def test_verbose():
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()
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, verbose=True)
with open("tests/test_scorecard_verbose.txt", "w") as f:
with redirect_stdout(f):
scorecard.fit(df)
def test_scaling_method_params_continuous_pdo_odds():
data = load_boston()
variable_names = data.feature_names
df = pd.DataFrame(data.data, columns=variable_names)
df["target"] = data.target
with raises(ValueError):
estimator = LinearRegression()
binning_process = BinningProcess(variable_names)
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, scaling_method="pdo_odds",
scaling_method_params={})
scorecard.fit(df)
def test_input():
data = load_breast_cancer()
variable_names = data.feature_names
X = pd.DataFrame(data.data, columns=variable_names)
y = data.target
y[0] = 4
binning_process = BinningProcess(variable_names)
estimator = LogisticRegression()
with raises(ValueError):
scorecard = Scorecard(binning_process=binning_process,
estimator=estimator)
scorecard.fit(X, y)
def test_input():
data = load_breast_cancer()
variable_names = data.feature_names
df = pd.DataFrame(data.data, columns=variable_names)
target = data.target
target[0] = 4
df["target"] = target
binning_process = BinningProcess(variable_names)
estimator = LogisticRegression()
with raises(ValueError):
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator)
scorecard.fit(df)
def test_estimator_not_coef():
from sklearn.ensemble import RandomForestClassifier
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 = RandomForestClassifier()
scorecard = Scorecard(binning_process=binning_process, estimator=estimator)
with raises(RuntimeError):
scorecard.fit(X, y)
def test_params():
with raises(TypeError):
cf = Counterfactual(scorecard=None)
cf.fit(X_binary)
with raises(NotFittedError):
binning_process = BinningProcess(feature_names_binary)
estimator = LogisticRegression()
scorecard = Scorecard(binning_process=binning_process,
estimator=estimator)
cf = Counterfactual(scorecard=scorecard)
cf.fit(X_binary)
with raises(TypeError):
cf = Counterfactual(scorecard_binary, special_missing=1)
cf.fit(X_binary)
with raises(ValueError):
cf = Counterfactual(scorecard_binary, n_jobs=-1)
cf.fit(X_binary)
with raises(TypeError):
cf = Counterfactual(scorecard_binary, verbose=1)
cf.fit(X_binary)
def test_default_continuous():
data = load_boston()
variable_names = data.feature_names
df = pd.DataFrame(data.data, columns=variable_names)
df["target"] = data.target
binning_process = BinningProcess(variable_names)
estimator = LinearRegression()
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator).fit(df)
sct = scorecard.table(style="detailed")
sc_min, sc_max = sct.groupby("Variable").agg(
{'Points': [np.min, np.max]}).sum()
assert sc_min == approx(-15.813545796848476, rel=1e-6)
assert sc_max == approx(85.08156623609487, 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()
def test_default():
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()
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator).fit(df)
with raises(ValueError):
sct = scorecard.table(style="new")
sct = scorecard.table(style="summary")
sc_min, sc_max = sct.groupby("Variable").agg(
{'Points': [np.min, np.max]}).sum()
assert sc_min == approx(-43.65762593147646, rel=1e-6)
assert sc_max == approx(42.69694657427327, rel=1e-6)
def _fit_scorecard(target_dtype, X_train, y_train):
if target_dtype == "binary":
estimator = LogisticRegression()
else:
estimator = LinearRegression()
variable_names = list(X_train.columns)
binning_process = BinningProcess(variable_names)
scorecard = Scorecard(binning_process=binning_process,
estimator=estimator).fit(X_train, y_train)
return scorecard
def test_scaling_method_min_max():
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, "max": 850}
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, scaling_method="min_max",
scaling_method_params=scaling_method_params).fit(df)
sct = scorecard.table(style="summary")
sc_min, sc_max = sct.groupby("Variable").agg(
{'Points': [np.min, np.max]}).sum()
assert sc_min == approx(300, rel=1e-6)
assert sc_max == approx(850, rel=1e-6)
def test_scaling_method_pdo_odd():
data = load_breast_cancer()
variable_names = data.feature_names
df = pd.DataFrame(data.data, columns=variable_names)
df["target"] = data.target
odds = 1 / data.target.mean()
binning_process = BinningProcess(variable_names)
estimator = LogisticRegression()
scaling_method_params = {"pdo": 20, "odds": odds, "scorecard_points": 600}
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, scaling_method="pdo_odds",
scaling_method_params=scaling_method_params).fit(df)
sct = scorecard.table(style="summary")
sc_min, sc_max = sct.groupby("Variable").agg(
{'Points': [np.min, np.max]}).sum()
assert sc_min == approx(-612.2266586867094, rel=1e-6)
