关键词：
Table of Contents
初始
初识机器学习
python机器学习的生态圈
第一个机器学习项目
import numpy as np
import matplotlib.pyplot as plt
from pandas.plotting import scatter_matrix
import pandas as pd
机器学习中的hello world项目
(1)导入数据
(2)概述数据
(3)数据可视化
(4)评估算法
(5)实施预测
#导入类库
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
导入数据
#导入数据
filename=r'iris.data'
names=['separ-length','separ-width','petal-length','petal-width','class']
dataset=pd.read_table(filename,names=names,sep=',')
dataset
| separ-length | separ-width | petal-length | petal-width | class | |
|---|---|---|---|---|---|
| 0 | 5.1 | 3.5 | 1.4 | 0.2 | Iris-setosa |
| 1 | 4.9 | 3.0 | 1.4 | 0.2 | Iris-setosa |
| 2 | 4.7 | 3.2 | 1.3 | 0.2 | Iris-setosa |
| 3 | 4.6 | 3.1 | 1.5 | 0.2 | Iris-setosa |
| 4 | 5.0 | 3.6 | 1.4 | 0.2 | Iris-setosa |
| ... | ... | ... | ... | ... | ... |
| 145 | 6.7 | 3.0 | 5.2 | 2.3 | Iris-virginica |
| 146 | 6.3 | 2.5 | 5.0 | 1.9 | Iris-virginica |
| 147 | 6.5 | 3.0 | 5.2 | 2.0 | Iris-virginica |
| 148 | 6.2 | 3.4 | 5.4 | 2.3 | Iris-virginica |
| 149 | 5.9 | 3.0 | 5.1 | 1.8 | Iris-virginica |
150 rows × 5 columns
概述数据
dataset.skew()
separ-length 0.314911
separ-width 0.334053
petal-length -0.274464
petal-width -0.104997
dtype: float64
dataset.hist()
array([[<AxesSubplot:title='center':'separ-length'>,
<AxesSubplot:title='center':'separ-width'>],
[<AxesSubplot:title='center':'petal-length'>,
<AxesSubplot:title='center':'petal-width'>]], dtype=object)
dataset.plot(kind='density',subplots=True,layout=(2,2))
array([[<AxesSubplot:ylabel='Density'>, <AxesSubplot:ylabel='Density'>],
[<AxesSubplot:ylabel='Density'>, <AxesSubplot:ylabel='Density'>]],
dtype=object)
#查看数据维度
dataset.shape
(150, 5)
#查看自身
dataset.head(10)
| separ-length | separ-width | petal-length | petal-width | class | |
|---|---|---|---|---|---|
| 0 | 5.1 | 3.5 | 1.4 | 0.2 | Iris-setosa |
| 1 | 4.9 | 3.0 | 1.4 | 0.2 | Iris-setosa |
| 2 | 4.7 | 3.2 | 1.3 | 0.2 | Iris-setosa |
| 3 | 4.6 | 3.1 | 1.5 | 0.2 | Iris-setosa |
| 4 | 5.0 | 3.6 | 1.4 | 0.2 | Iris-setosa |
| 5 | 5.4 | 3.9 | 1.7 | 0.4 | Iris-setosa |
| 6 | 4.6 | 3.4 | 1.4 | 0.3 | Iris-setosa |
| 7 | 5.0 | 3.4 | 1.5 | 0.2 | Iris-setosa |
| 8 | 4.4 | 2.9 | 1.4 | 0.2 | Iris-setosa |
| 9 | 4.9 | 3.1 | 1.5 | 0.1 | Iris-setosa |
#统计描述数据
dataset.describe()
| separ-length | separ-width | petal-length | petal-width | |
|---|---|---|---|---|
| count | 150.000000 | 150.000000 | 150.000000 | 150.000000 |
| mean | 5.843333 | 3.054000 | 3.758667 | 1.198667 |
| std | 0.828066 | 0.433594 | 1.764420 | 0.763161 |
| min | 4.300000 | 2.000000 | 1.000000 | 0.100000 |
| 25% | 5.100000 | 2.800000 | 1.600000 | 0.300000 |
| 50% | 5.800000 | 3.000000 | 4.350000 | 1.300000 |
| 75% | 6.400000 | 3.300000 | 5.100000 | 1.800000 |
| max | 7.900000 | 4.400000 | 6.900000 | 2.500000 |
#数据分类分布
dataset.groupby('class').count()
| separ-length | separ-width | petal-length | petal-width | |
|---|---|---|---|---|
| class | ||||
| Iris-setosa | 50 | 50 | 50 | 50 |
| Iris-versicolor | 50 | 50 | 50 | 50 |
| Iris-virginica | 50 | 50 | 50 | 50 |
数据可视化
#单变量图表
#箱线图
plt.style.use('seaborn-notebook')
dataset.plot(kind='box',subplots=True,layout=(2,2),sharex=False,sharey=False)
separ-length AxesSubplot(0.125,0.536818;0.352273x0.343182)
separ-width AxesSubplot(0.547727,0.536818;0.352273x0.343182)
petal-length AxesSubplot(0.125,0.125;0.352273x0.343182)
petal-width AxesSubplot(0.547727,0.125;0.352273x0.343182)
dtype: object
#直方图
dataset.hist()
array([[<AxesSubplot:title='center':'separ-length'>,
<AxesSubplot:title='center':'separ-width'>],
[<AxesSubplot:title='center':'petal-length'>,
<AxesSubplot:title='center':'petal-width'>]], dtype=object)
#多变量图表
#散点矩阵图
pd.plotting.scatter_matrix(dataset)
array([[<AxesSubplot:xlabel='separ-length', ylabel='separ-length'>,
<AxesSubplot:xlabel='separ-width', ylabel='separ-length'>,
<AxesSubplot:xlabel='petal-length', ylabel='separ-length'>,
<AxesSubplot:xlabel='petal-width', ylabel='separ-length'>],
