인프런 커뮤니티 질문&답변

df = pd.DataFrame({
    'f1': [2, 3, 5, 7, 11, 13, 17, 19, 23, 29],
    'f2': [30, 28, 26, 24, 22, 20, 18, 16, 14, 12],
    'target': ['A', 'A', 'A', 'B', 'B', 'A', 'A', 'A', 'A', 'B']
})

y_train = df.pop('target')

x_tr, x_val, y_tr, y_val = train_test_split(df, y_train, test_size=0.5, random_state=123)
print(x_tr.shape, x_val.shape, y_tr.shape, y_val.shape)

model_rfc = RandomForestClassifier(random_state=42)
model_rfc.fit(x_tr, y_tr)

y_proba_val_rfc = model_rfc.predict_proba(x_val)
print(y_proba_val_rfc)

roc = roc_auc_score(y_val, y_proba_val_rfc[:,1])
print(roc)

(5, 2) (5, 2) (5,) (5,)
[[0.29 0.71]
 [0.92 0.08]
 [0.7  0.3 ]
 [0.74 0.26]
 [0.45 0.55]]
1.0

-------------------------------------------------------------------------

df = pd.DataFrame({
    'f1': [2, 3, 5, 7, 11, 13, 17, 19, 23, 29],
    'f2': [30, 28, 26, 24, 22, 20, 18, 16, 14, 12],
    'target': ['A', 'A', 'A', 'B', 'B', 'A', 'A', 'A', 'A', 'B']
})

target = df.pop('target')
X_train, X_val, y_train, y_val = train_test_split(df, target, test_size=0.5, random_state=0)

clf = RandomForestClassifier(random_state=42)
clf.fit(X_train, y_train)
y_pred = clf.predict_proba(X_val)[:,1]

print(y_pred) # 예측값
roc_auc_score(y_val, y_pred) # 정확도 평가

[0.68 0.   0.25 0.   0.26]
np.float64(0.25)