前言

逻辑回归的一个小案例，使用sklearn自带的一个数据

代码

1
2
3
4
5
6

from sklearn.linear_model import LogisticRegression as LR #逻辑回归
from sklearn.datasets import load_breast_cancer #导入乳腺癌数据集
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split  # 导入分测试与训练集
from sklearn.metrics import accuracy_score#精确性分数

1
2

data = load_breast_cancer()#乳腺癌数据集
data

{'data': array([[1.799e+01, 1.038e+01, 1.228e+02, ..., 2.654e-01, 4.601e-01,
         1.189e-01],
        [2.057e+01, 1.777e+01, 1.329e+02, ..., 1.860e-01, 2.750e-01,
         8.902e-02],
        [1.969e+01, 2.125e+01, 1.300e+02, ..., 2.430e-01, 3.613e-01,
         8.758e-02],
        ...,
        [1.660e+01, 2.808e+01, 1.083e+02, ..., 1.418e-01, 2.218e-01,
         7.820e-02],
        [2.060e+01, 2.933e+01, 1.401e+02, ..., 2.650e-01, 4.087e-01,
         1.240e-01],
        [7.760e+00, 2.454e+01, 4.792e+01, ..., 0.000e+00, 2.871e-01,
         7.039e-02]]),
 'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1,
        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,
        0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0,
        1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0,
        1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1,
        1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0,
        0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1,
        1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 1,
        1, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0,
        0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0,
        1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1,
        1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
        0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1,
        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1,
        1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0,
        0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0,
        0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0,
        1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1,
        1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0,
        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1,
        1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0,
        1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1,
        1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1,
        1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,
        1, 1, 1, 1, 1, 0, 1, 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, 0, 0, 0, 0, 0, 0, 1]),
 'frame': None,
 'target_names': array(['malignant', 'benign'], dtype='<U9'),
 'DESCR': '.. _breast_cancer_dataset:\n\nBreast cancer wisconsin (diagnostic) dataset\n--------------------------------------------\n\n**Data Set Characteristics:**\n\n    :Number of Instances: 569\n\n    :Number of Attributes: 30 numeric, predictive attributes and the class\n\n    :Attribute Information:\n        - radius (mean of distances from center to points on the perimeter)\n        - texture (standard deviation of gray-scale values)\n        - perimeter\n        - area\n        - smoothness (local variation in radius lengths)\n        - compactness (perimeter^2 / area - 1.0)\n        - concavity (severity of concave portions of the contour)\n        - concave points (number of concave portions of the contour)\n        - symmetry\n        - fractal dimension ("coastline approximation" - 1)\n\n        The mean, standard error, and "worst" or largest (mean of the three\n        worst/largest values) of these features were computed for each image,\n        resulting in 30 features.  For instance, field 0 is Mean Radius, field\n        10 is Radius SE, field 20 is Worst Radius.\n\n        - class:\n                - WDBC-Malignant\n                - WDBC-Benign\n\n    :Summary Statistics:\n\n    ===================================== ====== ======\n                                           Min    Max\n    ===================================== ====== ======\n    radius (mean):                        6.981  28.11\n    texture (mean):                       9.71   39.28\n    perimeter (mean):                     43.79  188.5\n    area (mean):                          143.5  2501.0\n    smoothness (mean):                    0.053  0.163\n    compactness (mean):                   0.019  0.345\n    concavity (mean):                     0.0    0.427\n    concave points (mean):                0.0    0.201\n    symmetry (mean):                      0.106  0.304\n    fractal dimension (mean):             0.05   0.097\n    radius (standard error):              0.112  2.873\n    texture (standard error):             0.36   4.885\n    perimeter (standard error):           0.757  21.98\n    area (standard error):                6.802  542.2\n    smoothness (standard error):          0.002  0.031\n    compactness (standard error):         0.002  0.135\n    concavity (standard error):           0.0    0.396\n    concave points (standard error):      0.0    0.053\n    symmetry (standard error):            0.008  0.079\n    fractal dimension (standard error):   0.001  0.03\n    radius (worst):                       7.93   36.04\n    texture (worst):                      12.02  49.54\n    perimeter (worst):                    50.41  251.2\n    area (worst):                         185.2  4254.0\n    smoothness (worst):                   0.071  0.223\n    compactness (worst):                  0.027  1.058\n    concavity (worst):                    0.0    1.252\n    concave points (worst):               0.0    0.291\n    symmetry (worst):                     0.156  0.664\n    fractal dimension (worst):            0.055  0.208\n    ===================================== ====== ======\n\n    :Missing Attribute Values: None\n\n    :Class Distribution: 212 - Malignant, 357 - Benign\n\n    :Creator:  Dr. William H. Wolberg, W. Nick Street, Olvi L. Mangasarian\n\n    :Donor: Nick Street\n\n    :Date: November, 1995\n\nThis is a copy of UCI ML Breast Cancer Wisconsin (Diagnostic) datasets.\nhttps://goo.gl/U2Uwz2\n\nFeatures are computed from a digitized image of a fine needle\naspirate (FNA) of a breast mass.  They describe\ncharacteristics of the cell nuclei present in the image.\n\nSeparating plane described above was obtained using\nMultisurface Method-Tree (MSM-T) [K. P. Bennett, "Decision Tree\nConstruction Via Linear Programming." Proceedings of the 4th\nMidwest Artificial Intelligence and Cognitive Science Society,\npp. 97-101, 1992], a classification method which uses linear\nprogramming to construct a decision tree.  Relevant features\nwere selected using an exhaustive search in the space of 1-4\nfeatures and 1-3 separating planes.\n\nThe actual linear program used to obtain the separating plane\nin the 3-dimensional space is that described in:\n[K. P. Bennett and O. L. Mangasarian: "Robust Linear\nProgramming Discrimination of Two Linearly Inseparable Sets",\nOptimization Methods and Software 1, 1992, 23-34].\n\nThis database is also available through the UW CS ftp server:\n\nftp ftp.cs.wisc.edu\ncd math-prog/cpo-dataset/machine-learn/WDBC/\n\n.. topic:: References\n\n   - W.N. Street, W.H. Wolberg and O.L. Mangasarian. Nuclear feature extraction \n     for breast tumor diagnosis. IS&T/SPIE 1993 International Symposium on \n     Electronic Imaging: Science and Technology, volume 1905, pages 861-870,\n     San Jose, CA, 1993.\n   - O.L. Mangasarian, W.N. Street and W.H. Wolberg. Breast cancer diagnosis and \n     prognosis via linear programming. Operations Research, 43(4), pages 570-577, \n     July-August 1995.\n   - W.H. Wolberg, W.N. Street, and O.L. Mangasarian. Machine learning techniques\n     to diagnose breast cancer from fine-needle aspirates. Cancer Letters 77 (1994) \n     163-171.',
 'feature_names': array(['mean radius', 'mean texture', 'mean perimeter', 'mean area',
        'mean smoothness', 'mean compactness', 'mean concavity',
        'mean concave points', 'mean symmetry', 'mean fractal dimension',
        'radius error', 'texture error', 'perimeter error', 'area error',
        'smoothness error', 'compactness error', 'concavity error',
        'concave points error', 'symmetry error',
        'fractal dimension error', 'worst radius', 'worst texture',
        'worst perimeter', 'worst area', 'worst smoothness',
        'worst compactness', 'worst concavity', 'worst concave points',
        'worst symmetry', 'worst fractal dimension'], dtype='<U23'),
 'filename': '/home/ubuntu/.local/lib/python3.8/site-packages/sklearn/datasets/data/breast_cancer.csv'}

