• mean 代表平均值，se 代表标准差，worst 代表最大值（3 个最大值的平均值）
• 实际上是 10 个特征值（radius、texture、perimeter、area、smoothness、compactness、concavity、concave points、symmetry 和 fractal_dimension_mean）的 3 个维度，平均、标准差和最大值。这些特征值都保留了 4 位数字。字段中没有缺失的值。在 569 个患者中，一共有 357 个是良性，212 个是恶性。

import pandas as pd
import matplotlib.pyplot as plt# 画图
import seaborn as sns
from sklearn.model_selection import train_test_split#训练集与测试集
from  sklearn import svm
from sklearn import metrics #?
from sklearn.preprocessing import StandardScaler#标准分

data=pd.read_csv('data.csv')
data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 569 entries, 0 to 568
Data columns (total 32 columns):
id                         569 non-null int64
diagnosis                  569 non-null object
radius_mean                569 non-null float64
texture_mean               569 non-null float64
perimeter_mean             569 non-null float64
area_mean                  569 non-null float64
smoothness_mean            569 non-null float64
compactness_mean           569 non-null float64
concavity_mean             569 non-null float64
concave points_mean        569 non-null float64
symmetry_mean              569 non-null float64
fractal_dimension_mean     569 non-null float64
radius_se                  569 non-null float64
texture_se                 569 non-null float64
perimeter_se               569 non-null float64
area_se                    569 non-null float64
smoothness_se              569 non-null float64
compactness_se             569 non-null float64
concavity_se               569 non-null float64
concave points_se          569 non-null float64
symmetry_se                569 non-null float64
fractal_dimension_se       569 non-null float64
radius_worst               569 non-null float64
texture_worst              569 non-null float64
perimeter_worst            569 non-null float64
area_worst                 569 non-null float64
smoothness_worst           569 non-null float64
compactness_worst          569 non-null float64
concavity_worst            569 non-null float64
concave points_worst       569 non-null float64
symmetry_worst             569 non-null float64
fractal_dimension_worst    569 non-null float64
dtypes: float64(30), int64(1), object(1)
memory usage: 142.3+ KB

pd.set_option('display.max_columns',None)# 显示完整列
data.describe()

# 字段分成3组
features_mean=list(data.columns[2:12])
features_se=list(data.columns[12:22])
features_worst=list(data.columns[22:32])

data.drop('id',axis=1,inplace=True)
data['diagnosis']=data['diagnosis'].map({'M':1,'B':0})

# 可视化
sns.countplot(data['diagnosis'],label="Count")
plt.show()

#利用热力图呈现与均值的关系
corr=data[features_mean].corr()#字段间的相关性（计算pearson相关系数）
plt.figure(figsize=(18,18))
sns.heatmap(corr,annot=True)

<matplotlib.axes._subplots.AxesSubplot at 0x1a31c99828>

features_remain = ['radius_mean','texture_mean', 'smoothness_mean','compactness_mean','symmetry_mean', 'fractal_dimension_mean']

train,test=train_test_split(data,test_size=0.3)

train_x=train[features_remain]
train_y=train['diagnosis']
test_x=train[features_remain]
test_y=train['diagnosis']

ss=StandardScaler()
train_x=ss.fit_transform(train_x)
test_x=ss.fit_transform(test_x)

model1=svm.SVC()
model1.fit(train_x,train_y)

SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
    decision_function_shape='ovr', degree=3, gamma='auto_deprecated',
    kernel='rbf', max_iter=-1, probability=False, random_state=None,
    shrinking=True, tol=0.001, verbose=False)

prediction=model1.predict(test_x)
score=metrics.accuracy_score(prediction,test_y)

print(score)

0.9472361809045227

model2=svm.LinearSVC()
model2.fit(train_x,train_y)
prediction=model2.predict(test_x)
score=metrics.accuracy_score(prediction,test_y)
print(score)

0.9346733668341709

数据集

data.csv