from sklearn.datasets import load_breast_cancer

cancer = load_breast_cancer()##將數(shù)據(jù)集賦值給iris變量

print('breast_cancer數(shù)據(jù)集的長度為：',len(cancer))
print('breast_cancer數(shù)據(jù)集的類型為：',type(cancer))
#breast_cancer數(shù)據(jù)集的長度為： 6
#breast_cancer數(shù)據(jù)集的類型為： <class 'sklearn.utils.Bunch'>

cancer_data = cancer['data']
print('breast_cancer數(shù)據(jù)集的數(shù)據(jù)為：','\n',cancer_data)
#breast_cancer數(shù)據(jù)集的數(shù)據(jù)為：
[[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]]

cancer_target = cancer['target'] ## 取出數(shù)據(jù)集的標簽
print('breast_cancer數(shù)據(jù)集的標簽為：\n',cancer_target)
#breast_cancer數(shù)據(jù)集的標簽為：
[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]

cancer_names = cancer['feature_names'] ## 取出數(shù)據(jù)集的特征名
print('breast_cancer數(shù)據(jù)集的特征名為：\n',cancer_names)
#breast_cancer數(shù)據(jù)集的特征名為：
['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']

cancer_desc = cancer['DESCR'] ## 取出數(shù)據(jù)集的描述信息
print('breast_cancer數(shù)據(jù)集的描述信息為：\n',cancer_desc)
#breast_cancer數(shù)據(jù)集的描述信息為：
.. _breast_cancer_dataset:

Breast cancer wisconsin (diagnostic) dataset
--------------------------------------------

**Data Set Characteristics:**

:Number of Instances: 569

:Number of Attributes: 30 numeric, predictive attributes and the class

:Attribute Information:
- radius (mean of distances from center to points on the perimeter)
- texture (standard deviation of gray-scale values)
- perimeter
- area
- smoothness (local variation in radius lengths)
- compactness (perimeter^2 / area - 1.0)
- concavity (severity of concave portions of the contour)
- concave points (number of concave portions of the contour)
- symmetry
- fractal dimension ("coastline approximation" - 1)

The mean, standard error, and "worst" or largest (mean of the three
largest values) of these features were computed for each image,
resulting in 30 features. For instance, field 3 is Mean Radius, field
13 is Radius SE, field 23 is Worst Radius.

- class:
- WDBC-Malignant
- WDBC-Benign

:Summary Statistics:

===================================== ====== ======
Min Max
===================================== ====== ======
radius (mean): 6.981 28.11
texture (mean): 9.71 39.28
perimeter (mean): 43.79 188.5
area (mean): 143.5 2501.0
smoothness (mean): 0.053 0.163
compactness (mean): 0.019 0.345
concavity (mean): 0.0 0.427
concave points (mean): 0.0 0.201
symmetry (mean): 0.106 0.304
fractal dimension (mean): 0.05 0.097
radius (standard error): 0.112 2.873
texture (standard error): 0.36 4.885
perimeter (standard error): 0.757 21.98
area (standard error): 6.802 542.2
smoothness (standard error): 0.002 0.031
compactness (standard error): 0.002 0.135
concavity (standard error): 0.0 0.396
concave points (standard error): 0.0 0.053
symmetry (standard error): 0.008 0.079
fractal dimension (standard error): 0.001 0.03
radius (worst): 7.93 36.04
texture (worst): 12.02 49.54
perimeter (worst): 50.41 251.2
area (worst): 185.2 4254.0
smoothness (worst): 0.071 0.223
compactness (worst): 0.027 1.058
concavity (worst): 0.0 1.252
concave points (worst): 0.0 0.291
symmetry (worst): 0.156 0.664
fractal dimension (worst): 0.055 0.208
===================================== ====== ======

:Missing Attribute Values: None

:Class Distribution: 212 - Malignant, 357 - Benign

:Creator: Dr. William H. Wolberg, W. Nick Street, Olvi L. Mangasarian

:Donor: Nick Street

:Date: November, 1995

This is a copy of UCI ML Breast Cancer Wisconsin (Diagnostic) datasets.
https://goo.gl/U2Uwz2

Features are computed from a digitized image of a fine needle
aspirate (FNA) of a breast mass. They describe
characteristics of the cell nuclei present in the image.

