점 이연 상관계수

from scipy.stats import pointbiserialr correlation_org_lst, correlation_dealout_lst = [], [] p_value_org_lst, p_value_dealout_lst = [], [] feature_lst = train.columns[1:-1].to_list() # 점 이연 상관계수 계산 및 출력 for feature in feature_lst: correlation_org, p_value_org = pointbiserialr(train[feature], train['Outcome']) correlation_org_lst.append(correlation_org) p_value_org_lst.append(p_value_org) # 데이터프레임 생성 correlation_dict = {'Feature': feature_lst, 'correlation_org': correlation_org_lst, 'p_value_org' : p_value_org_lst} correlation_df = pd.DataFrame(correlation_dict) display(correlation_df)

import matplotlib.pyplot as plt import seaborn as sns # Seaborn barplot plt.figure(figsize=(16, 8)) plt.subplot(2,2,1) sns.barplot(x='Feature', y='correlation_org', data=correlation_df) plt.gca().set_title("Point Biserial Correlation [original train]") plt.gca().set_xticklabels(feature_lst, rotation=30) plt.subplot(2,2,2) sns.barplot(x='Feature', y='p_value_org', data=correlation_df) plt.gca().set_xticklabels(feature_lst, rotation=30) plt.gca().set_title("p_value [original train]") plt.show()