Python Pandas 中的分层抽样
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/44114463/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
Stratified Sampling in Pandas
提问by Wboy
I've looked at the Sklearn stratified sampling docsas well as the pandas docsand also Stratified samples from Pandasand sklearn stratified sampling based on a columnbut they do not address this issue.
我查看了Sklearn 分层抽样文档以及Pandas文档以及Pandas 的分层样本和基于列的 sklearn 分层抽样，但它们没有解决这个问题。
Im looking for a fast pandas/sklearn/numpy way to generate stratified samples of size n from a dataset. However, for rows with less than the specified sampling number, it should take all of the entries.
我正在寻找一种快速的 pandas/sklearn/numpy 方法来从数据集中生成大小为 n 的分层样本。但是，对于小于指定采样数的行，它应该取所有条目。
Concrete example:
具体例子：
Thank you! :)
谢谢！:)
回答by piRSquared
Use minwhen passing the number to sample. Consider the dataframe df
使用min经过数样本时。考虑数据框df
df = pd.DataFrame(dict(
A=[1, 1, 1, 2, 2, 2, 2, 3, 4, 4],
B=range(10)
))
df.groupby('A', group_keys=False).apply(lambda x: x.sample(min(len(x), 2)))
A B
1 1 1
2 1 2
3 2 3
6 2 6
7 3 7
9 4 9
8 4 8
回答by Ilya Prokin
Extending the groupbyanswer, we can make sure that sample is balanced. To do so, when for all classes the number of samples is >= n_samples, we can just take n_samplesfor all classes (previous answer). When minority class contains < n_samples, we can take the number of samples for all classes to be the same as of minority class.
扩展groupby答案，我们可以确保样本是平衡的。为此，当所有类别的样本数为 >= 时n_samples，我们可以n_samples针对所有类别（先前的答案）。当少数类包含 < 时n_samples，我们可以取所有类的样本数与少数类相同。
def stratified_sample_df(df, col, n_samples):
n = min(n_samples, df[col].value_counts().min())
df_ = df.groupby(col).apply(lambda x: x.sample(n))
df_.index = df_.index.droplevel(0)
return df_
回答by irkinosor
the following sample a total of N row where each group appear in its original proportion to the nearest integer, then shuffle and reset the index using:
以下示例总共 N 行，其中每个组以其与最接近的整数的原始比例出现，然后使用以下方法混洗和重置索引：
df = pd.DataFrame(dict(
A=[1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 3, 3, 4, 4, 4, 4, 4],
B=range(20)
))
Short and sweet:
简短而甜蜜：
df.sample(n=N, weights='A', random_state=1).reset_index(drop=True)
Long version
长版
df.groupby('A', group_keys=False).apply(lambda x: x.sample(int(np.rint(N*len(x)/len(df))))).sample(frac=1).reset_index(drop=True)
