下载数据集
pip install sklearn
加载数据集
数据集的返回值介绍
查看数据集代码
from sklearn import datasets
def datasets_demo():
iris=datasets.load_iris()
print(f'数据:',iris)
print('数据集描述',iris["DESCR"])
if __name__=="__main__":
datasets_demo()
数据: {'data': array([[5.1, 3.5, 1.4, 0.2],
[4.9, 3. , 1.4, 0.2],
[4.7, 3.2, 1.3, 0.2],
[4.6, 3.1, 1.5, 0.2],
[5. , 3.6, 1.4, 0.2],
[5.4, 3.9, 1.7, 0.4],
[4.6, 3.4, 1.4, 0.3],
[5. , 3.4, 1.5, 0.2],
[4.4, 2.9, 1.4, 0.2],
[4.9, 3.1, 1.5, 0.1],
[5.4, 3.7, 1.5, 0.2],
[4.8, 3.4, 1.6, 0.2],
[4.8, 3. , 1.4, 0.1],
[4.3, 3. , 1.1, 0.1],
[5.8, 4. , 1.2, 0.2],
[5.7, 4.4, 1.5, 0.4],
[5.4, 3.9, 1.3, 0.4],
[5.1, 3.5, 1.4, 0.3],
[5.7, 3.8, 1.7, 0.3],
[5.1, 3.8, 1.5, 0.3],
[5.4, 3.4, 1.7, 0.2],
[5.1, 3.7, 1.5, 0.4],
[4.6, 3.6, 1. , 0.2],
[5.1, 3.3, 1.7, 0.5],
[4.8, 3.4, 1.9, 0.2],
[5. , 3. , 1.6, 0.2],
[5. , 3.4, 1.6, 0.4],
[5.2, 3.5, 1.5, 0.2],
[5.2, 3.4, 1.4, 0.2],
[4.7, 3.2, 1.6, 0.2],
[4.8, 3.1, 1.6, 0.2],
[5.4, 3.4, 1.5, 0.4],
[5.2, 4.1, 1.5, 0.1],
[5.5, 4.2, 1.4, 0.2],
[4.9, 3.1, 1.5, 0.2],
[5. , 3.2, 1.2, 0.2],
[5.5, 3.5, 1.3, 0.2],
[4.9, 3.6, 1.4, 0.1],
[4.4, 3. , 1.3, 0.2],
[5.1, 3.4, 1.5, 0.2],
[5. , 3.5, 1.3, 0.3],
[4.5, 2.3, 1.3, 0.3],
[4.4, 3.2, 1.3, 0.2],
[5. , 3.5, 1.6, 0.6],
[5.1, 3.8, 1.9, 0.4],
[4.8, 3. , 1.4, 0.3],
[5.1, 3.8, 1.6, 0.2],
[4.6, 3.2, 1.4, 0.2],
[5.3, 3.7, 1.5, 0.2],
[5. , 3.3, 1.4, 0.2],
[7. , 3.2, 4.7, 1.4],
[6.4, 3.2, 4.5, 1.5],
[6.9, 3.1, 4.9, 1.5],
[5.5, 2.3, 4. , 1.3],
[6.5, 2.8, 4.6, 1.5],
[5.7, 2.8, 4.5, 1.3],
[6.3, 3.3, 4.7, 1.6],
[4.9, 2.4, 3.3, 1. ],
[6.6, 2.9, 4.6, 1.3],
[5.2, 2.7, 3.9, 1.4],
[5. , 2. , 3.5, 1. ],
[5.9, 3. , 4.2, 1.5],
[6. , 2.2, 4. , 1. ],
[6.1, 2.9, 4.7, 1.4],
[5.6, 2.9, 3.6, 1.3],
[6.7, 3.1, 4.4, 1.4],
[5.6, 3. , 4.5, 1.5],
[5.8, 2.7, 4.1, 1. ],
[6.2, 2.2, 4.5, 1.5],