1
2

X = data.data
X.shape

(569, 30)

1
2

y = data.target
y.shape

(569,)

1

X.data.shape#(569, 30)

(569, 30)

1
2

lrl1 = LR(penalty="l1",solver="liblinear",C=0.5,max_iter=1000)#l1 正则化会压缩到0
lrl2 = LR(penalty="l2",solver="liblinear",C=0.5,max_iter=1000)#l2 正则化不会压缩到0，默认l2正则化不填的话

1
2
3

#逻辑回归的重要属性coef_，查看每个特征所对应的参数
lrl1 = lrl1.fit(X,y)
lrl1.coef_

array([[ 4.00409758,  0.03192262, -0.13763277, -0.01622177,  0.        ,
         0.        ,  0.        ,  0.        ,  0.        ,  0.        ,
         0.        ,  0.50529191,  0.        , -0.07128513,  0.        ,
         0.        ,  0.        ,  0.        ,  0.        ,  0.        ,
         0.        , -0.2458918 , -0.12855748, -0.01441275,  0.        ,
         0.        , -2.03953157,  0.        ,  0.        ,  0.        ]])

1

(lrl1.coef_ != 0).sum(axis=1)#array([10])    30个特征中有10个特征的系数不为0

array([10])

1
2

lrl2 = lrl2.fit(X,y)
lrl2.coef_

array([[ 1.61331113e+00,  1.00124606e-01,  4.60084835e-02,
        -4.19839426e-03, -9.26228937e-02, -3.00484301e-01,
        -4.53250190e-01, -2.19778015e-01, -1.33074668e-01,
        -1.92576286e-02,  1.89635811e-02,  8.74998561e-01,
         1.32421950e-01, -9.53784315e-02, -9.62972408e-03,
        -2.53596204e-02, -5.83890299e-02, -2.67755115e-02,
        -2.73846616e-02, -8.05302922e-05,  1.28529688e+00,
        -3.00088054e-01, -1.74310770e-01, -2.23545072e-02,
        -1.70267493e-01, -8.77272211e-01, -1.15830085e+00,
        -4.22526360e-01, -4.12406225e-01, -8.66393364e-02]])

1

lrl2.coef_ != 0

array([[ True,  True,  True,  True,  True,  True,  True,  True,  True,
         True,  True,  True,  True,  True,  True,  True,  True,  True,
         True,  True,  True,  True,  True,  True,  True,  True,  True,
         True,  True,  True]])

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27

l1 = []
l2 = []
l1test = []
l2test = []

Xtrain, Xtest, Ytrain, Ytest = train_test_split(X,y,test_size=0.3,random_state=420)

for i in np.linspace(0.05,1.5,19):
    lrl1 = LR(penalty="l1",solver="liblinear",C=i,max_iter=1000)
    lrl2 = LR(penalty="l2",solver="liblinear",C=i,max_iter=1000)

    lrl1 = lrl1.fit(Xtrain,Ytrain)
    l1.append(accuracy_score(lrl1.predict(Xtrain),Ytrain))
    l1test.append(accuracy_score(lrl1.predict(Xtest),Ytest))
    lrl2 = lrl2.fit(Xtrain,Ytrain)
    l2.append(accuracy_score(lrl2.predict(Xtrain),Ytrain))
    l2test.append(accuracy_score(lrl2.predict(Xtest),Ytest))

graph = [l1,l2,l1test,l2test]
color = ["green","black","lightgreen","gray"]
label = ["L1","L2","L1test","L2test"]

plt.figure(figsize=(6,6))
for i in range(len(graph)):
    plt.plot(np.linspace(0.05,1.5,19),graph[i],color[i],label=label[i])
plt.legend(loc=4) #图例的位置在哪里?4表示，右下角
plt.show()#0.8~0.9比较好

