本文整理汇总了Python中sklearn.calibration.CalibratedClassifierCV.score方法的典型用法代码示例。如果您正苦于以下问题：Python CalibratedClassifierCV.score方法的具体用法？Python CalibratedClassifierCV.score怎么用？Python CalibratedClassifierCV.score使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类sklearn.calibration.CalibratedClassifierCV的用法示例。
在下文中一共展示了CalibratedClassifierCV.score方法的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: ReportPerfCV
# 需要导入模块: from sklearn.calibration import CalibratedClassifierCV [as 别名]
# 或者: from sklearn.calibration.CalibratedClassifierCV import score [as 别名]
def ReportPerfCV(model, feature_set, y, calibrated = False, n_folds = 5,
short = False):
kcv = StratifiedKFold(y, n_folds, shuffle = True); i = 1
res = np.empty((len(y), len(np.unique(y))))
X, Xtest = GetDataset(feature_set)
if calibrated:
logger.info("Enabling probability calibration...")
model = CalibratedClassifierCV(model, 'sigmoid', cv = n_folds - 1)
for train_idx, valid_idx in kcv:
logger.info("Running fold %d...", i);
model.fit(X[train_idx], y[train_idx])
logger.info("Fold %i Accuracy: %.4f", i,
model.score(X[valid_idx], y[valid_idx]))
res[valid_idx, :] = model.predict_proba(X[valid_idx])
logger.info("Fold %i Log Loss: %.4f", i,
log_loss(y[valid_idx], res[valid_idx]))
i += 1
if short: break
if short: return -log_loss(y[valid_idx], res[valid_idx])
yhat = np.argmax(res, axis = 1) + 1
Y = np.array([int(i[-1]) for i in y])
logger.info("CV Accuracy: %.5f", accuracy_score(Y, yhat))
logger.info("CV Log Loss: %.4f", log_loss(y, res))
return res, -log_loss(y, res)示例2: dmatrices
# 需要导入模块: from sklearn.calibration import CalibratedClassifierCV [as 别名]
# 或者: from sklearn.calibration.CalibratedClassifierCV import score [as 别名]
df_test.loc[df_test['Age'].isnull(), 'Age'] = np.nanmedian(df_test['Age'])
# Training/testing array creation
y_train, X_train = dmatrices('Survived ~ Age + Sex + Pclass + SibSp + Parch + Embarked', df_train)
X_test = dmatrix('Age + Sex + Pclass + SibSp + Parch + Embarked', df_test)
# Creating processing pipelines with preprocessing. Hyperparameters selected using cross validation
steps1 = [('poly_features', PolynomialFeatures(3, interaction_only=True)),
('logistic', LogisticRegression(C=5555., max_iter=16, penalty='l2'))]
steps2 = [('rforest', RandomForestClassifier(min_samples_split=15, n_estimators=73, criterion='entropy'))]
pipeline1 = Pipeline(steps=steps1)
pipeline2 = Pipeline(steps=steps2)
# Logistic model with cubic features
pipeline1.fit(X_train, y_train.ravel())
print('Accuracy (Logistic Regression-Poly Features (cubic)): {:.4f}'.format(pipeline1.score(X_train, y_train.ravel())))
# Random forest with calibration
pipeline2.fit(X_train[:600], y_train[:600].ravel())
calibratedpipe2 = CalibratedClassifierCV(pipeline2, cv=3, method='sigmoid')
calibratedpipe2.fit(X_train[600:], y_train[600:].ravel())
print('Accuracy (Random Forest - Calibration): {:.4f}'.format(calibratedpipe2.score(X_train, y_train.ravel())))
# Create the output dataframe
output = pd.DataFrame(columns=['PassengerId', 'Survived'])
output['PassengerId'] = df_test['PassengerId']
# Predict the survivors and output csv
output['Survived'] = pipeline1.predict(X_test).astype(int)
output.to_csv('output.csv', index=False)