class LightGBM(BaseAlgo):
default_params = {'exec_path': 'lightgbm', 'num_threads': 4}
def __init__(self, params):
self.params = self.default_params.copy()
for k in params:
self.params[k] = params[k]
def fit(self,
X_train,
y_train,
X_eval=None,
y_eval=None,
seed=42,
feature_names=None,
eval_func=None,
**kwa):
params = self.params.copy()
params['bagging_seed'] = seed
params['feature_fraction_seed'] = seed + 3
self.model = GBMClassifier(**params)
if X_eval is None:
self.model.fit(X_train, y_train)
else:
self.model.fit(X_train, y_train, test_data=[(X_eval, y_eval)])
def predict(self, X):
return self.model.predict(X)
def predict_proba(self, X):
return self.model.predict(X)
def test_multiclass(self):
clf = GBMClassifier(exec_path=path_to_exec,
min_data_in_leaf=1,
learning_rate=0.1,
num_leaves=5,
num_class=n_classes,
metric='multi_logloss',
application='multiclass',
num_iterations=100)
clf.fit(Xmulti, Ymulti.argmax(-1))
clf.fit(Xmulti,
Ymulti.argmax(-1),
test_data=[(Xmulti, Ymulti.argmax(-1))])
score = metrics.accuracy_score(Ymulti.argmax(-1), clf.predict(Xmulti))
assert score > 0.8
num_iterations=1000,
min_data_in_leaf=1,
num_leaves=10,
metric='binary_error',
learning_rate=0.1,
early_stopping_round=10,
verbose=False)
best_rounds = []
scores = []
for i, (train_idx, valid_idx) in enumerate(skf.split(X, Y)):
x_train = X[train_idx, :]
y_train = Y[train_idx]
x_valid = X[valid_idx, :]
y_valid = Y[valid_idx]
clf.fit(x_train, y_train, test_data=[(x_valid, y_valid)])
best_round = clf.best_round
best_rounds.append(best_round)
y_pred = clf.predict(x_valid)
score = metrics.accuracy_score(y_valid, y_pred)
scores.append(score)
print("Fold: [{}/{}]: Accuracy: {:.3f}, best round: {}".format(
i + 1, skf.n_splits, score, best_round))
print("Average: accuracy: {:.3f}, best round: {}".format(
np.mean(scores), int(np.mean(best_rounds))))
# -*- coding: utf-8 -*-
"""
@author: Ardalan MEHRANI <*****@*****.**>
@brief:
"""
import pickle
import numpy as np
from sklearn import datasets, metrics, model_selection
from pylightgbm.models import GBMClassifier
# Parameters
path_to_exec = "~/Documents/apps/LightGBM/lightgbm"
X, Y = datasets.make_classification(n_samples=1000,
n_features=100,
random_state=1337)
# 'exec_path' is the path to lightgbm executable
clf = GBMClassifier(exec_path=path_to_exec, verbose=False)
clf.fit(X, Y)
y_pred = clf.predict(X)
print("Accuracy: ", metrics.accuracy_score(Y, y_pred))
# The sklearn API models are picklable
print("Pickling sklearn API models")
pickle.dump(clf, open("clf_gbm.pkl", "wb"))
clf2 = pickle.load(open("clf_gbm.pkl", "rb"))
print(np.allclose(clf.predict(X), clf2.predict(X)))