Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update all models based on Pytorch. Remove the dependent of skorch library #2

Merged
merged 18 commits into from
Nov 2, 2024
Merged

Update all models based on Pytorch. Remove the dependent of skorch library #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
18 commits
Select commit Hold shift + click to select a range
1a073e4
Add EarlyStopper and CustomMLP class
anh9895 Nov 2, 2024
7099c30
Update BaseMlp class
anh9895 Nov 2, 2024
5ed0430
Add BaseStandardMlp class
anh9895 Nov 2, 2024
d431ca3
Update BaseMhaMlp class
anh9895 Nov 2, 2024
dbcb119
Update MlpClassifier class
anh9895 Nov 2, 2024
9631d4e
Update MlpRegressor class
anh9895 Nov 2, 2024
e0102bf
Update MhaMlpClassifier class
anh9895 Nov 2, 2024
d2aad02
Update MhaMlpRegressor class
anh9895 Nov 2, 2024
69a4d90
Update base_mlp module
anh9895 Nov 2, 2024
1612eb0
Remove un-used modules
anh9895 Nov 2, 2024
4eab07f
Update helpers examples
anh9895 Nov 2, 2024
303a185
Refactor model and network
anh9895 Nov 2, 2024
0a14f85
Update helpers module examples
anh9895 Nov 2, 2024
a288c98
Update examples
anh9895 Nov 2, 2024
bb427c9
Update all model classes
anh9895 Nov 2, 2024
c2cb620
Update examples for core sub-package
anh9895 Nov 2, 2024
23e95c2
Update base_mlp module
anh9895 Nov 2, 2024
60e1fdb
Update tests folder
anh9895 Nov 2, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
297 changes: 2 additions & 295 deletions examples/core/exam_base_mlp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,11 +4,7 @@
# Github: https://github.com/thieu1995 %
# --------------------------------------------------%

from sklearn.datasets import load_iris, load_breast_cancer, load_diabetes, make_regression
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score
from metaperceptron import CustomMLP, MlpClassifier, MlpRegressor
from metaperceptron.core.base_mlp import CustomMLP


def check_CustomMLP_class():
Expand All @@ -23,293 +19,4 @@ def check_CustomMLP_class():
print(model)


def check_MlpClassifier_multi_class():
# Load and prepare the dataset
data = load_iris()
X = data.data
y = data.target

# Split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Standardize the features
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

net = MlpClassifier(hidden_layers=(100, ), act_names="ReLU", dropout_rates=None, act_output=None,
epochs=10, batch_size=16, optim="Adam", optim_paras=None,
early_stopping=True, n_patience=10, epsilon=0.001, valid_rate=0.1,
seed=42, verbose=True)
net.fit(X_train, y_train)
res = net.score(X_test, y_test)
print(res)
print(net.model)
print(net.model.get_weights())


def check_MlpClassifier_multi_class_gridsearch():
# Load and prepare the dataset
data = load_iris()
X = data.data
y = data.target

# Split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Standardize the features
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Define parameters for grid search
param_grid = {
'hidden_layers': [(30,), (50,), [20, 10], (50, 20)],
'act_names': ["ReLU", "Tanh", "Sigmoid"],
'dropout_rates': [0.2, 0.3, None],
'epochs': [10, 20],
'batch_size': [16, 24],
'optim': ['Adam', 'SGD'],
"early_stopping": [True],
"valid_rate": [0.1, 0.2],
}

# Hyperparameter tuning with GridSearchCV
searcher = GridSearchCV(estimator=MlpClassifier(), param_grid=param_grid, cv=3, scoring='accuracy', verbose=2)
searcher.fit(X_train, y_train)

# Get best parameters and accuracy
print("Best Parameters:", searcher.best_params_)
print("Best Cross-Validation Accuracy:", searcher.best_score_)

# Evaluate on test set
best_net = searcher.best_estimator_
y_pred = best_net.predict(X_test)
test_accuracy = accuracy_score(y_test, y_pred)
print("Test Accuracy:", test_accuracy)

print(best_net.model)


def check_MlpClassifier_binary_class():
# Load and prepare the dataset
data = load_breast_cancer()
X = data.data
y = data.target

# Split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Standardize the features
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

net = MlpClassifier(hidden_layers=(100, 50), act_names="ReLU", dropout_rates=0.2, act_output=None,
epochs=50, batch_size=8, optim="Adam", optim_paras=None,
early_stopping=True, n_patience=5, epsilon=0.0, valid_rate=0.1,
seed=42, verbose=True)
net.fit(X_train, y_train)
res = net.score(X_test, y_test)
print(res)
print(net.model)


def check_MlpClassifier_binary_class_gridsearch():
# Load and prepare the dataset
data = load_breast_cancer()
X = data.data
y = data.target

# Split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Standardize the features
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Define parameters for grid search
param_grid = {
'hidden_layers': [(60,), (100,)],
'act_names': ["ReLU", "Tanh", "Sigmoid"],
'dropout_rates': [0.2, None],
'epochs': [10, 20],
'batch_size': [16, 24],
'optim': ['Adam', 'SGD'],
"early_stopping": [True],
"valid_rate": [0.1, 0.2],
}

# Hyperparameter tuning with GridSearchCV
searcher = GridSearchCV(estimator=MlpClassifier(), param_grid=param_grid, cv=3, scoring='accuracy', verbose=2)
searcher.fit(X_train, y_train)

# Get best parameters and accuracy
print("Best Parameters:", searcher.best_params_)
print("Best Cross-Validation Accuracy:", searcher.best_score_)

