1.数据预处理
将自己准备好的数据进行预处理,对数据的分布进行标准化,然后为了方便矩阵计算,为偏置项添加一列1
def prepare_for_training(data, polynomial_degree=0, sinusoid_degree=0, normalize_data=True):
# 计算样本总数
num_examples = data.shape[0]
data_processed = np.copy(data)
# 预处理
features_mean = 0
features_deviation = 0
data_normalized = data_processed
if normalize_data:
(
data_normalized,
features_mean,
features_deviation
) = normalize(data_processed)
data_processed = data_normalized
# 特征变换sinusoidal
if sinusoid_degree > 0:
sinusoids = generate_sinusoids(data_normalized, sinusoid_degree)
data_processed = np.concatenate((data_processed, sinusoids), axis=1)
# 特征变换polynomial
if polynomial_degree > 0:
polynomials = generate_polynomials(data_normalized, polynomial_degree, normalize_data)
data_processed = np.concatenate((data_processed, polynomials), axis=1)
# 加一列1
data_processed = np.hstack((np.ones((num_examples, 1)), data_processed))
return data_processed, features_mean, features_deviation
标准化方法,减去均值,在除标准差
def normalize(features):
features_normalized = np.copy(features).astype(float)
# 计算均值
features_mean = np.mean(features, 0)
# 计算标准差
features_deviation = np.std(features, 0)
# 标准化操作
if features.shape[0] > 1:
features_normalized -= features_mean
# 防止除以0
features_deviation[features_deviation == 0] = 1
features_normalized /= features_deviation
return features_normalized, features_mean, features_deviation
然后在LnearRegression类中调用数据预处理方法,得到处理后的数据
class LinearRegression:
"""
1,对数据进行预处理操作
2,先得到特征个数
3,初始化参数矩阵
"""
def __init__(self,data,labels,polynomial_degree=0,sinusoid_degree=0, normalize_data=True):
(data_processed,
features_mean,
features_deviation)=prepare_for_training(data,polynomial_degree=0,sinusoid_degree=0, normalize_data=True) #数据预处理
self.data = data_processed
self.labels = labels
self.features_mean = features_mean
self.features_deviation = features_deviation
self.polynomial_degree = polynomial_degree
self.sinusoid_degree = sinusoid_degree
self.normalize_data = normalize_data
num_features = self.data.shape[1]
self.theta = np.zeros((num_features,1))#初始化参数
2.线性回归实现
2.1 参数更新
得到样本量,预测值与真实值的差delta,就可以将线性回归的公式用代码写出来,完成参数的更新。预测值使用当前的theta求出
def gradient_step(self,alpha):
'''
梯度下降参数更新的计算方法,是矩阵的计算
'''
num_examples = self.data.shape[0]
prediction = LinearRegression.hypothesis(self.data,self.theta)
delta = prediction - self.labels
theta = self.theta
theta = theta - alpha*(1/num_examples)*(np.dot(delta.T,self.data)).T
self.theta = theta
@staticmethod
def hypothesis(data,theta):
'''
求出预测值
'''
predictions = np.dot(data,theta)
return predictions
2.2 梯度下降
根据预设的迭代次数和步长,对上一步参数更新进行迭代,用cost_history来记录每一次迭代的损失值
def gradient_descent(self,alpha,num_iterations):
'''
梯度下降的迭代,共迭代num_iterations次
'''
cost_history = []
for _ in range(num_iterations):
self.gradient_step(alpha)
cost_history.append(self.cost_function(self.data,self.labels))
return cost_history
损失函数
def cost_function(self,data,labels):
'''
损失值
'''
num_examples = self.data.shape[0]
delta = LinearRegression.hypothesis(self.data,self.theta) - labels
cost = (1/2)*np.dot(delta.T,delta)/num_examples
return cost[0][0]
到这里训练部分基本上就完成了
2.3 预测模块
同样要对需要预测的数据进行预处理,再用训练好的参数进行预测,使用get_cost方法得到预测结果的损失值
def get_cost(self,data,labels):
data_processed = prepare_for_training(data,self.polynomial_degree,self.sinusoid_degree, self.normalize_data)[0]
return self.cost_function(data_processed,labels)
def predict(self,data):
'''
利用训练好的参数进行预测
:return:
'''
data_processed = prepare_for_training(data, self.polynomial_degree, self.sinusoid_degree, self.normalize_data)[0]
predictions = LinearRegression.hypothesis(data_processed,self.theta)
return predictions
方法已经写好了,下面开始调用
3. 开始训练
3.1 读取数据
将数据读取进来,并且设置好训练集和测试集。特征为GDP,要预测幸福指数。画一个散点图将数据显示出来。
data = pd.read_csv('./data/world-happiness-report-2017.csv')
train_data = data.sample(frac=0.8)
test_data = data.drop(train_data.index)
input_param_name = 'Economy..GDP.per.Capita.'
output_param_name = 'Happiness.Score'
x_train = train_data[[input_param_name]].values
y_train = train_data[[output_param_name]].values
x_test = test_data[input_param_name].values
y_test = test_data[output_param_name].values
plt.scatter(x_train,y_train,label='train data')
plt.scatter(x_test,y_test,label='test data')
plt.xlabel(input_param_name)
plt.ylabel(output_param_name)
plt.legend()
plt.show()
3.2 设置参数,开始训练
设置迭代次数为500,学习率(步长)为0.01。开始训练,并把开始的损失值和最后训练完成的损失值打印出来。画一个折线图展示梯度下降
num_iterations = 500
learning_rate = 0.01
linear_regression = LinearRegression(x_train,y_train)
(theta,cos_thistory) = linear_regression.train(learning_rate,num_iterations)
print('开始的损失值:',cos_thistory[0])
print('最后的损失值:',cos_thistory[-1])
plt.plot(range(num_iterations),cos_thistory)
plt.xlabel('iter')
plt.ylabel('loss')
plt.show()
3.3 预测并画出回归方程
创建100个线性数据,最小值和最大值为训练集中的最小值和最大值,然后输入到模型中,画出结果
num_predictions=100
x_prediction=np.linspace(x_train.min(),x_train.max(),num_predictions).reshape(num_predictions,1)
y_prediction=linear_regression.predict(x_prediction)
plt.scatter(x_train,y_train,label='train data')
plt.scatter(x_test,y_test,label='test data')
plt.plot(x_prediction,y_prediction)
plt.xlabel(input_param_name)
plt.ylabel(output_param_name)
plt.legend()
plt.show()