机器学习实战3.4之ARIMA模型参数选择

import pandas as pd
import numpy as np
# TSA from Statsmodels
import statsmodels.api as sm
import statsmodels.formula.api as smf
import statsmodels.tsa.api as smt
# Display and Plotting
import matplotlib.pylab as plt
import seaborn as sns

pd.set_option('display.float_format', lambda x: '%.5f' % x)  # pandas
np.set_printoptions(precision=5, suppress=True)  # numpy
pd.set_option('display.max_columns', 100)
pd.set_option('display.max_rows', 100)
# seaborn plotting style
sns.set(style='ticks', context='poster')

filename_ts = 'data/series1.csv'
ts_df = pd.read_csv(filename_ts, index_col=0, parse_dates=[0])

n_sample = ts_df.shape[0]
print(ts_df.shape)
print(ts_df.head())

(120, 1)
              value
2006-06-01  0.21507
2006-07-01  1.14225
2006-08-01  0.08077
2006-09-01 -0.73952
2006-10-01  0.53552

#创建测试集和训练集
n_train = int(0.95 * n_sample) + 1
n_forecast = n_sample - n_train
#ts_df
ts_train = ts_df.iloc[