[<AxesSubplot:xlabel='separ-length', ylabel='separ-width'>,
<AxesSubplot:xlabel='separ-width', ylabel='separ-width'>,
<AxesSubplot:xlabel='petal-length', ylabel='separ-width'>,
<AxesSubplot:xlabel='petal-width', ylabel='separ-width'>],
[<AxesSubplot:xlabel='separ-length', ylabel='petal-length'>,
<AxesSubplot:xlabel='separ-width', ylabel='petal-length'>,
<AxesSubplot:xlabel='petal-length', ylabel='petal-length'>,
<AxesSubplot:xlabel='petal-width', ylabel='petal-length'>],
[<AxesSubplot:xlabel='separ-length', ylabel='petal-width'>,
<AxesSubplot:xlabel='separ-width', ylabel='petal-width'>,
<AxesSubplot:xlabel='petal-length', ylabel='petal-width'>,
<AxesSubplot:xlabel='petal-width', ylabel='petal-width'>]],
dtype=object)
评估算法
(1)分离出评估数据集
(2)采用10折交叉验证来评估算法模型
(3)生成6个不同的模型来预测新数据
(4)选择最优模型
分离评估数据集
X=np.array(dataset.iloc[:,0:4])
Y=np.array(dataset.iloc[:,4])
validation_size=0.2
seed=7
X_train,X_test,Y_train,Y_test=train_test_split(X,Y,test_size=validation_size,random_state=seed)
创建模型
models=
models['LR']=LogisticRegression(max_iter=1000)
models['LDA']=LinearDiscriminantAnalysis()
models['KNN']=KNeighborsClassifier()
models['CART']=DecisionTreeClassifier()
models['NB']=GaussianNB()
models['SVM']=SVC()
results=[]
for key in models:
kfold=KFold(n_splits=10,random_state=seed,shuffle=True)
cv_results=cross_val_score(models[key],X_train,Y_train,cv=kfold,scoring='accuracy')
results.append(cv_results)
print('%s:%f(%f)' %(key,cv_results.mean(),cv_results.std()))
LR:0.983333(0.033333)
LDA:0.975000(0.038188)
KNN:0.983333(0.033333)
CART:0.958333(0.076830)
NB:0.966667(0.040825)
SVM:0.983333(0.033333)
选择最优模型
plt.boxplot(results)
plt.xticks([i+1 for i in range(6)],models.keys())
([<matplotlib.axis.XTick at 0x17d53183250>,
<matplotlib.axis.XTick at 0x17d53183f40>,
<matplotlib.axis.XTick at 0x17d531aad00>,
<matplotlib.axis.XTick at 0x17d53644b80>,
<matplotlib.axis.XTick at 0x17d5364e0d0>,
<matplotlib.axis.XTick at 0x17d536448e0>],
[Text(1, 0, 'LR'),
Text(2, 0, 'LDA'),
Text(3, 0, 'KNN'),
Text(4, 0, 'CART'),
Text(5, 0, 'NB'),
Text(6, 0, 'SVM')])
实施预测
svm=SVC()
svm.fit(X=X_train,y=Y_train)
pred=svm.predict(X_test)
accuracy_score(Y_test,pred)
0.8666666666666667
confusion_matrix(Y_test,pred)
array([[ 7, 0, 0],
[ 0, 10, 2],
[ 0, 2, 9]], dtype=int64)
print(classification_report(Y_test,pred))
precision recall f1-score support
Iris-setosa 1.00 1.00 1.00 7
Iris-versicolor 0.83 0.83 0.83 12
Iris-virginica 0.82 0.82 0.82 11
accuracy 0.87 30
macro avg 0.88 0.88 0.88 30
weighted avg 0.87 0.87 0.87 30
数据准备
数据预处理
调整数据尺度
from sklearn import datasets
iris=datasets.load_iris()
from sklearn.preprocessing import MinMaxScaler
transformer=MinMaxScaler(feature_range=(0,1))#聚集到0附近，方差为1
newX=transformer.fit_transform(iris.data)
newX
array([[0.22222222, 0.625 , 0.06779661, 0.04166667],
[0.16666667, 0.41666667, 0.06779661, 0.04166667],
[0.11111111, 0.5 , 0.05084746, 0.04166667],
[0.08333333, 0.45833333, 0.08474576, 0.04166667],
[0.19444444, 0.66666667, 0.06779661, 0.04166667],
[0.30555556, 0.79166667, 0.11864407, 0.125 ],
[0.08333333, 0.58333333, 0.06779661, 0.08333333],
[0.19444444, 0.58333333, 0.08474576, 0.04166667],
[0.02777778, 0.375 , 0.06779661, 0.04166667],
[0.16666667, 0.45833333, 0.08474576, 0. ],
[0.30555556, 0.70833333, 0.08474576, 0.04166667],
[0.13888889, 0.58333333, 0.10169492, 0.04166667],
[0.13888889, 0.41666667, 0.06779661, 0. ],
[0. , 0.41666667, 0.01694915, 0. ],
[0.41666667, 0.83333333, 0.03389831, 0.04166667],
[0.38888889, 1. , 0.08474576, 0.125 ],
[0.30555556, 0.79166667, 0.05084746, 0.125 ],
[0.22222222, 0.625 , 0.06779661, 0.08333333],
[0.38888889, 0.75 , 0.11864407, 0.08333333],
[0.22222222, 0.75 , 0.08474576, 0.08333333],
[0.30555556, 0.58333333, 0.11864407, 0.04166667],
[0.22222222, 0.70833333, 0.08474576, 0.125 ],
[0.08333333, 0.66666667, 0. , 0.04166667],
[0.22222222, 0.54166667, 0.11864407, 0.16666667],
[0.13888889, 0.58333333, 0.15254237, 0.04166667],
[0.19444444, 0.41666667, 0.10169492, 0.04166667],
