2020-11-03 生成两个服从高斯分布的数据集并用XGBoost模型进行预测

# -*- coding=utf-8 -*-
import numpy as np
import matplotlib.pyplot as plt
import xgboost as xgb


# train data
def get_train_data(data_size=100):
    data_label = np.zeros((2*data_size, 1))
    # class 1
    x1 = np.reshape(np.random.normal(3, 1, data_size), (data_size, 1))
    y1 = np.reshape(np.random.normal(4, 1, data_size), (data_size, 1))
    data_train = np.concatenate((x1, y1), axis=1)
    data_label[0:data_size, :] = 0
    # class 2
    x2 = np.reshape(np.random.normal(1, 1, data_size), (data_size, 1))
    y2 = np.reshape(np.random.normal(0.5, 1, data_size), (data_size, 1))
    data_train = np.concatenate((data_train, np.concatenate((x2, y2), axis=1)), axis=0)
    data_label[data_size:2*data_size, :] = 1

    return data_train, data_label


# test data
def get_test_data(start, end, data_size=100):
    data1 = (end - start) * np.random.random((data_size, 1)) + start
    data2 &