求助！！！机器学习线性回归问题——单特征回归

1、首先将utils工具包直接导入项目

normalize.py

"""Normalize features"""

import numpy as np


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

generate_sinusoids.py

import numpy as np


def generate_sinusoids(dataset, sinusoid_degree):
    """
    sin(x).
    """

    num_examples = dataset.shape[0]
    sinusoids = np.empty((num_examples, 0))

    for degree in range(1, sinusoid_degree + 1):
        sinusoid_features = np.sin(degree * dataset)
        sinusoids = np.concatenate((sinusoids, sinusoid_features), axis=1)
        
    return sinusoids

generate_polynomials.py

"""Add polynomial features to the features set"""

import numpy as np
from .normalize import normalize


def generate_polynomials(dataset, polynomial_degree, normalize_data=False):
    """变换方法：
    x1, x2, x1^2, x2^2, x1*x2, x1*x2^2, etc.
    """

    features_split = np.array_split(dataset, 2, axis=1)
    dataset_1 = features_split[0]
    dataset_2 = features_split[1]

    (num_examples_1, num_features_1) = dataset_1.shape
    (num_examples_2, num_features_2) = dataset_2.shape

    if num_examples_1 != num_examples_2:
        raise ValueError('Can not generate polynomials for two sets with different number of rows')

    if num_features_1 == 0 and num_features_2 == 0:
        raise ValueError('Can not generate polynomials for two sets with no columns')

    if num_features_1 == 0:
        dataset_1 = dataset_2
    elif num_features_2 == 0:
        dataset_2 = dataset_1

    num_features = num_features_1 if num_features_1 < num_features_2 else num_features_2
    dataset_1 = dataset_1[:, :num_features]
    dataset_2 = dataset_2[:, :num_features]

    polynomials = np.empty((num_examples_1, 0))

    for i in range(1, polynomial_degree + 1):
        for j in range(i + 1):
            polynomial_feature = (dataset_1 ** (i - j)) * (dataset_2 ** j)
            polynomials = np.concatenate((polynomials, polynomial_feature), axis=1)

    if normalize_data:
        polynomials = normalize(polynomials)[0]

    return polynomials

然后就是重要的prepare_for_training.py

"""Prepares the dataset for training"""

import numpy as np
from .normalize import normalize
from .generate_sinusoids import generate_sinusoids
from .generate_polynomials import generate_polynomials


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

hypothesis包中的文件：

sigmoid.py

"""Sigmoid function"""

import numpy as np


def sigmoid(matrix):
    """Applies sigmoid function to NumPy matrix"""

    return 1 / (1 + np.exp(-matrix))

sigmoid_gradient.py

"""Sigmoid gradient function"""

from .sigmoid import sigmoid


def sigmoid_gradient(matrix):
    """Computes the gradient of the sigmoid function evaluated at z."""

    return sigmoid(matrix) * (1 - sigmoid(matrix))

然后就是线性回归linear_regression.py

import numpy as np
from utils.features import prepare_for_training

class LinearRegression:
    def __init__(self, data, labels, polynomial_degree = 0, sinusoid_degree = 0, normalize_data = True):
        """
        1.对数据进行预处理操作
        2.先得到所有的特征个数
        3.初始化参数矩阵
        """
        # 数据预处理
        (data_processed,
         feature_mean,
         feature_deviation) = prepare_for_training(data, polynomial_degree = 0, sinusoid_degree = 0, normalize_data = True)

        self.data = data
        self.labels = labels
        self.feature_mean = feature_mean
        self.feature_deviation = feature_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))

    def train(self, alpha, num_iterations = 500):
        """
        训练模块，执行梯度下降
        """
        cost_history = self.gradient_descent(alpha, num_iterations)
        return self.theta, cost_history


    # 梯度下降
    def gradient_descent(self, alpha, num_iterations):
        """
        实际迭代模块，会迭代num_iterations次
        """
        cost_history = []
        for i in range(num_iterations):
            self.gradient_step(alpha)
            cost_history.append(self.cost_function(self.data, self.labels))
        return cost_history

    # 进行参数更新的步骤
    def gradient_step(self, alpha):
        """
        梯度下降参数更新计算方法，注意是矩阵运算
        """
        # [0] 索引操作符用于访问元组的第一个元素，即行数。
        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

    def cost_function(self, data, labels):
        """
        损失计算方法
        """
        # self.data.shape[0]样本的个数
        num_examples = data.shape[0]
        delta = LinearRegression.hypothesis(self.data, self.theta) - labels
        cost = (1/2)*np.dot(delta.T, delta)
        return cost[0][0]


    @staticmethod
    def hypothesis(data, theta):
        """
        直接调用得到预测值
        """
        predictions = np.dot(data, theta)
        return predictions

    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):
        """
        用训练好的参数模型，去预测得到回归值结果
        """
        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

最后是主函数：UnivariteLinearRegression.py

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from linear_regression import LinearRegression

data = pd.read_csv('../data/world-happiness-report-2017.csv')

# 得到训练和测试数据
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.title('Happiness')
plt.legend()
plt.show()

num_iterations = 500
learning_rate = 0.01

linear_regression = LinearRegression(x_train, y_train)
(theta, cost_history) = linear_regression.train(learning_rate, num_iterations)
print('开始时的损失：', cost_history[0])
print('训练后的损失：', cost_history[-1])

plt.plot(range(num_iterations), cost_history)
plt.xlabel('Iter')
plt.ylabel('Cost')
plt.title('GD')
plt.show()

predictions_num = 100
x_predictions = np.linspace(x_train.min(), x_train.max(), predictions_num).reshape(predictions_num, 1)
y_predictions = linear_regression.predict(x_predictions)

plt.scatter(x_train, y_train, label = 'Train data')
plt.scatter(x_test, y_test, label = 'Test data')
plt.plot(x_predictions, y_predictions, 'r', label='Prediction')
plt.xlabel(input_param_name)
plt.ylabel(output_param_name)
plt.title('Happiness')
plt.legend()
plt.show()

最后的结果为什么会出现错误：

"D:\PycharmProjectsCode\Machine Learning\.venv\Scripts\python.exe" "D:\PycharmProjectsCode\Machine Learning\LinearRegression\UnivariteLinearRegression.py" 
开始时的损失： 1802.075384630608
训练后的损失： 131.20906966096783
Traceback (most recent call last):
  File "D:\PycharmProjectsCode\Machine Learning\LinearRegression\UnivariteLinearRegression.py", line 46, in <module>
    y_predictions = linear_regression.predict(x_predictions)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\PycharmProjectsCode\Machine Learning\LinearRegression\linear_regression.py", line 97, in predict
    predictions = LinearRegression.hypothesis(data_processed, self.theta)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\PycharmProjectsCode\Machine Learning\LinearRegression\linear_regression.py", line 75, in hypothesis
    predictions = np.dot(data, theta)
                  ^^^^^^^^^^^^^^^^^^^
ValueError: shapes (100,2) and (1,1) not aligned: 2 (dim 1) != 1 (dim 0)

Process finished with exit code 1

我是跟着唐宇迪老师的视频讲解一步一步写的，唐老师没有出现这个错误，我找了好久也不知道为什么，请各位大佬帮忙解答一下