def load_PD_data():
data = []
# Read the training data
file = open('data/train_data.txt')
reader = csv.reader(file)
for row in reader:
data.append(row)
file.close()
X = np.array([x[1:-2] for x in data]).astype(np.float)
y = np.array([x[-2] for x in data]).astype(np.float)
y_label = np.array([x[-1] for x in data]).astype(np.float)
y_label = y_label.astype(int)
del data # free up the memory
#X = preprocessing.scale(X)
#print(X.shape)
#return X, y, y_label
sel_fetaures = [4, 1, 3, 0, 16]
#sel_fetaures = [11, 20, 19, 12, 7]
#sel_fetaures = [0, 16]
X_star = X[:, sel_fetaures]
X = np.delete(X, np.s_[sel_fetaures], axis=1)
return X, y, X_star
def load_kc2_data():
data = []
# Read the training data
file = open('data/kc2_csv.csv')
reader = csv.reader(file)
next(reader, None) # skip the headers
for row in reader:
data.append(row)
file.close()
X = np.array([x[:-1] for x in data]).astype(np.float)
print(X.shape)
y = np.array([x[-1] for x in data])
'''
scaler = StandardScaler()
scaler.fit(X)
X = scaler.transform(X)
'''
y[y == 'yes'] = 1
y[y == 'no'] = 0
y = y.astype(int)
x_star = X[:, 14:21]
X = X[:, 0:14]
del data # free up the memory
return X, y, x_star
def load_CBM_data():
data = []
# Read the training data
file = open('data/CBM_data.txt')
reader = csv.reader(file, delimiter=',')
#next(reader)
for row in reader:
data.append(row)
file.close()
X = np.array([x[1:-2] for x in data]).astype(np.float)
y = np.array([x[-1] for x in data]).astype(np.float)
del data # free up the memory
#X = preprocessing.scale(X)
#y = preprocessing.scale(y)
print(X.shape)
return X, y
def load_energy_data():
data = []
# Read the training data
file = open('data/ENB2012_data.csv')
reader = csv.reader(file)
for row in reader:
data.append(row)
file.close()
X = np.array([x[:-2] for x in data]).astype(np.float)
y = np.array([x[-2] for x in data]).astype(np.float)
x_star = np.array([x[-1] for x in data]).astype(np.float)
del data # free up the memory
#X = preprocessing.scale(X)
print(X.shape)
return X, y, x_star
def load_concrete_data():
data = []
# Read the training data
file = open('data/Concrete_Data.csv')
reader = csv.reader(file)
for row in reader:
data.append(row)
file.close()
X = np.array([x[:-1] for x in data]).astype(np.float)
y = np.array([x[-1] for x in data]).astype(np.float)
del data # free up the memory
sel_fetaures = [6, 7]
X_star = X[:, sel_fetaures]
X = np.delete(X, np.s_[sel_fetaures], axis=1)
return X, y, X_star
def load_wpbc_data():
data = []
# Read the training data
file = open('data/wpbc.data')
reader = csv.reader(file, delimiter=',')
for row in reader:
data.append(row)
file.close()
X = np.array([x[3:-3] for x in data]).astype(float)
y = np.array([x[2] for x in data]).astype(float)
y_label = np.array([x[1] for x in data])
y_label[y_label == 'R'] = 1
y_label[y_label == 'N'] = 0
y_label = y_label.astype(int)
del data # free up the memory
#X = preprocessing.scale(X)
#y = preprocessing.scale(y)
print(X.shape)
return X, y, y_label
def load_ionosphere_data():
data = []
# Read the training data
file = open('data/ionosphere.data')
reader = csv.reader(file)
for row in reader:
data.append(row)
file.close()
X = np.array([x[:-1] for x in data]).astype(np.float)
print(X.shape)
y = np.array([x[-1] for x in data])
#x_star = np.array([x[-1] for x in data]).astype(np.float)
y[y == 'g'] = 1
y[y == 'b'] = 0
y = y.astype(int)
x_star = X[:, [4, 5, 20, 21]]
X = np.delete(X, np.s_[4, 5, 20, 21], axis=1)
del data # free up the memory
#X = preprocessing.scale(X)
return X, y, x_star
def load_gridStability_data():
data = []
# Read the training data
file = open('data/grid_stability.csv')
reader = csv.reader(file)
for row in reader:
data.append(row)
file.close()
X = np.array([x[:-2] for x in data]).astype(np.float)
y = np.array([x[-2] for x in data]).astype(np.float)
y_label = np.array([x[-1] for x in data])
y_label[y_label == 'stable'] = 1
y_label[y_label == 'unstable'] = 0
y_label = y_label.astype(int)
del data # free up the memory
#X = preprocessing.scale(X)
print(X.shape)
return X, y, y_label
def load_parkinsons_data():
data = []
# Read the training data
file = open('data/parkinsons.data')
reader = csv.reader(file)
next(reader) # skip the headers
for row in reader:
data.append(row)
file.close()
X = np.array([x[1:] for x in data]).astype(np.float)
y_label = np.array([x[-7] for x in data]).astype(np.float)
y_label = y_label.astype(int)
#delete label from the features
X = np.delete(X, -7, axis=1)
del data # free up the memory
sel_fetaures = [19, 4, 10, 13, 9, 12, 11, 8, 21, 18]
#sel_fetaures = [21, 18]
X_star = X[:, sel_fetaures]
X = np.delete(X, np.s_[sel_fetaures], axis=1)
return X, y_label, X_star
