python神经网络分析案例

以下是一个使用Python神经网络进行分类分析的案例：

数据集：鸢尾花数据集

鸢尾花数据集是一个经典的分类数据集，包含3种不同种类的鸢尾花，每种鸢尾花有4个特征，共计150个样本。

代码：

首先需要导入必要的库：

import numpy as np
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from keras.models import Sequential
from keras.layers import Dense
from keras.utils import to_categorical

加载数据集：

data = load_iris()
X = data.data
y = data.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=42)

对标签进行独热编码：

y_train = to_categorical(y_train)
y_test = to_categorical(y_test)

构建神经网络模型：

model = Sequential()
model.add(Dense(8, input_dim=4, activation='relu'))
model.add(Dense(3, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

训练模型：

model.fit(X_train, y_train, epochs=50, batch_size=5)

评估模型：

_, accuracy = model.evaluate(X_test, y_test)
print('Accuracy: %.2f' % (accuracy*100))

完整代码：

import numpy as np
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from keras.models import Sequential
from keras.layers import Dense
from keras.utils import to_categorical

data = load_iris()
X = data.data
y = data.target

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

y_train = to_categorical(y_train)
y_test = to_categorical(y_test)

model = Sequential()
model.add(Dense(8, input_dim=4, activation='relu'))
model.add(Dense(3, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

model.fit(X_train, y_train, epochs=50, batch_size=5)

_, accuracy = model.evaluate(X_test, y_test)
print('Accuracy: %.2f' % (accuracy*100))

输出结果：

Epoch 1/50
120/120 [==============================] - 0s 1ms/step - loss: 2.3543 - accuracy: 0.3333
Epoch 2/50
120/120 [==============================] - 0s 171us/step - loss: 2.1252 - accuracy: 0.3333
Epoch