'score_function': None,
'leaf_estimation_backtracking': None,
'ctr_history_unit': None,
'monotone_constraints': None
}
catboost = GBM(package='catboost',
X=X[y < 200000],
y=y[y < 200000],
feature_names=data['features'],
cv=5,
grid_search=False,
eval_metric='rmse',
parameters=parameters)
catboost.run_model()
print(catboost.__dict__)
np.save('catboost_res.npy', catboost.__dict__)
catboost.parity_plot(data='train', quantity='CT_RT',
scheme=1).savefig('parity_CT_RT_train.png')
catboost.parity_plot(data='test', quantity='CT_RT',
scheme=1).savefig('parity_CT_RT_test.png')
plt.clf()
explainer = shap.TreeExplainer(catboost.model[-1])
shap_values = explainer.shap_values(data['X'])
XX = scale.inverse_transform(data['X'])
X = pd.DataFrame(XX, columns=data['features'])
# summarize the effects of all the features
shap.summary_plot(shap_values, X, plot_type="bar", show=False)
plt.savefig('feature_importance.png', dpi=150, bbox_inches='tight')
C = np.array([25 for i in ID])
xgboost = GBM(package='xgboost',
X=data['X'],
y=data['y'],
feature_names=data['features'],
cv=5,
grid_search=False,
eval_metric='rmse',
parameters=parameters,
CT_Temp=CT_Temp,
CT_RT=CT_RT,
C=C)
xgboost.run_model()
print(xgboost.__dict__)
xgboost.parity_plot(data='train', quantity='LMP').savefig('parity_LMP_train.png')
xgboost.parity_plot(data='test', quantity='LMP').savefig('parity_LMP_test.png')
xgboost.parity_plot(data='train', quantity='CT_RT').savefig('parity_CT_RT_train.png')
xgboost.parity_plot(data='test', quantity='CT_RT').savefig('parity_CT_RT_test.png')
np.save('xgb_dict.npy', xgboost.__dict__)
plt.clf()
explainer = shap.TreeExplainer(xgboost.model[-1])
shap_values = explainer.shap_values(data['X'])
XX = scale.inverse_transform(data['X'])
X = pd.DataFrame(XX, columns=data['features'])
# summarize the effects of all the features
shap.summary_plot(shap_values, X, plot_type="bar", show=False)
plt.savefig('feature_importance.png', dpi=150, bbox_inches='tight')
'random_state': 42,
'n_jobs': -1,
'silent': True,
'importance_type': 'split',
'num_boost_round': 500,
'tree_learner': 'feature'
}
lgb = GBM(package='lightgbm',
X=data['X'],
y=data['y'],
feature_names=data['features'],
cv=5,
grid_search=False,
eval_metric='rmse',
parameters=parameters)
lgb.run_model()
print(lgb.__dict__)
'''
print(data['features'])
plot_importance(lgb.model)
plt.show()
plt.clf()
plot_metric(lgb.model, metric='rmse')
plt.show()
plt.clf()
plot_tree(lgb.model)
plt.show()
'''
ID = [i[0] for i in data['y2']]
C = np.array([C_data[i] for i in ID])
xgb = GBM(package='xgboost',
X=data['X'],
y=data['y'],
model_scheme='LMP',
cv=5,
grid_search=False,
eval_metric='rmse',
parameters=parameters,
CT_Temp=CT_Temp,
CT_RT=CT_RT,
C=C)
xgb.run_model()
print(xgb.__dict__)
xgb.parity_plot(data='train', quantity='LMP').savefig('parity_LMP_train.png')
xgb.parity_plot(data='test', quantity='LMP').savefig('parity_LMP_test.png')
xgb.parity_plot(data='train',
quantity='CT_RT').savefig('parity_CT_RT_train.png')
xgb.parity_plot(data='test', quantity='CT_RT').savefig('parity_CT_RT_test.png')
np.save('xgb_dict.npy', xgb.__dict__)
plt.clf()
explainer = shap.TreeExplainer(xgb.model[-1])
shap_values = explainer.shap_values(data['X'])
XX = scale.inverse_transform(data['X'])
X = pd.DataFrame(XX, columns=data['features'])
# summarize the effects of all the features
shap.summary_plot(shap_values, X, plot_type="bar", show=False)