from models import train_test_split
import numpy as np
from matplotlib import pyplot as plt
import feature_extraction
from scipy.stats import norm
from sklearn.metrics import precision_score
data, labels, name_list = feature_extraction.raw_data(two_cat = True)
trainX, testX, trainY, testY = train_test_split(data, labels, name_list)
train_sigs = np.std(trainX, axis=1)
test_sigs = np.std(testX, axis=1)
thresh = np.linspace(np.min(train_sigs),np.max(train_sigs),50)
tpr = np.zeros((thresh.shape))
fpr = np.zeros((thresh.shape))
for t in range((thresh).size) :
th = thresh[t]
labels_pred = (train_sigs > th)
tpr[t] = np.sum(((labels_pred == 1) & (trainY == 1)))/np.sum(trainY)
fpr[t] = np.sum(((labels_pred == 1) * (trainY == 0))).astype(float)/np.sum((trainY == 0).astype(int))
plt.figure()
plt.plot(fpr,tpr,'-o')
plt.xlabel('FPR')
plt.ylabel('TPR')
plt.savefig('test.png')
import numpy as np
from models import RBF, SEED, train_test_split
dataset = np.genfromtxt('data_points.csv', delimiter=',')
x = dataset[1:, :2]
y = dataset[1:, 2]
y = np.expand_dims(y, -1) # row -> column vector
# train 70%, test 30%
x_train, x_test, y_train, y_test = train_test_split(x,
y,
train_size=0.7,
random_state=SEED)
rbf = RBF(hidden_size=25, _rho=1e-5, _sigma=1)
rbf.fit(x_train, y_train)
print(f'Test error: {rbf.test_loss(x_test, y_test):.4f}')
rbf.surface_plot(x_test)
plt.plot(fpr, tpr, '-o')
plt.xlabel('false positive rate')
plt.ylabel('true positive rate')
plt.title('ROC: Random Forest')
plt.show()
cvsc = np.mean(cross_val_score(rf.clf, data, labels, cv=10))
print('Random Forest Accuracy: ' + str(sc[0]))
print('Random Forest Cross Validation Score: ' + str(cvsc))
# SVM Model
#=======
X_train, X_test, y_train, y_test = train_test_split(data,
labels,
name_list,
test_size=0.2)
svm = models.SVM()
svm.train(X_train, y_train, name_list)
svm_sc, svm_prec = svm.test(X_test, y_test)
# construct ROC curve for SVM
svm.roc_auc(data, labels)
svm.plot_margin(data, labels)
svm_cvsc = cross_val_score(svm.clf, data, labels, cv=5)
print('SVM Accuracy: ' + str(svm_sc))
print('SVM Precision: ' + str(svm_prec))
print('SVM Cross Validation Scores: ' + str(svm_cvsc))