数据分析与机器学习--剃度下降求解逻辑回归_如果运行时间足够长,在逻辑回归中,是否所有剃度下降算法都能得到相同模型-CSDN博客

我的机器学习第一个算法-逻辑回归

读懂本算法，需要你具备矩阵求导及相关基本运算、概率论中的极大似然函数求解、高等数学的求偏导数，以及python的工具包pandas、numpy、matplotlib的基本使用（非常感谢B站唐宇迪老师的讲解，虽然跟的磕磕巴巴哈），上代码：

# # 逻辑回归（二分类）

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
get_ipython().run_line_magic('matplotlib', 'inline')


pdData = pd.read_csv('LogiReg_data.txt', header=None, names=['Exam1',
                                                            'Exam2', 'Admitted'])
pdData.head()

positive = pdData[pdData['Admitted'] == 1]
negative = pdData[pdData['Admitted'] == 0]

fix, ax = plt.subplots(figsize=(10, 5))
ax.scatter(positive['Exam1'], positive['Exam2'], s=30, c='b', 
          marker='o', label='Admitted')
ax.scatter(negative['Exam1'], negative['Exam2'], s=30, c='r', 
          marker='x', label='Not Admitted')
ax.legend()
ax.set_xlabel('Exam 1 Score')
ax.set_ylabel('Exam 2 Score')

def sigmoid(z):
    return 1 / (1 + np.exp(-z))

nums = np.arange(-10, 10, step=1)
fig, ax = plt.subplots(figsize=(12, 4))
ax.plot(nums, sigmoid(nums), 'r')

def model(X, theta):
    return sigmoid(np.dot(X, theta.T))


# 添加‘1’列
pdData.insert(0, 'Ones', 1)
pdData.head()


# 转换pandas数据为有用数组
orig_data = pdData.as_matrix()
cols = orig_data.shape[1]
# 处理X。y值
X = orig_data[:, 0:cols-1]
y = orig_data[:, cols-1:cols]


# 构造三个参数
theta = np.zeros([1, 3])

# 构造似然对数函数
def cost(X, y, theta):
    left = np.multiply(-y, np.log(model(X, theta)))
    right = np.multiply(1 - y, np.log(1 - model(X, theta)))
    return np.sum(left - right) / (len(X))


# In[35]:


# 将梯度上升转换为梯度下降


# In[47]:


print(cost(X, y, theta))


# # 计算梯度

# In[48]:


def gradient(X, y, theta):
    grad = np.zeros(theta.shape)
    error = (model(X, theta) - y).ravel()
    for j in range(len(theta.ravel())):
        term = np.multiply(error, X[:, j])
        grad[0, j] = np.sum(term) / len(X)
        
    return grad


# # Gradient descent

# In[69]:


STOP_ITER = 0
STOP_COST = 1
STOP_GRAD = 2

def stopGriterion(type, value, threshold):
    # 三重不同的停止策略
    if type == STOP_ITER:
        return value > threshold
    elif type == STOP_COST:
        return abs(value[-1]-value[-2]) < threshold
    elif type == STOP_GRAD:
        return np.linalg.norm(value) < threshold


# In[67]:


import numpy.random
# 洗牌
def shuffleData(data):
    np.random.shuffle(data)
    cols = data.shape[1]
    X = data[:, 0:cols-1]
    y = data[:, cols-1:]
    return X, y


# In[71]:


import time

def descent(data, theta, batchSize, stopType, thresh, alpha):
    # 梯度下降求解
    init_time = time.time()
    i = 0 # 迭代次数
    k = 0 # batch
    X, y = shuffleData(data)
    grad = np.zeros(theta.shape) #计算的梯度
    costs = [cost(X, y, theta)] # 损失值
    
    while True:
        grad = gradient(X[k:k+batchSize], y[k:k+batchSize], theta)
        k += batchSize # 取batch数量个数据
        if k >= n:
            k = 0
            X, y = shuffleData(data) # 重新洗牌
        theta = theta - alpha*grad # 参数更新
        costs.append(cost(X, y, theta)) # 计算新的损失
        i += 1
        
        if stopType == STOP_ITER:
            value = i
        elif stopType == STOP_COST:
            value = costs
        elif stopType == STOP_GRAD:
            value = grad
        if stopGriterion(stopType, value, thresh):
            break;
            
    return theta, i-1, costs, grad, time.time() - init_time 
            


# In[59]:


def runExpe(data, theta, batchSize, stopType, thresh, alpha):
    #import pdb; pdb.set_trace();
    theta, iter, costs, grad, dur = descent(data, theta, batchSize, stopType, thresh, alpha)
    name = "Original" if (data[:,1]>2).sum() > 1 else "Scaled"
    name += " data - learning rate: {} - ".format(alpha)
    if batchSize==n: strDescType = "Gradient"
    elif batchSize==1:  strDescType = "Stochastic"
    else: strDescType = "Mini-batch ({})".format(batchSize)
    name += strDescType + " descent - Stop: "
    if stopType == STOP_ITER: strStop = "{} iterations".format(thresh)
    elif stopType == STOP_COST: strStop = "costs change < {}".format(thresh)
    else: strStop = "gradient norm < {}".format(thresh)
    name += strStop
    print ("***{}\nTheta: {} - Iter: {} - Last cost: {:03.2f} - Duration: {:03.2f}s".format(
        name, theta, iter, costs[-1], dur))
    fig, ax = plt.subplots(figsize=(12,4))
    ax.plot(np.arange(len(costs)), costs, 'r')
    ax.set_xlabel('Iterations')
    ax.set_ylabel('Cost')
    ax.set_title(name.upper() + ' - Error vs. Iteration')
    return theta


# # 不同的停止策略 

# 设定迭代次数

# In[73]:


#选择的梯度下降方法是基于所有样本的
n=100
runExpe(orig_data, theta, n, STOP_ITER, thresh=5000, alpha=0.000001)

# 根据损失值停止

# 设定阈值 1E-6, 差不多需要110 000次迭代

# In[77]:


runExpe(orig_data, theta, n, STOP_COST, thresh=0.000001, alpha=0.001)

# ## 根据梯度变化停止

# 设定阈值 0.05,差不多需要40 000次迭代

# In[79]:


runExpe(orig_data, theta, n, STOP_GRAD, thresh=0.05, alpha=0.001)

# # 不同的梯度下降策略

# ## Stochastic descent

# In[81]:


runExpe(orig_data, theta, 1, STOP_ITER, thresh=5000, alpha=0.001)

# 改小学习率，增加迭代次数，解决上诉问题

# In[83]:


runExpe(orig_data, theta, 1, STOP_ITER, thresh=15000, alpha=0.000002)

# ## batch梯度下降策略 

# In[85]:


runExpe(orig_data, theta, 16, STOP_ITER, thresh=15000, alpha=0.001)

数据分析与机器学习--剃度下降求解逻辑回归

我的机器学习第一个算法-逻辑回归

浮动仍然比较大，我们来尝试下对数据进行标准化 将数据按其属性(按列进行)减去其均值，然后除以其方差。最后得到的结果是，对每个属性/每列来说所有数据都聚集在0附近，方差值为1

浮动仍然比较大，我们来尝试下对数据进行标准化将数据按其属性(按列进行)减去其均值，然后除以其方差。最后得到的结果是，对每个属性/每列来说所有数据都聚集在0附近，方差值为1