def baeysian_clas(train,
test,
val_trai,
val_test,
auto_calibration=False,
calibration_func=None,
clf=None,
CostMatrix=None,
CostMatrixTrain=None):
scaler = MinMaxScaler()
train = scaler.fit_transform(train)
val_trai = scaler.fit_transform(val_trai)
if calibration_func is None:
model = clf.fit(train, test)
else:
cc = CalibratedClassifierCV(clf, method=calibration_func, cv=3)
model = cc.fit(train, test)
prob_test = model.predict_proba(val_trai)
bmr = BayesMinimumRiskClassifier(calibration=auto_calibration)
pred_test = bmr.predict(prob_test, CostMatrix)
prob_test_train = model.predict_proba(train)
bmr_train = BayesMinimumRiskClassifier(calibration=auto_calibration)
pred_train = bmr_train.predict(prob_test_train, CostMatrixTrain)
print(classification_report(val_test, pred_test))
loss = cost_loss(val_test, pred_test, CostMatrix)
print("%d\n" % loss)
print(confusion_matrix(val_test, pred_test).T)
return pred_train, pred_test
def main():
X_train, X_test, y_train, y_test = load_data(train=True, test_size=0.4)
classifiers = {"RF": {"f": RandomForestClassifier()},
"DT": {"f": DecisionTreeClassifier()}}
ci_models = ['DT', 'RF']
# Fit the classifiers using the training dataset
for model in classifiers.keys():
classifiers[model]["f"].fit(X_train, y_train)
classifiers[model]["c"] = classifiers[model]["f"].predict(X_test)
classifiers[model]["p"] = classifiers[model]["f"].predict_proba(X_test)
classifiers[model]["p_train"] = classifiers[model]["f"].predict_proba(X_train)
from sklearn.metrics import f1_score, precision_score, recall_score, accuracy_score
measures = {"F1Score": f1_score, "Precision": precision_score,
"Recall": recall_score, "Accuracy": accuracy_score}
results = pd.DataFrame(columns=__labels__)
from costcla.models import BayesMinimumRiskClassifier
for model in ci_models:
classifiers[model+"-BMR"] = {"f": BayesMinimumRiskClassifier()}
# Fit
classifiers[model+"-BMR"]["f"].fit(y_test, classifiers[model]["p"])
# Calibration must be made in a validation set
# Predict
classifiers[model+"-BMR"]["c"] = classifiers[model+"-BMR"]["f"].predict(classifiers[model]["p"], cost_mat_test)
def _create_bmr_model(model, X_val, y_val, calibration=True):
y_hat_val_proba = model.predict_proba(X_val)
bmr = BayesMinimumRiskClassifier(calibration=calibration)
bmr.fit(y_val, y_hat_val_proba)
return model, bmr
def cost_sensitive_classification(model, X_train, X_test, y_train, y_test, cost_mat_test): c_model = BayesMinimumRiskClassifier() y_prob_test = model.predict_proba(X_test) y_pred_test_model = model.predict(X_test) c_model.fit(y_test, y_prob_test) y_pred_test_c_model = c_model.predict(y_prob_test, cost_mat_test) c_accuracy = accuracy_score(y_test, y_pred_test_c_model) return c_accuracy, y_pred_test_c_model
cost_matrix = np.hstack((fp, fn, tp, tn))
print("no cost minimization")
clf = RandomForestClassifier(random_state=0, n_estimators=100)
model = clf.fit(X_train, y_train)
pred_test = model.predict(X_test)
print(classification_report(y_test, pred_test, target_names=data.target_names))
loss = cost_loss(y_test, pred_test, cost_matrix)
print("%d\n" % loss)
print(confusion_matrix(y_test, pred_test).T) # transpose to align with slides
print("no calibration")
clf = RandomForestClassifier(random_state=0, n_estimators=100)
model = clf.fit(X_train, y_train)
prob_test = model.predict_proba(X_test)
bmr = BayesMinimumRiskClassifier(calibration=False)
pred_test = bmr.predict(prob_test, cost_matrix)
print(classification_report(y_test, pred_test, target_names=data.target_names))
loss = cost_loss(y_test, pred_test, cost_matrix)
print("%d\n" % loss)
print(confusion_matrix(y_test, pred_test).T) # transpose to align with slides
print("costcla calibration on training set")
clf = RandomForestClassifier(random_state=0, n_estimators=100)
model = clf.fit(X_train, y_train)
prob_train = model.predict_proba(X_train)
bmr = BayesMinimumRiskClassifier(calibration=True)
bmr.fit(y_train, prob_train)
prob_test = model.predict_proba(X_test)
pred_test = bmr.predict(prob_test, cost_matrix)
print(classification_report(y_test, pred_test, target_names=data.target_names))
def _fit_bmr_model(self, X, y):
"""Private function used to fit the BayesMinimumRisk model."""
self.f_bmr = BayesMinimumRiskClassifier()
X_bmr = self.predict_proba(X)
self.f_bmr.fit(y, X_bmr)
return self
