def lgbm_cv(X,
y,
params,
cv,
states=1,
pipe=None,
early_stopping_rounds=20,
verbose=False):
importance = []
n = cv.get_n_splits() * states
scores = [[] for _ in range(cv.get_n_splits())]
iterations = [[] for _ in range(cv.get_n_splits())]
clf = LGBMClassifier(**params, importance_type="gain")
with tqdm(total=n, ncols=50) as pbar:
for i, (train_index, test_index) in enumerate(cv.split(X)):
X_train, y_train = X.iloc[train_index], y.iloc[train_index]
X_test, y_test = X.iloc[test_index], y.iloc[test_index]
if pipe is not None:
X_train = pipe.fit_transform(X_train, y_train, X_test=X_test)
X_test = pipe.transform(X_test)
for state in range(states):
clf.random_state = state
clf.fit(X_train,
y_train,
eval_set=[(X_test, y_test)],
eval_metric="auc",
early_stopping_rounds=early_stopping_rounds,
verbose=verbose)
iterations[i].append(clf.best_iteration_)
scores[i].append(clf.best_score_["valid_0"]["auc"])
importance.append([i, state] +
clf.feature_importances_.tolist())
pbar.update(1)
importance = pd.DataFrame(importance,
columns=["fold", "state"] +
X_train.columns.tolist())
# sort columns from most to least important
importance = importance[importance.mean().sort_values(
ascending=False).index]
importance = importance.set_index(["fold", "state"])
return {
"importance": importance,
"scores": scores,
"iterations": iterations
}
def get_model(PARAMS):
"""Get model according to parameters"""
scale_pos_weight = 577.88 # scale_pos_weight = number of negative samples / number of positive samples
model = LGBMClassifier()
model.num_leaves = PARAMS.get("num_leaves")
model.max_depth = PARAMS.get("max_depth")
model.n_estimators = 10000
model.early_stopping_rounds = 20
model.scale_pos_weight = scale_pos_weight # we set this parameter to solve the class imbalance problem
model.objective = "binary"
model.min_child_weight = PARAMS.get("min_child_weight")
model.subsample = PARAMS.get("subsample")
model.subsample_freq = 1
model.colsample_bytree = PARAMS.get("colsample_bytree")
model.random_state = 42
model.n_jobs = -1
model.max_bin = 63
model.device = "gpu"
model.gpu_use_dp = False
model.gpu_platform_id = 0
model.gpu_device_id = 0
return model
