def dndt_predict(train_X, test_X, train_Y, num_class, num_cut, num_leaf,
n_bag):
#
#
d = train_X.shape[1]
sess = tf.InteractiveSession()
x_ph = tf.placeholder(tf.float32, [None, d])
y_ph = tf.placeholder(tf.float32, [None, num_class])
cut_points_list = [tf.Variable(tf.random_uniform([i])) for i in num_cut]
leaf_score = tf.Variable(tf.random_uniform([num_leaf, num_class]))
y_pred = nn_decision_tree(x_ph,
cut_points_list,
leaf_score,
temperature=0.1)
loss = tf.reduce_mean(
tf.losses.softmax_cross_entropy(logits=y_pred, onehot_labels=y_ph))
opt = tf.train.AdamOptimizer(0.1)
train_step = opt.minimize(loss)
sess.run(tf.global_variables_initializer())
x_example = []
y_label = []
y_ens = []
label_list = []
indx = np.array(range(len(train_X)))
for k in range(n_bag):
examples = random1(indx)
for i in examples:
x = train_X[i]
x_example.append(x)
x_data = np.array(x_example)
y = train_Y[i]
y_label.append(y)
y_data = np.array(y_label)
#
#
for i in range(1000):
_, loss_e = sess.run([train_step, loss],
feed_dict={
x_ph: train_X,
y_ph: train_Y
})
#
#
sample_label = np.argmax(y_pred.eval(feed_dict={x_ph: test_X}), axis=1)
#
#
label_list.append(sample_label)
x_example.clear()
y_label.clear()
avg = np.array(label_list)
avg = avg.reshape(n_bag, len(test_X))
avg = np.transpose(avg)
for i in range(len(test_X)):
x = ensemble(avg[i, ])
y_ens.append(x)
return y_ens
def test_nn_decision_tree(self):
sess = tf.InteractiveSession()
x = np.array([[1, 2], [2, 3], [1, 3], [2, 2]]).astype(np.float32)
cut_points_list = [
np.array([1.5]).astype(np.float32),
np.array([2.5]).astype(np.float32)
]
leaf_score = np.array([[4, 1], [3, 2], [2, 3], [1,
4]]).astype(np.float32)
res = nn_decision_tree(tf.constant(x),
[tf.constant(i) for i in cut_points_list],
tf.constant(leaf_score)).eval()
exp = np.array([[4, 1], [1, 4], [3, 2], [2, 3]])
np.testing.assert_almost_equal(res, exp, decimal=1)
sess.close()
def random_forest(train_data, test_data, max_features, batch_size, epochs,
*args, **kwargs):
#No. of trees defined by diving the total no. of features by the max no. of features in each tree
num_trees = int(train_data[0].shape[1] / max_features)
error = []
for i in xrange(num_trees):
features = []
for i in xrange(max_features):
features.append(random.randrange(0, train_data[0].shape[1]))
col_idx = np.array(features)
X_train = train_data[0][:, col_idx]
y_train = train_data[1]
X_test = test_data[0][:, col_idx]
y_test = test_data[1]
num_cut = []
for f in xrange(max_features):
num_cut.append(1)
num_leaf = np.prod(np.array(num_cut) + 1)
num_class = y_train.shape[1]
seed = 1990
x_ph = tf.placeholder(tf.float32, [None, max_features])
y_ph = tf.placeholder(tf.float32, [None, num_class])
cut_points_list = [
tf.Variable(tf.random_uniform([i])) for i in num_cut
]
leaf_score = tf.Variable(tf.random_uniform([num_leaf, num_class]))
y_pred = nn_decision_tree(x_ph,
cut_points_list,
leaf_score,
temperature=10)
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=y_pred,
labels=y_ph))
opt = tf.train.AdamOptimizer(0.1)
train_step = opt.minimize(loss)
sess = tf.InteractiveSession()
tf.set_random_seed(1990)
sess.run(tf.initialize_all_variables())
for epoch in range(epochs):
total_batch = int(X_train.shape[0] / batch_size)
for i in range(total_batch):
batch_mask = np.random.choice(X_train.shape[0], batch_size)
batch_x = X_train[batch_mask].reshape(-1, X_train.shape[1])
batch_y = y_train[batch_mask].reshape(-1, y_train.shape[1])
_, loss_e = sess.run([train_step, loss],
feed_dict={
x_ph: batch_x,
y_ph: batch_y
})
"""For each tree, the predicted values and the original y_values are stacked vertically
in two different numpy arrays after training each tree for 100 epochs"""
pred = np.vstack(
np.array(y_pred.eval(feed_dict={x_ph: X_test}), dtype=np.float32))
orig = np.vstack(np.array(y_test, dtype=np.float32))
sess.close()
return (pred, orig)
num_cut = []
for features in xrange(d):
num_cut.append(1)
num_leaf = np.prod(np.array(num_cut) + 1)
num_class = y.shape[1]
x_ph = tf.placeholder(tf.float32, [None, d])
y_ph = tf.placeholder(tf.float32, [None, num_class])
cut_points_list = [tf.Variable(tf.random_uniform([i])) for i in num_cut]
leaf_score = tf.Variable(tf.random_uniform([num_leaf, num_class]))
y_pred = nn_decision_tree(x_ph, cut_points_list, leaf_score, temperature=10)
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=y_pred, labels=y_ph))
opt = tf.train.AdamOptimizer(0.1)
train_step = opt.minimize(loss)
sess = tf.InteractiveSession()
tf.set_random_seed(1990)
start_time = time.time()
sess.run(tf.initialize_all_variables())
for epoch in range(epochs):