def train_model(X, y, clf):
#split the dataset
crossvalidation = cross_validation.StratifiedKFold(y, n_folds=5)
#fit the model
cms = []
train_scores = []
test_scores = []
for train, test in crossvalidation:
X_train, y_train = X[train], y[train]
X_test, y_test = X[test], y[test]
X_train, X_test = impute_nan(X_train, X_test)
X_train, X_test = normalize_features(X_train, X_test)
#print(X_train[0])
clf.fit(X_train, y_train)
#evaluate the model
train_score = clf.score(X_train, y_train)
train_scores.append(train_score)
test_score = clf.score(X_test, y_test)
test_scores.append(test_score)
y_predict = clf.predict(X_test)
cm = confusion_matrix(y_test, y_predict)
cms.append(cm)
return np.mean(test_scores), np.mean(train_scores), np.asarray(cms)
def feature_extraction(audio_file, wl=20, ws=10, nf=24, nceps=19, fmin=0., fmax=4000., d_w=2, pre=0.97, mel=True):
# Parameters used to extract MFCC (These can be defined in a separate configuration file)
# wl = 20 # The window length in milliseconds
# ws = 10 # The window shift of the in milliseconds
# nf = 24 # The number of filter bands
# nceps = 19 # The number of cepstral coefficients
# fmin = 0. # The minimal frequency of the filter bank
# fmax = 4000. # The maximal frequency of the filter bank
# d_w = 2 # The delta value used to compute 1st and 2nd derivatives
# pre = 0.97 # The coefficient used for the pre-emphasis
# mel = True # Tell whether MFCC or LFCC are extracted
# We could also add 1st and 2nd derivatives by activating their flags!
# read the audio file
#(rate, signal) = utils.read(audio_file)
(rate, signal) = utils.load_wav_as_mono(audio_file)
# extract MFCCsu
ceps = bob.ap.Ceps(rate, wl, ws, nf, nceps, fmin, fmax, d_w, pre, mel)
#Convert signal to float array
signal = numpy.cast['float'](signal)
mfcc = ceps(signal)
# let's just normalize them using this helper function
# This will reduce the effect of the channel
mfcc = utils.normalize_features(mfcc)
return mfcc
def train_model(X, y, c):
svm_clf = SVC(kernel='linear', C=c)
crossvalidation = cross_validation.StratifiedKFold(y, n_folds=5)
#fit the model
clfs = []
cms = []
train_scores = []
test_scores = []
for train, test in crossvalidation:
X_train, y_train = X[train], y[train]
X_test, y_test = X[test], y[test]
X_train, X_test = normalize_features(X_train, X_test)
svm_clf.fit(X_train, y_train)
train_score = svm_clf.score(X_train, y_train)
train_scores.append(train_score)
test_score = svm_clf.score(X_test, y_test)
test_scores.append(test_score)
y_predict = svm_clf.predict(X_test)
cm = confusion_matrix(y_test, y_predict)
cms.append(cm)
return np.mean(test_scores), np.mean(train_scores), np.asarray(cms)
def train_nolearn_model(X, y):
'''
NeuralNet with nolearn
'''
X = X.astype(np.float32)
y = y.astype(np.int32)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 5)
X_train, X_test = impute_nan(X_train, X_test)
X_train, X_test = normalize_features(X_train, X_test)
lays = [('input', layers.InputLayer),
('hidden', layers.DenseLayer),
('output', layers.DenseLayer),
]
net = NeuralNet(
layers = lays,
input_shape=(None, 23),
hidden_num_units=10,
objective_loss_function=lasagne.objectives.categorical_crossentropy,