[0.19444444, 0.58333333, 0.10169492, 0.125 ],
[0.25 , 0.625 , 0.08474576, 0.04166667],
[0.25 , 0.58333333, 0.06779661, 0.04166667],
[0.11111111, 0.5 , 0.10169492, 0.04166667],
[0.13888889, 0.45833333, 0.10169492, 0.04166667],
[0.30555556, 0.58333333, 0.08474576, 0.125 ],
[0.25 , 0.875 , 0.08474576, 0. ],
[0.33333333, 0.91666667, 0.06779661, 0.04166667],
[0.16666667, 0.45833333, 0.08474576, 0.04166667],
[0.19444444, 0.5 , 0.03389831, 0.04166667],
[0.33333333, 0.625 , 0.05084746, 0.04166667],
[0.16666667, 0.66666667, 0.06779661, 0. ],
[0.02777778, 0.41666667, 0.05084746, 0.04166667],
[0.22222222, 0.58333333, 0.08474576, 0.04166667],
[0.19444444, 0.625 , 0.05084746, 0.08333333],
[0.05555556, 0.125 , 0.05084746, 0.08333333],
[0.02777778, 0.5 , 0.05084746, 0.04166667],
[0.19444444, 0.625 , 0.10169492, 0.20833333],
[0.22222222, 0.75 , 0.15254237, 0.125 ],
[0.13888889, 0.41666667, 0.06779661, 0.08333333],
[0.22222222, 0.75 , 0.10169492, 0.04166667],
[0.08333333, 0.5 , 0.06779661, 0.04166667],
[0.27777778, 0.70833333, 0.08474576, 0.04166667],
[0.19444444, 0.54166667, 0.06779661, 0.04166667],
[0.75 , 0.5 , 0.62711864, 0.54166667],
[0.58333333, 0.5 , 0.59322034, 0.58333333],
[0.72222222, 0.45833333, 0.66101695, 0.58333333],
[0.33333333, 0.125 , 0.50847458, 0.5 ],
[0.61111111, 0.33333333, 0.61016949, 0.58333333],
[0.38888889, 0.33333333, 0.59322034, 0.5 ],
[0.55555556, 0.54166667, 0.62711864, 0.625 ],
[0.16666667, 0.16666667, 0.38983051, 0.375 ],
[0.63888889, 0.375 , 0.61016949, 0.5 ],
[0.25 , 0.29166667, 0.49152542, 0.54166667],
[0.19444444, 0. , 0.42372881, 0.375 ],
[0.44444444, 0.41666667, 0.54237288, 0.58333333],
[0.47222222, 0.08333333, 0.50847458, 0.375 ],
[0.5 , 0.375 , 0.62711864, 0.54166667],
[0.36111111, 0.375 , 0.44067797, 0.5 ],
[0.66666667, 0.45833333, 0.57627119, 0.54166667],
[0.36111111, 0.41666667, 0.59322034, 0.58333333],
[0.41666667, 0.29166667, 0.52542373, 0.375 ],
[0.52777778, 0.08333333, 0.59322034, 0.58333333],
[0.36111111, 0.20833333, 0.49152542, 0.41666667],
[0.44444444, 0.5 , 0.6440678 , 0.70833333],
[0.5 , 0.33333333, 0.50847458, 0.5 ],
[0.55555556, 0.20833333, 0.66101695, 0.58333333],
[0.5 , 0.33333333, 0.62711864, 0.45833333],
[0.58333333, 0.375 , 0.55932203, 0.5 ],
[0.63888889, 0.41666667, 0.57627119, 0.54166667],
[0.69444444, 0.33333333, 0.6440678 , 0.54166667],
[0.66666667, 0.41666667, 0.6779661 , 0.66666667],
[0.47222222, 0.375 , 0.59322034, 0.58333333],
[0.38888889, 0.25 , 0.42372881, 0.375 ],
[0.33333333, 0.16666667, 0.47457627, 0.41666667],
[0.33333333, 0.16666667, 0.45762712, 0.375 ],
[0.41666667, 0.29166667, 0.49152542, 0.45833333],
[0.47222222, 0.29166667, 0.69491525, 0.625 ],
[0.30555556, 0.41666667, 0.59322034, 0.58333333],
[0.47222222, 0.58333333, 0.59322034, 0.625 ],
[0.66666667, 0.45833333, 0.62711864, 0.58333333],
[0.55555556, 0.125 , 0.57627119, 0.5 ],
[0.36111111, 0.41666667, 0.52542373, 0.5 ],
[0.33333333, 0.20833333, 0.50847458, 0.5 ],
[0.33333333, 0.25 , 0.57627119, 0.45833333],
[0.5 , 0.41666667, 0.61016949, 0.54166667],
[0.41666667, 0.25 , 0.50847458, 0.45833333],
[0.19444444, 0.125 , 0.38983051, 0.375 ],
[0.36111111, 0.29166667, 0.54237288, 0.5 ],
[0.38888889, 0.41666667, 0.54237288, 0.45833333],
[0.38888889, 0.375 , 0.54237288, 0.5 ],
[0.52777778, 0.375 , 0.55932203, 0.5 ],
[0.22222222, 0.20833333, 0.33898305, 0.41666667],
[0.38888889, 0.33333333, 0.52542373, 0.5 ],
[0.55555556, 0.54166667, 0.84745763, 1. ],
[0.41666667, 0.29166667, 0.69491525, 0.75 ],
[0.77777778, 0.41666667, 0.83050847, 0.83333333],
[0.55555556, 0.375 , 0.77966102, 0.70833333],
[0.61111111, 0.41666667, 0.81355932, 0.875 ],
[0.91666667, 0.41666667, 0.94915254, 0.83333333],
[0.16666667, 0.20833333, 0.59322034, 0.66666667],
[0.83333333, 0.375 , 0.89830508, 0.70833333],
[0.66666667, 0.20833333, 0.81355932, 0.70833333],
[0.80555556, 0.66666667, 0.86440678, 1. ],
[0.61111111, 0.5 , 0.69491525, 0.79166667],
[0.58333333, 0.29166667, 0.72881356, 0.75 ],
[0.69444444, 0.41666667, 0.76271186, 0.83333333],
