air_ARIMA 모델분석

시계열 예측의 대표적 모델, 자기회귀차분이동평균모델, 아리마

In statistics and econometrics, and in particular in time series analysis, an autoregressive integrated moving average (ARIMA) model is a generalization of an autoregressive moving average (ARMA) model.

AR (Auto Regressive) - 자기회귀모델
I ( Integrated ) - 차분
MA (Moving Average) - 이동평균모델

# !pip install pyramid-arima

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from math import sqrt
from pandas import datetime

from statsmodels.graphics.tsaplots import plot_acf, plot_pacf
from statsmodels.tsa.arima_model import ARIMA
from sklearn.metrics import mean_squared_error

from asset.config import *
from asset.get_savelog import get_savelog

(SAVE_LOG, SAVE_LOG1) = get_savelog()


# dir_work,
# dir_data,
# dir_data_collect,
# dir_data_realtime,
# dir_data_trash,
# dir_img,
# dir_img_heatmap,
# dir_img_nulschool,
# dir_img_plot_plot,
# dir_img_plot_scatter,
# dir_img_result,
# dir_img_test,


# get_savelog()

# 수집된 데이터의 가장 마지막 화일을 읽어온다.
file_name = os.listdir(dir_data_collect)[-1]    # ['_air_20190109_Wed_1700.csv']

df = pd.read_csv(dir_data_collect + f'/{file_name}')
series = df.PM10.dropna()      # 아리마는 공백이 있으면 안됨 (seq)

plt.figure(figsize=(15,8))

plot_acf(series)
plt.ylim(-0.15, 1.0)
plt.xlim(0, 15)
plt.show()

<Figure size 1080x576 with 0 Axes>