model.fit(train_data, y=label_data, eval_set=eval_dataset)
eval_dataset = Pool(val_data, val_labels)
model = CatBoostClassifier(depth=8 or 10, iterations=10, task_type="GPU", devices='0-2', eval_metric='Accuracy', boosting_type="Ordered", bagging_temperature=0, use_best_model=True)
当我运行上面的代码时(以2次单独运行/深度设置为8或10),我得到以下结果:
深度10:0.6864865 深度8:0.6756757
我想以某种方式设置和运行GridSearch-使其运行完全相同的组合并产生完全相同的结果-与我手动运行代码时一样。
GridSearch代码:
model = CatBoostClassifier(iterations=10, task_type="GPU", devices='0-2', eval_metric='Accuracy', boosting_type="Ordered", depth=10, bagging_temperature=0, use_best_model=True)
grid = {'depth': [8,10]}
grid_search_result = GridSearchCV(model, grid, cv=2)
results = grid_search_result.fit(train_data, y=label_data, eval_set=eval_dataset)
问题:
我希望GridSearch使用我的“ eval_set”来比较/验证所有不同的运行(例如手动运行时)-但它使用了其他我不理解是什么但它不知道的东西似乎完全看“ eval_set”?
它不仅产生2个结果-而且取决于“ cv”(交叉验证拆分策略)。它运行3、5、7、9或11运行?我不要。
我试图通过调试器遍历整个“结果”对象-但我根本找不到最佳或所有其他运行的验证“准确性”分数。我可以找到很多其他值-但它们都不符合我的期望。这些数字与“ eval_set”数据集生成的数字不匹配吗?
我通过实现自己的简单GridSearch解决了我的问题(如果它可以帮助/激发其他人:-)):如果您对代码有任何评论,请告诉我:-)
import pandas as pd
from catboost import CatBoostClassifier, Pool
from sklearn.model_selection import GridSearchCV
import csv
from datetime import datetime
# Initialize data
train_data = pd.read_csv('./train_x.csv')
label_data = pd.read_csv('./labels_train_x.csv')
val_data = pd.read_csv('./val_x.csv')
val_labels = pd.read_csv('./labels_val_x.csv')
eval_dataset = Pool(val_data, val_labels)
ite = [1000,2000]
depth = [6,7,8,9,10]
max_bin = [None,32,46,100,254]
l2_leaf_reg = [None,2,10,20,30]
bagging_temperature = [None,0,0.5,1]
random_strength = [None,1,5,10]
total_runs = len(ite) * len(depth) * len(max_bin) * len(l2_leaf_reg) * len(bagging_temperature) * len(random_strength)
print('Total runs: ' + str(total_runs))
counter = 0
file_name = './Results/Catboost_' + str(datetime.now().strftime("%d_%m_%Y_%H_%M_%S")) + '.csv'
row = ['Validation Accuray','Logloss','Iterations', 'Depth', 'Max_bin', 'L2_leaf_reg', 'Bagging_temperature', 'Random_strength']
with open(file_name, 'a') as csvFile:
writer = csv.writer(csvFile)
writer.writerow(row)
csvFile.close()
for a in ite:
for b in depth:
for c in max_bin:
for d in l2_leaf_reg:
for e in bagging_temperature:
for f in random_strength:
model = CatBoostClassifier(task_type="GPU", devices='0-2', eval_metric='Accuracy', boosting_type="Ordered", use_best_model=True,
iterations=a, depth=b, max_bin=c, l2_leaf_reg=d, bagging_temperature=e, random_strength=f)
counter += 1
print('Run # ' + str(counter) + '/' + str(total_runs))
result = model.fit(train_data, y=label_data, eval_set=eval_dataset, verbose=1)
accuracy = float(result.best_score_['validation']['Accuracy'])
logLoss = result.best_score_['validation']['Logloss']
row = [ accuracy, logLoss,
('Auto' if a == None else a),
('Auto' if b == None else b),
('Auto' if c == None else c),
('Auto' if d == None else d),
('Auto' if e == None else e),
('Auto' if f == None else f)]
with open(file_name, 'a') as csvFile:
writer = csv.writer(csvFile)
writer.writerow(row)
csvFile.close()
答案 0 :(得分:0)
Catboost中的评估集充当保留集。
在GridSearchCV中,对您的train_data执行简历。
一种解决方案是将您的train_data和eval_dataset合并,并在GridSearchCV中传递train和eval的索引。尝试在 cv 参数中产生两组索引。然后,您将只有一个分割数和准确度数,它们将为您提供相同的结果。