1
2
3
4
5
6

from sklearn.linear_model import LogisticRegression as LR
from sklearn.datasets import load_breast_cancer
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import cross_val_score
from sklearn.feature_selection import SelectFromModel

1
2

data = load_breast_cancer()
data.data.shape

(569, 30)

1
2

LR_ = LR(solver="liblinear",C=0.9,random_state=420)
cross_val_score(LR_,data.data,data.target,cv=10).mean()

0.9508145363408522

1
2
3

X_embedded = SelectFromModel(LR_,norm_order=1).fit_transform(data.data,data.target)
#threshold=float筛选特征的一个阈值，norm_order范式为l1，嵌入法
X_embedded.shape

(569, 9)

1

cross_val_score(LR_,X_embedded,data.target,cv=10).mean()#0.9368323826808401

0.9368107769423559

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19

fullx = []
fsx = []

threshold = np.linspace(0,abs((LR_.fit(data.data,data.target).coef_)).max(),20)

k=0
for i in threshold:
    X_embedded = SelectFromModel(LR_,threshold=i).fit_transform(data.data,data.target)
    fullx.append(cross_val_score(LR_,data.data,data.target,cv=5).mean())
    fsx.append(cross_val_score(LR_,X_embedded,data.target,cv=5).mean())
    print((threshold[k],X_embedded.shape[1]))
    k+=1

plt.figure(figsize=(20,5))
plt.plot(threshold,fullx,label="full")
plt.plot(threshold,fsx,label="feature selection")
plt.xticks(threshold)
plt.legend()
plt.show()

(0.0, 30)
(0.10700725930906944, 17)
(0.2140145186181389, 12)
(0.3210217779272083, 11)
(0.4280290372362778, 8)
(0.5350362965453472, 8)
(0.6420435558544166, 6)
(0.7490508151634862, 5)
(0.8560580744725556, 5)
(0.963065333781625, 5)
(1.0700725930906945, 5)
(1.1770798523997639, 4)
(1.2840871117088333, 2)
(1.3910943710179027, 2)
(1.4981016303269723, 2)
(1.6051088896360417, 1)
(1.712116148945111, 1)
(1.8191234082541805, 1)
(1.92613066756325, 1)
(2.0331379268723193, 1)

前言

数据集合来自kaggle

链接：https://www.kaggle.com/c/digit-recognizer/data

其中test和train的csv数据集为所需数据集。

删除指定端口的所有进程

1

sudo kill -9 $(lsof -i:端口号 -t)

删除指定名称的所有进程

1

sudo kill -9 $(pidof 名字)

查看指定端口占用情况

1

sudo lsof -i:端口号

删除指定pid的进程

1

sudo kill -9 pid号

docker-compose搭建

wordpress

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27

version: '3.3'

services:
   db:
     image: mysql:latest
     volumes:
       - /data/wordpress_db:/var/lib/mysql
     restart: always
     environment:
       MYSQL_ROOT_PASSWORD: rootwordpress
       MYSQL_DATABASE: wordpress
       MYSQL_USER: wordpress
       MYSQL_PASSWORD: wordpress

   wordpress:
     depends_on:
       - db
     image: wordpress:latest
     ports:
       - "8000:80"
     restart: always
     environment:
       WORDPRESS_DB_HOST: db:3306
       WORDPRESS_DB_USER: wordpress
       WORDPRESS_DB_PASSWORD: wordpress
       WORDPRESS_DB_NAME: wordpress

Cloudreve

1
2
3
4
5
6
7
8
9

services:
    cloudreve:
        public: true
        container_name: cloudreve
        image: jialezi/cloudreve
        ports:
            - 5212:5212
        volumes:
            - /root/cloudreve

Bitwarden

管理地址为“xxx/admin”。

前言

使用的相关数据链接如下：

点我跳转

代码

连续值预处理

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

import pandas as pd
data = pd.read_csv("Narrativedata.csv"
                   ,index_col=0
                  )#index_col=0将第0列作为索引，不写则认为第0列为特征
data.loc[:,"Age"] = data.loc[:,"Age"].fillna(data.loc[:,"Age"].median())

#将年龄二值化

data_2 = data.copy()
data_2.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 891 entries, 0 to 890
Data columns (total 4 columns):
 #   Column    Non-Null Count  Dtype
---  ------    --------------  -----
 0   Age       891 non-null    float64
 1   Sex       891 non-null    object
 2   Embarked  889 non-null    object
 3   Survived  891 non-null    object
dtypes: float64(1), object(3)
memory usage: 34.8+ KB

1
2
3

from sklearn.preprocessing import Binarizer
X = data_2.iloc[:,0].values.reshape(-1,1)               #类为特征专用，所以不能使用一维数组
transformer = Binarizer(threshold=30).fit_transform(X)  #阈值threshold=n, 小于等于n的数值转为0, 大于n的数值转为1

1
2

data_2.iloc[:,0] = transformer
data_2.head()

随机森林填补缺失值(实测回归比较好)

1
2
3
4
5

%matplotlib inline
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier#随机森林分类树
from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split