# Evaluate on test set
best_net = searcher.best_estimator_
y_pred = best_net.predict(X_test)
test_accuracy = accuracy_score(y_test, y_pred)
print("Test Accuracy:", test_accuracy)

print(best_net.model)


def check_MlpRegressor_single_output():
# Load and prepare the dataset
data = load_diabetes()
X = data.data
y = data.target

# Split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Standardize the features
X_scaler = StandardScaler()
X_train = X_scaler.fit_transform(X_train)
X_test = X_scaler.transform(X_test)

y_scaler = StandardScaler()
y_train = y_scaler.fit_transform(y_train.reshape(-1, 1))
y_test = y_scaler.transform(y_test.reshape(-1, 1))

net = MlpRegressor(hidden_layers=(30, 15), act_names="ELU", dropout_rates=0.2, act_output=None,
epochs=50, batch_size=8, optim="Adam", optim_paras=None,
early_stopping=True, n_patience=5, epsilon=0.0, valid_rate=0.1,
seed=42, verbose=True)
net.fit(X_train, y_train)
res = net.score(X_test, y_test)
print(res)
print(net.model)


def check_MlpRegressor_single_output_gridsearch():
# Load and prepare the dataset
data = load_diabetes()
X = data.data
y = data.target

# Split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Standardize the features
X_scaler = StandardScaler()
X_train = X_scaler.fit_transform(X_train)
X_test = X_scaler.transform(X_test)

y_scaler = StandardScaler()
y_train = y_scaler.fit_transform(y_train.reshape(-1, 1))
y_test = y_scaler.transform(y_test.reshape(-1, 1))

# Define parameters for grid search
param_grid = {
'hidden_layers': [(60,), (100,)],
'act_names': ["ELU", "Tanh", "Sigmoid"],
'dropout_rates': [0.2, None],
'epochs': [10, 20],
'batch_size': [16, 24],
'optim': ['Adam', 'SGD'],
"early_stopping": [True],
"valid_rate": [0.1, 0.2],
}

# Hyperparameter tuning with GridSearchCV
searcher = GridSearchCV(estimator=MlpRegressor(), param_grid=param_grid, cv=3,
scoring='neg_mean_squared_error', verbose=2)
searcher.fit(X_train, y_train)

# Get best parameters and accuracy
print("Best Parameters:", searcher.best_params_)
print("Best Cross-Validation Accuracy:", searcher.best_score_)

# Evaluate on test set
best_net = searcher.best_estimator_
# y_pred = best_net.predict(X_test)
print(best_net.score(X_test, y_test))
print(best_net.model)


def check_MlpRegressor_multi_output():
# Load and prepare the dataset
# 1. Generate synthetic multi-output regression dataset
# Setting n_targets=2 for multi-output (2 target variables)
X, y = make_regression(n_samples=1000, n_features=10, n_targets=2, noise=0.1, random_state=42)

# Split into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Standardize the features
X_scaler = StandardScaler()
X_train = X_scaler.fit_transform(X_train)
X_test = X_scaler.transform(X_test)

y_scaler = StandardScaler()
y_train = y_scaler.fit_transform(y_train)
y_test = y_scaler.transform(y_test)

net = MlpRegressor(hidden_layers=(30, 15), act_names="ELU", dropout_rates=0.2, act_output=None,
epochs=50, batch_size=8, optim="Adam", optim_paras=None,
early_stopping=True, n_patience=5, epsilon=0.0, valid_rate=0.1,
seed=42, verbose=True)
net.fit(X_train, y_train)
res = net.score(X_test, y_test)
print(res)
print(net.model)


def check_MlpRegressor_multi_output_gridsearch():
# Load and prepare the dataset
X, y = make_regression(n_samples=1000, n_features=10, n_targets=2, noise=0.1, random_state=42)

# Split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Standardize the features
X_scaler = StandardScaler()
X_train = X_scaler.fit_transform(X_train)
X_test = X_scaler.transform(X_test)

y_scaler = StandardScaler()
y_train = y_scaler.fit_transform(y_train)
y_test = y_scaler.transform(y_test)

# Define parameters for grid search
param_grid = {
'hidden_layers': [(60,), (100,)],
'act_names': ["ELU", "Tanh", "Sigmoid"],
'dropout_rates': [0.2, None],
'epochs': [10, 20],
'batch_size': [16, 24],
'optim': ['Adam', 'SGD'],
"early_stopping": [True],
"valid_rate": [0.1, 0.2],
}

# Hyperparameter tuning with GridSearchCV
searcher = GridSearchCV(estimator=MlpRegressor(), param_grid=param_grid, cv=3,
scoring='neg_mean_squared_error', verbose=2)
searcher.fit(X_train, y_train)

# Get best parameters and accuracy
print("Best Parameters:", searcher.best_params_)
print("Best Cross-Validation Accuracy:", searcher.best_score_)

# Evaluate on test set
best_net = searcher.best_estimator_
# y_pred = best_net.predict(X_test)
print(best_net.score(X_test, y_test))
print(best_net.model)


# check_CustomMLP_class()
check_MlpClassifier_multi_class()
# check_MlpClassifier_multi_class_gridsearch()
# check_MlpClassifier_binary_class()
# check_MlpClassifier_binary_class_gridsearch()
# check_MlpRegressor_single_output()
# check_MlpRegressor_single_output_gridsearch()
# check_MlpRegressor_multi_output()
# check_MlpRegressor_multi_output_gridsearch()
check_CustomMLP_class()
Loading
Loading