9.4 소수집단 데이터 업샘플링하기 

from sklearn.utils import resample
mask = df.survived == 1
surv_df = df[mask]
death_df = df[~mask]

df_upsample = resample(
  surv_df,
  replace=True,
  n_samples=len(death_df),
  random_state=42,
)

df2 = pd.concat([death_df, df_upsample])
df2.survived.value_counts()

1    809
0    809
Name: survived, dtype: int64
from imblearn.over_sampling import (
  RandomOverSampler,
)

ros = RandomOverSampler(random_state=42)
X_ros, y_ros = ros.fit_sample(X, y)
pd.Series(y_ros).value_counts()

1    809
0    809
dtype: int64

9.5 과반수집단 데이터를 다운샘플링하기 

from sklearn.utils import resample
mask = df.survived == 1
surv_df = df[mask]
death_df = df[~mask]

df_downsample = resample(
  death_df,
  replace=False,
  n_samples=len(surv_df),
  random_state=42,
)

df3 = pd.concat([surv_df, df_downsample])
df3.survived.value_counts()

1    500
0    500
Name: survived, dtype: int64