1
2

wine = load_wine()
wine

{'data': array([[1.423e+01, 1.710e+00, 2.430e+00, ..., 1.040e+00, 3.920e+00,
         1.065e+03],
        [1.320e+01, 1.780e+00, 2.140e+00, ..., 1.050e+00, 3.400e+00,
         1.050e+03],
        [1.316e+01, 2.360e+00, 2.670e+00, ..., 1.030e+00, 3.170e+00,
         1.185e+03],
        ...,
        [1.327e+01, 4.280e+00, 2.260e+00, ..., 5.900e-01, 1.560e+00,
         8.350e+02],
        [1.317e+01, 2.590e+00, 2.370e+00, ..., 6.000e-01, 1.620e+00,
         8.400e+02],
        [1.413e+01, 4.100e+00, 2.740e+00, ..., 6.100e-01, 1.600e+00,
         5.600e+02]]),
 '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, 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, 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]),
 'frame': None,
 'target_names': array(['class_0', 'class_1', 'class_2'], dtype='<U7'),
 'DESCR': '.. _wine_dataset:\n\nWine recognition dataset\n------------------------\n\n**Data Set Characteristics:**\n\n    :Number of Instances: 178 (50 in each of three classes)\n    :Number of Attributes: 13 numeric, predictive attributes and the class\n    :Attribute Information:\n \t\t- Alcohol\n \t\t- Malic acid\n \t\t- Ash\n\t\t- Alcalinity of ash  \n \t\t- Magnesium\n\t\t- Total phenols\n \t\t- Flavanoids\n \t\t- Nonflavanoid phenols\n \t\t- Proanthocyanins\n\t\t- Color intensity\n \t\t- Hue\n \t\t- OD280/OD315 of diluted wines\n \t\t- Proline\n\n    - class:\n            - class_0\n            - class_1\n            - class_2\n\t\t\n    :Summary Statistics:\n    \n    ============================= ==== ===== ======= =====\n                                   Min   Max   Mean     SD\n    ============================= ==== ===== ======= =====\n    Alcohol:                      11.0  14.8    13.0   0.8\n    Malic Acid:                   0.74  5.80    2.34  1.12\n    Ash:                          1.36  3.23    2.36  0.27\n    Alcalinity of Ash:            10.6  30.0    19.5   3.3\n    Magnesium:                    70.0 162.0    99.7  14.3\n    Total Phenols:                0.98  3.88    2.29  0.63\n    Flavanoids:                   0.34  5.08    2.03  1.00\n    Nonflavanoid Phenols:         0.13  0.66    0.36  0.12\n    Proanthocyanins:              0.41  3.58    1.59  0.57\n    Colour Intensity:              1.3  13.0     5.1   2.3\n    Hue:                          0.48  1.71    0.96  0.23\n    OD280/OD315 of diluted wines: 1.27  4.00    2.61  0.71\n    Proline:                       278  1680     746   315\n    ============================= ==== ===== ======= =====\n\n    :Missing Attribute Values: None\n    :Class Distribution: class_0 (59), class_1 (71), class_2 (48)\n    :Creator: R.A. Fisher\n    :Donor: Michael Marshall (MARSHALL%[email protected])\n    :Date: July, 1988\n\nThis is a copy of UCI ML Wine recognition datasets.\nhttps://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data\n\nThe data is the results of a chemical analysis of wines grown in the same\nregion in Italy by three different cultivators. There are thirteen different\nmeasurements taken for different constituents found in the three types of\nwine.\n\nOriginal Owners: \n\nForina, M. et al, PARVUS - \nAn Extendible Package for Data Exploration, Classification and Correlation. \nInstitute of Pharmaceutical and Food Analysis and Technologies,\nVia Brigata Salerno, 16147 Genoa, Italy.\n\nCitation:\n\nLichman, M. (2013). UCI Machine Learning Repository\n[https://archive.ics.uci.edu/ml]. Irvine, CA: University of California,\nSchool of Information and Computer Science. \n\n.. topic:: References\n\n  (1) S. Aeberhard, D. Coomans and O. de Vel, \n  Comparison of Classifiers in High Dimensional Settings, \n  Tech. Rep. no. 92-02, (1992), Dept. of Computer Science and Dept. of  \n  Mathematics and Statistics, James Cook University of North Queensland. \n  (Also submitted to Technometrics). \n\n  The data was used with many others for comparing various \n  classifiers. The classes are separable, though only RDA \n  has achieved 100% correct classification. \n  (RDA : 100%, QDA 99.4%, LDA 98.9%, 1NN 96.1% (z-transformed data)) \n  (All results using the leave-one-out technique) \n\n  (2) S. Aeberhard, D. Coomans and O. de Vel, \n  "THE CLASSIFICATION PERFORMANCE OF RDA" \n  Tech. Rep. no. 92-01, (1992), Dept. of Computer Science and Dept. of \n  Mathematics and Statistics, James Cook University of North Queensland. \n  (Also submitted to Journal of Chemometrics).\n',
 'feature_names': ['alcohol',
  'malic_acid',
  'ash',
  'alcalinity_of_ash',
  'magnesium',
  'total_phenols',
  'flavanoids',
  'nonflavanoid_phenols',
  'proanthocyanins',
  'color_intensity',
  'hue',
  'od280/od315_of_diluted_wines',
  'proline']}

1

wine.data.shape#特征矩阵

(178, 13)

1

wine.target.shape#标签，以数的形式呈现

(178,)

1
2
3

#实例化
clf = DecisionTreeClassifier(random_state=25)
xtrain,xtest,ytrain,ytest = train_test_split(wine.data,wine.target,test_size=0.3)#数据和特征分开导入