output_nonlinearity=lasagne.nonlinearities.sigmoid,
output_num_units=10,
update = nesterov_momentum,
update_learning_rate= 0.001,
update_momentum=0.9,
max_epochs=10,
verbose=1,
)
#net.fit(X_train, y_train)
#predicted = net.predict(X_test)
test_score = net.predict(X_test, y_test)
train_score = net.score(X_train, y_train)
return train_score, test_score
def train_sknn(X, y):
'''
NeuralNet with sknn
'''
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 5)
X_train, X_test = impute_nan(X_train, X_test)
X_train, X_test = normalize_features(X_train, X_test)
nn = Classifier(
layers=[
Layer("Tanh", units=12),
Layer("Softmax")],
learning_rate=0.005,
n_iter=25)
# gs = GridSearchCV(nn, param_grid={
# 'learning_rate': [0.05, 0.01, 0.005, 0.001],
# 'hidden0__units': [4, 8, 12,100],
# 'hidden0__type': ["Rectifier", "Sigmoid", "Tanh"]})
# gs.fit(X_train, y_train)
# print(gs.best_estimator_)
nn.fit(X_train, y_train)
predicted = nn.predict(X_test).flatten()
labels = y_test
return predicted, labels
def test7():
print("\n\nTest 7 - K-Means Clustering & PCA")
print("Expected / Actual:")
print("\nCentroid assignment:")
raw = ut.read_mat_raw('mat/ex7data2.mat')
X = raw['X']
K = 3
mu = np.array([[3, 3], [6, 2], [8, 5]])
idx = km.assign_centroids(X, mu)
print("0 /", idx[0])
print("2 /", idx[1])
print("1 /", idx[2])
print("1 /", idx[-3])
print("1 /", idx[-2])
print("0 /", idx[-1])
print("\nCentroid adjustment:")
mu = km.adjust_centroids(X, idx, K)
print("2.428301 /", mu[0, 0])
print("3.157924 /", mu[0, 1])
print("5.813503 /", mu[1, 0])
print("2.633656 /", mu[1, 1])
print("7.119387 /", mu[2, 0])
print("3.616684 /", mu[2, 1])
print("\nPixel clustering:")
A = mpl.imread('img/bird_small.png')
# mpl.imshow(A, extent=[0, 1, 0, 1])
# mpl.colorbar()
# mpl.show()
imgsz = A.shape
A = A.reshape(imgsz[0] * imgsz[1], imgsz[2])
K = 16
iter = 10
mu, idx = km.clusterize(A, K, iter)
min = km.compute_cost(A, mu, idx)
print("Iteration %d cost - %.10f" % (0, min))
for i in range(1, 1):
mu_tmp, idx_tmp = km.clusterize(A, K, iter)
curr = km.compute_cost(A, mu_tmp, idx_tmp)
print("Iteration %d cost - %.10f" % (i, curr))
if (curr < min):
min = curr
mu = mu_tmp
idx = idx_tmp
print("Minimum cost found - %.10f" % min)
A_new = mu[idx].reshape(imgsz[0], imgsz[1], imgsz[2])
# mpl.imshow(A_new, extent=[0, 1, 0, 1])
# mpl.colorbar()
# mpl.show()
print("\nPrincipal Component Analysis: ")
raw = ut.read_mat_raw('mat/ex7data1.mat')
X = raw['X']
X = ut.normalize_features(X)[0].T
U, S = alg.PCA(X)
print("0.707 /", np.abs(U[0, 0]))
print("0.707 /", np.abs(U[1, 0]))
K = 1
Z = alg.project_data(X, U, K)
print("1.481 / ", np.abs(Z[0, 0]))
X_app = alg.recover_data(Z, U, K)
print("1.047 / ", np.abs(X_app[0, 0]))
print("1.047 / ", np.abs(X_app[1, 0]))
# print(X_app.T)
print("% Variance =", alg.compute_retention(S, K))
def test1():
print("\n\nTest 1 - Linear Regression")
print("Expected / Actual:")
print("\nBatch gradient descent: ")
X, y = ut.read_csv('csv/ex1data1.csv')
X = ut.create_design(X)
theta = np.zeros((X.shape[1], ))
iterations = 1500
alpha = 0.01
print("32.0727 / ", alg.SSD(theta, X, y))
print("52.2425 / ", alg.SSD(np.array([-1, 2]), X, y))
