)).fit()
print(arma_mod30.params)
print(arma_mod30.aic, arma_mod30.bic, arma_mod30.hqic)

sm.stats.durbin_watson(arma_mod30.resid.values)
fig = plt.figure(figsize=(12,8))
ax = fig.add_subplot(111)
ax = arma_mod30.resid.plot(ax=ax);  ###一定记得加分号，要不然后面的图片显示不了

resid = arma_mod30.resid
stats.normaltest(resid)

fig = plt.figure(figsize=(12, 8))
ax = fig.add_subplot(111)
fig = qqplot(resid, line='q', ax=ax, fit=True)


fig = plt.figure(figsize=(12, 8))
ax1 = fig.add_subplot(211)
fig = sm.graphics.tsa.plot_acf(resid.values.squeeze(), lags=40, ax=ax1)
ax2 = fig.add_subplot(212)
fig = sm.graphics.tsa.plot_pacf(resid, lags=40, ax=ax2)


r, q, p = sm.tsa.acf(resid.values.squeeze(), qstat=True)
data = np.c_[range(1,41), r[1:], q, p]
table = pd.DataFrame(data, columns=['lag', "AC", "Q", "Prob(>Q)"])
print(table.set_index('lag'))

predict_sunspots = arma_mod30.predict('1990', '2012', dynamic=True)
print(predict_sunspots)


fig, ax = plt.subplots(figsize=(12, 8))
ax = dta.ix['1950':].plot(ax=ax)
fig = arma_mod30.plot_predict('1990', '2012', dynamic=True, ax=ax, plot_insample=False)

def mean_forecast_err(y, yhat):
    return y.sub(yhat).mean()

mean_forecast_err(dta.SUNACTIVITY, predict_sunspots)


##############
""" ADF test """
import numpy as np
import statsmodels.tsa.stattools as ts
x = np.array([1,2,3,4,3,4,2,3])
result = ts.adfuller(x, 1)

print("Test statistic", result[0])
print("p-value", result[1])
print("Lags Used", result[2])
print("Number of observations Used", result[3])
print("Critical Value(1%)", result[4]['1%'])
print("Critical Value(5%)", result[4]['5%'])
print("Critical Value(10%)", result[4]['10%'])

转载于:https://my.oschina.net/kyo4321/blog/1068623