给出python实现BP神经网络的代码，不使用sklearn库，完成对二分类任务

好的，请参考下面的代码实现：

import numpy as np

class BPNeuralNetwork:
    def __init__(self, input_nodes, hidden_nodes, output_nodes, learning_rate):
        self.input_nodes = input_nodes
        self.hidden_nodes = hidden_nodes
        self.output_nodes = output_nodes
        self.learning_rate = learning_rate
        self.weights_input_hidden = np.random.normal(0.0, pow(self.input_nodes, -0.5), (self.input_nodes, self.hidden_nodes))
        self.weights_hidden_output = np.random.normal(0.0, pow(self.hidden_nodes, -0.5), (self.hidden_nodes, self.output_nodes))
    
    def sigmoid(self, x):
        return 1 / (1 + np.exp(-x))
    
    def train(self, inputs_list, targets_list):
        inputs = np.array(inputs_list, ndmin=2).T
        targets = np.array(targets_list, ndmin=2).T
        
        hidden_inputs = np.dot(self.weights_input_hidden.T, inputs)
        hidden_outputs = self.sigmoid(hidden_inputs)
        
        final_inputs = np.dot(self.weights_hidden_output.T, hidden_outputs)
        final_outputs = self.sigmoid(final_inputs)
        
        output_errors = targets - final_outputs
        hidden_errors = np.dot(self.weights_hidden_output, output_errors)
        
        self.weights_hidden_output += self.learning_rate * np.dot((output_errors * final_outputs * (1 - final_outputs)), hidden_outputs.T)
        self.weights_input_hidden += self.learning_rate * np.dot((hidden_errors * hidden_outputs * (1 - hidden_outputs)), inputs.T)
    
    def query(self, inputs_list):
        inputs = np.array(inputs_list, ndmin=2).T
        
        hidden_inputs = np.dot(self.weights_input_hidden.T, inputs)
        hidden_outputs = self.sigmoid(hidden_inputs)
        
        final_inputs = np.dot(self.weights_hidden_output.T, hidden_outputs)
        final_outputs = self.sigmoid(final_inputs)
        
        return final_outputs

其中，input_nodes、hidden_nodes、output_nodes分别代表输入层、隐层、输出层的节点数；learning_rate为学习率。train方法用于对神经网络进行训练，inputs_list和targets_list分别为训练数据和目标数据。query方法用于对新数据进行预测。