1
2

clf = DecisionTreeClassifier(random_state=0)
rfc = RandomForestClassifier(random_state=0)

1
2
3

#导入训练
clf = clf.fit(xtrain,ytrain)
rfc = rfc.fit(xtrain,ytrain)

1
2
3

#打分
score_c = clf.score(xtest,ytest)
score_r = rfc.score(xtest,ytest)

1
2

print("Single Tree:{}".format(score_c)
      ,"Random Forest:{}".format(score_r))

Single Tree:0.8703703703703703 Random Forest:0.9629629629629629

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14

# 交叉验证
from sklearn.model_selection import cross_val_score
import matplotlib.pyplot as plt

rfc = RandomForestClassifier(random_state=25)
rfc_s = cross_val_score(rfc,wine.data,wine.target,cv=10)

clf = DecisionTreeClassifier(random_state=25)
clf_s = cross_val_score(clf,wine.data,wine.target,cv=10)

plt.plot(range(1,11),rfc_s,label="RandomForest")
plt.plot(range(1,11),clf_s,label="DecisionTree")
plt.legend()
plt.show()

1
2
3
4
5
6
7
8
9

superpa = []
for i in range(200):
    rfc = RandomForestClassifier(n_estimators=i+1,n_jobs=-1)#n_jobs是-1时表示CPU所有core进行工作
    rfc_s = cross_val_score(rfc,wine.data,wine.target,cv=10).mean()
    superpa.append(rfc_s)
print (max(superpa),superpa.index(max(superpa)))
plt.figure(figsize=[20,5])
plt.plot(range(1, 201),superpa)
plt.show( )

0.9888888888888889 35

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16

rfc_l = []
clf_l = []

for i in range(10):
    #弱学习器的最大迭代次数，或者说最大的弱学习器的个数
    rfc = RandomForestClassifier(n_estimators=25)
    rfc_s = cross_val_score(rfc,wine.data,wine.target,cv=10).mean()
    rfc_l.append(rfc_s)
    clf = DecisionTreeClassifier()
    clf_s = cross_val_score(clf,wine.data,wine.target,cv=10).mean()
    clf_l.append(clf_s)

plt.plot(range(1,11),rfc_l,label="RandomForest")
plt.plot(range(1,11),clf_l,label="DecisionTree")
plt.legend()
plt.show()

1
2

rfc = RandomForestClassifier(n_estimators=25,random_state=2)#这里是森林生成的随机树模式固定，不是每个树都一致
rfc = rfc.fit(xtrain,ytrain)

1
2

#rfc.estimators_查看森林中所有树参数的状况，发现每个树只有random_state变了
rfc.estimators_[0].random_state

1872583848

1
2

for i in range(len(rfc.estimators_)):
    print(rfc.estimators_[i].random_state)

1872583848
794921487
111352301
1853453896
213298710
1922988331
1869695442
2081981515
1805465960
1376693511
1418777250
663257521
878959199
854108747
512264917
515183663
1287007039
2083814687
1146014426
570104212
520265852
1366773364
125164325
786090663
578016451

1
2
3
4
5

#无需划分训练集和测试集
rfc = RandomForestClassifier(n_estimators=25,oob_score=True)
rfc = rfc.fit(wine.data,wine.target)
#袋外数据评分
rfc.oob_score_

0.9606741573033708

1
2

rfc = RandomForestClassifier(n_estimators=25)
rfc = rfc.fit(xtrain,ytrain)

1

rfc.score(xtest,ytest)

0.9629629629629629

1

rfc.feature_importances_#特征重要性数值 #zip联系名字和特征值

array([0.09877403, 0.04378921, 0.00627884, 0.03234554, 0.06983567,
       0.0588977 , 0.17206286, 0.00407809, 0.01527506, 0.18783169,
       0.07655246, 0.11355569, 0.12072316])

1

rfc.apply(xtest)

array([[ 2,  8,  6, ...,  3,  4,  8],
       [ 2,  9,  9, ...,  4,  4,  8],
       [ 9, 15,  9, ...,  8,  1,  5],
       ...,
       [14, 18, 18, ..., 19,  8, 16],
       [ 7, 18, 15, ..., 19,  8, 16],
       [ 2,  8, 10, ..., 19,  4,  8]])

1

rfc.predict(xtest)#测试集预测结果

array([2, 2, 1, 0, 0, 1, 1, 0, 0, 2, 1, 1, 2, 2, 0, 0, 0, 2, 0, 0, 2, 1,
       1, 2, 1, 2, 1, 0, 2, 0, 1, 2, 0, 1, 2, 2, 1, 2, 0, 1, 1, 0, 2, 0,
       2, 2, 1, 0, 2, 0, 0, 0, 0, 2])