[5.6, 2.5, 3.9, 1.1],
[5.9, 3.2, 4.8, 1.8],
[6.1, 2.8, 4. , 1.3],
[6.3, 2.5, 4.9, 1.5],
[6.1, 2.8, 4.7, 1.2],
[6.4, 2.9, 4.3, 1.3],
[6.6, 3. , 4.4, 1.4],
[6.8, 2.8, 4.8, 1.4],
[6.7, 3. , 5. , 1.7],
[6. , 2.9, 4.5, 1.5],
[5.7, 2.6, 3.5, 1. ],
[5.5, 2.4, 3.8, 1.1],
[5.5, 2.4, 3.7, 1. ],
[5.8, 2.7, 3.9, 1.2],
[6. , 2.7, 5.1, 1.6],
[5.4, 3. , 4.5, 1.5],
[6. , 3.4, 4.5, 1.6],
[6.7, 3.1, 4.7, 1.5],
[6.3, 2.3, 4.4, 1.3],
[5.6, 3. , 4.1, 1.3],
[5.5, 2.5, 4. , 1.3],
[5.5, 2.6, 4.4, 1.2],
[6.1, 3. , 4.6, 1.4],
[5.8, 2.6, 4. , 1.2],
[5. , 2.3, 3.3, 1. ],
[5.6, 2.7, 4.2, 1.3],
[5.7, 3. , 4.2, 1.2],
[5.7, 2.9, 4.2, 1.3],
[6.2, 2.9, 4.3, 1.3],
[5.1, 2.5, 3. , 1.1],
[5.7, 2.8, 4.1, 1.3],
[6.3, 3.3, 6. , 2.5],
[5.8, 2.7, 5.1, 1.9],
[7.1, 3. , 5.9, 2.1],
[6.3, 2.9, 5.6, 1.8],
[6.5, 3. , 5.8, 2.2],
[7.6, 3. , 6.6, 2.1],
[4.9, 2.5, 4.5, 1.7],
[7.3, 2.9, 6.3, 1.8],
[6.7, 2.5, 5.8, 1.8],
[7.2, 3.6, 6.1, 2.5],
[6.5, 3.2, 5.1, 2. ],
[6.4, 2.7, 5.3, 1.9],
[6.8, 3. , 5.5, 2.1],
[5.7, 2.5, 5. , 2. ],
[5.8, 2.8, 5.1, 2.4],
[6.4, 3.2, 5.3, 2.3],
[6.5, 3. , 5.5, 1.8],
[7.7, 3.8, 6.7, 2.2],
[7.7, 2.6, 6.9, 2.3],
[6. , 2.2, 5. , 1.5],
[6.9, 3.2, 5.7, 2.3],
[5.6, 2.8, 4.9, 2. ],
[7.7, 2.8, 6.7, 2. ],
[6.3, 2.7, 4.9, 1.8],
[6.7, 3.3, 5.7, 2.1],
[7.2, 3.2, 6. , 1.8],
[6.2, 2.8, 4.8, 1.8],
[6.1, 3. , 4.9, 1.8],
[6.4, 2.8, 5.6, 2.1],
[7.2, 3. , 5.8, 1.6],
[7.4, 2.8, 6.1, 1.9],
[7.9, 3.8, 6.4, 2. ],
[6.4, 2.8, 5.6, 2.2],
[6.3, 2.8, 5.1, 1.5],
[6.1, 2.6, 5.6, 1.4],
[7.7, 3. , 6.1, 2.3],
[6.3, 3.4, 5.6, 2.4],
[6.4, 3.1, 5.5, 1.8],
[6. , 3. , 4.8, 1.8],
[6.9, 3.1, 5.4, 2.1],
[6.7, 3.1, 5.6, 2.4],
[6.9, 3.1, 5.1, 2.3],
[5.8, 2.7, 5.1, 1.9],
[6.8, 3.2, 5.9, 2.3],
[6.7, 3.3, 5.7, 2.5],
[6.7, 3. , 5.2, 2.3],
[6.3, 2.5, 5. , 1.9],
[6.5, 3. , 5.2, 2. ],
