lightgbm - simple race car example

Description of sample data

The sample data is pretty straight forward (intended to be that way). We have 3 main column which are:-

1. Horse power

2. Has Turbo

3. IsRaceCar - this is the label which basically conclusively tells us if this is a race car or not.

For example :-

CarCC,Turbo,IsRaceCar

3000,1,1 (race car)
2500,1,1
1300,0,0
1200,0,0


The sample code for learning and predicting from this dataset  is shown below :-

	# coding: utf-8
	# pylint: disable = invalid-name, C0111
	import json
	import lightgbm as lgb
	import pandas as pd
	from sklearn.metrics import mean_squared_error
	import numpy as np
	# load or create your dataset
	print('Load data...')
	df_train = pd.read_csv('cardata.csv', header=None, sep=',')
	df_test = pd.read_csv('testcardata.csv', header=None, sep=',')
	y_train = df_train[2].values
	print(y_train)
	y_test = df_test[2].values
	X_train = df_train.drop(2, axis=1).values
	X_test = df_test.drop(2, axis=1).values
	# create dataset for lightgbm
	lgb_train = lgb.Dataset(X_train, y_train)
	lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train)
	# specify your configurations as a dict
	params = {
	'task': 'train',
	'boosting_type': 'gbdt',
	'objective': 'binary',
	'metric': {'l2'},
	'num_leaves': 31,
	'learning_rate': 0.05,
	#'feature_fraction': 0.9,
	#'bagging_fraction': 0.8,
	'bagging_freq': 5, 'min_data' : 1,
	'verbose': 0
	}
	print('Start training...')
	# train
	gbm = lgb.train(params,
	lgb_train,
	num_boost_round=20,
	valid_sets=lgb_eval,
	early_stopping_rounds=5)
	print('Save model...')
	# save model to file
	gbm.save_model('model.txt')
	print('Start predicting...')
	y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration)
	# eval
	print(y_pred)

view raw simple_lightgbm.py hosted with ❤ by GitHub