wehub-resource-sync
81 lines
2.6 KiB
Python
81 lines
2.6 KiB
Python
# coding: utf-8
|
|
from pathlib import Path
|
|
|
|
import numpy as np
|
|
import pandas as pd
|
|
from sklearn.metrics import mean_squared_error
|
|
from sklearn.model_selection import GridSearchCV
|
|
|
|
import lightgbm as lgb
|
|
|
|
print("Loading data...")
|
|
# load or create your dataset
|
|
regression_example_dir = Path(__file__).absolute().parents[1] / "regression"
|
|
df_train = pd.read_csv(str(regression_example_dir / "regression.train"), header=None, sep="\t")
|
|
df_test = pd.read_csv(str(regression_example_dir / "regression.test"), header=None, sep="\t")
|
|
|
|
y_train = df_train[0]
|
|
y_test = df_test[0]
|
|
X_train = df_train.drop(0, axis=1)
|
|
X_test = df_test.drop(0, axis=1)
|
|
|
|
print("Starting training...")
|
|
# train
|
|
gbm = lgb.LGBMRegressor(num_leaves=31, learning_rate=0.05, n_estimators=20)
|
|
gbm.fit(X_train, y_train, eval_X=(X_test,), eval_y=(y_test,), eval_metric="l1", callbacks=[lgb.early_stopping(5)])
|
|
|
|
print("Starting predicting...")
|
|
# predict
|
|
y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration_)
|
|
# eval
|
|
rmse_test = mean_squared_error(y_test, y_pred) ** 0.5
|
|
print(f"The RMSE of prediction is: {rmse_test}")
|
|
|
|
# feature importances
|
|
print(f"Feature importances: {list(gbm.feature_importances_)}")
|
|
|
|
|
|
# self-defined eval metric
|
|
# f(y_true: array, y_pred: array) -> metric_name: str, metric_value: float, maximize: bool
|
|
# Root Mean Squared Logarithmic Error (RMSLE)
|
|
def rmsle(y_true, y_pred):
|
|
return "RMSLE", np.sqrt(np.mean(np.power(np.log1p(y_pred) - np.log1p(y_true), 2))), False
|
|
|
|
|
|
print("Starting training with custom eval function...")
|
|
# train
|
|
gbm.fit(X_train, y_train, eval_X=(X_test,), eval_y=(y_test,), eval_metric=rmsle, callbacks=[lgb.early_stopping(5)])
|
|
|
|
|
|
# another self-defined eval metric
|
|
# f(y_true: array, y_pred: array) -> metric_name: str, metric_value: float, maximize: bool
|
|
# Relative Absolute Error (RAE)
|
|
def rae(y_true, y_pred):
|
|
return "RAE", np.sum(np.abs(y_pred - y_true)) / np.sum(np.abs(np.mean(y_true) - y_true)), False
|
|
|
|
|
|
print("Starting training with multiple custom eval functions...")
|
|
# train
|
|
gbm.fit(
|
|
X_train, y_train, eval_X=(X_test,), eval_y=(y_test,), eval_metric=[rmsle, rae], callbacks=[lgb.early_stopping(5)]
|
|
)
|
|
|
|
print("Starting predicting...")
|
|
# predict
|
|
y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration_)
|
|
# eval
|
|
rmsle_test = rmsle(y_test, y_pred)[1]
|
|
rae_test = rae(y_test, y_pred)[1]
|
|
print(f"The RMSLE of prediction is: {rmsle_test}")
|
|
print(f"The RAE of prediction is: {rae_test}")
|
|
|
|
# other scikit-learn modules
|
|
estimator = lgb.LGBMRegressor(num_leaves=31)
|
|
|
|
param_grid = {"learning_rate": [0.01, 0.1, 1], "n_estimators": [20, 40]}
|
|
|
|
gbm = GridSearchCV(estimator, param_grid, cv=3)
|
|
gbm.fit(X_train, y_train)
|
|
|
|
print(f"Best parameters found by grid search are: {gbm.best_params_}")
|