특집 리포트: W&B 임베딩 프로젝터

## https://scikit-learn.org/stable/datasets/toy_dataset.html

import wandb
from sklearn.datasets import load_iris, load_diabetes, load_digits, load_wine, load_breast_cancer

def get_df_from_sklearn_dataset(loader_fn):
  ds = loader_fn(as_frame=True)
  df = ds.data
  df["target"] = ds.target
  cols = df.columns.tolist()
  df = df[cols[-1:] + cols[:-1]]
  if (loader_fn == load_digits):
    df["image"] = df.apply(lambda row: wandb.Image(row[1:].values.reshape(8, 8) / 16.0), axis=1)
    cols = df.columns.tolist()
    df = df[cols[-1:] + cols[:-1]]
  return df

def get_all_dfs():
  return {name: get_df_from_sklearn_dataset(fn) for name, fn in ({
      "iris": load_iris,
      "diabetes": load_diabetes,
      "digits": load_digits,
      "wine": load_wine,
      "breast_cancer": load_breast_cancer,
  }).items()}

wandb.init(project="toy_datasets")
wandb.log(get_all_dfs())
wandb.finish()