alg.batch_gd(X, y, theta, alpha, iterations, alg.SSD_gradient)
print("-3.630291 / ", theta[0])
print("1.166362 / ", theta[1])
print("34962.991574 / ",
ut.predict(np.array([[6.1101]]), theta)[0] * 10**4)
print("45342.450129 / ", ut.predict(np.array([[7]]), theta)[0] * 10**4)
print("\nWith optimization: ")
theta = np.zeros((X.shape[1]), )
res = opt.minimize(alg.SSD,
theta, (X, y),
jac=alg.SSD_gradient,
method='Newton-CG',
options={"maxiter": 1500})
theta = res.x
print("-3.630291 / ", theta[0])
print("1.166362 / ", theta[1])
print("34962.991574 / ",
ut.predict(np.array([[6.1101]]), theta)[0] * 10**4)
print("45342.450129 / ", ut.predict(np.array([[7]]), theta)[0] * 10**4)
print("\nNormalized batch gradient descent:")
X, y = ut.read_csv('csv/ex1data2.csv')
X, mu, sigma = ut.normalize_features(X)
X = ut.create_design(X)
alpha = 0.1
iterations = 400
theta = np.zeros((X.shape[1], ))
alg.batch_gd(X, y, theta, alpha, iterations, alg.SSD_gradient)
print("2000.680851 / ", mu[0])
print("3.170213 / ", mu[1])
print("794.7024 / ", sigma[0])
print("0.7610 / ", sigma[1])
print("340412.659574 / ", theta[0])
print("110631.048958 / ", theta[1])
print("-6649.472950 / ", theta[2])
print("\nNormal equation:")
X, y, = ut.read_csv('csv/ex1data2.csv')
X = ut.create_design(X)
alg.normal_eqn(X, y)
print("340412.659574 / ", theta[0])
print("110631.048958 / ", theta[1])
print("-6649.472950 / ", theta[2])
print("\nNormalized prediction:")
print("293081.464622 / ",
ut.predict(np.array([[1650, 3]]), theta, mu, sigma)[0])
print("284343.447245 / ",
ut.predict(np.array([[1650, 4]]), theta, mu, sigma)[0])
return
X_test_node2 = path+'motifs/'+day+'_thres_'+thres+'_test_'+contacts+'_out_node2_3_0.0001/mat.npy'
X_test_window = path+'motifs/'+day+'_thres_'+thres+'_test_'+contacts+'_out_btw_nodes_3_0.0001/mat.npy'
X_valid_node1 = path+'motifs/'+day+'_thres_'+thres+'_valid_'+contacts+'_out_node1_3_0.0001/mat.npy'
X_valid_node2 = path+'motifs/'+day+'_thres_'+thres+'_valid_'+contacts+'_out_node2_3_0.0001/mat.npy'
X_valid_window = path+'motifs/'+day+'_thres_'+thres+'_valid_'+contacts+'_out_btw_nodes_3_0.0001/mat.npy'
y_train = get_labels(path+day+'_y_train_thres_'+thres+'.npy')
y_test = get_labels(path+day+'_y_test_thres_'+thres+'.npy')
y_valid = get_labels(path+day+'_y_valid_thres_'+thres+'.npy')
X_train=concat_motifs([X_train_node1, X_train_node2])
X_test=concat_motifs([X_test_node1, X_test_node2])
X_valid=concat_motifs([X_valid_node1, X_valid_node2])
X_train_normalized_pairs, X_valid_normalized_pairs, X_test_normalized_pairs = normalize_features(X_train, X_valid, X_test)
X_train_normalized = X_train_normalized_pairs.reshape(X_train_normalized_pairs.shape[0],X_train_normalized_pairs.shape[2]*X_train_normalized_pairs.shape[3])
X_valid_normalized = X_valid_normalized_pairs.reshape(X_valid_normalized_pairs.shape[0],X_valid_normalized_pairs.shape[2]*X_valid_normalized_pairs.shape[3])
X_test_normalized = X_test_normalized_pairs.reshape(X_test_normalized_pairs.shape[0],X_test_normalized_pairs.shape[2]*X_test_normalized_pairs.shape[3])
X_train_valid = np.concatenate((X_train_normalized, X_valid_normalized), axis=0)
y_train_valid = np.concatenate((y_train, y_valid), axis=0)
