当前位置：首页 > wzjs >正文

ai写作网站宁波网络推广方法

wzjs 2025/8/13 7:51:13

ai写作网站,宁波网络推广方法,建筑资料管理规程,微信公众号平台官网客服逻辑回归模型构建及训练流程关于逻辑回归的数据，有很多学习⽤的⽰例样本。这⾥我们使⽤scikit learn提供的数据集⽣成函数来创建具体参数可参照官网 Scikit-learn 是⽤ Python 开发的开源机器学习库，⼴泛⽤于数据挖掘和数据分析。特点：易…

逻辑回归模型构建及训练流程

关于逻辑回归的数据，有很多学习⽤的⽰例样本。这⾥我们使⽤scikit learn提供的数据集⽣成函数来创建
具体参数可参照官网

Scikit-learn 是⽤ Python 开发的开源机器学习库，⼴泛⽤于数据挖掘和数据分析。

特点：易⽤、⾼效，具有丰富的⼯具，涵盖分类、回归、聚类等多种机器学习算法。
功能：提供数据预处理、模型选择、评估等功能，便于构建完整的机器学习⼯作流。
优势：有详细⽂档和⽰例，社区活跃，能降低开发成本、提⾼效率。

#生成分类数据
from sklearn.datasets  import make_classification  #生成的是numpy.ndarray数组(随机生成)
from sklearn.model_selection import train_test_split #划分数据集 
import numpy as np

demo_X,demo_y = make_classification() #默认生成100个样本，20个特征，2个类别
print(demo_X) #特征
print(demo_y) #标签
print(demo_X.shape)
print(demo_y.shape)

[[ 0.96837399  0.69991556 -0.80719258 ...  1.07349589  0.600931011.25834368][ 1.54064333 -0.72874526  0.05101656 ...  1.69469224  0.68078434-0.22108232][ 1.3130273   0.13845124 -0.17878829 ... -2.51988675  0.73565307-0.61197128]...[-0.96507974  0.62850721  0.25545924 ... -1.03533221 -0.02341121.86283345][-1.09606837 -0.92451774 -0.59875319 ... -0.19421878  0.62418285-0.26886614][-0.18375534  0.12046227  0.52649374 ...  0.93921941  0.896507111.14815417]]
[0 0 1 1 1 0 1 1 0 1 1 1 1 1 0 0 0 1 1 1 1 1 0 0 1 1 1 1 1 0 0 0 1 0 0 1 00 0 1 0 1 0 1 1 0 0 1 0 1 1 0 0 0 1 0 0 1 1 0 1 0 1 0 0 1 0 1 1 1 0 0 0 00 0 0 1 1 1 1 0 0 1 1 0 1 0 0 1 1 1 0 0 1 0 0 1 1 0]
(100, 20)
(100,)

查看生成结果发现，这是一个元组，里面包含两组值，默认生成100个样本，20个特征，2个类别

demo_X[1]

array([ 1.54064333, -0.72874526,  0.05101656,  2.66218782,  1.94089634,-0.10555552,  0.12877297, -0.47275342, -0.23722334, -0.24897953,0.29021104, -1.03756101, -0.6875083 , -1.57963226,  1.81221622,-0.04901801, -0.91022508,  1.69469224,  0.68078434, -0.22108232])

demo_y[1]

步骤

数据准备，参数初始化
模型计算函数
计算损失函数
计算梯度
模型训练

模型训练的数据，通常还需要拆分为训练集和测试集。⽬的是为了防⽌数据泄露

**数据泄露（Data Leakage）**指的是训练数据中包含了不应该有的信息，这些信息会使模型在评估时表现得⽐在真实应⽤场景中更好，导致对模型性能的⾼估，使得模型的泛化能⼒被错误判断。

#1.数据准备，参数初始化
#生成150个样本，10个特征，2个类别的训练数据
X,y = make_classification(n_samples=150,n_features=10) #shape(150,10)#数据拆分
#局部样本训练模型（过拟合模型）测试预测不好（泛化能力差）
#全局样本训练模型（泛化能力好）测试预测好（泛化能力好）
#新样本数据模型表现不好（泛化能力差）
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.3) #30%作为测试集
#X_train, X_test表示一部分用作训练，一部分用作测试，避免过拟合

print(X_train.shape) 
print(X_test.shape)

(105, 10)
(45, 10)

#权重参数
theta = np.random.randn(1,10) #10个特征 1个权重 #shape(1,10) #随机生成一个权重参数
#偏置参数
bias = 0 
#超参数
lr = 0.01 #学习率
epochs = 3000 #迭代次数,训练次数

