def lr_predict(train, test, preprocessing_type):
# separate class label (last column)
train, labels = preprocessing.split_labels(train)
if preprocessing_type == 'smote':
train, labels = preprocessing.apply_smote(train, labels)
classifier = linear_model.LogisticRegression()
validation.cross_validate(classifier, train, labels)
classifier.fit(train, labels)
# test
test, test_labels = preprocessing.split_labels(test)
validation.test(classifier, test, test_labels)
def multiple_balanced_sets():
train, test = preprocessing.prepare_data()
train_list = preprocessing.multiple_balanced_samples(train, 5)
# separate class label (last column)
for i in range(5):
train, labels = preprocessing.split_labels(train_list[i])
classifier = linear_model.LogisticRegression()
validation.cross_validate_set(classifier, train, labels)
validation.cross_validate(classifier, train, labels)
classifier.fit(train, labels)
# test
test, test_labels = preprocessing.split_labels(test)
validation.test(classifier, test, test_labels)
def nn_predict(train, labels, test, writer, params):
clf = MLPClassifier(solver='lbfgs', alpha=1.e-3,
hidden_layer_sizes=(20,params['layer_2']), random_state=1)
vresult = validation.cross_validate(clf, train, labels)
clf.fit(train, labels)
# test
test_labels = test[['Class']]
test_labels = test_labels.values.ravel()
test = test.drop('Class', 1)
tresult = validation.test(clf, test, test_labels)
results = list(params.values())
results.append(vresult['roc_auc'])
results.append(vresult['precision'])
results.append(vresult['recall'])
results.append(vresult['f1'])
results.append(vresult['fp'])
results.append(vresult['fn'])
results.append(tresult['roc_auc'])
results.append(tresult['precision'])
results.append(tresult['recall'])
results.append(tresult['f1'])
results.append(tresult['fp'])
results.append(tresult['fn'])
writer.writerow(results)
def svm_predict(train, test, preprocessing_type):
# separate class label (last column)
train, labels = preprocessing.split_labels(train)
if preprocessing_type == 'smote':
train, labels = preprocessing.apply_smote(train, labels)
# Classifier
# Class weight parameter: weights positive class more strongly than negative class.
# class_weight={1: 2.61, 0: 0.383}
classifier = svm.SVC(kernel='rbf')
validation.cross_validate(classifier, train, labels)
classifier.fit(train, labels)
# test
test, test_labels = preprocessing.split_labels(test)
validation.test(classifier, test, test_labels)
def rf_predict(train, test, preprocessing_type, results_file):
# separate class label
train, labels = preprocessing.split_labels(train)
if preprocessing_type == 'smote':
train, labels = preprocessing.apply_smote(train, labels)
classifier = ensemble.RandomForestClassifier(class_weight={
0: 0.75,
1: 1.5
},
min_samples_split=40,
n_estimators=15)
classifier.fit(train, labels)
vresult = validation.cross_validate(classifier, train, labels)
# test
test, test_labels = preprocessing.split_labels(test)
tresult = validation.test(classifier, test, test_labels)
# save results
results = []
results.append("low_skew (0=0.75, 1=1.5)")
results.append(40)
results.append(15)
results.append(vresult['roc_auc'])
results.append(vresult['precision'])
results.append(vresult['recall'])
results.append(vresult['f1'])
results.append(vresult['fp'])
results.append(vresult['fn'])
results.append(tresult['roc_auc'])
results.append(tresult['precision'])
results.append(tresult['recall'])
results.append(tresult['f1'])
results.append(tresult['fp'])
results.append(tresult['fn'])
results_file.writerow(results)
print(xTrain.shape, yTrain.shape)
print("Data loaded...")
print("Training data")
print(xTrain)
print(yTrain)
print("Verification data")
print(xTest)
print(yTest)
print("length of x" + str(len(xTrain)))
print("length of y" + str(len(yTrain)))
print("Creating classifiers...")
clf = KNeighborsClassifier()
# Validation
validation.cross_validate(clf, xTrain, yTrain)
clf.fit(xTrain, yTrain)
print("KNeighborsClassifier")
score = clf.score(xTest, yTest)
print(str(score))
# Test
validation.test(clf, xTest, yTest)