def get_minimum():
"""Get list of function minimimums
:return: list of function minimimums
:rtype: list
"""
return [convert_variables([-1, -1]), convert_variables([1, 1])]
def get_minimum():
"""Get list of function minimimums
:return: list of function minimimums
:rtype: list
"""
return [
convert_variables([-math.pi, 12.275]),
convert_variables([math.pi, 2.275]),
convert_variables([9.42478, 2.475]),
]
def get_minimum():
"""Get list of function minimimums
:return: list of function minimimums
:rtype: list
"""
return [convert_variables([-0.029896, 0])]
def get_approximate_options(n, m, methods, losses):
#X, y = load_boston(return_X_y=True)
#x = X[:100]
#x_validate = X[420:]
x = [[y] * m for y in range(1, 25)]
x_validate = [[y + 0.5] * m for y in range(0, 25)]
#x = [[y] * m for y in range(1, 101)]
#x_validate = [[y + 0.5] * m for y in range(0, 100)]
#X, y = load_diabetes(return_X_y=True)
#x = X[:50]
#x_validate = X[400:]
options = []
for method in methods:
options.append({
"x": [convert_variables_without_trainable(x_tmp) for x_tmp in x],
"x_validate": [
convert_variables_without_trainable(x_tmp)
for x_tmp in x_validate
],
"params":
convert_variables([1 for x in range(n)]),
"loss_function":
losses,
"opt":
method,
"eps":
0.0001,
"max_steps":
100,
})
return options
def get_minimum():
"""Get list of function minimimums
:return: list of function minimimums
:rtype: list
"""
return [
convert_variables([-pi, 12.275]),
]
def get_minimum():
"""Get list of function minimimums
:return: list of function minimimums
:rtype: list
"""
return [
convert_variables([math.pi, math.pi]),
]
def get_minimum():
"""Get list of function minimimums
:return: list of function minimimums
:rtype: list
"""
return [
convert_variables([0.78547, 0.78547, 0.78547]),
]
def get_minimum():
"""Get list of function minimimums
:return: list of function minimimums
:rtype: list
"""
return [
convert_variables([0, 1.253115]),
]
def get_minimum():
"""Get list of function minimimums
:return: list of function minimimums
:rtype: list
"""
return [
convert_variables([420.9687, 420.9687]),
]
def get_minimum():
"""Get list of function minimimums
:return: list of function minimimums
:rtype: list
"""
return [
convert_variables([-0.547198, -1.5472]),
]
def get_minimum():
"""Get list of function minimimums
:return: list of function minimimums
:rtype: list
"""
return [
convert_variables([512, 404.2319]),
]
def get_minimum():
"""Get list of function minimimums
:return: list of function minimimums
:rtype: list
"""
return [
convert_variables([
3.0814879110195774e-31,
]),
]
"""
Approximate options
"""
approximate_options2 = [
{
"x": [
convert_variables_without_trainable([x, x])
for x in range(-10, 10, 1)
],
"x_validate": [
convert_variables_without_trainable([x, x])
for x in range(-11, 10, 1)
],
"params":
convert_variables([1 for x in range(11)]),
"loss_function":
tf.keras.losses.MAE,
"opt":
tf.keras.optimizers.Adam(learning_rate=0.001),
"eps":
0.0001,
"max_steps":
1000,
},
{
"x": [
convert_variables_without_trainable([x, x])
for x in range(-10, 10, 1)
],
"x_validate": [
from utils.utils import convert_variables, convert_variables_without_trainable
"""
Approximate options
"""
X, y = load_boston(return_X_y=True)
x = X[:100]
x_validate = X[420:]
approximate_options5 = [
{
"x": [convert_variables_without_trainable(x_tmp) for x_tmp in x],
"x_validate":
[convert_variables_without_trainable(x_tmp) for x_tmp in x_validate],
"params":
convert_variables([5 for x in range(82)]),
"loss_function":
tf.keras.losses.MAE,
"opt":
tf.keras.optimizers.SGD(learning_rate=1, momentum=0.1),
"eps":
0.0001,
"max_steps":
30,
},
{
"x": [convert_variables_without_trainable(x_tmp) for x_tmp in x],
"x_validate":
[convert_variables_without_trainable(x_tmp) for x_tmp in x_validate],
"params":
convert_variables([5 for x in range(82)]),
import numpy as np
import tensorflow as tf
from utils.utils import convert_variables, convert_variables_without_trainable
"""
Approximate options
"""
approximate_options1 = [
{
"x": [convert_variables_without_trainable([x, x]) for x in list(np.arange(0, 5, 0.2))],
"x_validate": [convert_variables_without_trainable([x, x]) for x in list(np.arange(0.1, 5, 0.02))],
"params": convert_variables([1 for x in range(11)]),
"loss_function": tf.keras.losses.MAE,
"opt": tf.keras.optimizers.Adam(learning_rate=0.001),
"eps": 0.0001,
"max_steps": 1000,
},
{
"x": [convert_variables_without_trainable([x, x]) for x in list(np.arange(0, 5, 0.2))],
