def test_predict_score():
data = load_breast_cancer()
variable_names = data.feature_names
df = pd.DataFrame(data.data, columns=variable_names)
df["target"] = data.target
binning_process = BinningProcess(variable_names)
estimator = LogisticRegression()
scaling_method_params = {"min": 300.12, "max": 850.66}
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, scaling_method="min_max",
scaling_method_params=scaling_method_params)
with raises(NotFittedError):
pred = scorecard.predict(df)
with raises(NotFittedError):
pred_proba = scorecard.predict_proba(df)
with raises(NotFittedError):
score = scorecard.score(df)
scorecard.fit(df)
pred = scorecard.predict(df)
pred_proba = scorecard.predict_proba(df)
score = scorecard.score(df)
assert pred[:5] == approx([0, 0, 0, 0, 0])
assert pred_proba[:5, 1] == approx(
[1.15260206e-06, 9.79035720e-06, 7.52481206e-08, 1.12438599e-03,
9.83145644e-06], rel=1e-6)
assert score[:5] == approx([652.16590046, 638.52659074, 669.56413105,
608.27744027, 638.49988325], rel=1e-6)
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()