f819a34e2fbea2dab4997b3b236b517fa12d115d,examples/03_midwest_survey.py,,,#,110

Before Change

from sklearn.model_selection import StratifiedKFold

cv = StratifiedKFold(n_splits=3, random_state=12, shuffle=True)
all_scores = []
for method in ["one-hot", "similarity"]:
    pipeline = make_pipeline(method)
    // Now predict the census region of each participant
    scores = cross_val_score(pipeline, df, y, cv=cv)

After Change

ax = seaborn.boxplot(data=pd.DataFrame(all_scores), orient="h")
import matplotlib.pyplot as plt
plt.ylabel("Encoding", size=17)
plt.xlabel("Prediction accuracy", size=17)
plt.yticks(size=17)
plt.tight_layout()

//////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////

Instances