Separating plane described above was obtained using
Multisurface Method-Tree (MSM-T) [K. P. Bennett, "Decision Tree
Construction Via Linear Programming." Proceedings of the 4th
Midwest Artificial Intelligence and Cognitive Science Society,
pp. 97-101, 1992], a classification method which uses linear
programming to construct a decision tree. Relevant features
were selected using an exhaustive search in the space of 1-4
features and 1-3 separating planes.

The actual linear program used to obtain the separating plane
in the 3-dimensional space is that described in:
[K. P. Bennett and O. L. Mangasarian: "Robust Linear
Programming Discrimination of Two Linearly Inseparable Sets",
Optimization Methods and Software 1, 1992, 23-34].

This database is also available through the UW CS ftp server:

ftp ftp.cs.wisc.edu
cd math-prog/cpo-dataset/machine-learn/WDBC/

.. topic:: References

- W.N. Street, W.H. Wolberg and O.L. Mangasarian. Nuclear feature extraction
for breast tumor diagnosis. IS&T/SPIE 1993 International Symposium on
Electronic Imaging: Science and Technology, volume 1905, pages 861-870,
San Jose, CA, 1993.
- O.L. Mangasarian, W.N. Street and W.H. Wolberg. Breast cancer diagnosis and
prognosis via linear programming. Operations Research, 43(4), pages 570-577,
July-August 1995.
- W.H. Wolberg, W.N. Street, and O.L. Mangasarian. Machine learning techniques
to diagnose breast cancer from fine-needle aspirates. Cancer Letters 77 (1994)
163-171.

sklearn.model_selection.train_test_split(*arrays,**options)

print('原始數(shù)據(jù)集數(shù)據(jù)的形狀為：',cancer_data.shape)
print('原始數(shù)據(jù)集標簽的形狀為：',cancer_target.shape)
原始數(shù)據(jù)集數(shù)據(jù)的形狀為： (569, 30)
原始數(shù)據(jù)集標簽的形狀為： (569,)

from sklearn.model_selection import train_test_split

cancer_data_train,cancer_data_test,cancer_target_train,cancer_target_test = train_test_split(cancer_data,cancer_target,
test_size=0.2,random_state=42)
print('訓(xùn)練集數(shù)據(jù)的形狀為：',cancer_data_train.shape)
print('訓(xùn)練集數(shù)據(jù)的標簽形狀為：',cancer_target_train.shape)
print('測試集數(shù)據(jù)的形狀為：',cancer_data_test.shape)
print('測試集數(shù)據(jù)的標簽形狀為：',cancer_target_test.shape)
訓(xùn)練集數(shù)據(jù)的形狀為： (455, 30)
訓(xùn)練集數(shù)據(jù)的標簽形狀為： (455,)
測試集數(shù)據(jù)的形狀為： (114, 30)
測試集數(shù)據(jù)的標簽形狀為： (114,)

import numpy as np
from sklearn.preprocessing import MinMaxScaler

# 生成規(guī)則
Scaler = MinMaxScaler().fit(cancer_data_train)
# 將規(guī)則應(yīng)用于訓(xùn)練集
cancer_trainScaler = Scaler.transform(cancer_data_train)
# 將規(guī)則應(yīng)用于測試集
cancer_testScaler = Scaler.transform(cancer_data_test)

print('離差標準化前訓(xùn)練集數(shù)據(jù)的最小值：',cancer_data_train.min())
print('離差標準化后訓(xùn)練集數(shù)據(jù)的最小值：',np.min(cancer_trainScaler))
print('離差標準化前訓(xùn)練集數(shù)據(jù)的最大值：',np.max(cancer_data_train))
print('離差標準化后訓(xùn)練集數(shù)據(jù)的最大值：',np.max(cancer_trainScaler))
print('離差標準化前測試集數(shù)據(jù)的最小值：',np.min(cancer_data_test))
print('離差標準化后測試集數(shù)據(jù)的最小值：',np.min(cancer_testScaler))
print('離差標準化前測試集數(shù)據(jù)的最大值：',np.max(cancer_data_test))
print('離差標準化后測試集數(shù)據(jù)的最大值：',np.max(cancer_testScaler))
離差標準化前訓(xùn)練集數(shù)據(jù)的最小值： 0.0
離差標準化后訓(xùn)練集數(shù)據(jù)的最小值： 0.0
離差標準化前訓(xùn)練集數(shù)據(jù)的最大值： 4254.0
離差標準化后訓(xùn)練集數(shù)據(jù)的最大值： 1.0000000000000002
離差標準化前測試集數(shù)據(jù)的最小值： 0.0
離差標準化后測試集數(shù)據(jù)的最小值： -0.057127602776294695
離差標準化前測試集數(shù)據(jù)的最大值： 3432.0
離差標準化后測試集數(shù)據(jù)的最大值： 1.3264399566986453