[0.38888889, 0.20833333, 0.6779661 , 0.79166667],
[0.41666667, 0.33333333, 0.69491525, 0.95833333],
[0.58333333, 0.5 , 0.72881356, 0.91666667],
[0.61111111, 0.41666667, 0.76271186, 0.70833333],
[0.94444444, 0.75 , 0.96610169, 0.875 ],
[0.94444444, 0.25 , 1. , 0.91666667],
[0.47222222, 0.08333333, 0.6779661 , 0.58333333],
[0.72222222, 0.5 , 0.79661017, 0.91666667],
[0.36111111, 0.33333333, 0.66101695, 0.79166667],
[0.94444444, 0.33333333, 0.96610169, 0.79166667],
[0.55555556, 0.29166667, 0.66101695, 0.70833333],
[0.66666667, 0.54166667, 0.79661017, 0.83333333],
[0.80555556, 0.5 , 0.84745763, 0.70833333],
[0.52777778, 0.33333333, 0.6440678 , 0.70833333],
[0.5 , 0.41666667, 0.66101695, 0.70833333],
[0.58333333, 0.33333333, 0.77966102, 0.83333333],
[0.80555556, 0.41666667, 0.81355932, 0.625 ],
[0.86111111, 0.33333333, 0.86440678, 0.75 ],
[1. , 0.75 , 0.91525424, 0.79166667],
[0.58333333, 0.33333333, 0.77966102, 0.875 ],
[0.55555556, 0.33333333, 0.69491525, 0.58333333],
[0.5 , 0.25 , 0.77966102, 0.54166667],
[0.94444444, 0.41666667, 0.86440678, 0.91666667],
[0.55555556, 0.58333333, 0.77966102, 0.95833333],
[0.58333333, 0.45833333, 0.76271186, 0.70833333],
[0.47222222, 0.41666667, 0.6440678 , 0.70833333],
[0.72222222, 0.45833333, 0.74576271, 0.83333333],
[0.66666667, 0.45833333, 0.77966102, 0.95833333],
[0.72222222, 0.45833333, 0.69491525, 0.91666667],
[0.41666667, 0.29166667, 0.69491525, 0.75 ],
[0.69444444, 0.5 , 0.83050847, 0.91666667],
[0.66666667, 0.54166667, 0.79661017, 1. ],
[0.66666667, 0.41666667, 0.71186441, 0.91666667],
[0.55555556, 0.20833333, 0.6779661 , 0.75 ],
[0.61111111, 0.41666667, 0.71186441, 0.79166667],
[0.52777778, 0.58333333, 0.74576271, 0.91666667],
[0.44444444, 0.41666667, 0.69491525, 0.70833333]])
正态化数据
from sklearn.preprocessing import StandardScaler
transformer=StandardScaler()
newX=transformer.fit_transform(iris.data)
newX
array([[-9.00681170e-01, 1.01900435e+00, -1.34022653e+00,
-1.31544430e+00],
[-1.14301691e+00, -1.31979479e-01, -1.34022653e+00,
-1.31544430e+00],
[-1.38535265e+00, 3.28414053e-01, -1.39706395e+00,
-1.31544430e+00],
[-1.50652052e+00, 9.82172869e-02, -1.28338910e+00,
-1.31544430e+00],
[-1.02184904e+00, 1.24920112e+00, -1.34022653e+00,
-1.31544430e+00],
[-5.37177559e-01, 1.93979142e+00, -1.16971425e+00,
-1.05217993e+00],
[-1.50652052e+00, 7.88807586e-01, -1.34022653e+00,
-1.18381211e+00],
[-1.02184904e+00, 7.88807586e-01, -1.28338910e+00,
-1.31544430e+00],
[-1.74885626e+00, -3.62176246e-01, -1.34022653e+00,
-1.31544430e+00],
[-1.14301691e+00, 9.82172869e-02, -1.28338910e+00,
-1.44707648e+00],
[-5.37177559e-01, 1.47939788e+00, -1.28338910e+00,
-1.31544430e+00],
[-1.26418478e+00, 7.88807586e-01, -1.22655167e+00,
-1.31544430e+00],
[-1.26418478e+00, -1.31979479e-01, -1.34022653e+00,
-1.44707648e+00],
[-1.87002413e+00, -1.31979479e-01, -1.51073881e+00,
-1.44707648e+00],
[-5.25060772e-02, 2.16998818e+00, -1.45390138e+00,
-1.31544430e+00],
[-1.73673948e-01, 3.09077525e+00, -1.28338910e+00,
-1.05217993e+00],
[-5.37177559e-01, 1.93979142e+00, -1.39706395e+00,
-1.05217993e+00],
[-9.00681170e-01, 1.01900435e+00, -1.34022653e+00,
-1.18381211e+00],
[-1.73673948e-01, 1.70959465e+00, -1.16971425e+00,
-1.18381211e+00],
[-9.00681170e-01, 1.70959465e+00, -1.28338910e+00,
-1.18381211e+00],
[-5.37177559e-01, 7.88807586e-01, -1.16971425e+00,
-1.31544430e+00],
[-9.00681170e-01, 1.47939788e+00, -1.28338910e+00,
-1.05217993e+00],
[-1.50652052e+00, 1.24920112e+00, -1.56757623e+00,
-1.31544430e+00],
[-9.00681170e-01, 5.58610819e-01, -1.16971425e+00,
-9.20547742e-01],
[-1.26418478e+00, 7.88807586e-01, -1.05603939e+00,
-1.31544430e+00],
[-1.02184904e+00, -1.31979479e-01, -1.22655167e+00,
-1.31544430e+00],
[-1.02184904e+00, 7.88807586e-01, -1.22655167e+00,
-1.05217993e+00],
[-7.79513300e-01, 1.01900435e+00, -1.28338910e+00,
-1.31544430e+00],
[-7.79513300e-01, 7.88807586e-01, -1.34022653e+00,
-1.31544430e+00],
[-1.38535265e+00, 3.28414053e-01, -1.22655167e+00,
