y = cancer.target
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=42)
model = lgb.LGBMClassifier()
param_dists = {
"n_estimators": [400, 700, 1000],
"colsample_bytree": [0.7, 0.8],
"max_depth": [15, 20, 25],
"num_leaves": [50, 100, 200],
"reg_alpha": [1.1, 1.2, 1.3],
"reg_lambda": [1.1, 1.2, 1.3],
"min_split_gain": [0.3, 0.4],
"subsample": [0.7, 0.8, 0.9],
"subsample_freq": [20]
}
gs = TuneSearchCV(model, param_dists, n_trials=5, scoring="accuracy")
gs.fit(X_train, y_train)
print(gs.cv_results_)
pred = gs.predict(X_test)
correct = 0
for i in range(len(y_test)):
if pred[i] == y_test[i]:
correct += 1
print("Accuracy:", correct / len(pred))
from tune_sklearn import TuneSearchCV
from sklearn.linear_model import SGDClassifier
from sklearn import datasets
from sklearn.model_selection import train_test_split
from ray.tune.schedulers import MedianStoppingRule
import numpy as np
digits = datasets.load_digits()
x = digits.data
y = digits.target
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=.2)
clf = SGDClassifier()
parameter_grid = {"alpha": (1e-4, 1), "epsilon": (0.01, 0.1)}
scheduler = MedianStoppingRule(grace_period=10.0)
tune_search = TuneSearchCV(clf,
parameter_grid,
search_optimization="bayesian",
n_iter=3,
early_stopping=scheduler,
max_iters=10)
tune_search.fit(x_train, y_train)
pred = tune_search.predict(x_test)
accuracy = np.count_nonzero(np.array(pred) == np.array(y_test)) / len(pred)
print(accuracy)
verbose=1)
tune_search.fit(X_train, y_train, sample_weight=sample_weights)
# bayesian search
tune_search = TuneSearchCV(rf,
param_random,
search_optimization='bayesian',
max_iters=100,
scoring='accuracy',
n_jobs=12,
cv=cv,
verbose=1)
tune_search.fit(X_train, y_train, sample_weight=sample_weights)
# scores
clf_predictions = tune_search.predict(X_test)
tune_search.best_params_
print(tune_search.cv_results_)
tune_search.cv_results_['mean_test_score'].mean()
tune_search.best_score_
# model scores
clf_f1_score = sklearn.metrics.f1_score(y_test, clf_predictions)
clf_accuracy_score = sklearn.metrics.accuracy_score(y_test, clf_predictions)
print(f'f1_score: {clf_f1_score}')
# print(f'optimal_max_depth: {max_depth}')
# print(f'optimal_n_features: {n_features}')
# print(f'optimal_max_leaf_nodes {max_leaf_nodes}')
# print(f'optimal_n_estimators {n_estimators}')
# save_id = f'{max_depth}{n_features}{max_leaf_nodes}{n_estimators}{str(clf_f1_score)[2:6]}'
