def get_point(ys):
xs = range(len(ys))
ys = ys['Adj. Close']
result = (0, -99999)
for i in xs[CHECK_PERIOD:-CHECK_PERIOD]:
before_line = linear_regression.train(xs[i - CHECK_PERIOD:i],
ys[i - CHECK_PERIOD:i])
after_line = linear_regression.train(xs[i:i + CHECK_PERIOD],
ys[i:i + CHECK_PERIOD])
fracture = after_line[0]**2 / before_line[0]**2
if fracture > result[1]:
result = i, fracture, before_line, after_line
if result[0]:
return result
else:
return None
def train_function(x, y, model, window_state):
if not model:
class Model:
w = np.zeros((x.shape[1] + 1, 1))
sum_error = 0
i = 0
model = Model()
model.w = train(x, y, self.draw)
self.w = model.w
error = evaluate_error(x, y, model.w)
if self.output:
print "Error: ", error
model.sum_error += error
model.i += 1
return model
def train_function(x, y, model, window_state):
if not model:
class Model:
w = np.zeros((x.shape[1] + 1, 1))
sum_error = 0
i = 0
model = Model()
model.w = train(x, y, self.draw)
self.w = model.w
error = evaluate_error(x, y, model.w)
if self.output:
print "Error: ", error
model.sum_error += error
model.i += 1
return model
def main():
x = []
valid = []
test = []
for i in xrange(2, 68, 5):
print "Current training set size: ", i
shutil.rmtree(TRAIN_DIR, ignore_errors=True)
shutil.rmtree(TEST_DIR, ignore_errors=True)
shutil.rmtree(VALIDATION_DIR, ignore_errors=True)
split_data.split_data(i)
theta = linear_regression.train()
x.append(i)
valid.append(linear_regression.validation(theta))
test.append(linear_regression.eval(theta))
plt.plot(x, valid)
plt.plot(x, test)
plt.ylabel('Accuracy')
plt.xlabel('Training Set Size')
plt.show()
import numpy as np
import linear_regression
# Import the dataset
X, Y = np.loadtxt("pizza.txt", skiprows=1, unpack=True)
# Train the system with a learning rate of 0.00001
w, b = linear_regression.train(X, Y, iterations=10000, lr=0.00001)
print("\nw=%.3f, b=%.3f" % (w, b))
# Predict the number of pizzas
print("Prediction: x=%d => y=%.2f" % (20, linear_regression.predict(20, w, b)))
# !/usr/bin/python3
import my_dataset
import neural_network
import linear_regression
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
if False:
data = my_dataset.random_linear()
linear_regression.train(data)
if False:
train_dataset, test_normed_dataframe, test_labels_dataframe = my_dataset.auto_mpg(
)
neural_network.mpg_train(train_dataset, test_normed_dataframe,
test_labels_dataframe)
if False:
(x_train,
y_train), (x_test, y_test), input_shape, num_classes = my_dataset.mnist()
neural_network.mnist_train(x_train, y_train, x_test, y_test, input_shape,
num_classes)
if True:
x_batch = my_dataset.synthetic_batch(4)
neural_network.resnet50_train(x_batch)