def time_sequence_predict(ts):
'''
# 查看数据格式
print ts.head()
print ts.head().index
#对数变换
draw_ts(ts)
draw_trend(ts, 25)
draw_acf_pacf(ts)
'''
#平滑法
ts_log = np.log(ts)
'''
draw_ts(ts_log)
print testStationarity(ts)
draw_trend(ts_log, 25)
#差分
diff_25 = ts_log.diff(25)
diff_25.dropna(inplace=True)
diff_25_1 = diff_25.diff(1)
diff_25_1.dropna(inplace=True)
print testStationarity(diff_25_1)
draw_trend(diff_25_1, 25)
draw_acf_pacf(diff_25_1)
#季节性分解
decomposition = seasonal_decompose(ts_log, model="additive")
trend = decomposition.trend
seasonal = decomposition.seasonal
residual = decomposition.resid
'''
#模型识别
rol_mean = ts_log.rolling(window=25).mean()
rol_mean.dropna(inplace=True)
ts_diff_1 = rol_mean.diff(1)
ts_diff_1.dropna(inplace=True)
'''
print testStationarity(ts_diff_1)
'''
ts_diff_2 = ts_diff_1.diff(1)
ts_diff_2.dropna(inplace=True)
###
ts_diff_2 = ts_diff_2.diff(1)
ts_diff_2.dropna(inplace=True)
ts_diff_2 = ts_diff_2.diff(1)
ts_diff_2.dropna(inplace=True)
#print ts_diff_2
'''
draw_trend(ts_diff_2, 25)
draw_acf_pacf(ts_diff_2)
'''
###
model = ARMA(ts_diff_2, order=(4, 1))
result_arma = model.fit(disp=-1, method='css')
#样本拟合
predict_ts = result_arma.predict()
# 一阶差分还原
diff_shift_ts = ts_diff_1.shift(1)
diff_recover_1 = predict_ts.add(diff_shift_ts)
# 再次一阶差分还原
rol_shift_ts = rol_mean.shift(1)
diff_recover = diff_recover_1.add(rol_shift_ts)
# 移动平均还原
rol_sum = ts_log.rolling(window=24).sum()
rol_recover = diff_recover * 25 - rol_sum.shift(1)
# 对数还原
log_recover = np.exp(rol_recover)
log_recover.dropna(inplace=True)
ts = ts[log_recover.index] # 过滤没有预测的记录
'''
plt.figure(facecolor='white')
log_recover.plot(color='blue', label='Predict')
ts.plot(color='red', label='Original')
plt.legend(loc='best')
plt.title('RMSE: %.4f'% np.sqrt(sum((log_recover-ts)**2)/ts.size))
plt.show()
'''
#ARIMA
diffed_ts = diff_ts(ts_log, d=[25, 1])
model = arima_modeling(ts_diff_2)
model.certain_model(4, 1)
predict_ts = model.properModel.predict()
diff_recover_ts = predict_diff_recover(predict_ts, d=[25, 1])
log_recover = np.exp(diff_recover_ts)
ts = ts[log_recover.index] # 过滤没有预测的记录
'''
plt.figure(facecolor='white')
log_recover.plot(color='blue', label='Predict')
ts.plot(color='red', label='Original')
plt.legend(loc='best')
plt.title('RMSE: %.4f'% np.sqrt(sum((log_recover-ts)**2)/ts.size))
plt.show()
'''
#滚动预测
ts_train = ts_log[:'2016-06-30']
date_test = pd.date_range('2016-07-01', periods=31, freq='D').tolist()
ts_test = [0 for i in range(31)]
ts_test = pd.Series(ts_test)
ts_test.index = pd.Index(date_test)
diffed_ts = diff_ts(ts_train, [25, 1])
forecast_list = []
for i, dta in enumerate(ts_test):
if i % 7 == 0:
model = arima_modeling(ts_diff_2)
model.certain_model(4, 1)
forecast_data = forecast_next_day_data(model, type='day')
forecast_list.append(forecast_data)
add_today_data(model, ts_train, forecast_data, [25, 1], type='day')
predict_ts = pd.Series(data=forecast_list,
index=ts_test['2016-07-01':].index)
log_recover = np.exp(predict_ts)
original_ts = ts['2016-07-01':]
'''
plt.figure(facecolor='white')
log_recover.plot(color='blue', label='Predict')
original_ts.plot(color='red', label='Original')
plt.legend(loc='best')
plt.title('RMSE: %.4f'% np.sqrt(sum((log_recover-original_ts)**2)/original_ts.size))
plt.show()
'''
return log_recover