# test_fold to 0 for all samples that are part of the validation set, and to -1 for all other samples.
valid_index=[-1 for i in range(X_train_normalized.shape[0])]+[0 for i in range(X_valid_normalized.shape[0])]
param_grid = {'gamma': [1e-3, 1e-4, 0.005, 0.05, 0.5],'C': [1, 10, 100]}
best_param={}
svm = Genome3D_SVM_RBF(best_param)
best_param = svm.train_cross_val(X_train_valid[:,:], [i for i in y_train_valid[:,0]], valid_index, param_grid)
cost = np.sum(np.multiply(y, np.log(sigmoid(X.dot(theta)))) + np.multiply((1 - y), np.log(1 - sigmoid(X.dot(theta))))) / -m + \
l2_lambda / (2 * m) * np.sum(np.power(theta[1:], 2)) / (2 * m) # cost + regularization parameter
gradient = X.T.dot(sigmoid(X.dot(theta)) -
y) / m + l2_lambda / m * np.vstack([0, theta[1:]])
return cost, gradient
if __name__ == "__main__":
# Load data from the file
data = np.matrix(
np.genfromtxt('logistic_regression/data/data.csv', delimiter=','))
X = data[:, 0:2]
y = data[:, 2]
# Initial setup
alpha = 5
X = normalize_features(X) # normalize features
X = np.append(np.ones((X.shape[0], 1)), X, axis=1)
theta = np.zeros((X.shape[1], 1))
l2_lambda = 0.1
costs = np.array([])
iterations = 0
# Calculate the changing theta
while True:
# Re-calculate theta
cost, gradient = calculate_cost_and_gradient(theta, X, y, l2_lambda)
theta = theta - alpha * gradient
print('Cost: %f' % (cost))
print("Theta: [ %f, %f, %f ]" %
(theta[0, 0], theta[1, 0], theta[2, 0]))
#Plot the dependence of cost vs iteration
plt.clf()
from scipy.io import wavfile
audioname = "1brian.wav"
fs, signal = wavfile.read(audioname)
#fs=8000
mt_size = 2.0
mt_step = 0.2
st_win = 0.05
st_step = st_win
#FEATURE EXTRACTION AND NORMALISATION
[mid_term_features,
short_term_features] = mt_feature_extraction(signal, fs, mt_size * fs,
mt_step * fs, round(fs * st_win))
[mid_term_features_norm, _, _] = normalize_features([mid_term_features.T])
mid_term_features_norm = mid_term_features_norm[0].T
num_of_windows = mid_term_features.shape[1]
# VAD
reserved_time = 1
segment_limits = vad(short_term_features,
st_step,
smooth_window=0.5,
weight=0.3)
i_vad = ivad(segment_limits, mt_step, reserved_time, num_of_windows)
mid_term_features_norm = mid_term_features_norm[:, i_vad]
# remove outliers:
distances_all = numpy.sum(distance.squareform(
distance.pdist(mid_term_features_norm.T)),
import matplotlib.pyplot as plt
from sklearn.decomposition import PCA
import numpy as np
from utils import normalize_features
file = "ex7data1.mat"
current_dir = os.path.abspath(".")
