汽车安全性评估数据分类

import pandas as pd

# 加载数据集
df = pd.read_csv(
    "http://labfile.oss.aliyuncs.com/courses/1211/car.data", header=None)
# 设置列名
df.columns = ['buying', 'maint', 'doors',
              'persons', 'lug_boot', 'safety', 'class']

from sklearn.model_selection import train_test_split

X = df.iloc[:, :-1]  # 特征
y = df['class']  # 目标


X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1)

#数据处理，利用one-hot编码
X_train = pd.get_dummies(X_train).values
X_test = pd.get_dummies(X_test).values
y_train = pd.get_dummies(y_train).values
y_test = pd.get_dummies(y_test).values

import tensorflow as tf
model = tf.keras.Sequential()  # 建立顺序模型
model.add(tf.keras.layers.Dense(units=30, input_dim=21, activation='relu'))  # 隐含层 1
model.add(tf.keras.layers.Dense(units=15, activation='relu'))  # 隐含层 2
model.add(tf.keras.layers.Dense(units=4, activation='softmax'))  # 输出层
#通俗来说，input_length就是输入数据的长度，Input_dim就是数据的维度。比如一条数据内容是： “人人车” ，  one hot编码后是 [[1 0] [1 0] [0 1]]表示 ，则  batch_size = 3, input_dim = 2. 
model.summary()  # 查看模型结构

# 编译模型，添加优化器，损失函数和评估方法。tf.optimizers.Adam 作为优化器，tf.losses.categorical_crossentropy 多分类交叉熵
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
# 训练模型
model.fit(X_train, y_train, batch_size=64, epochs=20, validation_data=(X_test, y_test))