-1.31544430e+00],
[-1.26418478e+00, 9.82172869e-02, -1.22655167e+00,
-1.31544430e+00],
[-5.37177559e-01, 7.88807586e-01, -1.28338910e+00,
-1.05217993e+00],
[-7.79513300e-01, 2.40018495e+00, -1.28338910e+00,
-1.44707648e+00],
[-4.16009689e-01, 2.63038172e+00, -1.34022653e+00,
-1.31544430e+00],
[-1.14301691e+00, 9.82172869e-02, -1.28338910e+00,
-1.31544430e+00],
[-1.02184904e+00, 3.28414053e-01, -1.45390138e+00,
-1.31544430e+00],
[-4.16009689e-01, 1.01900435e+00, -1.39706395e+00,
-1.31544430e+00],
[-1.14301691e+00, 1.24920112e+00, -1.34022653e+00,
-1.44707648e+00],
[-1.74885626e+00, -1.31979479e-01, -1.39706395e+00,
-1.31544430e+00],
[-9.00681170e-01, 7.88807586e-01, -1.28338910e+00,
-1.31544430e+00],
[-1.02184904e+00, 1.01900435e+00, -1.39706395e+00,
-1.18381211e+00],
[-1.62768839e+00, -1.74335684e+00, -1.39706395e+00,
-1.18381211e+00],
[-1.74885626e+00, 3.28414053e-01, -1.39706395e+00,
-1.31544430e+00],
[-1.02184904e+00, 1.01900435e+00, -1.22655167e+00,
-7.88915558e-01],
[-9.00681170e-01, 1.70959465e+00, -1.05603939e+00,
-1.05217993e+00],
[-1.26418478e+00, -1.31979479e-01, -1.34022653e+00,
-1.18381211e+00],
[-9.00681170e-01, 1.70959465e+00, -1.22655167e+00,
-1.31544430e+00],
[-1.50652052e+00, 3.28414053e-01, -1.34022653e+00,
-1.31544430e+00],
[-6.58345429e-01, 1.47939788e+00, -1.28338910e+00,
-1.31544430e+00],
[-1.02184904e+00, 5.58610819e-01, -1.34022653e+00,
-1.31544430e+00],
[ 1.40150837e+00, 3.28414053e-01, 5.35408562e-01,
2.64141916e-01],
[ 6.74501145e-01, 3.28414053e-01, 4.21733708e-01,
3.95774101e-01],
[ 1.28034050e+00, 9.82172869e-02, 6.49083415e-01,
3.95774101e-01],
[-4.16009689e-01, -1.74335684e+00, 1.37546573e-01,
1.32509732e-01],
[ 7.95669016e-01, -5.92373012e-01, 4.78571135e-01,
3.95774101e-01],
[-1.73673948e-01, -5.92373012e-01, 4.21733708e-01,
1.32509732e-01],
[ 5.53333275e-01, 5.58610819e-01, 5.35408562e-01,
5.27406285e-01],
[-1.14301691e+00, -1.51316008e+00, -2.60315415e-01,
-2.62386821e-01],
[ 9.16836886e-01, -3.62176246e-01, 4.78571135e-01,
1.32509732e-01],
[-7.79513300e-01, -8.22569778e-01, 8.07091462e-02,
2.64141916e-01],
[-1.02184904e+00, -2.43394714e+00, -1.46640561e-01,
-2.62386821e-01],
[ 6.86617933e-02, -1.31979479e-01, 2.51221427e-01,
3.95774101e-01],
[ 1.89829664e-01, -1.97355361e+00, 1.37546573e-01,
-2.62386821e-01],
[ 3.10997534e-01, -3.62176246e-01, 5.35408562e-01,
2.64141916e-01],
[-2.94841818e-01, -3.62176246e-01, -8.98031345e-02,
1.32509732e-01],
[ 1.03800476e+00, 9.82172869e-02, 3.64896281e-01,
2.64141916e-01],
[-2.94841818e-01, -1.31979479e-01, 4.21733708e-01,
3.95774101e-01],
[-5.25060772e-02, -8.22569778e-01, 1.94384000e-01,
-2.62386821e-01],
[ 4.32165405e-01, -1.97355361e+00, 4.21733708e-01,
3.95774101e-01],
[-2.94841818e-01, -1.28296331e+00, 8.07091462e-02,
-1.30754636e-01],
[ 6.86617933e-02, 3.28414053e-01, 5.92245988e-01,
7.90670654e-01],
[ 3.10997534e-01, -5.92373012e-01, 1.37546573e-01,
1.32509732e-01],
[ 5.53333275e-01, -1.28296331e+00, 6.49083415e-01,
3.95774101e-01],
[ 3.10997534e-01, -5.92373012e-01, 5.35408562e-01,
8.77547895e-04],
[ 6.74501145e-01, -3.62176246e-01, 3.08058854e-01,
1.32509732e-01],
[ 9.16836886e-01, -1.31979479e-01, 3.64896281e-01,
2.64141916e-01],
[ 1.15917263e+00, -5.92373012e-01, 5.92245988e-01,
2.64141916e-01],
[ 1.03800476e+00, -1.31979479e-01, 7.05920842e-01,
6.59038469e-01],
[ 1.89829664e-01, -3.62176246e-01, 4.21733708e-01,
3.95774101e-01],
[-1.73673948e-01, -1.05276654e+00, -1.46640561e-01,
-2.62386821e-01],
[-4.16009689e-01, -1.51316008e+00, 2.38717193e-02,
-1.30754636e-01],
[-4.16009689e-01, -1.51316008e+00, -3.29657076e-02,
-2.62386821e-01],
[-5.25060772e-02, -8.22569778e-01, 8.07091462e-02,
8.77547895e-04],
[ 1.89829664e-01, -8.22569778e-01, 7.62758269e-01,
5.27406285e-01],
[-5.37177559e-01, -1.31979479e-01, 4.21733708e-01,
3.95774101e-01],
[ 1.89829664e-01, 7.88807586e-01, 4.21733708e-01,
5.27406285e-01],
[ 1.03800476e+00, 9.82172869e-02, 5.35408562e-01,
3.95774101e-01],