data_dir = join(current_dir, 'data')
file_name = join(data_dir, file)
mat_dict = sio.loadmat(file_name)
print("mat_dict.keys() : ", mat_dict.keys())
X = mat_dict["X"]
m = X.shape[0]
# remove mean and feature scaling is recommended by Andrew Ng
X_normalized = normalize_features(X)
# m = x1.size
sigma = (1 / m) * np.dot(X_normalized.T,
X_normalized) # nxn (n is 2 : number of features)
def plot(_X, title):
x1 = _X[:, 0]
x2 = _X[:, 1]
plt.plot(x1, x2, 'o')
plt.title(title)
plt.xlabel('x1')
plt.ylabel('x2')
plt.grid()
plt.show()
def dayday_feature(data, n_class=2, label_most_common_1=19, flag_unlabel=0):
t1 = time.time()
data = data.copy()
x = data['fea_table'].copy()
num_nodes = x.shape[0]
nodes_all = list(x.index)
df = data['edge_file'].copy()
max_weight = max(df['edge_weight'])
df.rename(columns={'edge_weight': 'weight'}, inplace=True)
degree_in_1st = np.zeros(num_nodes)
degree_out_1st = np.zeros(num_nodes)
weight_in_1st = np.zeros(num_nodes)
weight_out_1st = np.zeros(num_nodes)
for source, target, weight in df.values:
source = int(source)
target = int(target)
degree_in_1st[target] += 1
degree_out_1st[source] += 1
weight_in_1st[target] += weight
weight_out_1st[source] += weight
degree_1st_diff = degree_in_1st - degree_out_1st
weight_1st_diff = weight_in_1st - weight_out_1st
features_1 = np.concatenate([
degree_in_1st.reshape(-1, 1),
degree_out_1st.reshape(-1, 1),
weight_in_1st.reshape(-1, 1),
weight_out_1st.reshape(-1, 1),
degree_1st_diff.reshape(-1, 1),
weight_1st_diff.reshape(-1, 1)
],
axis=1)
features_in_1st = pd.DataFrame({
"node_index": np.arange(num_nodes),
"degree_in_1st": degree_in_1st,
"weight_in_1st": weight_in_1st
})
df_degree_in_1st = pd.merge(left=df,
right=features_in_1st,
left_on="src_idx",
right_on="node_index",
how="left")
df_degree_in_1st_info = df_degree_in_1st.groupby(
'dst_idx')['degree_in_1st'].agg({
'degree_in_1st_sum': np.sum,
'degree_in_1st_mean': np.mean,
'degree_in_1st_min': np.min,
'degree_in_1st_max': np.max,
'degree_in_1st_median': np.median
})
df_weight_in_1st_info = df_degree_in_1st.groupby(
'dst_idx')['weight_in_1st'].agg({
'weight_in_1st_sum': np.sum,
'weight_in_1st_mean': np.mean,
'weight_in_1st_min': np.min,
'weight_in_1st_max': np.max,
'weight_in_1st_median': np.median
})
df_degree_in_2nd = pd.DataFrame({
"node_index":
df_degree_in_1st_info.index,
"degree_in_2nd":
df_degree_in_1st_info['degree_in_1st_sum']
})
df_degree_in_2nd = pd.merge(left=df,
right=df_degree_in_2nd,
how="left",
left_on="src_idx",
right_on="node_index")
df_degree_in_2nd_info = df_degree_in_2nd.groupby(
'dst_idx')['degree_in_2nd'].agg({
'degree_in_2nd_sum': np.sum,
'degree_in_2nd_mean': np.mean,
'degree_in_2nd_min': np.min,
'degree_in_2nd_max': np.max,
'degree_in_2nd_median': np.median
})
features_2_index = df_degree_in_1st_info.index
features_2_t = np.hstack([
df_degree_in_1st_info.values, df_weight_in_1st_info.values,
df_degree_in_2nd_info.values
])
features_2 = np.zeros((num_nodes, features_2_t.shape[1]))
for i, index in enumerate(features_2_index):
features_2[index] = features_2_t[i]
train_y = data['train_label'].copy()
df_info_in = pd.merge(left=df,
right=train_y,
how='left',
left_on='src_idx',
right_on='node_index')
if flag_unlabel == 0:
df_info_in.dropna(inplace=True)
else:
df_info_in.fillna(-1, inplace=True)