assert sc_max == approx(1879.4396115559216, rel=1e-6)
def test_rounding():
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()
scaling_method_params = {"min": 200.52, "max": 850.66}
scorecard = Scorecard(binning_process=binning_process,
estimator=estimator, scaling_method="min_max",
scaling_method_params=scaling_method_params,
rounding=True).fit(X, y)
sct = scorecard.table(style="summary")
sc_min, sc_max = sct.groupby("Variable").agg(
{'Points': [np.min, np.max]}).sum()
assert sc_min == approx(201, rel=1e-6)
assert sc_max == approx(851, rel=1e-6)
def test_rounding_pdo_odds():
data = load_breast_cancer()
variable_names = data.feature_names
X = pd.DataFrame(data.data, columns=variable_names)
y = data.target
odds = 1 / data.target.mean()
binning_process = BinningProcess(variable_names)
estimator = LogisticRegression()
scaling_method_params = {"pdo": 20, "odds": odds, "scorecard_points": 600}
scorecard = Scorecard(binning_process=binning_process,
estimator=estimator, scaling_method="pdo_odds",
scaling_method_params=scaling_method_params,
rounding=True).fit(X, y)
sct = scorecard.table(style="summary")
sc_min, sc_max = sct.groupby("Variable").agg(
{'Points': [np.min, np.max]}).sum()
assert sc_min == approx(-612, rel=1e-6)
assert sc_max == approx(1880, rel=1e-6)
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 test_scaling_params():
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()
with raises(ValueError):
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, scaling_method="pdo_odds",
scaling_method_params={"pdo": 20})
scorecard.fit(df)
with raises(ValueError):
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, scaling_method="pdo_odds",
scaling_method_params={"pdo": 20, "odds": -2,
"scorecard_points": -22})
scorecard.fit(df)
with raises(ValueError):
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, scaling_method="min_max",
scaling_method_params={"min": "a", "max": 600})
scorecard.fit(df)
with raises(ValueError):
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, scaling_method="min_max",
scaling_method_params={"min": 900, "max": 600})
scorecard.fit(df)
from optbinning.exceptions import CounterfactualsFoundWarning
from optbinning.scorecard import Counterfactual
from sklearn.datasets import load_breast_cancer
from sklearn.exceptions import NotFittedError
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import LogisticRegression
from tests.datasets import load_boston
data = load_breast_cancer()
feature_names_binary = data.feature_names
X_binary = pd.DataFrame(data.data, columns=feature_names_binary)
y_binary = data.target
scorecard_binary = Scorecard(
binning_process=BinningProcess(feature_names_binary),
estimator=LogisticRegression()).fit(X_binary, y_binary)
data = load_boston()
feature_names_continuous = data.feature_names
X_continuous = pd.DataFrame(data.data, columns=feature_names_continuous)
y_continuous = data.target
scorecard_continuous = Scorecard(
binning_process=BinningProcess(feature_names_continuous),
estimator=LinearRegression()).fit(X_continuous, y_continuous)
def test_params():
with raises(TypeError):
cf = Counterfactual(scorecard=None)
def test_information():
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()
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator)
with raises(NotFittedError):
scorecard.information()
scorecard.fit(df)
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)
def test_params():
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()
with raises(TypeError):
scorecard = Scorecard(target=1, binning_process=binning_process,
estimator=estimator)
scorecard.fit(df)
with raises(TypeError):
scorecard = Scorecard(target="target", binning_process=estimator,
estimator=estimator)
scorecard.fit(df)
with raises(TypeError):
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=binning_process)
scorecard.fit(df)
with raises(ValueError):
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, scaling_method="new_method",
scaling_method_params=dict())
scorecard.fit(df)
with raises(ValueError):
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, scaling_method="min_max",
scaling_method_params=None)
scorecard.fit(df)
with raises(TypeError):
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, scaling_method="min_max",
scaling_method_params=[])
scorecard.fit(df)
with raises(TypeError):
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, intercept_based=1)
scorecard.fit(df)
with raises(TypeError):
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, reverse_scorecard=1)
scorecard.fit(df)
with raises(TypeError):
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, rounding=1)
scorecard.fit(df)
with raises(TypeError):
scorecard = Scorecard(target="target", binning_process=binning_process,
estimator=estimator, verbose=1)
scorecard.fit(df)