#假设 X 是shape(3,3)
#[[x1,x2,x3],
# [x4x5,x6],
# [x7,x8,x9]]
#X.T 是shape(3,3)
#[[x1,x4,x7],
# [x2,x5,x8],
# [x3,x6,x9]]
# 
#假设theta 模型参数shape(1,3)
#[[w1,w2,w3]]
#theta * X.T = shape(1,3) * shape(3,3) = shape(1,3)
#y1 = w1*x1 + w2*x2 + w3*x3
#y2 = w1*x4 + w2*x5 + w3*x6
#y3 = w1*x7 + w2*x8 + w3*x9
#y = [[y1,y2,y3]]
##2. 模型计算函数
def forward(X,theta,bias):#线性运算z = np.dot(theta,X.T) + bias #shape(105,10)#sigmod 是为了将线性运算的结果映射到0-1之间y_hat = 1/(1+np.exp(-z)) #shape(105,10)return y_hat        #3. 计算损失函数
def loss(y,y_hat):#损失函数e = 1e-8 #防止除0错误return - y*np.log(y_hat +e ) - (1-y)*np.log(1-y_hat + e)#4. 计算梯度
def calc_gradient(x,y,y_hat):m = x.shape[-1] #样本数delta_theta = np.dot(y_hat-y,x)/m #shape(1,10) #梯度delta_bias = np.mean(y_hat-y) #shape(1,) #偏置的梯度return delta_theta,delta_bias#5. 模型训练
for i in range(epochs): #epochs是训练次数#前向传播y_hat = forward(X_train,theta,bias)#计算损失loss_value = loss(y_train,y_hat)#计算梯度delta_theta,delta_bias = calc_gradient(X_train,y_train,y_hat)#更新参数theta = theta - lr * delta_thetabias = bias - lr * delta_biasif i % 100 == 0:print(f"epoch:{i},loss:{np.mean(loss_value)}")#计算准确率acc = np.mean(np.round(y_hat) == y_train) #[Fales,True,True,False,True] --> [0,1,1,0,1] --> 0.6 print(f"epoch:{i},loss:{np.mean(loss_value)},acc:{acc}")

epoch:0,loss:0.9826484121456485
epoch:0,loss:0.9826484121456485,acc:0.6
epoch:100,loss:0.28410629245685803
epoch:100,loss:0.28410629245685803,acc:0.8857142857142857
epoch:200,loss:0.24510667568678654
epoch:200,loss:0.24510667568678654,acc:0.8666666666666667
epoch:300,loss:0.23505007869724906
epoch:300,loss:0.23505007869724906,acc:0.8571428571428571
epoch:400,loss:0.23103972248220034
epoch:400,loss:0.23103972248220034,acc:0.8666666666666667
epoch:500,loss:0.22908011250548505
epoch:500,loss:0.22908011250548505,acc:0.8761904761904762
epoch:600,loss:0.2280154352157034
epoch:600,loss:0.2280154352157034,acc:0.8761904761904762
epoch:700,loss:0.22739935077291418
epoch:700,loss:0.22739935077291418,acc:0.8761904761904762
epoch:800,loss:0.2270275272465418
epoch:800,loss:0.2270275272465418,acc:0.8761904761904762
epoch:900,loss:0.22679615751708468
epoch:900,loss:0.22679615751708468,acc:0.8761904761904762
epoch:1000,loss:0.2266487526019183
epoch:1000,loss:0.2266487526019183,acc:0.8761904761904762
epoch:1100,loss:0.22655303465776838
epoch:1100,loss:0.22655303465776838,acc:0.8761904761904762
epoch:1200,loss:0.22648987077080793
epoch:1200,loss:0.22648987077080793,acc:0.8761904761904762
epoch:1300,loss:0.22644759054763966
epoch:1300,loss:0.22644759054763966,acc:0.8761904761904762
epoch:1400,loss:0.2264189111347839
epoch:1400,loss:0.2264189111347839,acc:0.8666666666666667
epoch:1500,loss:0.22639920302759006
epoch:1500,loss:0.22639920302759006,acc:0.8666666666666667
epoch:1600,loss:0.22638547862134517
epoch:1600,loss:0.22638547862134517,acc:0.8666666666666667
epoch:1700,loss:0.22637578566413857
epoch:1700,loss:0.22637578566413857,acc:0.8666666666666667
epoch:1800,loss:0.22636883499686028
epoch:1800,loss:0.22636883499686028,acc:0.8666666666666667
epoch:1900,loss:0.2263637676238141
epoch:1900,loss:0.2263637676238141,acc:0.8666666666666667
epoch:2000,loss:0.2263600065967938
epoch:2000,loss:0.2263600065967938,acc:0.8666666666666667
epoch:2100,loss:0.22635716155827576
epoch:2100,loss:0.22635716155827576,acc:0.8666666666666667
epoch:2200,loss:0.2263549665310887
epoch:2200,loss:0.2263549665310887,acc:0.8666666666666667
epoch:2300,loss:0.2263532389959844
epoch:2300,loss:0.2263532389959844,acc:0.8666666666666667
epoch:2400,loss:0.2263518527619451
epoch:2400,loss:0.2263518527619451,acc:0.8666666666666667
epoch:2500,loss:0.22635071986180172
epoch:2500,loss:0.22635071986180172,acc:0.8666666666666667
epoch:2600,loss:0.22634977840264098
epoch:2600,loss:0.22634977840264098,acc:0.8666666666666667
epoch:2700,loss:0.22634898437242262
epoch:2700,loss:0.22634898437242262,acc:0.8666666666666667
epoch:2800,loss:0.2263483060903649
epoch:2800,loss:0.2263483060903649,acc:0.8666666666666667
epoch:2900,loss:0.2263477204327887
epoch:2900,loss:0.2263477204327887,acc:0.8666666666666667

#模型推理
idx = np.random.randint(len(X_test)) #随机生成一个索引作为测试样本
x = X_test[idx] #shape(10,)
y = y_test[idx] #shape(1,)
#模型预测
predict = np.round(forward(x,theta,bias)) 
print(f"y:{y},predict:{predict}")