MLP(SGD or Adam) Perceptron Neural Network Working by Pytorch(including data preprocessing)

通过MLP多层感知机神经网络训练模型,使之能够根据sonar的六十个特征成功预测物体是金属还是石头。由于是简单的linearr线性仿射层,所以网络模型的匹配度并不高。

这是我的第一篇随笔,就拿这个来练练手吧(O(∩_∩)O)。

相关文件可到github下载。本案例采用python编写。(Juypter notebook)

首先导入所需的工具包

 1 import numpy as np   
 2 import pandas as pd
 3 import matplotlib.pyplot as plt
 4 import seaborn as sns
 5 import torch 
 6 %matplotlib inline
 7 
 8 plt.rcParams['figure.figsize'] = (4, 4)
 9 plt.rcParams['figure.dpi'] = 150
10 plt.rcParams['lines.linewidth'] = 3
11 sns.set()
12 #初始化定义

相关工具包可到官网查看其功能。接下来进入数据的预处理部分。

传统的csv文件一般带有特征标志,例如下面的’tips.csv‘。

1 data = sns.load_dataset("tips")
2 data.head(5)

结果如下:

MLP(SGD or Adam) Perceptron Neural Network Working by Pytorch(including data preprocessing)

 

而现在要训练的数据是不带有total_bill,tip,sex这些特征标志的 。

所以要在read_csv的时候加入header=None用于默认创建一个索引。

origin_data = pd.read_csv('sonar.csv',header=None ) 
origin_data.head(5)

 

此时数据集建立完毕,结果如下:

 

  0.0200 0.0371 0.0428 0.0207 0.0954 0.0986 0.1539 0.1601 0.3109 0.2111 ... 0.0027 0.0065 0.0159 0.0072 0.0167 0.0180 0.0084 0.0090 0.0032 R
0 0.0453 0.0523 0.0843 0.0689 0.1183 0.2583 0.2156 0.3481 0.3337 0.2872 ... 0.0084 0.0089 0.0048 0.0094 0.0191 0.0140 0.0049 0.0052 0.0044 R
1 0.0262 0.0582 0.1099 0.1083 0.0974 0.2280 0.2431 0.3771 0.5598 0.6194 ... 0.0232 0.0166 0.0095 0.0180 0.0244 0.0316 0.0164 0.0095 0.0078 R
2 0.0100 0.0171 0.0623 0.0205 0.0205 0.0368 0.1098 0.1276 0.0598 0.1264 ... 0.0121 0.0036 0.0150 0.0085 0.0073 0.0050 0.0044 0.0040 0.0117 R
3 0.0762 0.0666 0.0481 0.0394 0.0590 0.0649 0.1209 0.2467 0.3564 0.4459 ... 0.0031 0.0054 0.0105 0.0110 0.0015 0.0072 0.0048 0.0107 0.0094 R
4 0.0286 0.0453 0.0277 0.0174 0.0384 0.0990 0.1201 0.1833 0.2105 0.3039 ... 0.0045 0.0014 0.0038 0.0013 0.0089 0.0057 0.0027 0.0051 0.0062 R

5 rows × 61 columns

 

该数据集有61列,其中最后一列应作为所要预测的数据。而观察最后一列可以看到数据为字符类型,而这在训练模

型时是不允许的,故将第六十一列提取并将字符R改为1,M改为0,即用1代表R,用0代表M,达到训练模型的要求。

代码如下:

y_data = origin_data.iloc[:,60]
y_data.head(5)#分出需要预测的数据并检验
y_data.shape

调用y_data.shape查看共有多少个数据,以调用循环修改R、M。该数据集共有208个数据。代码如下:

Y=y_data.copy()#由于DataFrame复制会报警,故采用copy
   for i in range(208):
        
        if(y_data[i]=='R'):
            Y[i]=1
        else:
            Y[i]=0
        #将数据R转化为1,数据M转化为0

而后提取数据前六十列作为x数据集用于预测Y。在提取后,将x数据进行标准化处理(之前就是因为没有标准化而导致训练的模型loss曲线上下跌宕)。代码如下:

1 from sklearn.preprocessing import scale
2 x_data=origin_data.iloc[:,:-1]
3 x_data = scale(x_data)

