result_file_path = ''.join([str(item) for item in config['result_file_path']])
result_file_path = result_file_path%seed
print model_file_path
print result_file_path
# quit()
if config['refresh_all_model']:
bow_rf.fit(train_data=(train_X_feature, train_data['LABEL_INDEX']),
validation_data=(test_X_feature, test_data['LABEL_INDEX']))
bow_rf.save_model(model_file_path)
else:
bow_rf.model_from_pickle(model_file_path)
bow_rf.print_model_descibe()
print(index_to_label[bow_rf.predict('啥', transform_input=True)])
print(index_to_label[bow_rf.predict('哪台好', transform_input=True)])
bow_rf.accuracy((train_X_feature, train_data['LABEL_INDEX'].as_matrix()), False)
y_pred, is_correct, accu, f1 = bow_rf.accuracy((test_X_feature,test_data['LABEL_INDEX'].as_matrix()),False)
test_data['PREDICT'] = [index_to_label[item] for item in y_pred]
test_data['IS_CORRECT'] = is_correct
data_util.save_data(test_data,result_file_path)
end_time = timeit.default_timer()
print 'end! Running time:%ds!' % (end_time - start_time)
logging.debug('=' * 20)
logging.debug('end! Running time:%ds!' % (end_time - start_time))
dev_X_feature = feature_encoder.fit_transform(x)
test_X_feature = feature_encoder.transform(test_data[u'SENTENCE'].as_matrix())
bow_rf = BowRandomForest(
# rand_seed=rand_seed,
verbose=0,
n_estimators=estimators,
min_samples_leaf=1,
feature_encoder=None,
)
bow_rf.fit(train_data=(dev_X_feature, y),
validation_data=(test_X_feature, test_y))
_, _, dev_accuracy, _ = bow_rf.accuracy((dev_X_feature, y), False)
_, _, val_accuracy, _ = bow_rf.accuracy((test_X_feature, test_y), False)
train_accu.append(dev_accuracy)
test_accu.append(val_accuracy)
print('-' * 80)
print('#***#训练准确率：%s'%(train_accu))
print('#***#测试准确率：%s'%(test_accu))
ave_acc.append(test_accu)
counter += 1
print(np.asarray(ave_acc))
print('验证中平均准确率：%f' % np.average(np.asarray(ave_acc),axis=0))
else:
bow_rf.model_from_pickle(model_file_path)
# bow_rf.print_model_descibe()
# print(index_to_label[bow_rf.predict('啥', transform_input=True)])
# print(index_to_label[bow_rf.predict('哪台好', transform_input=True)])
# print(index_to_label[bow_rf.predict('恩恩拜', transform_input=True)])
# print(index_to_label[bow_rf.predict('恩恩拜拜', transform_input=True)])
# y_pred, is_correct, accu, f1 = bow_rf.accuracy((train_X_feature, train_y), False)
# train_data['PREDICT'] = [index_to_label[item] for item in y_pred]
# train_data['IS_CORRECT'] = is_correct
# data_util.save_data(train_data,'train_resul.csv')
# quit()
y_pred, is_correct, accu, f1 = bow_rf.accuracy((test_X_feature,test_y),False)
# test_data['PREDICT'] = [index_to_label[item] for item in y_pred]
# test_data['IS_CORRECT'] = is_correct
# print(result_file_path)
# data_util.save_data(test_data,result_file_path)
# print('='*20)
# quit()
end_time = timeit.default_timer()
print 'end! Running time:%ds!' % (end_time - start_time)
logging.debug('=' * 20)
logging.debug('end! Running time:%ds!' % (end_time - start_time))
