After the use of smote (oversampling) in pipeline not getting result

Question

after the deployment of smote library on target columns still showing the imbalance target result.code is running successful but not showing the smote deployment results. y_train.value_counts():

False 538 True 38 Name: isLegendary, dtype: int64

from sklearn.compose import ColumnTransformer #apply trnasformation on columns
from imblearn.pipeline import Pipeline as imbpipeline

from imblearn.over_sampling import SMOTE
smote = SMOTE(sampling_strategy='auto',random_state=42)

prepro = ColumnTransformer(
    transformers=[
        ('ohe', OneHotEncoder(handle_unknown='ignore', sparse=False, drop='first'), ["Type_1", "Type_2", "Color", "Egg_Group_1", "Body_Style"]),
        ('ft', FunctionTransformer(func=np.log1p), ['Total', 'HP', 'Attack', 'Defense', 'Sp_Atk', 'Sp_Def', 'Speed', 'Generation', 'Pr_Male', 'Height_m', 'Weight_kg']),
        ('scaler', MinMaxScaler(), ['Total', 'HP', 'Attack', 'Defense', 'Sp_Atk', 'Sp_Def', 'Speed', 'Generation', 'Pr_Male', 'Height_m', 'Weight_kg'])
    ],
    remainder='passthrough'
)

from sklearn.ensemble import RandomForestClassifier
model=RandomForestClassifier(bootstrap= True,criterion='gini',max_depth=15,max_features='log2',n_estimators= 10,verbose=False)


# Create the imbalanced-learn pipeline
pipeline = imbpipeline([
    ('preprocessor', prepro),
    ('smote', smote),
    ('model',model)
])
# Fit the pipeline on the data
pipeline.fit(x_train, y_train)

i am expecting that it should convert imbalance into balance class:-
y_train.value_counts():

False    538
True     538
Name: isLegendary, dtype: int64

Answer 1

The code is running successful but not converting it into balanced class