Stats Model

必要モジュールの読み込み

import pandas as pd
import numpy as np
import random
import matplotlib.pyplot as plt
import seaborn as sns
import statsmodels.api as sm
import math
from scipy import stats
import re

データ分割

from sklearn.model_selection import train_test_split
# データを分割
X, Xt, y, yt = train_test_split(df_dummy_train,df_dummy_test , random_state=0, test_size=0.3)

モデル作成

X = sm.add_constant(X)
stats_model = sm. OLS(y,X).fit()
stats_model.summary()

MAE確認

from sklearn.metrics import mean_absolute_error

pred_y_ts = stats_model.predict(Xt)
#pred_y_ts = scaler.inverse_transform(pred_y_ts)
mae_ts = mean_absolute_error(yt,pred_y_ts)
print("Test_MAE: " + str(round(mae_ts,4)))