而后将数据x_data,y_data分为训练集和测试集,分割比例为4:1(size=0.2)。将train,test集打包成dataset。这里为了减少GPU的负载,采用Mini-Batch分割数据,调用了dataloader自动将数据集分割成10个batch。

 1 x_data=x_data
 2 y_data=Y
 3 x_data = np.array(x_data).reshape(208,60)
 4 y_data = np.array(y_data).reshape(208,)
 5 y_data = y_data.tolist()#重新转化为list形式方便split
 6 x_data = x_data.tolist()
 7 #split为train和test集合
 8 from sklearn.model_selection import train_test_split
 9 from sklearn.preprocessing import OneHotEncoder
10 #X_train,X_test,y_train,y_test = train_test_split(x_data,y_data,test_size=0.2)
11 X_train, X_test, y_train, y_test = train_test_split(x_data, y_data, test_size=0.2)
12 from torch.utils.data import TensorDataset, DataLoader
13 train_dataset = TensorDataset(torch.Tensor(X_train), 
14                               torch.LongTensor(y_train))
15 
16 test_dataset = TensorDataset(torch.Tensor(X_test), 
17                               torch.LongTensor(y_test))#封装打包
18 TRAIN_SIZE = np.array(X_train).shape[0]
19 BATCH_SIZE = 10
20 NUM_EPOCH = 200
21 iters_per_epoch = TRAIN_SIZE // BATCH_SIZE
22 #采用mini——batch进行迭代,将训练数据分为10份,共迭代200次,共200*int(166/10)=3200次
23 train_loader = DataLoader(train_dataset, batch_size=BATCH_SIZE, shuffle=True)
24 test_loader = DataLoader(test_dataset, batch_size=BATCH_SIZE, shuffle=True)
25 #打包成loader形式自动分割样本

MLP模型定义类代码如下:(应用了nn.sequential序列构建模型,采用了三层hidden_layer,且中间采用ReLu Function激活函数,最后采用输出在[0,1]之间的Softmax激活函数,模型较简单)。

 1 from torch import nn#nn.sequiential()
 2 class MLP(nn.Module):
 3     
 4     def __init__(self, in_dim, hid_dim1, hid_dim2,hid_dim3, out_dim):
 5         super(MLP, self).__init__()
 6         self.layers = nn.Sequential(
 7                         nn.Linear(in_dim, hid_dim1),
 8                         nn.ReLU(),
 9                         nn.Linear(hid_dim1, hid_dim2),
10                         nn.ReLU(),
11                         nn.Linear(hid_dim2,hid_dim3),
12                         nn.ReLU(),
13                         nn.Linear(hid_dim3, out_dim),
14                         nn.Softmax(dim=1))
15         
16     def forward(self, x):
17         y = self.layers(x)
18         return y

创建一个以SGD为优化器的迭代网络模型,代码如下:

1 net = MLP(in_dim=60, hid_dim1=300, hid_dim2=180,hid_dim3=60, out_dim=10)
2 criterion = nn.CrossEntropyLoss()#采用交叉熵进行loss反馈
3 from torch import optim
4 optimizer = optim.SGD(params=net.parameters(), lr=0.1)#学习率0.1,SGD随机梯度下降优化器
5 optimizer.zero_grad()# 每次优化前都要清空梯度,这里先清空防止意外发生
 1 #SGD迭代
 2 train_loss_history = []
 3 test_acc_history = []
 4 
 5 for epoch in range(NUM_EPOCH):
 6     
 7     for i, data in enumerate(train_loader):
 8         
 9         inputs, labels = data
10         
11         optimizer.zero_grad()
12         outputs = net(inputs)
13                 
14         loss = criterion(outputs, labels)
15         loss.backward()
16         
17         optimizer.step()
18         
19         train_loss = loss.tolist()
20         train_loss_history.append(train_loss)
21         
22         if (i+1) % iters_per_epoch == 0:
23             print("[{}, {}] Loss: {}".format(epoch+1, i+1, train_loss))
24     
25     total = 0
26     correct = 0
27     for data in test_loader:
28         inputs, labels = data
29         outputs = net(inputs)
30         _, preds = torch.max(outputs.data, 1)
31         
32         total += labels.size(0)
33         correct += (preds == labels).sum()
34 
35     print("Accuracy: {:.2f}%".format(100.0 * correct / total))

