diff --git a/utils/subsampling.py b/utils/subsampling.py new file mode 100644 index 0000000..47bf870 --- /dev/null +++ b/utils/subsampling.py @@ -0,0 +1,7 @@ +import numpy as np + +def random_subsample(df, num_samples): + np.random.seed(42) + indices = np.random.choice(df.index, num_samples, replace=False) + subsampled_df = df.loc[indices] + return subsampled_df