df_labels_in_count = df_info_in.pivot_table(index=["dst_idx"],
columns='label',
aggfunc='size',
fill_value=0)
df_labels_in_precent = pd.crosstab(index=df_info_in.dst_idx,
columns=df_info_in.label,
normalize='index')
df_labels_in_without_most_common = df_info_in.copy()
df_labels_in_without_most_common = df_labels_in_without_most_common[
df_labels_in_without_most_common.label != label_most_common_1]
df_labels_in_precent_without_most_common = pd.crosstab(
index=df_labels_in_without_most_common.dst_idx,
columns=df_labels_in_without_most_common.label,
normalize='index')
df_labels_weight_count_in = df_info_in.pivot_table(index=['dst_idx'],
columns='label',
values='weight',
aggfunc='sum',
fill_value=0)
df_labels_weight_percent_in = pd.crosstab(index=df_info_in.dst_idx,
columns=df_info_in.label,
values=df_info_in.weight,
aggfunc='sum',
normalize='index')
df_labels_weight_percent_in_without_most_common = pd.crosstab(
index=df_labels_in_without_most_common.dst_idx,
columns=df_labels_in_without_most_common.label,
values=df_labels_in_without_most_common.weight,
aggfunc='sum',
normalize='index')
features_3_index = list(df_labels_in_count.index)
features_3_t = np.hstack(
(df_labels_in_count.values, df_labels_in_precent.values,
df_labels_weight_count_in.values, df_labels_weight_percent_in.values))
features_3 = np.zeros((num_nodes, features_3_t.shape[1]))
for i, index in enumerate(features_3_index):
features_3[index] = features_3_t[i]
labels_in_temp = features_3[:, :n_class]
labels_weight_in_temp = features_3[:, 2 * n_class:3 * n_class]
features_labels_all_in_2nd = np.zeros((num_nodes, n_class))
features_labels_weight_all_in_2nd = np.zeros((num_nodes, n_class))
for source, target, weight in df.values:
source = int(source)
target = int(target)
features_labels_all_in_2nd[source] += labels_in_temp[target]
features_labels_weight_all_in_2nd[source] += labels_weight_in_temp[
target]
features_labels_all_in_2nd_percent = np.delete(features_labels_all_in_2nd,
label_most_common_1,
axis=1)
features_labels_all_in_2nd_percent = normalize_features(
features_labels_all_in_2nd_percent)
features_out_1st = pd.DataFrame({
"node_index": np.arange(num_nodes),
"degree_out_1st": degree_out_1st,
"weight_out_1st": weight_out_1st
})
df_degree_out_1st = pd.merge(left=df,
right=features_out_1st,
left_on="dst_idx",
right_on="node_index",
how="left")
df_degree_out_1st_info = df_degree_out_1st.groupby(
'src_idx')['degree_out_1st'].agg({
'degree_out_1st_sum': np.sum,
'degree_out_1st_mean': np.mean,
'degree_out_1st_min': np.min,
'degree_out_1st_max': np.max,
'degree_out_1st_median': np.median
})
df_weight_out_1st_info = df_degree_out_1st.groupby(
'src_idx')['weight_out_1st'].agg({
'weight_out_1st_sum': np.sum,
'weight_out_1st_mean': np.mean,
'weight_out_1st_min': np.min,
'weight_out_1st_max': np.max,
'weight_out_1st_median': np.median
})
df_degree_out_2nd = pd.DataFrame({
"node_index":
df_degree_out_1st_info.index,
"degree_out_2nd":
df_degree_out_1st_info['degree_out_1st_sum']
})
df_degree_out_2nd = pd.merge(left=df,
right=df_degree_out_2nd,
how="left",
left_on="dst_idx",
right_on="node_index")
df_degree_out_2nd_info = df_degree_out_2nd.groupby(
'src_idx')['degree_out_2nd'].agg({
'degree_out_2nd_sum': np.sum,
'degree_out_2nd_mean': np.mean,
'degree_out_2nd_min': np.min,
'degree_out_2nd_max': np.max,
