def buildScoreCard(df, features, labelCol):
binning_process = BinningProcess(features)
estimator = HuberRegressor(max_iter=200)
scorecard = Scorecard(binning_process=binning_process, target=labelCol,
estimator=estimator, scaling_method=None,
scaling_method_params={"min": 0, "max": 100},
reverse_scorecard=True)
scorecard.verbose = True
scorecard.fit(df, check_input=False)
scorecard.information(print_level=2)
print(scorecard.table(style="summary"))
score = scorecard.score(df)
y_pred = scorecard.predict(df)
plt.scatter(score, df[labelCol], alpha=0.01, label="Average profit")
plt.plot(score, y_pred, label="Huber regression", linewidth=2, color="orange")
plt.ylabel("Average profit value (unit=100,000)")
plt.xlabel("Score")
plt.legend()
plt.show()
def test_information():
data = load_breast_cancer()
variable_names = data.feature_names
X = pd.DataFrame(data.data, columns=variable_names)
y = data.target
binning_process = BinningProcess(variable_names)
estimator = LogisticRegression()
scorecard = Scorecard(binning_process=binning_process, estimator=estimator)
with raises(NotFittedError):
scorecard.information()
scorecard.fit(X, y)
with raises(ValueError):
scorecard.information(print_level=-1)
with open("tests/test_scorecard_information.txt", "w") as f:
with redirect_stdout(f):
scorecard.information(print_level=0)
scorecard.information(print_level=1)
scorecard.information(print_level=2)