[6.2, 3.4, 5.4, 2.3],
[5.9, 3. , 5.1, 1.8]]), 'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]), 'frame': None, 'target_names': array(['setosa', 'versicolor', 'virginica'], dtype='<U10')
划分数据集
训练数据:构建模型(80%)
测试数据:评估模型是否有效(20%)
代码:
from sklearn import model_selection
x_train,x_test,y_train,y_test=model_selection.train_test_split(iris.data,iris.target,test_size=0.2,random_state=22)
print("训练模型的特征值是",x_train,x_test,x_train.shape)
训练模型的特征值是 [[4.8 3.1 1.6 0.2]
[5.4 3.4 1.5 0.4]
[5.5 2.5 4. 1.3]
[5.5 2.6 4.4 1.2]
[5.7 2.8 4.5 1.3]
[5. 3.4 1.6 0.4]
[5.1 3.4 1.5 0.2]
[4.9 3.6 1.4 0.1]
[6.9 3.1 5.4 2.1]
[6.7 2.5 5.8 1.8]
[7. 3.2 4.7 1.4]
[6.3 3.3 4.7 1.6]
[5.4 3.9 1.3 0.4]
[4.4 3.2 1.3 0.2]
[6.7 3. 5. 1.7]
[5.6 3. 4.1 1.3]
[5.7 2.5 5. 2. ]
[6.5 3. 5.8 2.2]
[5. 3.6 1.4 0.2]
[6.1 2.8 4. 1.3]
[6. 3.4 4.5 1.6]
[6.7 3. 5.2 2.3]
[5.7 4.4 1.5 0.4]
[5.4 3.4 1.7 0.2]
[5. 3.5 1.3 0.3]
[4.8 3. 1.4 0.1]
[5.5 4.2 1.4 0.2]
[4.6 3.6 1. 0.2]
[7.2 3.2 6. 1.8]
[5.1 2.5 3. 1.1]
[6.4 3.2 4.5 1.5]
[7.3 2.9 6.3 1.8]
[4.5 2.3 1.3 0.3]
[5. 3. 1.6 0.2]
[5.7 3.8 1.7 0.3]
[5. 3.3 1.4 0.2]
[6.2 2.2 4.5 1.5]
[5.1 3.5 1.4 0.2]
[6.4 2.9 4.3 1.3]
[4.9 2.4 3.3 1. ]
[6.3 2.5 4.9 1.5]
[6.1 2.8 4.7 1.2]
[5.9 3.2 4.8 1.8]
[5.4 3.9 1.7 0.4]
[6. 2.2 4. 1. ]
[6.4 2.8 5.6 2.1]
[4.8 3.4 1.9 0.2]
[6.4 3.1 5.5 1.8]
[5.9 3. 4.2 1.5]
[6.5 3. 5.5 1.8]
[6. 2.9 4.5 1.5]
[5.5 2.4 3.8 1.1]
[6.2 2.9 4.3 1.3]
[5.2 4.1 1.5 0.1]
[5.2 3.4 1.4 0.2]
[7.7 2.6 6.9 2.3]
[5.7 2.6 3.5 1. ]
[4.6 3.4 1.4 0.3]
[5.8 2.7 4.1 1. ]
[5.8 2.7 3.9 1.2]
[6.2 3.4 5.4 2.3]
[5.9 3. 5.1 1.8]
[4.6 3.1 1.5 0.2]
[5.8 2.8 5.1 2.4]
[5.1 3.5 1.4 0.3]
[6.8 3.2 5.9 2.3]
[4.9 3.1 1.5 0.1]
[5.5 2.3 4. 1.3]
[5.1 3.7 1.5 0.4]
[5.8 2.7 5.1 1.9]
[6.7 3.1 4.4 1.4]
[6.8 3. 5.5 2.1]
[5.2 2.7 3.9 1.4]
[6.7 3.1 5.6 2.4]