sklearn.decomposition.PCA(n_components=None, *, copy=True, whiten=False, svd_solver='auto', tol=0.0, iterated_power='auto', random_state=None)

from sklearn.decomposition import PCA
# 生成規(guī)則
pca_model=PCA(n_components=10).fit(cancer_trainScaler)
# 將規(guī)則應(yīng)用到訓(xùn)練集
cancer_trainPca = pca_model.transform(cancer_trainScaler)
# 將規(guī)則應(yīng)用到測試集
cancer_testPca = pca_model.transform(cancer_testScaler)

print('PCA降維前訓(xùn)練集數(shù)據(jù)的形狀為：',cancer_trainScaler.shape)
print('PCA降維后訓(xùn)練集數(shù)據(jù)的形狀為：',cancer_trainPca.shape)
print('PCA降維前測試集數(shù)據(jù)的形狀為：',cancer_testScaler.shape)
print('PCA降維后測試集數(shù)據(jù)的形狀為：',cancer_testPca.shape)
PCA降維前訓(xùn)練集數(shù)據(jù)的形狀為： (455, 30)
PCA降維后訓(xùn)練集數(shù)據(jù)的形狀為： (455, 10)
PCA降維前測試集數(shù)據(jù)的形狀為： (114, 30)
PCA降維后測試集數(shù)據(jù)的形狀為： (114, 10)

from sklearn.datasets import load_iris
from sklearn.preprocessing import MinMaxScaler
from sklearn.cluster import KMeans

iris = load_iris() # 加載iris數(shù)據(jù)集
iris_data = iris['data'] # 提取iris數(shù)據(jù)集中的特征
iris_target = iris['target'] # 提取iris數(shù)據(jù)集中的標簽
iris_feature_names = iris['feature_names'] #提取iris數(shù)據(jù)集中的特征名稱

scale = MinMaxScaler().fit(iris_data) # 對數(shù)據(jù)集中的特征設(shè)定訓(xùn)練規(guī)則
iris_dataScale = scale.transform(iris_data) # 應(yīng)用規(guī)則

kmeans = KMeans(n_clusters=3,random_state=123).fit(iris_dataScale) # 構(gòu)建并訓(xùn)練模型
print('構(gòu)建的K-Means模型為：\n',kmeans)
#構(gòu)建的K-Means模型為：
KMeans(algorithm='auto', copy_x=True, init='k-means++', max_iter=300,
n_clusters=3, n_init=10, n_jobs=None, precompute_distances='auto',
random_state=123, tol=0.0001, verbose=0)

import pandas as pd
from sklearn.manifold import TSNE
import matplotlib.pyplot as plt

# 使用TSNE進行數(shù)據(jù)降維，降成2維
tsne = TSNE(n_components=2,init='random',random_state=177).fit(iris_data)

df = pd.DataFrame(tsne.embedding_) # 將原始數(shù)據(jù)轉(zhuǎn)換為DataFrame
df['labels'] = kmeans.labels_ # 將聚類結(jié)果存儲進df數(shù)據(jù)表

# 提取不同標簽的數(shù)據(jù)
df1 = df[df['labels']==0]
df2 = df[df['labels']==1]
df3 = df[df['labels']==2]

# 繪制圖形
# 繪制畫布大小
fig = plt.figure(figsize=(9,6))
# 用不同顏色表示不同數(shù)據(jù)
plt.plot(df1[0],df1[1],'bo',df2[0],df2[1],'r*',df3[0],df3[1],'gD')
# 保存圖片
plt.savefig('tmp/聚類結(jié)果.png')
# 展示
plt.show()

import numpy as np
from sklearn.datasets import load_breast_cancer
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

cancer = load_breast_cancer()
cancer_data = cancer['data']
cancer_target = cancer['target']
cancer_names = cancer['feature_names']