[ 5.53333275e-01, -1.74335684e+00, 3.64896281e-01,
1.32509732e-01],
[-2.94841818e-01, -1.31979479e-01, 1.94384000e-01,
1.32509732e-01],
[-4.16009689e-01, -1.28296331e+00, 1.37546573e-01,
1.32509732e-01],
[-4.16009689e-01, -1.05276654e+00, 3.64896281e-01,
8.77547895e-04],
[ 3.10997534e-01, -1.31979479e-01, 4.78571135e-01,
2.64141916e-01],
[-5.25060772e-02, -1.05276654e+00, 1.37546573e-01,
8.77547895e-04],
[-1.02184904e+00, -1.74335684e+00, -2.60315415e-01,
-2.62386821e-01],
[-2.94841818e-01, -8.22569778e-01, 2.51221427e-01,
1.32509732e-01],
[-1.73673948e-01, -1.31979479e-01, 2.51221427e-01,
8.77547895e-04],
[-1.73673948e-01, -3.62176246e-01, 2.51221427e-01,
1.32509732e-01],
[ 4.32165405e-01, -3.62176246e-01, 3.08058854e-01,
1.32509732e-01],
[-9.00681170e-01, -1.28296331e+00, -4.30827696e-01,
-1.30754636e-01],
[-1.73673948e-01, -5.92373012e-01, 1.94384000e-01,
1.32509732e-01],
[ 5.53333275e-01, 5.58610819e-01, 1.27429511e+00,
1.71209594e+00],
[-5.25060772e-02, -8.22569778e-01, 7.62758269e-01,
9.22302838e-01],
[ 1.52267624e+00, -1.31979479e-01, 1.21745768e+00,
1.18556721e+00],
[ 5.53333275e-01, -3.62176246e-01, 1.04694540e+00,
7.90670654e-01],
[ 7.95669016e-01, -1.31979479e-01, 1.16062026e+00,
1.31719939e+00],
[ 2.12851559e+00, -1.31979479e-01, 1.61531967e+00,
1.18556721e+00],
[-1.14301691e+00, -1.28296331e+00, 4.21733708e-01,
6.59038469e-01],
[ 1.76501198e+00, -3.62176246e-01, 1.44480739e+00,
7.90670654e-01],
[ 1.03800476e+00, -1.28296331e+00, 1.16062026e+00,
7.90670654e-01],
[ 1.64384411e+00, 1.24920112e+00, 1.33113254e+00,
1.71209594e+00],
[ 7.95669016e-01, 3.28414053e-01, 7.62758269e-01,
1.05393502e+00],
[ 6.74501145e-01, -8.22569778e-01, 8.76433123e-01,
9.22302838e-01],
[ 1.15917263e+00, -1.31979479e-01, 9.90107977e-01,
1.18556721e+00],
[-1.73673948e-01, -1.28296331e+00, 7.05920842e-01,
1.05393502e+00],
[-5.25060772e-02, -5.92373012e-01, 7.62758269e-01,
1.58046376e+00],
[ 6.74501145e-01, 3.28414053e-01, 8.76433123e-01,
1.44883158e+00],
[ 7.95669016e-01, -1.31979479e-01, 9.90107977e-01,
7.90670654e-01],
[ 2.24968346e+00, 1.70959465e+00, 1.67215710e+00,
1.31719939e+00],
[ 2.24968346e+00, -1.05276654e+00, 1.78583195e+00,
1.44883158e+00],
[ 1.89829664e-01, -1.97355361e+00, 7.05920842e-01,
3.95774101e-01],
[ 1.28034050e+00, 3.28414053e-01, 1.10378283e+00,
1.44883158e+00],
[-2.94841818e-01, -5.92373012e-01, 6.49083415e-01,
1.05393502e+00],
[ 2.24968346e+00, -5.92373012e-01, 1.67215710e+00,
1.05393502e+00],
[ 5.53333275e-01, -8.22569778e-01, 6.49083415e-01,
7.90670654e-01],
[ 1.03800476e+00, 5.58610819e-01, 1.10378283e+00,
1.18556721e+00],
[ 1.64384411e+00, 3.28414053e-01, 1.27429511e+00,
7.90670654e-01],
[ 4.32165405e-01, -5.92373012e-01, 5.92245988e-01,
7.90670654e-01],
[ 3.10997534e-01, -1.31979479e-01, 6.49083415e-01,
7.90670654e-01],
[ 6.74501145e-01, -5.92373012e-01, 1.04694540e+00,
1.18556721e+00],
[ 1.64384411e+00, -1.31979479e-01, 1.16062026e+00,
5.27406285e-01],
[ 1.88617985e+00, -5.92373012e-01, 1.33113254e+00,
9.22302838e-01],
[ 2.49201920e+00, 1.70959465e+00, 1.50164482e+00,
1.05393502e+00],
[ 6.74501145e-01, -5.92373012e-01, 1.04694540e+00,
1.31719939e+00],
[ 5.53333275e-01, -5.92373012e-01, 7.62758269e-01,
3.95774101e-01],
[ 3.10997534e-01, -1.05276654e+00, 1.04694540e+00,
2.64141916e-01],
[ 2.24968346e+00, -1.31979479e-01, 1.33113254e+00,
1.44883158e+00],
[ 5.53333275e-01, 7.88807586e-01, 1.04694540e+00,
1.58046376e+00],
[ 6.74501145e-01, 9.82172869e-02, 9.90107977e-01,
7.90670654e-01],
[ 1.89829664e-01, -1.31979479e-01, 5.92245988e-01,
7.90670654e-01],
[ 1.28034050e+00, 9.82172869e-02, 9.33270550e-01,
1.18556721e+00],
[ 1.03800476e+00, 9.82172869e-02, 1.04694540e+00,
1.58046376e+00],
[ 1.28034050e+00, 9.82172869e-02, 7.62758269e-01,
1.44883158e+00],
[-5.25060772e-02, -8.22569778e-01, 7.62758269e-01,
9.22302838e-01],
[ 1.15917263e+00, 3.28414053e-01, 1.21745768e+00,
1.44883158e+00],
[ 1.03800476e+00, 5.58610819e-01, 1.10378283e+00,
1.71209594e+00],