[5.3 3.7 1.5 0.2]
[5. 2. 3.5 1. ]
[6.6 2.9 4.6 1.3]
[6. 2.7 5.1 1.6]
[6.3 2.3 4.4 1.3]
[7.7 3. 6.1 2.3]
[4.9 3. 1.4 0.2]
[4.6 3.2 1.4 0.2]
[6.3 2.7 4.9 1.8]
[6.6 3. 4.4 1.4]
[6.9 3.1 4.9 1.5]
[4.3 3. 1.1 0.1]
[5.6 2.7 4.2 1.3]
[4.8 3.4 1.6 0.2]
[7.6 3. 6.6 2.1]
[7.7 2.8 6.7 2. ]
[4.9 2.5 4.5 1.7]
[6.5 3.2 5.1 2. ]
[5.1 3.3 1.7 0.5]
[6.3 2.9 5.6 1.8]
[6.1 2.6 5.6 1.4]
[5. 3.4 1.5 0.2]
[6.1 3. 4.6 1.4]
[5.6 3. 4.5 1.5]
[5.1 3.8 1.5 0.3]
[5.6 2.8 4.9 2. ]
[4.4 3. 1.3 0.2]
[5.5 2.4 3.7 1. ]
[4.7 3.2 1.6 0.2]
[6.7 3.3 5.7 2.5]
[5.2 3.5 1.5 0.2]
[6.4 2.7 5.3 1.9]
[6.3 2.8 5.1 1.5]
[4.4 2.9 1.4 0.2]
[6.1 3. 4.9 1.8]
[4.9 3.1 1.5 0.2]
[5. 2.3 3.3 1. ]
[4.8 3. 1.4 0.3]
[5.8 4. 1.2 0.2]
[6.3 3.4 5.6 2.4]
[5.4 3. 4.5 1.5]
[7.1 3. 5.9 2.1]
[6.3 3.3 6. 2.5]
[5.1 3.8 1.9 0.4]
[6.4 2.8 5.6 2.2]
[7.7 3.8 6.7 2.2]] [[5.4 3.7 1.5 0.2]
[6.4 3.2 5.3 2.3]
[6.5 2.8 4.6 1.5]
[6.3 2.5 5. 1.9]
[6.1 2.9 4.7 1.4]
[6.8 2.8 4.8 1.4]
[6.7 3.1 4.7 1.5]
[6. 3. 4.8 1.8]
[5.6 2.9 3.6 1.3]
[5. 3.2 1.2 0.2]
[6.9 3.2 5.7 2.3]
[5.7 3. 4.2 1.2]
[7.4 2.8 6.1 1.9]
[7.2 3.6 6.1 2.5]
[5. 3.5 1.6 0.6]
[7.9 3.8 6.4 2. ]
[5.6 2.5 3.9 1.1]
[5.7 2.8 4.1 1.3]
[6. 2.2 5. 1.5]
[5.7 2.9 4.2 1.3]
[5.1 3.8 1.6 0.2]
[6.9 3.1 5.1 2.3]
[5.5 3.5 1.3 0.2]
[5.8 2.6 4. 1.2]
[5.8 2.7 5.1 1.9]
[4.7 3.2 1.3 0.2]
[7.2 3. 5.8 1.6]
[6.5 3. 5.2 2. ]
[6.7 3.3 5.7 2.1]
[6.2 2.8 4.8 1.8]] (120, 4)Process finished with exit code 0
整体代码
from sklearn import datasets
from sklearn import model_selection
def datasets_demo():
iris=datasets.load_iris()
print(f'数据:',iris)
print('数据集描述',iris["DESCR"])
x_train,x_test,y_train,y_test=model_selection.train_test_split(iris.data,iris.target,test_size=0.2,random_state=22)
print("训练模型的特征值是",x_train,x_test,x_train.shape)
if __name__=="__main__":
datasets_demo()