def main():
# load data
training_data = load_data.read_data("train.csv")
testing_data = load_data.read_data("test.csv")
testing_labels = load_data.read_data("submission.csv")
X_train, X_test = load_data.vectorize_data(training_data, testing_data)
Y_train = np.array(training_data)[:, -1]
Y_test = np.array(testing_labels)[:, -1]
svm(X_train, Y_train, X_test, Y_test)
def main():
# load data
training_data = load_data.read_data("train.csv")
testing_data = load_data.read_data("test.csv")
testing_labels = load_data.read_data("submission.csv")
X_train, X_test = load_data.vectorize_data(training_data, testing_data)
Y_train = np.array(training_data)[:, -1]
Y_test = np.array(testing_labels)[:, -1]
#uncommment for grid searching
#params = grid_search_kmeans(X_train, Y_train)
params = {'n_clusters': 2}
kmeans(X_train, Y_train, X_test, Y_test, params)
def main():
# load data
training_data = load_data.read_data("train.csv")
testing_data = load_data.read_data("test.csv")
testing_labels = load_data.read_data("submission.csv")
X_train, X_test = load_data.vectorize_data(training_data, testing_data)
Y_train = np.array(training_data)[:, -1]
Y_test = np.array(testing_labels)[:, -1]
print(X_train.shape)
print(X_test.shape)
X_train = X_train.toarray()
X_test = X_test.toarray()
# reduce data
X_train, X_test = fld(X_train, Y_train, X_test, 2)
def main():
# load data
training_data = load_data.read_data("train.csv")
testing_data = load_data.read_data("test.csv")
testing_labels = load_data.read_data("submission.csv")
X_train, X_test = load_data.vectorize_data(training_data, testing_data)
Y_train = np.array(training_data)[:, -1]
Y_test = np.array(testing_labels)[:, -1]
print(X_train.shape)
print(X_test.shape)
X_train = X_train.toarray()
X_test = X_test.toarray()
#
# means = np.mean(X_train.T, axis=1)
# # center columns
# cols = X_train - means
# # print(cols)
#
# # cov matrix
# cov = np.cov(cols.T)
#
# # calculate dims needed to be kept based on error rate
# values, vectors = np.linalg.eig(cov)
# dim = pca_error_rate(values, 0.2)
# print("Reduced DIMS to: " + str(dim) + " from " + str(len(training_data[0])))
# reduce data
X_train, X_test = pca(X_train, X_test, 2952)
print(X_train.shape)
print(X_test.shape)
params = {
'activation': 'relu',
'solver': 'lbfgs',
'hidden_layer_sizes': (100, 10),
'learning_rate_init': 0.0009
}
bpnn.bpnn(X_train, Y_train, X_test, Y_test, params)
def main():
# load data
training_data = load_data.read_data("train.csv")
testing_data = load_data.read_data("test.csv")
testing_labels = load_data.read_data("submission.csv")
X_train, X_test = load_data.vectorize_data(training_data, testing_data)
Y_train = np.array(training_data)[:, -1]
Y_test = np.array(testing_labels)[:, -1]
#uncommment for grid searching
#params = grid_search_bpnn(X_train, Y_train)
params = {
'activation': 'relu',
'solver': 'lbfgs',
'hidden_layer_sizes': (100, 10),
'learning_rate_init': 0.0009
}
bpnn(X_train, Y_train, X_test, Y_test, params)
def main():
# load data
training_data = load_data.read_data("train.csv")
testing_data = load_data.read_data("test.csv")
testing_labels = load_data.read_data("submission.csv")
X_train, X_test = load_data.vectorize_data(training_data, testing_data)
X_train = X_train.toarray()
X_test = X_test.toarray()
Y_train = np.array(training_data)[:, -1]
Y_test = np.array(testing_labels)[:, -1]
# the training and testing datasets should have the same dimension
_, nftrain = X_train.shape
_, nftest = X_test.shape
assert nftrain == nftest
# ask the user to input which discriminant function to use
prompt = '''
Type of discriminant functions supported assuming Gaussian pdf:
1 - minimum Euclidean distance classifier
2 - minimum Mahalanobis distance classifier
3 - quadratic classifier
'''
print(prompt)
str = input('Please input 1, 2, or 3: ')
cases = int(str)
# ask the user to input prior probability that needs to sum to 1
prop_str = input(
"Please input prior probabilities in float numbers, separated by space, and they must add to 1: \n"
)
numbers = prop_str.split()
P = np.zeros(len(numbers))
Psum = 0
for i in range(len(numbers)):
P[i] = float(numbers[i])
Psum += P[i]
if Psum != 1:
print("Prior probabilities do not add up to 1. Please check!")
sys.exit(1)
# derive the decision rule from the training set and apply on the test set
t0 = time.time() # start time
Y_pred = mpp(X_train, Y_train, X_test, cases, P)
t1 = time.time() # ending time
print(Y_pred)
Y_pred = Y_pred.astype("int")
Y_pred = Y_pred.astype("str")
# calculate accuracy
precision, recall, fscore, train_support = score(Y_test,
Y_pred,
pos_label='1',
average='binary')
print('Precision: {} / Recall: {} / F1-Score: {} / Accuracy: {}'.format(
round(precision, 3), round(recall, 3), round(fscore, 3),
round(acs(Y_test, Y_pred), 3)))
cm = confusion_matrix(Y_test, Y_pred)
class_label = ["0", "1"]
df_cm = pd.DataFrame(cm, index=class_label, columns=class_label)
sns.heatmap(df_cm, annot=True, fmt='d')
plt.title("Confusion Matrix")
plt.xlabel("Predicted Label")
plt.ylabel("True Label")
plt.show()
print(f'The learning process takes {t1 - t0} seconds.')