plot_example.py

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

if lgb.compat.MATPLOTLIB_INSTALLED:
    import matplotlib.pyplot as plt
else:
    raise ImportError('You need to install matplotlib for plot_example.py.')

print('Loading data...')
# load or create your dataset
df_train = pd.read_csv('../regression/regression.train', header=None, sep='\t')
df_test = pd.read_csv('../regression/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)

# create dataset for lightgbm
lgb_train = lgb.Dataset(X_train, y_train)
lgb_test = lgb.Dataset(X_test, y_test, reference=lgb_train)

# specify your configurations as a dict
params = {
    'num_leaves': 5,
    'metric': ('l1', 'l2'),
    'verbose': 0
}

evals_result = {}  # to record eval results for plotting

print('Starting training...')
# train
gbm = lgb.train(params,
                lgb_train,
                num_boost_round=100,
                valid_sets=[lgb_train, lgb_test],
                feature_name=['f' + str(i + 1) for i in range(X_train.shape[-1])],
                categorical_feature=[21],
                evals_result=evals_result,
                verbose_eval=10)

print('Plotting metrics recorded during training...')
ax = lgb.plot_metric(evals_result, metric='l1')
plt.show()

print('Plotting feature importances...')
ax = lgb.plot_importance(gbm, max_num_features=10)
plt.show()

print('Plotting split value histogram...')
ax = lgb.plot_split_value_histogram(gbm, feature='f26', bins='auto')
plt.show()

print('Plotting 54th tree...')  # one tree use categorical feature to split
ax = lgb.plot_tree(gbm, tree_index=53, figsize=(15, 15), show_info=['split_gain'])
plt.show()

print('Plotting 54th tree with graphviz...')
graph = lgb.create_tree_digraph(gbm, tree_index=53, name='Tree54')
graph.render(view=True)