时间序列

03年到19年第一季度分季度的数据，13年之前只有传统汽车的销量，13年之后是传统汽车+新能源汽车的销量，需要预测未来三期传统汽车的销量

data = pd.read_excel("/Users/jackwang/downloads/时序数据.xlsx")
data.head()

data = data[['日期','传统汽车销量']]
for i in range(data.shape[0]):
    if  data.loc[i,'日期'][-2:]  == 'Q1':
        data.loc[i,'日期'] = data.loc[i,'日期'][:4] + '-02'
    elif  data.loc[i,'日期'][-2:]  == 'Q2':
        data.loc[i,'日期'] = data.loc[i,'日期'][:4] + '-05'
    elif  data.loc[i,'日期'][-2:]  == 'Q3':
        data.loc[i,'日期'] = data.loc[i,'日期'][:4] + '-08'
    elif  data.loc[i,'日期'][-2:]  == 'Q4':
        data.loc[i,'日期'] = data.loc[i,'日期'][:4] + '-11'

train = data[:56]
test = data[56:]
 

train['Timestamp'] = pd.to_datetime(train['Timestamp'], format='%Y-%m')
train.index = train['Timestamp']
 
test['Timestamp'] = pd.to_datetime(test['日期'],format='%Y-%m')
test.index = test['Timestamp']
 

train.传统汽车销量.plot(figsize=(15,8), title= 'Q_SALE', fontsize=14)
test.传统汽车销量.plot(figsize=(15,8), title= 'Q_SALE', fontsize=14)

arma_mod20 = sm.tsa.ARMA(dta, (2,0)).fit(disp=False)
arma_mod30 = sm.tsa.ARMA(dta, (3,0)).fit(disp=False)
 
 
print(arma_mod20.aic, arma_mod20.bic, arma_mod20.hqic)
 
 
# In[128]:
 
 
print(arma_mod30.params)
 
 
# In[129]:
 
 
sm.stats.durbin_watson(arma_mod30.resid.values)
 
 
# In[130]:
 
 
 
fig = plt.figure(figsize=(12,8))
ax = fig.add_subplot(111)
ax = arma_mod30.resid.plot(ax=ax);
 
 
# In[131]:
 
 
resid = arma_mod30.resid
 
 
# In[133]:
 
 
from scipy import stats
stats.normaltest(resid)
 
 
# In[135]:
 
 
from statsmodels.graphics.api import qqplot
fig = plt.figure(figsize=(12,8))
ax = fig.add_subplot(111)
fig = qqplot(resid, line='q', ax=ax, fit=True)
 
 
# In[136]:
 
 
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)
 
 
# In[137]:
 
 
r,q,p = sm.tsa.acf(resid.values.squeeze(), fft=True, 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'))
 
 
# In[138]:
 
 
predict_sunspots = arma_mod30.predict('2019', '2020', dynamic=True)
print(predict_sunspots)
 
 
 
fig, ax = plt.subplots(figsize=(12, 8))
ax = dta.plot(ax=ax)
fig = arma_mod30.plot_predict('2019', '2020', dynamic=True, ax=ax, plot_insample=False)

参考文章：https://blog.youkuaiyun.com/zkyxgs518/article/details/104728828；
https://github.com/xiasummer1019/statis_learning/blob/master/time_series/time_series.ipynb