def basic():
train, test = preprocessing.prepare_data(True)
with open('nn_resultsfeaturedrop_nosmote.csv', 'w') as csvfile:
writer = csv.writer(csvfile)
# add header
# vary each parameter of random forest
split_train, split_labels = preprocessing.split_labels(train)
split_train, split_labels = preprocessing.apply_smote(
split_train, split_labels)
nn_predict(split_train, split_labels, test, writer, {})
def basic():
train, test = preprocessing.prepare_data(True)
train = train.drop('Amount', axis=1)
test = test.drop('Amount', axis=1)
with open('nn_results.csv', 'w') as csvfile:
writer = csv.writer(csvfile)
split_train, split_labels = preprocessing.split_labels(train)
nn_predict(split_train, split_labels, test, writer)
split_train, split_labels = preprocessing.apply_smote(
split_train, split_labels)
nn_predict(split_train, split_labels, test, writer)
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 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)
spliced_data = data[:, :30]
spliced_target = data[:, 30]
print(spliced_data.shape, spliced_target.shape)
#print(spliced_data)
#print(spliced_target)
xTrain, xTest, yTrain, yTest = model_selection.train_test_split(spliced_data,
spliced_target,
test_size=0.2,
random_state=0)
# applying smote
preprocessing.apply_smote(xTrain, yTrain)
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)))