1

rfc.predict_proba(xtest)#多少样本多少行，多少特征多少列，按照平均值特征大小分类

array([[0.  , 0.04, 0.96],
       [0.  , 0.36, 0.64],
       [0.  , 1.  , 0.  ],
       [0.56, 0.4 , 0.04],
       [0.96, 0.04, 0.  ],
       [0.  , 1.  , 0.  ],
       [0.  , 1.  , 0.  ],
       [0.8 , 0.2 , 0.  ],
       [0.68, 0.28, 0.04],
       [0.  , 0.16, 0.84],
       [0.04, 0.96, 0.  ],
       [0.12, 0.88, 0.  ],
       [0.  , 0.32, 0.68],
       [0.  , 0.16, 0.84],
       [0.96, 0.04, 0.  ],
       [1.  , 0.  , 0.  ],
       [0.96, 0.04, 0.  ],
       [0.08, 0.  , 0.92],
       [0.96, 0.04, 0.  ],
       [0.84, 0.08, 0.08],
       [0.  , 0.4 , 0.6 ],
       [0.  , 1.  , 0.  ],
       [0.04, 0.96, 0.  ],
       [0.04, 0.28, 0.68],
       [0.  , 1.  , 0.  ],
       [0.  , 0.  , 1.  ],
       [0.08, 0.92, 0.  ],
       [0.88, 0.12, 0.  ],
       [0.  , 0.16, 0.84],
       [0.52, 0.48, 0.  ],
       [0.  , 0.88, 0.12],
       [0.  , 0.12, 0.88],
       [0.96, 0.04, 0.  ],
       [0.04, 0.88, 0.08],
       [0.  , 0.04, 0.96],
       [0.04, 0.28, 0.68],
       [0.04, 0.92, 0.04],
       [0.08, 0.12, 0.8 ],
       [0.68, 0.28, 0.04],
       [0.  , 0.88, 0.12],
       [0.04, 0.92, 0.04],
       [1.  , 0.  , 0.  ],
       [0.16, 0.24, 0.6 ],
       [0.64, 0.36, 0.  ],
       [0.  , 0.32, 0.68],
       [0.  , 0.  , 1.  ],
       [0.08, 0.92, 0.  ],
       [0.92, 0.08, 0.  ],
       [0.  , 0.  , 1.  ],
       [0.48, 0.48, 0.04],
       [1.  , 0.  , 0.  ],
       [1.  , 0.  , 0.  ],
       [0.8 , 0.2 , 0.  ],
       [0.16, 0.  , 0.84]])

1
2
3
4
5
6
7

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import load_boston
from sklearn.impute import SimpleImputer#填补缺失值的类
from sklearn.ensemble import RandomForestRegressor#随机森林回归器
from sklearn.model_selection import cross_val_score#交叉验证

1
2
3
4

boston = load_boston()
regressor = RandomForestRegressor(n_estimators=100,random_state=0)#实例化模型
cross_val_score(regressor,boston.data,boston.target,cv=10
                ,scoring="neg_mean_squared_error")

array([-11.22504076,  -5.3945749 ,  -4.74755867, -22.54699078,
       -12.31243335, -17.18030718,  -6.94019868, -94.14567212,
       -28.541145  , -14.6250416 ])

1
2
3

#sklearn当中的模型评估指标（打分）列表
import sklearn
sorted(sklearn.metrics.SCORERS.keys())

['accuracy',
 'adjusted_mutual_info_score',
 'adjusted_rand_score',
 'average_precision',
 'balanced_accuracy',
 'completeness_score',
 'explained_variance',
 'f1',
 'f1_macro',
 'f1_micro',
 'f1_samples',
 'f1_weighted',
 'fowlkes_mallows_score',
 'homogeneity_score',
 'jaccard',
 'jaccard_macro',
 'jaccard_micro',
 'jaccard_samples',
 'jaccard_weighted',
 'max_error',
 'mutual_info_score',
 'neg_brier_score',
 'neg_log_loss',
 'neg_mean_absolute_error',
 'neg_mean_absolute_percentage_error',
 'neg_mean_gamma_deviance',
 'neg_mean_poisson_deviance',
 'neg_mean_squared_error',
 'neg_mean_squared_log_error',
 'neg_median_absolute_error',
 'neg_root_mean_squared_error',
 'normalized_mutual_info_score',
 'precision',
 'precision_macro',
 'precision_micro',
 'precision_samples',
 'precision_weighted',
 'r2',
 'rand_score',
 'recall',
 'recall_macro',
 'recall_micro',
 'recall_samples',
 'recall_weighted',
 'roc_auc',
 'roc_auc_ovo',
 'roc_auc_ovo_weighted',
 'roc_auc_ovr',
 'roc_auc_ovr_weighted',
 'top_k_accuracy',
 'v_measure_score']

