advanced_example.py

# coding: utf-8
# pylint: disable = invalid-name, C0111
import lightgbm as lgb
import pandas as pd
import numpy as np

# load or create your dataset
print('Load data...')
df_train = pd.read_csv('../binary_classification/binary.train', header=None, sep='\t')
df_test = pd.read_csv('../binary_classification/binary.test', header=None, sep='\t')
W_train = pd.read_csv('../binary_classification/binary.train.weight', header=None)[0]
W_test = pd.read_csv('../binary_classification/binary.test.weight', header=None)[0]

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)

num_train, num_feature = X_train.shape

# create dataset for lightgbm
# if you want to re-use data, remember to set free_raw_data=False
lgb_train = lgb.Dataset(X_train, y_train,
                        weight=W_train, free_raw_data=False)
lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train,
                       weight=W_test, free_raw_data=False)

# specify your configurations as a dict
params = {
    'boosting_type': 'gbdt',
    'objective': 'binary',
    'metric': 'binary_logloss',
    'num_leaves': 31,
    'learning_rate': 0.05,
    'feature_fraction': 0.9,
    'bagging_fraction': 0.8,
    'bagging_freq': 5,
    'verbose': 0
}

# generate a feature name
feature_name = ['feature_' + str(col) for col in range(num_feature)]

print('Start training...')
# feature_name and categorical_feature
gbm = lgb.train(params,
                lgb_train,
                num_boost_round=10,
                valid_sets=lgb_train,  # eval training data
                feature_name=feature_name,
                categorical_feature=[21])

# check feature name
print('Finish first 10 rounds...')
print('7th feature name is:', repr(lgb_train.feature_name[6]))

# save model to file
gbm.save_model('model.txt')

# continue training
# init_model accepts:
# 1. model file name
# 2. Booster()
gbm = lgb.train(params,
                lgb_train,
                num_boost_round=10,
                init_model='model.txt',
                valid_sets=lgb_eval)

print('Finish 10 - 20 rounds with model file...')

# decay learning rates
# learning_rates accepts:
# 1. list/tuple with length = num_boost_round
# 2. function(curr_iter)
gbm = lgb.train(params,
                lgb_train,
                num_boost_round=10,
                init_model=gbm,
                learning_rates=lambda iter: 0.05 * (0.99 ** iter),
                valid_sets=lgb_eval)

print('Finish 20 - 30 rounds with decay learning rates...')

# change other parameters during training
gbm = lgb.train(params,
                lgb_train,
                num_boost_round=10,
                init_model=gbm,
                valid_sets=lgb_eval,
                callbacks=[lgb.reset_parameter(bagging_fraction=[0.7] * 5 + [0.6] * 5)])

print('Finish 30 - 40 rounds with changing bagging_fraction...')


# self-defined objective function
# f(preds: array, train_data: Dataset) -> grad: array, hess: array
# log likelihood loss
def loglikelood(preds, train_data):
    labels = train_data.get_label()
    preds = 1. / (1. + np.exp(-preds))
    grad = preds - labels
    hess = preds * (1. - preds)
    return grad, hess


# self-defined eval metric
# f(preds: array, train_data: Dataset) -> name: string, value: array, is_higher_better: bool
# binary error
def binary_error(preds, train_data):
    labels = train_data.get_label()
    return 'error', np.mean(labels != (preds > 0.5)), False


gbm = lgb.train(params,
                lgb_train,
                num_boost_round=10,
                init_model=gbm,
                fobj=loglikelood,
                feval=binary_error,
                valid_sets=lgb_eval)

print('Finish 40 - 50 rounds with self-defined objective function and eval metric...')

print('Start a new training job...')


# callback
def reset_metrics():
    def callback(env):
        lgb_eval_new = lgb.Dataset(X_test, y_test, reference=lgb_train)
        if env.iteration - env.begin_iteration == 5:
            print('Add a new valid dataset at iteration 5...')
            env.model.add_valid(lgb_eval_new, 'new valid')
    callback.before_iteration = True
    callback.order = 0
    return callback


gbm = lgb.train(params,
                lgb_train,
                num_boost_round=10,
                valid_sets=lgb_train,
                callbacks=[reset_metrics()])

print('Finish first 10 rounds with callback function...')