scikit-学习交叉验证时间序列数据的自定义拆分

scikit-学习交叉验证时间序列数据的自定义拆分

您只需要将拆分的可迭代对象传递给GridSearchCV。此拆分应采用以下格式：

[ (split1_train_idxs, split1_test_idxs), (split2_train_idxs, split2_test_idxs), (split3_train_idxs, split3_test_idxs), ...]

要获取idx，您可以执行以下 *** 作：

groups = df.groupby(df.date.dt.year).groups# {2012: [0, 1], 2013: [2], 2014: [3], 2015: [4, 5]}sorted_groups = [value for (key, value) in sorted(groups.items())] # [[0, 1], [2], [3], [4, 5]]cv = [(sorted_groups[i] + sorted_groups[i+1], sorted_groups[i+2])      for i in range(len(sorted_groups)-2)]

看起来像这样：

[([0, 1, 2], [3]),  # idxs of first split as (train, test) tuple ([2, 3], [4, 5])]  # idxs of second split as (train, test) tuple

然后，您可以执行以下 *** 作：

GridSearchCV(estimator, param_grid, cv=cv, ...)