[ 1.03800476e+00, -1.31979479e-01, 8.19595696e-01,
1.44883158e+00],
[ 5.53333275e-01, -1.28296331e+00, 7.05920842e-01,
9.22302838e-01],
[ 7.95669016e-01, -1.31979479e-01, 8.19595696e-01,
1.05393502e+00],
[ 4.32165405e-01, 7.88807586e-01, 9.33270550e-01,
1.44883158e+00],
[ 6.86617933e-02, -1.31979479e-01, 7.62758269e-01,
7.90670654e-01]])
标准化数据
from sklearn.preprocessing import Normalizer
transformer=Normalizer()
newX=transformer.fit_transform(iris.data)
newX
array([[0.80377277, 0.55160877, 0.22064351, 0.0315205 ],
[0.82813287, 0.50702013, 0.23660939, 0.03380134],
[0.80533308, 0.54831188, 0.2227517 , 0.03426949],
[0.80003025, 0.53915082, 0.26087943, 0.03478392],
[0.790965 , 0.5694948 , 0.2214702 , 0.0316386 ],
[0.78417499, 0.5663486 , 0.2468699 , 0.05808704],
[0.78010936, 0.57660257, 0.23742459, 0.0508767 ],
[0.80218492, 0.54548574, 0.24065548, 0.0320874 ],
[0.80642366, 0.5315065 , 0.25658935, 0.03665562],
[0.81803119, 0.51752994, 0.25041771, 0.01669451],
[0.80373519, 0.55070744, 0.22325977, 0.02976797],
[0.786991 , 0.55745196, 0.26233033, 0.03279129],
[0.82307218, 0.51442011, 0.24006272, 0.01714734],
[0.8025126 , 0.55989251, 0.20529392, 0.01866308],
[0.81120865, 0.55945424, 0.16783627, 0.02797271],
[0.77381111, 0.59732787, 0.2036345 , 0.05430253],
[0.79428944, 0.57365349, 0.19121783, 0.05883625],
[0.80327412, 0.55126656, 0.22050662, 0.04725142],
[0.8068282 , 0.53788547, 0.24063297, 0.04246464],
[0.77964883, 0.58091482, 0.22930848, 0.0458617 ],
[0.8173379 , 0.51462016, 0.25731008, 0.03027177],
[0.78591858, 0.57017622, 0.23115252, 0.06164067],
[0.77577075, 0.60712493, 0.16864581, 0.03372916],
[0.80597792, 0.52151512, 0.26865931, 0.07901744],
[0.776114 , 0.54974742, 0.30721179, 0.03233808],
[0.82647451, 0.4958847 , 0.26447184, 0.03305898],
[0.79778206, 0.5424918 , 0.25529026, 0.06382256],
[0.80641965, 0.54278246, 0.23262105, 0.03101614],
[0.81609427, 0.5336001 , 0.21971769, 0.03138824],
[0.79524064, 0.54144043, 0.27072022, 0.03384003],
[0.80846584, 0.52213419, 0.26948861, 0.03368608],
[0.82225028, 0.51771314, 0.22840286, 0.06090743],
[0.76578311, 0.60379053, 0.22089897, 0.0147266 ],
[0.77867447, 0.59462414, 0.19820805, 0.02831544],
[0.81768942, 0.51731371, 0.25031309, 0.03337508],
[0.82512295, 0.52807869, 0.19802951, 0.03300492],
[0.82699754, 0.52627116, 0.19547215, 0.03007264],
[0.78523221, 0.5769053 , 0.22435206, 0.01602515],
[0.80212413, 0.54690282, 0.23699122, 0.03646019],
[0.80779568, 0.53853046, 0.23758697, 0.03167826],
[0.80033301, 0.56023311, 0.20808658, 0.04801998],
[0.86093857, 0.44003527, 0.24871559, 0.0573959 ],
[0.78609038, 0.57170209, 0.23225397, 0.03573138],
[0.78889479, 0.55222635, 0.25244633, 0.09466737],
[0.76693897, 0.57144472, 0.28572236, 0.06015208],
[0.82210585, 0.51381615, 0.23978087, 0.05138162],
[0.77729093, 0.57915795, 0.24385598, 0.030482 ],
[0.79594782, 0.55370283, 0.24224499, 0.03460643],
[0.79837025, 0.55735281, 0.22595384, 0.03012718],
[0.81228363, 0.5361072 , 0.22743942, 0.03249135],
[0.76701103, 0.35063361, 0.51499312, 0.15340221],
[0.74549757, 0.37274878, 0.52417798, 0.17472599],
[0.75519285, 0.33928954, 0.53629637, 0.16417236],
[0.75384916, 0.31524601, 0.54825394, 0.17818253],
[0.7581754 , 0.32659863, 0.5365549 , 0.17496355],
[0.72232962, 0.35482858, 0.57026022, 0.16474184],
[0.72634846, 0.38046824, 0.54187901, 0.18446945],
[0.75916547, 0.37183615, 0.51127471, 0.15493173],
[0.76301853, 0.33526572, 0.53180079, 0.15029153],
[0.72460233, 0.37623583, 0.54345175, 0.19508524],
[0.76923077, 0.30769231, 0.53846154, 0.15384615],
[0.73923462, 0.37588201, 0.52623481, 0.187941 ],
[0.78892752, 0.28927343, 0.52595168, 0.13148792],
[0.73081412, 0.34743622, 0.56308629, 0.16772783],
[0.75911707, 0.3931142 , 0.48800383, 0.17622361],
[0.76945444, 0.35601624, 0.50531337, 0.16078153],
[0.70631892, 0.37838513, 0.5675777 , 0.18919257],
[0.75676497, 0.35228714, 0.53495455, 0.13047672],
[0.76444238, 0.27125375, 0.55483721, 0.18494574],
[0.76185188, 0.34011245, 0.53057542, 0.14964948],