 

用loss_history列表record了所有的loss数据,此时调用matlab.pyplot包画出loss曲线图

1 import matplotlib.pyplot as plt
2 plt.plot(train_loss_history)

输出如下:

[<matplotlib.lines.Line2D at 0x25be01fcdf0>]
            MLP(SGD or Adam) Perceptron Neural Network Working by Pytorch(including data preprocessing)   若采用Adam优化器,则代码与结果如下:
 1 from torch import optim
 2 net = MLP(in_dim=60, hid_dim1=540, hid_dim2=180,hid_dim3=30, out_dim=10)#调整了隐藏层参数
 3 optimizer = optim.Adam(params=net.parameters(), lr=0.001)#更换为Adam优化器
 4 criterion = nn.CrossEntropyLoss()
 5 
 6 train_loader = DataLoader(train_dataset, batch_size=BATCH_SIZE, shuffle=True)
 7 test_loader = DataLoader(test_dataset, batch_size=BATCH_SIZE, shuffle=True)
 8 train_loss_history = []
 9 test_acc_history = []
10 #Adam优化器迭代
11 for epoch in range(NUM_EPOCH):
12     
13     for i, data in enumerate(train_loader):
14         
15         inputs, labels = data
16         
17         optimizer.zero_grad()
18         outputs = net(inputs)
19                 
20         loss = criterion(outputs, labels)
21         loss.backward()
22         
23         optimizer.step()
24         
25         train_loss = loss.tolist()
26         train_loss_history.append(train_loss)
27         
28         if (i+1) % iters_per_epoch == 0:
29             print("[{}, {}] Loss: {}".format(epoch+1, i+1, train_loss))
30     
31     total = 0
32     correct = 0
33     for data in test_loader:
34         inputs, labels = data
35         outputs = net(inputs)
36         _, preds = torch.max(outputs.data, 1)
37         
38         total += labels.size(0)
39         correct += (preds == labels).sum()
40 
41     print("Accuracy: {:.2f}%".format(100.0 * correct / total))
1 import matplotlib.pyplot as plt
2 plt.plot(train_loss_history)
[<matplotlib.lines.Line2D at 0x25be08b49d0>]
               MLP(SGD or Adam) Perceptron Neural Network Working by Pytorch(including data preprocessing)   模型训练完毕后,可通过将所有数据导入模型训练得出Confusion Matrix以查看性能指标,根据自己的实际需求调整模型以达到更优化的性能。 这里仅贴上画Adam模型的Matrix的代码。中间过程请仿照上述代码自行拟定。
1 #画confusion_matrix
2 from sklearn.metrics import confusion_matrix
3 cm = confusion_matrix(y_data, total_down)
4 sns.heatmap(cm, annot=True, fmt = "d", cmap = "Blues", annot_kws={"size": 20}, cbar = False)
5 plt.ylabel('True')
6 plt.xlabel('Predicted')
7 sns.set(font_scale = 2)

Matrix如下:

MLP(SGD or Adam) Perceptron Neural Network Working by Pytorch(including data preprocessing)

 

 

 通过简单计算得到Precision,Sensitivity,Accuracy,Specificity性能指标

 1 TP=77
 2 FN=34
 3 FP=45
 4 TN=52
 5 Accuracy= (TP+TN)/(TP+TN+FP+FN)
 6 Precison = TP/(TP+FP)
 7 Sensitivity = TP/(TP+FN)
 8 Specificity = TN/(TN+FP)
 9 print("Accuracy is:{}  Precision is:{}  Sensitivity is:{}  Specificity is:{}".format(Accuracy,Precison,Sensitivity,Specificity))
10 #计算评估指标

输出如下:

Accuracy is:0.6201923076923077  Precision is:0.6311475409836066  Sensitivity is:0.6936936936936937  Specificity is:0.5360824742268041

本模型采用IPython编写,如用Pycharm等请自行删除一些代码。

 
上一篇:Git 常用操作


下一篇:python基础操作之路径的处理