f819a34e2fbea2dab4997b3b236b517fa12d115d,examples/02_predict_employee_salaries.py,,,#,115

Before Change

from sklearn.model_selection import KFold, cross_val_score
import numpy as np

all_scores = []

cv = KFold(n_splits=5, random_state=12, shuffle=True)
scoring = "r2"
for method in encoding_methods:
    pipeline = make_pipeline(method)
    scores = cross_val_score(pipeline, df, y, cv=cv, scoring=scoring)
    print("{} encoding".format(method))
    print("{} score:  mean: {:.3f}; std: {:.3f}\n".format(
        scoring, np.mean(scores), np.std(scores)))
    all_scores.append(scores)

//////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
// Plotting the results
// --------------------

After Change

from sklearn.model_selection import KFold, cross_val_score
import numpy as np

all_scores = dict()

cv = KFold(n_splits=5, random_state=12, shuffle=True)
scoring = "r2"
for method in encoding_methods:
    pipeline = make_pipeline(method)
    scores = cross_val_score(pipeline, df, y, cv=cv, scoring=scoring)
    print("{} encoding".format(method))
    print("{} score:  mean: {:.3f}; std: {:.3f}\n".format(
        scoring, np.mean(scores), np.std(scores)))
    all_scores[method] = scores

//////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
// Plotting the results
// --------------------
// Finally, we plot the scores on a boxplot:
import seaborn
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)

Instances