python sklearn 随机森林分类器

下载文件地址：
链接: https://pan.baidu.com/s/1VdjCSw9MfKZ1WAcaiDyi8w 提取码: wtck

"""
    使用随机森林分类器 对汽车进行分类
"""
import numpy as np
import sklearn.preprocessing as sp
import sklearn.ensemble as se
import sklearn.model_selection as ms

# 读取数据
lines = np.loadtxt(r".\car.txt", delimiter=',', dtype='str')
print(lines.shape)

# 整理样本空间 并编码 （对列执行标签编码）
train_x, train_y = [], []
encoders = []  # 标签编码数组
for index, row in enumerate(lines.T):
    encoder = sp.LabelEncoder()
    if index < (len(lines.T) - 1):  # 训练样本 X
        train_x.append(encoder.fit_transform(row))
    else:
        train_y = encoder.fit_transform(row)  # 训练样本结果 Y
    encoders.append(encoder)

train_x = np.array(train_x).T  # 转置
train_y = np.array(train_y)

print(train_x.shape, train_y.shape)
print(train_x[0], train_y[0])

# 随机森林分类模型
model = se.RandomForestClassifier(
    max_depth=6, n_estimators=200, random_state=7)
score = ms.cross_val_score(model, train_x, train_y, cv=5, scoring="f1_weighted")  # 交叉验证
print(score.mean())

# 训练模型
model.fit(train_x, train_y)

# 自定义测试数据 用已经训练好的模型进行测试
data = [
    ['high', 'med', '5more', '4', 'big', 'low', 'unacc'],
    ['high', 'high', '4', '4', 'med', 'med', 'acc'],
    ['low', 'low', '2', '4', 'small', 'high', 'good'],
    ['low', 'med', '3', '4', 'med', 'high', 'vgood']]
data = np.array(data)

# 自定义数据集整理 标签编码
test_x, test_y = [], []
for index, row in enumerate(data.T):
    encoder = encoders[index]   # 使用原保存的标签编码
    if index < (len(data.T) - 1):
        test_x.append(encoder.transform(row))
    else:
        test_y = encoder.transform(row)

test_x = np.array(test_x).T
test_y = np.array(test_y)

print("----------------->测试数据\n", test_x.shape, test_y.shape)
print(test_x[0], test_y[0])

# 预测结果
prd_test_y = model.predict(test_x)
print("----------------->预测结果\n", test_y)
print(prd_test_y)
print(encoders[-1].inverse_transform(test_y))
print(encoders[-1].inverse_transform(prd_test_y))