## 將數(shù)據(jù)劃分為訓(xùn)練集測試集
cancer_data_train,cancer_data_test,cancer_target_train,cancer_target_test = \
train_test_split(cancer_data,cancer_target,test_size = 0.2,random_state = 22)

## 數(shù)據(jù)標準化
stdScaler = StandardScaler().fit(cancer_data_train) # 設(shè)定標準化規(guī)則
cancer_trainStd = stdScaler.transform(cancer_data_train) # 將標準化規(guī)則應(yīng)用到訓(xùn)練集
cancer_testStd = stdScaler.transform(cancer_data_test) # 將標準化規(guī)則應(yīng)用到測試集

## 建立SVM模型
svm = SVC().fit(cancer_trainStd,cancer_target_train)
print('建立的SVM模型為：\n',svm)
#建立的SVM模型為：
SVC(C=1.0, break_ties=False, cache_size=200, class_weight=None, coef0=0.0,
decision_function_shape='ovr', degree=3, gamma='scale', kernel='rbf',
max_iter=-1, probability=False, random_state=None, shrinking=True,
tol=0.001, verbose=False)

## 預(yù)測訓(xùn)練集結(jié)果
cancer_target_pred = svm.predict(cancer_testStd)
print('預(yù)測前20個結(jié)果為：\n',cancer_target_pred[:20])
#預(yù)測前20個結(jié)果為：
[1 0 0 0 1 1 1 1 1 1 1 1 0 1 1 1 0 0 1 1]

## 求出預(yù)測和真實一樣的數(shù)目
true = np.sum(cancer_target_pred == cancer_target_test )
print('預(yù)測對的結(jié)果數(shù)目為：', true)
print('預(yù)測錯的的結(jié)果數(shù)目為：', cancer_target_test.shape[0]-true)
print('預(yù)測結(jié)果準確率為：', true/cancer_target_test.shape[0])
預(yù)測對的結(jié)果數(shù)目為： 111
預(yù)測錯的的結(jié)果數(shù)目為： 3
預(yù)測結(jié)果準確率為： 0.9736842105263158

from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

# 加載boston數(shù)據(jù)集
boston = load_boston()
# 提取數(shù)據(jù)
x = boston['data']
y = boston['target']
names = boston['feature_names']

# 將數(shù)據(jù)劃分為訓(xùn)練集和測試集
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=125)

# 建立線性回歸模型
clf = LinearRegression().fit(x_train,y_train)
print('建立的Linear Regression模型為：\n',clf)
#建立的 Linear Regression模型為：
LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)

# 預(yù)測測試集結(jié)果
y_pred = clf.predict(x_test)
print('預(yù)測前20個結(jié)果為：\n',y_pred[:20])
#預(yù)測前20個結(jié)果為：
[21.16289134 19.67630366 22.02458756 24.61877465 14.44016461 23.32107187
16.64386997 14.97085403 33.58043891 17.49079058 25.50429987 36.60653092
25.95062329 28.49744469 19.35133847 20.17145783 25.97572083 18.26842082
16.52840639 17.08939063]

# 回歸結(jié)果可視化
import matplotlib.pyplot as plt
from matplotlib import rcParams

# 設(shè)置中文顯示
rcParams['font.sans-serif'] = 'SimHei'

# 設(shè)置畫布
plt.figure(figsize=(10,6))

# 繪圖
plt.plot(range(y_test.shape[0]),y_test,color='blue',linewidth=1.5,linestyle='-')
plt.plot(range(y_test.shape[0]),y_pred,color='red',linewidth=1.5,linestyle='-.')

# 設(shè)置圖像屬性
plt.xlim((0,102))
plt.ylim((0,55))
plt.legend(['真實值','預(yù)測值'])

# 保存圖片
plt.savefig('tmp/聚回歸類結(jié)果.png')

#展示
plt.show()