"x_validate": [convert_variables_without_trainable([x, x]) for x in list(np.arange(0.1, 5, 0.02))],
"params": convert_variables([1 for x in range(11)]),
"loss_function": tf.keras.losses.MAE,
"opt": tf.keras.optimizers.Adam(learning_rate=0.01),
"eps": 0.0001,
"max_steps": 10000,
},
{
"x": [convert_variables_without_trainable([x, x]) for x in list(np.arange(0, 5, 0.2))],
"x_validate": [convert_variables_without_trainable([x, x]) for x in list(np.arange(0.1, 5, 0.02))],
import tensorflow as tf
from utils.utils import convert_variables
"""
Minimize options
"""
schmitt_wetters_function_options = [
{
"x": convert_variables([-1, 1, 1]),
"opt": tf.keras.optimizers.SGD(learning_rate=0.0002),
"eps": 0.0001,
"max_steps": 100,
},
{
"x": convert_variables([-1, 1, 1]),
"opt": tf.keras.optimizers.SGD(learning_rate=0.0004),
"eps": 0.0001,
"max_steps": 100,
},
{
"x": convert_variables([-1, 1, 1]),
"opt": tf.keras.optimizers.SGD(learning_rate=0.0006),
"eps": 0.0001,
"max_steps": 100,
},
{
"x": convert_variables([-1, 1, 1]),
"opt": tf.keras.optimizers.SGD(learning_rate=0.0008),
"eps": 0.0001,
"max_steps": 100,
from utils.generate_data import generate_set
from sklearn.datasets import load_boston
X, y = load_boston(return_X_y=True)
x = X[:100]
x_validate = X[420:]
approximate_options9_2 = [
{
"x": [convert_variables_without_trainable(x_tmp) for x_tmp in x],
"x_validate":
[convert_variables_without_trainable(x_tmp) for x_tmp in x_validate],
"params":
convert_variables([5 for x in range(261)]),
"loss_function":
tf.keras.losses.MSE,
"opt":
tf.keras.optimizers.SGD(learning_rate=1),
"eps":
0.0001,
"max_steps":
30,
},
{
"x": [convert_variables_without_trainable(x_tmp) for x_tmp in x],
"x_validate":
[convert_variables_without_trainable(x_tmp) for x_tmp in x_validate],
"params":
convert_variables([5 for x in range(261)]),
import tensorflow as tf
from utils.utils import convert_variables
"""
Minimize options
"""
zettla_function_options = [
{
"x": convert_variables([1, 1]),
"opt": tf.keras.optimizers.SGD(learning_rate=0.05),
"eps": 0.0001,
"max_steps": 100,
},
{
"x": convert_variables([1, 1]),
"opt": tf.keras.optimizers.SGD(learning_rate=0.01),
"eps": 0.0001,
"max_steps": 100,
},
{
"x": convert_variables([1, 1]),
"opt": tf.keras.optimizers.SGD(learning_rate=0.5),
"eps": 0.0001,
"max_steps": 100,
},
{
"x": convert_variables([1, 1]),
"opt": tf.keras.optimizers.SGD(learning_rate=0.1),
"eps": 0.0001,
"max_steps": 100,
import tensorflow as tf
from utils.utils import convert_variables
"""
Minimize options
"""
smooth_function_options3 = [
{
"x": convert_variables([10, 10]),
"opt": tf.keras.optimizers.Adagrad(learning_rate=18.45),
"eps": 0.0001,
"max_steps": 1000,
},
{
"x": convert_variables([10, 10]),
"opt": tf.keras.optimizers.Adagrad(learning_rate=18.47),
"eps": 0.0001,
"max_steps": 1000,
},
{
"x": convert_variables([10, 10]),
"opt": tf.keras.optimizers.Adagrad(learning_rate=18.49),
"eps": 0.0001,
"max_steps": 1000,
},
{
"x": convert_variables([10, 10]),
"opt": tf.keras.optimizers.Adagrad(learning_rate=18.51),
"eps": 0.0001,
"max_steps": 1000,
from utils.utils import convert_variables, convert_variables_without_trainable
from utils.generate_data import generate_set
from sklearn.datasets import load_boston
X, y = load_boston(return_X_y=True)
x = X[:100]
x_validate = X[420:]
approximate_options9_3 = [
{
"x": [convert_variables_without_trainable(x_tmp) for x_tmp in x],
"x_validate": [convert_variables_without_trainable(x_tmp) for x_tmp in x_validate],
"params": convert_variables([5 for x in range(79)]),
"loss_function": tf.keras.losses.MSE,
"opt": tf.keras.optimizers.SGD(learning_rate=1),
"eps": 0.0001,
"max_steps": 30,
},
{
"x": [convert_variables_without_trainable(x_tmp) for x_tmp in x],
"x_validate": [convert_variables_without_trainable(x_tmp) for x_tmp in x_validate],
"params": convert_variables([5 for x in range(79)]),
"loss_function": tf.keras.losses.MSE,
"opt": tf.keras.optimizers.SGD(learning_rate=0.1),
"eps": 0.0001,
"max_steps": 30,
},
{
import tensorflow as tf
from utils.utils import convert_variables
"""
Minimize options
"""
kin_function_options = [
{
"x": convert_variables([0, 1.4]),
"opt": tf.keras.optimizers.Adagrad(learning_rate=10),
"eps": 0.001,
"max_steps": 100,
},
{
"x": convert_variables([0, 1.4]),
"opt": tf.keras.optimizers.Adam(learning_rate=20),
"eps": 0.001,
"max_steps": 100,
},
{
"x": convert_variables([0, 1.4]),
"opt": tf.keras.optimizers.Adamax(learning_rate=2),
"eps": 0.001,
"max_steps": 100,
},
]