1

boston.target#标签是连续型变量做回归

array([24. , 21.6, 34.7, 33.4, 36.2, 28.7, 22.9, 27.1, 16.5, 18.9, 15. ,
       18.9, 21.7, 20.4, 18.2, 19.9, 23.1, 17.5, 20.2, 18.2, 13.6, 19.6,
       15.2, 14.5, 15.6, 13.9, 16.6, 14.8, 18.4, 21. , 12.7, 14.5, 13.2,
       13.1, 13.5, 18.9, 20. , 21. , 24.7, 30.8, 34.9, 26.6, 25.3, 24.7,
       21.2, 19.3, 20. , 16.6, 14.4, 19.4, 19.7, 20.5, 25. , 23.4, 18.9,
       35.4, 24.7, 31.6, 23.3, 19.6, 18.7, 16. , 22.2, 25. , 33. , 23.5,
       19.4, 22. , 17.4, 20.9, 24.2, 21.7, 22.8, 23.4, 24.1, 21.4, 20. ,
       20.8, 21.2, 20.3, 28. , 23.9, 24.8, 22.9, 23.9, 26.6, 22.5, 22.2,
       23.6, 28.7, 22.6, 22. , 22.9, 25. , 20.6, 28.4, 21.4, 38.7, 43.8,
       33.2, 27.5, 26.5, 18.6, 19.3, 20.1, 19.5, 19.5, 20.4, 19.8, 19.4,
       21.7, 22.8, 18.8, 18.7, 18.5, 18.3, 21.2, 19.2, 20.4, 19.3, 22. ,
       20.3, 20.5, 17.3, 18.8, 21.4, 15.7, 16.2, 18. , 14.3, 19.2, 19.6,
       23. , 18.4, 15.6, 18.1, 17.4, 17.1, 13.3, 17.8, 14. , 14.4, 13.4,
       15.6, 11.8, 13.8, 15.6, 14.6, 17.8, 15.4, 21.5, 19.6, 15.3, 19.4,
       17. , 15.6, 13.1, 41.3, 24.3, 23.3, 27. , 50. , 50. , 50. , 22.7,
       25. , 50. , 23.8, 23.8, 22.3, 17.4, 19.1, 23.1, 23.6, 22.6, 29.4,
       23.2, 24.6, 29.9, 37.2, 39.8, 36.2, 37.9, 32.5, 26.4, 29.6, 50. ,
       32. , 29.8, 34.9, 37. , 30.5, 36.4, 31.1, 29.1, 50. , 33.3, 30.3,
       34.6, 34.9, 32.9, 24.1, 42.3, 48.5, 50. , 22.6, 24.4, 22.5, 24.4,
       20. , 21.7, 19.3, 22.4, 28.1, 23.7, 25. , 23.3, 28.7, 21.5, 23. ,
       26.7, 21.7, 27.5, 30.1, 44.8, 50. , 37.6, 31.6, 46.7, 31.5, 24.3,
       31.7, 41.7, 48.3, 29. , 24. , 25.1, 31.5, 23.7, 23.3, 22. , 20.1,
       22.2, 23.7, 17.6, 18.5, 24.3, 20.5, 24.5, 26.2, 24.4, 24.8, 29.6,
       42.8, 21.9, 20.9, 44. , 50. , 36. , 30.1, 33.8, 43.1, 48.8, 31. ,
       36.5, 22.8, 30.7, 50. , 43.5, 20.7, 21.1, 25.2, 24.4, 35.2, 32.4,
       32. , 33.2, 33.1, 29.1, 35.1, 45.4, 35.4, 46. , 50. , 32.2, 22. ,
       20.1, 23.2, 22.3, 24.8, 28.5, 37.3, 27.9, 23.9, 21.7, 28.6, 27.1,
       20.3, 22.5, 29. , 24.8, 22. , 26.4, 33.1, 36.1, 28.4, 33.4, 28.2,
       22.8, 20.3, 16.1, 22.1, 19.4, 21.6, 23.8, 16.2, 17.8, 19.8, 23.1,
       21. , 23.8, 23.1, 20.4, 18.5, 25. , 24.6, 23. , 22.2, 19.3, 22.6,
       19.8, 17.1, 19.4, 22.2, 20.7, 21.1, 19.5, 18.5, 20.6, 19. , 18.7,
       32.7, 16.5, 23.9, 31.2, 17.5, 17.2, 23.1, 24.5, 26.6, 22.9, 24.1,
       18.6, 30.1, 18.2, 20.6, 17.8, 21.7, 22.7, 22.6, 25. , 19.9, 20.8,
       16.8, 21.9, 27.5, 21.9, 23.1, 50. , 50. , 50. , 50. , 50. , 13.8,
       13.8, 15. , 13.9, 13.3, 13.1, 10.2, 10.4, 10.9, 11.3, 12.3,  8.8,
        7.2, 10.5,  7.4, 10.2, 11.5, 15.1, 23.2,  9.7, 13.8, 12.7, 13.1,
       12.5,  8.5,  5. ,  6.3,  5.6,  7.2, 12.1,  8.3,  8.5,  5. , 11.9,
       27.9, 17.2, 27.5, 15. , 17.2, 17.9, 16.3,  7. ,  7.2,  7.5, 10.4,
        8.8,  8.4, 16.7, 14.2, 20.8, 13.4, 11.7,  8.3, 10.2, 10.9, 11. ,
        9.5, 14.5, 14.1, 16.1, 14.3, 11.7, 13.4,  9.6,  8.7,  8.4, 12.8,
       10.5, 17.1, 18.4, 15.4, 10.8, 11.8, 14.9, 12.6, 14.1, 13. , 13.4,
       15.2, 16.1, 17.8, 14.9, 14.1, 12.7, 13.5, 14.9, 20. , 16.4, 17.7,
       19.5, 20.2, 21.4, 19.9, 19. , 19.1, 19.1, 20.1, 19.9, 19.6, 23.2,
       29.8, 13.8, 13.3, 16.7, 12. , 14.6, 21.4, 23. , 23.7, 25. , 21.8,
       20.6, 21.2, 19.1, 20.6, 15.2,  7. ,  8.1, 13.6, 20.1, 21.8, 24.5,
       23.1, 19.7, 18.3, 21.2, 17.5, 16.8, 22.4, 20.6, 23.9, 22. , 11.9])

1
2

dataset = boston
dataset.data.shape

(506, 13)

1
2
3

X_full, y_full = dataset.data, dataset.target
n_samples = X_full.shape[0]#506
n_features = X_full.shape[1]#13

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26

#首先确定我们希望放入的缺失数据的比例，在这里我们假设是50%，那总共就要有3289个数据缺失

rng = np.random.RandomState(0)#设置一个随机种子，方便观察
missing_rate = 0.5
n_missing_samples = int(np.floor(n_samples * n_features * missing_rate))#3289
#np.floor向下取整，返回.0格式的浮点数

