Practical demonstration of SimpleImputer with CV

simpleimputer_pipeline.py

# import required libraries
from sklearn.ensemble import RandomForestClassifier # can be any classifier of your choice
from sklearn.impute import SimpleImputer
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.pipeline import Pipeline

# define modeling pipeline
model = RandomForestClassifier() # can be any model that you want to use
imputer = SimpleImputer(strategy='mean') #other allowed imputation strategies can also be used
pipeline = Pipeline(steps=[('i', imputer), ('m', model)])

# define cross-validation criteria
cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)

# fit and evaluate the model defined in pipeline with cross-validation as defined in cv
scores = cross_val_score(pipeline, X, y, scoring='accuracy', cv=cv) #use any scoring parameter of your choice

# print the mean accuracy score
print('Mean Accuracy: %.3f' % (np.mean(scores)))