[0.6985796 , 0.37889063, 0.56833595, 0.21312598],
[0.77011854, 0.35349703, 0.50499576, 0.16412362],
[0.74143307, 0.29421947, 0.57667016, 0.17653168],
[0.73659895, 0.33811099, 0.56754345, 0.14490471],
[0.76741698, 0.34773582, 0.51560829, 0.15588157],
[0.76785726, 0.34902603, 0.51190484, 0.16287881],
[0.76467269, 0.31486523, 0.53976896, 0.15743261],
[0.74088576, 0.33173989, 0.55289982, 0.18798594],
[0.73350949, 0.35452959, 0.55013212, 0.18337737],
[0.78667474, 0.35883409, 0.48304589, 0.13801311],
[0.76521855, 0.33391355, 0.52869645, 0.15304371],
[0.77242925, 0.33706004, 0.51963422, 0.14044168],
[0.76434981, 0.35581802, 0.51395936, 0.15814134],
[0.70779525, 0.31850786, 0.60162596, 0.1887454 ],
[0.69333409, 0.38518561, 0.57777841, 0.1925928 ],
[0.71524936, 0.40530797, 0.53643702, 0.19073316],
[0.75457341, 0.34913098, 0.52932761, 0.16893434],
[0.77530021, 0.28304611, 0.54147951, 0.15998258],
[0.72992443, 0.39103094, 0.53440896, 0.16944674],
[0.74714194, 0.33960997, 0.54337595, 0.17659719],
[0.72337118, 0.34195729, 0.57869695, 0.15782644],
[0.73260391, 0.36029701, 0.55245541, 0.1681386 ],
[0.76262994, 0.3《python机器学习及实践》----监督学习经典模型
本片博客是根据《Python机器学习及实践》一书中的实例，所有代码均在本地编译通过。数据为从该书指定的百度网盘上下载的，或者是sklearn自带数据下载到本地使用的。代码片段：importpandasaspdimportnumpyasnpcolumn_names=... 查看详情
python机器学习3大宝典
...er编辑：Peter大家好，我是Peter~今天给大家推荐3本Python机器学习相关的书籍，如果你想提升Python能力，想开启kaggle实战，想了解机器学习神器Scikit-Learn库的使用，建议下载学习~一、流畅的Python一本关于Python... 查看详情
《python机器学习及实践》----模型实用技巧
本片博客是根据《Python机器学习及实践》一书中的实例，所有代码均在本地编译通过。数据为从该书指定的百度网盘上下载的，或者是sklearn自带数据下载到本地使用的。代码片段：measurements=['city':'Dubai'... 查看详情
学习《python机器学习(第2版)》中文pdf+英文pdf+代码分析+sebastian
...学者，想进一步拓展对数据科学领域的认知，推荐学习《Python机器学习(第二版)》。《Python机器学习(第二版)》将机器学习背后的基本理论与应用实践联系起来，聚焦于如何正确地提出问题、解决问题，能帮助了解如何使用Python... 查看详情
《python机器学习及实践》----良/恶性乳腺癌肿瘤预测
本片博客是根据《Python机器学习及实践》一书中的实例，所有代码均在本地编译通过。数据为从该书指定的百度网盘上下载的。代码片段：importpandasaspdimportmatplotlib.pyplotaspltimportnumpyasnpfromsklearn.linear_modelimportLogisticRegression... 查看详情
python机器学习及实践+从零开始通往kaggle竞赛之路
...习与数据挖掘的实践及竞赛感兴趣的读者，从零开始，以Python编程语言为基础，在不涉及大量数学模型与复杂编程知识的前提下，逐步带领读者熟悉并且掌握当下最流行的机器学习、数据挖掘与自然语言处理工具，如Scikitlearn... 查看详情
《python机器学习及实践》----监督学习经典模型
本片博客是根据《Python机器学习及实践》一书中的实例，所有代码均在本地编译通过。数据为从该书指定的百度网盘上下载的，或者是sklearn自带数据下载到本地使用的。代码片段：importpandasaspdimportnumpyasnpcolumn_names=... 查看详情
《python机器学习及实践》----无监督学习之数据聚类
本片博客是根据《Python机器学习及实践》一书中的实例，所有代码均在本地编译通过。数据为从该书指定的百度网盘上下载的，或者是sklearn自带数据下载到本地使用的。代码片段：#coding:utf-8#分别导入numpy、matplotlib以... 查看详情
《python机器学习及实践》----无监督学习之特征降维
本片博客是根据《Python机器学习及实践》一书中的实例，所有代码均在本地编译通过。数据为从该书指定的百度网盘上下载的，或者是sklearn自带数据下载到本地使用的。代码片段：#coding:utf-8importnumpyasnpM=np.array([[1,... 查看详情
python机器学习|超参数优化黑盒（black-box）非凸优化技术实践
文章目录一、关键原理二、Python实践CSDN叶庭云：https://yetingyun.blog.csdn.net/一、关键原理为什么要做超参数优化？机器学习建模预测时，超参数是用于控制机器学习模型学习过程的参数。为了与从数据中学到的机器学习模型参数区... 查看详情
python机器学习及实践——特征降维
特征降维是无监督学习的另一个应用，目的有两个：一是我们经常在实际项目中遭遇特征维度非常高的训练样本，而往往无法借助自己的领域知识人工构建有效特征；二是在数据表现方面，我们无法用肉眼观... 查看详情
《python机器学习及实践》----模型实用技巧
本片博客是根据《Python机器学习及实践》一书中的实例，所有代码均在本地编译通过。数据为从该书指定的百度网盘上下载的，或者是sklearn自带数据下载到本地使用的。代码片段：measurements=['city':'Dubai'... 查看详情
机器学习教材推荐
Python机器学习手册，韩慧吕，林然，徐江等，人民邮电出版社Python机器学习实践，张建伟、陈锐等，清华大学出版社 查看详情
《机器学习及实践--从零开始通往kaggle竞赛之路》
...个把月的时间把这本书过了一遍。这是一本非常适合基于python入门的机器学习入门的书籍，全书通俗易懂且有代码提供。书中源代码连接为Ipython环境。主页君使用的是pycharm，python2.7，具体安转过程书本写的很详细。码完书中代... 查看详情
python机器学习及实践——进阶篇5（模型检验）
前面时不时提到模型检验或者交叉验证等词汇，特别是在对不同模型的配置，不同的特征组合，在相同的数据和任务下进行评价的时候。究其原因是因为仅仅使用默认配置的模型与不经处理的数据特征，在大多数... 查看详情
ai人工智能机器学习深度学习学习路径及推荐书籍
...习Pytorch，需要掌握以下基本知识：编程语言：Pytorch使用Python作为主要编程语言，因此需要熟悉Python编程语言。线性代数和微积分：Pytorch主要用于深度学习领域，深度学习是基于线性代数和微积分的，因此需要具备线性代数和微... 查看详情
《python机器学习及实践》----良/恶性乳腺癌肿瘤预测
本片博客是根据《Python机器学习及实践》一书中的实例，所有代码均在本地编译通过。数据为从该书指定的百度网盘上下载的。代码片段：importpandasaspdimportmatplotlib.pyplotaspltimportnumpyasnpfromsklearn.linear_modelimportLogisticRegression... 查看详情
python机器学习及实践——基础篇3（svm）(代码片段)
图中有三种颜色的线，用来划分这两种类别的训练样本。其中绿色直线H1在这些训练样本上表现不佳，本身就带有分类错误；蓝色直线H2和红色直线H3如果作为这个二分类问题的线性分类模型，在训练集上的... 查看详情