def main():
settings_path = get_settings_path_from_arg("decision_tree")
settings = load_settings(settings_path)
init_logger(settings.log.dir, "decision_tree_classifier", logging.DEBUG)
dl = DataLoader()
dl.load_train(settings.data.train_path)
dl.load_test(settings.data.test_path)
ms = ModelSelector()
# Load test and training
dl = DataLoader()
dl.load_train(settings.data.train_path)
dl.load_test(settings.data.test_path)
dl.scale_data()
# Image feature extraction
k = np.size(dl.classes) *10
dl.load_from_images(settings.data.image_path, k, k*3, verbose=False)
# Add Data Selector
ds = DataSelector(
dl.id_train, dl.x_train, dl.y_train,
dl.id_test, dl.x_test
)
ds.add_all()
# Use lasso
ds.auto_remove_lasso(0.17)
# Dimensionality reduction
dr = DataReducer(ds.train_x, ds.test_x)
dr.pca_data_reduction()
ds = DataSelector(
dl.id_train, dr.x_train, dl.y_train,
dl.id_test, dr.x_test
)
ds.add_all()
# Add data selection to model selector
ms.add_selector("all_feature", ds)
clf = DecisionTreeClassifier()
ms.add_classifier("", clf)
ms.get_best_model(k=10, plot=True)
ms.generate_submission(settings.data.submission_dir, dl.classes)
def main():
settings_path = get_settings_path_from_arg("qda_classifier")
settings = load_settings(settings_path)
init_logger(settings.log.dir, "qda_classifier", logging.DEBUG)
ms = ModelSelector()
# Load test and training
dl = DataLoader()
dl.load_train(settings.data.train_path)
dl.load_test(settings.data.test_path)
dl.scale_data()
# Image feature extraction
k = np.size(dl.classes) * 10
dl.load_from_images(settings.data.image_path, k, k * 3, verbose=False)
# Add Data Selector
ds = DataSelector(dl.id_train, dl.x_train, dl.y_train, dl.id_test,
dl.x_test)
ds.add_all()
# Use lasso
ds.auto_remove_lasso(0.17)
# Dimensionality reduction
dr = DataReducer(ds.train_x, ds.test_x)
dr.pca_data_reduction()
ds = DataSelector(dl.id_train, dr.x_train, dl.y_train, dl.id_test,
dr.x_test)
ds.add_all()
# Add Classifier to model selector
clf = QuadraticDiscriminantAnalysis(store_covariance=True)
ms.add_classifier("store_covariance=True", clf)
clf = QuadraticDiscriminantAnalysis(store_covariance=False)
ms.add_classifier("store_covariance=False", clf)
clf = QuadraticDiscriminantAnalysis(priors=None,
reg_param=0.0,
store_covariance=False,
store_covariances=None,
tol=0.0001)
ms.add_classifier("final", clf)
# Get best model
ms.get_best_model(k=10, plot=True)
ms.generate_submission(settings.data.submission_dir, dl.classes)
def main():
settings_path = get_settings_path_from_arg("naive_bayes_classifier")
settings = load_settings(settings_path)
init_logger(settings.log.dir, "naive_bayes_classifier", logging.DEBUG)
ms = ModelSelector()
# Load test and training
dl = DataLoader()
dl.load_train(settings.data.train_path)
dl.load_test(settings.data.test_path)
dl.scale_data()
# Add Data Selector
ds = DataSelector(dl.id_train, dl.x_train, dl.y_train, dl.id_test,
dl.x_test)
ds.add_all()
# Image feature extraction
k = np.size(dl.classes) * 10
dl.load_from_images(settings.data.image_path, k, k * 3, verbose=False)
# Add Data Selector
ds = DataSelector(dl.id_train, dl.x_train, dl.y_train, dl.id_test,
dl.x_test)
ds.add_all()
# Use lasso
ds.auto_remove_lasso(0.17)
# Dimensionality reduction
dr = DataReducer(ds.train_x, ds.test_x)
dr.pca_data_reduction()
ds = DataSelector(dl.id_train, dr.x_train, dl.y_train, dl.id_test,
dr.x_test)
ds.add_all()
# Add data selection to model selector
ms.add_selector("all_feature", ds)
# Add classifier to model selector
clf = BernoulliNB(alpha=3.5, binarize=0.03)
ms.add_classifier("bernoulli", clf)
# Get best model
ms.get_best_model(k=10)
ms.generate_submission(settings.data.submission_dir, dl.classes)
def main():
settings_path = get_settings_path_from_arg("random_forest_classifier")
settings = load_settings(settings_path)
init_logger(settings.log.dir, "random_forest_classifier", logging.DEBUG)
ms = ModelSelector()
# Load test and training
dl = DataLoader()
dl.load_train(settings.data.train_path)
dl.load_test(settings.data.test_path)
dl.scale_data()
# Image feature extraction
k = np.size(dl.classes) * 10
dl.load_from_images(settings.data.image_path, k, k * 3, verbose=False)
# Add Data Selector
ds = DataSelector(dl.id_train, dl.x_train, dl.y_train, dl.id_test,
dl.x_test)
ds.add_all()
# Use lasso
ds.auto_remove_lasso(0.17)
# Dimensionality reduction
dr = DataReducer(ds.train_x, ds.test_x)
dr.pca_data_reduction()
ds = DataSelector(dl.id_train, dr.x_train, dl.y_train, dl.id_test,
dr.x_test)
ds.add_all()
# Add data selection to model selector
ms.add_selector("all_feature", ds)
# Add Classifier to model selector
clf = RandomForestClassifier(n_estimators=13,
random_state=0,
min_samples_leaf=3,
bootstrap=False)
ms.add_classifier(
"n_estimators=13, random_state=0, min_samples_leaf=3, bootsrap=False",
clf)
# Get best model
ms.get_best_model(k=10)
ms.generate_submission(settings.data.submission_dir, dl.classes)
def main():
settings_path = get_settings_path_from_arg("k_neighbors_classifier")
settings = load_settings(settings_path)
init_logger(settings.log.dir, "k_neighbors_classifier", logging.DEBUG)
ms = ModelSelector()
# Load test and training
dl = DataLoader()
dl.load_train(settings.data.train_path)
dl.load_test(settings.data.test_path)
dl.scale_data()
# Image feature extraction
k = np.size(dl.classes) * 10
dl.load_from_images(settings.data.image_path, k, k * 3, verbose=False)
# Add Data Selector
ds = DataSelector(dl.id_train, dl.x_train, dl.y_train, dl.id_test,
dl.x_test)
ds.add_all()
# Use lasso
ds.auto_remove_lasso(0.17)
# Dimensionality reduction
dr = DataReducer(ds.train_x, ds.test_x)
dr.pca_data_reduction()
ds = DataSelector(dl.id_train, dr.x_train, dl.y_train, dl.id_test,
dr.x_test)
ds.add_all()
# Add data selection to model selector
ms.add_selector("all_feature", ds)
for i in range(1, 40):
clf_k = KNeighborsClassifier(i, weights="distance", p=1)
ms.add_classifier("k_{}_distance_p1".format(i), clf_k)
# Get best model
ms.get_best_model(k=10, plot=True)
ms.generate_submission(settings.data.submission_dir, dl.classes)