'degree_out_2nd_median': np.median
})
features_4_index = df_degree_out_1st_info.index
features_4_t = np.hstack([
df_degree_out_1st_info.values, df_weight_out_1st_info.values,
df_degree_out_2nd_info.values
])
features_4 = np.zeros((num_nodes, features_4_t.shape[1]))
for i, index in enumerate(features_4_index):
features_4[index] = features_4_t[i]
df_info_out = pd.merge(left=df,
right=train_y,
how='left',
left_on='dst_idx',
right_on='node_index')
if flag_unlabel == 0:
df_info_out.dropna(inplace=True)
else:
df_info_out.fillna(-1, inplace=True)
df_labels_out_count = df_info_out.pivot_table(index=["src_idx"],
columns='label',
aggfunc='size',
fill_value=0)
df_labels_out_precent = pd.crosstab(index=df_info_out.src_idx,
columns=df_info_out.label,
normalize='index')
df_labels_out_without_most_common = df_info_out.copy()
df_labels_out_without_most_common = df_labels_out_without_most_common[
df_labels_out_without_most_common.label != label_most_common_1]
df_labels_out_precent_without_most_common = pd.crosstab(
index=df_labels_out_without_most_common.src_idx,
columns=df_labels_out_without_most_common.label,
normalize='index')
df_labels_weight_count_out = df_info_out.pivot_table(index=['src_idx'],
columns='label',
values='weight',
aggfunc='sum',
fill_value=0)
df_labels_weight_percent_out = pd.crosstab(index=df_info_out.src_idx,
columns=df_info_out.label,
values=df_info_out.weight,
aggfunc='sum',
normalize='index')
df_labels_weight_percent_out_without_most_common = pd.crosstab(
index=df_labels_out_without_most_common.src_idx,
columns=df_labels_out_without_most_common.label,
values=df_labels_out_without_most_common.weight,
aggfunc='sum',
normalize='index')
features_5_index = list(df_labels_out_count.index)
features_5_t = np.hstack(
(df_labels_out_count.values, df_labels_out_precent.values,
df_labels_weight_count_out.values,
df_labels_weight_percent_out.values))
features_5 = np.zeros((num_nodes, features_5_t.shape[1]))
for i, index in enumerate(features_5_index):
features_5[index] = features_5_t[i]
features_merge = np.concatenate([
features_1, features_2, features_3, features_4, features_5,
features_labels_all_in_2nd, features_labels_all_in_2nd_percent
],
axis=1)
features_merge = np.unique(features_merge, axis=1)
features_merge = np.delete(
features_merge,
np.argwhere(np.sum(features_merge, axis=0) == 0),
axis=1)
return features_merge
print("Params: lr={:.4f}, epochs={}, weight_decay={:.5f}, patience={}, hidden_size={}, num_layers={}, package={}, dataset={}"\
.format(args.lr, args.epochs, args.weight_decay, args.patience, args.hidden_size, args.num_layers, args.package, args.dataset))
if args.dataset == "cora":
data = load_data("data/cora/cora.pkl")
adj = data['adj']
features = data['features']
y_train = data['y_train']
y_val = data['y_val']
y_test = data['y_test']
train_mask = data['train_index']
val_mask = data['val_index']
test_mask = data['test_index']
adj = normalize_adj(adj)
features = normalize_features(features)
if args.package == "numpy":
features = features.toarray()
adj = adj.toarray()
elif args.package == "ctf":
y_train = ctf.astensor(y_train)
y_val = ctf.astensor(y_val)
y_test = ctf.astensor(y_test)
features = features.toarray()
adj = adj.toarray()
adj = ctf.astensor(adj)
features = ctf.astensor(features)
adj = ctf.tensor(sp=True, copy=adj)