#所有数据要随机遍布在数据集的各行各列当中，而一个缺失的数据会需要一个行索引和一个列索引
#如果能够创造一个数组，包含3289个分布在0~506中间的行索引，和3289个分布在0~13之间的列索引，那我们就可以利用索引来为数据中的任意3289个位置赋空值
#然后我们用0，均值和随机森林来填写这些缺失值，然后查看回归的结果如何

missing_features = rng.randint(0,n_features,n_missing_samples)#randint（下限，上限，n）指在下限和上限之间取出n个整数
len(missing_features)#3289
missing_samples = rng.randint(0,n_samples,n_missing_samples)
len(missing_samples)#3289

#missing_samples = rng.choice(n_samples,n_missing_samples,replace=False)
#我们现在采样了3289个数据，远远超过我们的样本量506，所以我们使用随机抽取的函数randint。
# 但如果我们需要的数据量小于我们的样本量506，那我们可以采用np.random.choice来抽样，choice会随机抽取不重复的随机数，
# 因此可以帮助我们让数据更加分散，确保数据不会集中在一些行中!
#这里我们不采用np.random.choice,因为我们现在采样了3289个数据，远远超过我们的样本量506，使用np.random.choice会报错

X_missing = X_full.copy()
y_missing = y_full.copy()

X_missing[missing_samples,missing_features] = np.nan

1
2
3
4
5

X_missing = pd.DataFrame(X_missing)
#转换成DataFrame是为了后续方便各种操作，numpy对矩阵的运算速度快到拯救人生，但是在索引等功能上却不如pandas来得好用
X_missing.head()

#并没有对y_missing进行缺失值填补，原因是有监督学习，不能缺标签啊

前言

使用的相关数据链接如下：

点我跳转

数据预处理

无量纲化

1
2

#归一化 收到0~1之间
#正则化不是归一化

1
2
3
4
5
6
7
8

from sklearn.preprocessing import MinMaxScaler

data = [[-1, 2], [-0.5, 6], [0, 10], [1, 18]]

#不太熟悉numpy的小伙伴，能够判断data的结构吗？
#如果换成表是什么样子？
import pandas as pd
pd.DataFrame(data)

前言

数据集来自kaggle

链接：https://www.kaggle.com/c/titanic/data

里面的test和train的csv数据集为所需数据集。

代码

1
2
3

from sklearn import tree
from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split

1

wine = load_wine()

1

wine.data.shape

(178, 13)

1

wine.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, 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, 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])

1
2

import pandas as pd
pd.concat([pd.DataFrame(wine.data),pd.DataFrame(wine.target)],axis=1)

代码

1
2
3
4
5

import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split     #分割训练集和测试集
from sklearn.neighbors import KNeighborsClassifier       #K近邻

简单案例

1
2
3

iris=datasets.load_iris()
iris_X = iris.data
iris_y=iris.target

1

iris_X[:2,:]#四个属性两朵花

array([[5.1, 3.5, 1.4, 0.2],
       [4.9, 3. , 1.4, 0.2]])

1

iris_y#三类花

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])

1
2

#分割训练集和测试集
X_train,X_test,y_train,y_test=train_test_split(iris_X,iris_y,test_size=0.3)#测试占30%

1

y_train#顺便打乱了数据

array([0, 0, 2, 1, 0, 0, 2, 0, 0, 2, 0, 2, 1, 1, 2, 1, 2, 2, 2, 1, 2, 1,
       1, 0, 0, 2, 1, 1, 2, 1, 2, 1, 0, 2, 2, 0, 1, 1, 1, 0, 2, 0, 1, 0,
       1, 2, 2, 1, 0, 1, 2, 1, 2, 0, 2, 1, 2, 1, 1, 0, 0, 2, 2, 0, 1, 2,
       1, 0, 0, 0, 2, 0, 0, 1, 2, 2, 2, 1, 2, 1, 0, 1, 1, 0, 1, 2, 0, 2,
       1, 2, 0, 1, 0, 0, 0, 1, 1, 0, 0, 2, 2, 2, 0, 2, 0])

1
2

knn = KNeighborsClassifier() #使用K近邻分类
knn.fit(X_train,y_train)     #输入测试集

KNeighborsClassifier()

1

knn.predict(X_test)#预测

array([2, 2, 2, 1, 0, 2, 0, 2, 2, 0, 0, 0, 1, 0, 0, 2, 1, 0, 1, 1, 0, 2,
       2, 1, 1, 1, 0, 1, 0, 2, 2, 2, 2, 0, 1, 0, 1, 2, 2, 0, 1, 0, 1, 1,
       1])

1

y_test

array([2, 2, 2, 1, 0, 1, 0, 2, 2, 0, 0, 0, 2, 0, 0, 2, 1, 0, 1, 1, 0, 2,
       2, 1, 1, 1, 0, 1, 0, 2, 1, 2, 2, 0, 1, 0, 1, 2, 2, 0, 1, 0, 1, 1,
       1])

模型导入训练

1
2

from sklearn import datasets #导入基础数据
from sklearn.linear_model import LinearRegression  #导入模型

1
2
3
4

#导入数据
loaded_data = datasets.load_boston()
data_X = loaded_data.data
data_y = loaded_data.target

1
2
3

#定义模型并训练
model = LinearRegression()#线性模型
model.fit(data_X,data_y)

LinearRegression()

1
2

#预测
model.predict(data_X[:4,:])

array([30.00384338, 25.02556238, 30.56759672, 28.60703649])

1

data_y[:4]

array([24. , 21.6, 34.7, 33.4])

import matplotlib.pyplot as plt