I was too curious, here are the results with ordinal encoding:

import pandas as pd
import sklearn
from sklearn import preprocessing
from sklearn import metrics
import time
import lightgbm as lgb
from sklearn.compose import ColumnTransformer

from sklearn.experimental import enable_hist_gradient_boosting  # noqa
from sklearn.ensemble import HistGradientBoostingClassifier


d_train = pd.read_csv("https://s3.amazonaws.com/benchm-ml--main/train-0.1m.csv")
d_test = pd.read_csv("https://s3.amazonaws.com/benchm-ml--main/test.csv")
vars_cat = ["Month", "DayofMonth", "DayOfWeek", "UniqueCarrier", "Origin", "Dest"]
vars_num = ["DepTime", "Distance"]
input_all = vars_cat + vars_num

ordinal_encoder = preprocessing.OrdinalEncoder(
    handle_unknown="use_encoded_value",
    unknown_value=-1,
)

preprocessor = ColumnTransformer([
        ("cat", ordinal_encoder, vars_cat),
    ],
    remainder="passthrough",
)
X_train = preprocessor.fit_transform(d_train[vars_cat + vars_num])
y_train = (d_train["dep_delayed_15min"] == "Y").values

X_test = preprocessor.transform(d_test[vars_cat + vars_num])
y_test = (d_test["dep_delayed_15min"] == "Y").values

print(f"n_samples={X_train.shape[0]}")
print(f"n_features={X_train.shape[1]}")

print(f"LightGBM {lgb.__version__}:")
md = lgb.LGBMClassifier(num_leaves=512, learning_rate=0.1, n_estimators=100)
start_time = time.time()
md.fit(X_train, y_train)
print(f"  - training time: {time.time() - start_time:.3f}s")

y_pred = md.predict_proba(X_test)[:, 1]
print(f"  - ROC AUC: {metrics.roc_auc_score(y_test, y_pred):.3f}")

print(f"scikit-learn {sklearn.__version__}:")
md = HistGradientBoostingClassifier(max_leaf_nodes=512, learning_rate=0.1,
                                    max_iter=100)
start_time = time.time()
md.fit(X_train, y_train)
print(f"  - training time: {time.time() - start_time:.3f}s")

y_pred = md.predict_proba(X_test)[:, 1]
print(f"  - ROC AUC: {metrics.roc_auc_score(y_test, y_pred):.3f}")

I set: OMP_NUM_THREADS=4 (this dataset has too few features to really benefit from many threads and both lightgbm and scikit-learn suffer from over-subscription):

n_samples=100000
n_features=8
LightGBM 3.0.0:
  - training time: 1.508s
  - ROC AUC: 0.718
scikit-learn 0.24.dev0:
  - training time: 3.487s
  - ROC AUC: 0.718

So indeed LighGBM 3.0 is a bit more than 2x faster than scikit-learn master but there is some variability on such short runs.

sklearn HistGBT #36

Description

Activity

Metadata

Metadata

Assignees

Labels

Projects

Milestone

Relationships

Development

Issue actions