鸢尾花数据集分类（PyTorch实现）

Posted 2023-03-02 小龙呀

一、数据集介绍

Data Set Information:
This is perhaps the best known database to be found in the pattern recognition literature. Fisher’s paper is a classic in the field and is referenced frequently to this day. (See Duda & Hart, for example.) The data set contains 3 classes of 50 instances each, where each class refers to a type of iris plant. One class is linearly separable from the other 2; the latter are NOT linearly separable from each other.

Attribute Information:

1. sepal length in cm
2. sepal width in cm
3. petal length in cm
4. petal width in cm
5. class:
   – Iris Setosa
   – Iris Versicolour
   – Iris Virginica

二、使用贝叶斯分类

import torch
import torch.nn as nn
import torch.optim as optim
from sklearn import datasets

# 读取数据
iris = datasets.load_iris()
iris_data = iris.data
iris_target = iris.target

# 划分训练集和测试集
data_size = iris_data.shape[0]
train_data = iris_data[: int(data_size * 0.8)]
train_target = iris_target[: int(data_size * 0.8)]
test_data = iris_data[int(data_size * 0.8):]
test_target = iris_target[int(data_size * 0.8):]


# 定义模型
class BayesianModel(nn.Module):
    def __init__(self, input_size, output_size):
        super(BayesianModel, self).__init__()
        self.fc = nn.Linear(input_size, output_size)

    def forward(self, x):
        x = self.fc(x)
        return x


# 实例化模型
model = BayesianModel(input_size=4, output_size=3)

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.03)

# 训练模型
for epoch in range(10000):
    optimizer.zero_grad()
    outputs = model(torch.tensor(train_data, dtype=torch.float32))
    loss = criterion(outputs, torch.tensor(train_target, dtype=torch.long))
    loss.backward()
    optimizer.step()
    if epoch % 1000 == 0:
        print("Epoch: %d, Loss: %.4f" % (epoch, loss.item()))

# 评估模型
with torch.no_grad():
    outputs = model(torch.tensor(test_data, dtype=torch.float32))
    _, predicted = torch.max(outputs, 1)
    accuracy = (predicted == torch.tensor(test_target, dtype=torch.long)).sum().item() / len(test_target)
    print("Accuracy: %.2f %%" % (accuracy * 100))

三、使用支持向量机分类

import torch
import torch.nn as nn
import torch.optim as optim
from sklearn import datasets
from sklearn.model_selection import train_test_split

# 加载数据集
iris = datasets.load_iris()
X = iris["data"]
y = iris["target"]

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

# 转换为PyTorch tensor
X_train = torch.tensor(X_train, dtype=torch.float32)
y_train = torch.tensor(y_train, dtype=torch.long)
X_test = torch.tensor(X_test, dtype=torch.float32)
y_test = torch.tensor(y_test, dtype=torch.long)


# 定义SVM模型
class SVM(nn.Module):
    def __init__(self, input_dim, num_classes):
        super().__init__()
        self.linear = nn.Linear(input_dim, num_classes)

    def forward(self, x):
        return self.linear(x)


# 创建模型实例
input_dim = X_train.shape[1]
num_classes = 3
model = SVM(input_dim, num_classes)

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01)

# 训练模型
num_epochs = 1000
for epoch in range(num_epochs):
    optimizer.zero_grad()
    outputs = model(X_train)
    loss = criterion(outputs, y_train)
    loss.backward()
    optimizer.step()

    if (epoch + 1) % 100 == 0:
        print(f"Epoch [epoch + 1/num_epochs], Loss: loss.item()")

# 评估模型
with torch.no_grad():
    outputs = model(X_test)
    _, pred = torch.max(outputs, 1)
    correct = (pred == y_test).sum().item()
    accuracy = correct / y_test.shape[0]
    print("Accuracy: %.2f %%" % (accuracy * 100))

四、使用神经网络分类

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from sklearn import datasets
import numpy as np

# 加载鸢尾花数据集
iris = datasets.load_iris()
X = iris["data"].astype(np.float32)
y = iris["target"].astype(np.int64)

# 将数据分为训练集和测试集
train_ratio = 0.8
index = np.random.permutation(X.shape[0])
train_index = index[:int(X.shape[0] * train_ratio)]
test_index = index[int(X.shape[0] * train_ratio):]
X_train, y_train = X[train_index], y[train_index]
X_test, y_test = X[test_index], y[test_index]

# 定义神经网络模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(4, 32)
        self.fc2 = nn.Linear(32, 32)
        self.fc3 = nn.Linear(32, 3)

    def forward(self, x):
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

# 初始化模型、损失函数和优化器
model = Net()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9)

# 训练模型
num_epochs = 100
for epoch in range(num_epochs):
    inputs = torch.from_numpy(X_train)
    labels = torch.from_numpy(y_train)
    optimizer.zero_grad()
    outputs = model(inputs)
    loss = criterion(outputs, labels)
    loss.backward()
    optimizer.step()

# 评估模型
with torch.no_grad():
    inputs = torch.from_numpy(X_test)
    labels = torch.from_numpy(y_test)
    outputs = model(inputs)
    _, predictions = torch.max(outputs, 1)
    accuracy = (predictions == labels).float().mean()
    print("Accuracy: %.2f %%" % (accuracy.item() * 100))