task5 掌握基本的分类模型

# 我们先来对未调参的SVR进行评价： 
from sklearn.svm import SVR     # 引入SVR类
from sklearn.pipeline import make_pipeline   # 引入管道简化学习流程
from sklearn.preprocessing import StandardScaler # 由于SVR基于距离计算，引入对数据进行标准化的类
from sklearn.model_selection import GridSearchCV  # 引入网格搜索调优
from sklearn.model_selection import cross_val_score # 引入K折交叉验证
from sklearn import datasets


boston = datasets.load_boston()     # 返回一个类似于字典的类
X = boston.data
y = boston.target
features = boston.feature_names
pipe_SVR = make_pipeline(StandardScaler(),
                                                         SVR())
score1 = cross_val_score(estimator=pipe_SVR,
                                                     X = X,
                                                     y = y,
                                                     scoring = 'r2',
                                                      cv = 10)       # 10折交叉验证
print("CV accuracy: %.3f +/- %.3f" % ((np.mean(score1)),np.std(score1)))

CV accuracy: 0.187 +/- 0.649

# 下面我们使用网格搜索来对SVR调参：
from sklearn.pipeline import Pipeline
pipe_svr = Pipeline([("StandardScaler",StandardScaler()),
                                                         ("svr",SVR())])
param_range = [0.0001,0.001,0.01,0.1,1.0,10.0,100.0,1000.0]
param_grid = [{"svr__C":param_range,"svr__kernel":["linear"]},  # 注意__是指两个下划线，一个下划线会报错的
                            {"svr__C":param_range,"svr__gamma":param_range,"svr__kernel":["rbf"]}]
gs = GridSearchCV(estimator=pipe_svr,
                                                     param_grid = param_grid,
                                                     scoring = 'r2',
                                                      cv = 10)       # 10折交叉验证
gs = gs.fit(X,y)
print("网格搜索最优得分：",gs.best_score_)
print("网格搜索最优参数组合：\n",gs.best_params_)

网格搜索最优得分： 0.6081303070817127
网格搜索最优参数组合：
 {'svr__C': 1000.0, 'svr__gamma': 0.001, 'svr__kernel': 'rbf'}

# 下面我们使用随机搜索来对SVR调参：
from sklearn.model_selection import RandomizedSearchCV
from scipy.stats import uniform  # 引入均匀分布设置参数
pipe_svr = Pipeline([("StandardScaler",StandardScaler()),
                                                         ("svr",SVR())])
distributions = dict(svr__C=uniform(loc=1.0, scale=4),    # 构建连续参数的分布
                     svr__kernel=["linear","rbf"],                                   # 离散参数的集合
                    svr__gamma=uniform(loc=0, scale=4))

rs = RandomizedSearchCV(estimator=pipe_svr,
                                                     param_distributions = distributions,
                                                     scoring = 'r2',
                                                      cv = 10)       # 10折交叉验证
rs = rs.fit(X,y)
print("随机搜索最优得分：",rs.best_score_)
print("随机搜索最优参数组合：\n",rs.best_params_)

随机搜索最优得分： 0.29880287171934033
随机搜索最优参数组合：
 {'svr__C': 3.1000343983291017, 'svr__gamma': 0.7023437908841612, 'svr__kernel': 'linear'}

from sklearn import datasets
iris = datasets.load_iris()
X = iris.data
y = iris.target
feature = iris.feature_names
data = pd.DataFrame(X,columns=feature)
data['target'] = y
data.head()

	sepal length (cm)	sepal width (cm)	petal length (cm)	petal width (cm)	target
0	5.1	3.5	1.4	0.2	0
1	4.9	3.0	1.4	0.2	0
2	4.7	3.2	1.3	0.2	0
3	4.6	3.1	1.5	0.2	0
4	5.0	3.6	1.4	0.2	0

#  逻辑回归
'''
penalty       {‘l1’, ‘l2’, ‘elasticnet’, ‘none’}, default=’l2’正则化方式
dual      bool, default=False   是否使用对偶形式，当n_samples> n_features时，默认dual = False。   
C        float, default=1.0      
solver       {‘newton-cg’, ‘lbfgs’, ‘liblinear’, ‘sag’, ‘saga’}, default=’lbfgs’     
l1_ratio         float, default=None           
'''
from sklearn.linear_model import LogisticRegression
log_iris = LogisticRegression()
log_iris.fit(X,y)
log_iris.score(X,y)

C:\Users\lenovo\anaconda3\lib\site-packages\sklearn\linear_model\_logistic.py:762: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(





0.9733333333333334

# 线性判别分析
'''
参数：
solver:{'svd'，'lsqr'，'eigen'}，默认='svd'
solver的使用，可能的值：
'svd'：奇异值分解（默认）。不计算协方差矩阵，因此建议将此求解器用于具有大量特征的数据。

'lsqr'：最小二乘解，可以与收缩结合使用。

'eigen'：特征值分解，可以与收缩结合使用。
'''
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
lda_iris = LinearDiscriminantAnalysis()
lda_iris.fit(X,y)
lda_iris.score(X,y)
   

0.98

# 朴素贝叶斯             
from sklearn.naive_bayes import GaussianNB
NB_iris = GaussianNB()
NB_iris.fit(X, y)
NB_iris.score(X,y)

0.96

# 使用决策树算法对iris分类：
'''
criterion:{“gini”, “entropy”}, default=”gini”
max_depth:树的最大深度。
min_samples_split:拆分内部节点所需的最少样本数
min_samples_leaf :在叶节点处需要的最小样本数。

'''
from sklearn.tree import DecisionTreeClassifier
tree_iris = DecisionTreeClassifier(min_samples_leaf=5)
tree_iris.fit(X,y)
tree_iris.score(X,y)

0.9733333333333334

from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
'''
C:正则化参数。正则化的强度与C成反比。必须严格为正。惩罚是平方的l2惩罚。
kernel:{'linear'，'poly'，'rbf'，'sigmoid'，'precomputed'}，默认='rbf'
degree:多项式和的阶数
gamma:“ rbf”，“ poly”和“ Sigmoid”的内核系数。
shrinking:是否软间隔分类，默认true

'''
svc_iris = make_pipeline(StandardScaler(), SVC(gamma='auto'))
svc_iris.fit(X, y)
svc_iris.score(X,y)

0.9733333333333334

# 使用网格搜索进行超参数调优：
# 方式1：网格搜索GridSearchCV()
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
import time

start_time = time.time()
pipe_svc = make_pipeline(StandardScaler(),SVC(random_state=1))
param_range = [0.0001,0.001,0.01,0.1,1.0,10.0,100.0,1000.0]
param_grid = [{'svc__C':param_range,'svc__kernel':['linear']},{'svc__C':param_range,'svc__gamma':param_range,'svc__kernel':['rbf']}]
gs = GridSearchCV(estimator=pipe_svc,param_grid=param_grid,scoring='accuracy',cv=10,n_jobs=-1)
gs = gs.fit(X,y)
end_time = time.time()
print("网格搜索经历时间：%.3f S" % float(end_time-start_time))
print(gs.best_score_)
print(gs.best_params_)

网格搜索经历时间：9.560 S
0.9800000000000001
{'svc__C': 1.0, 'svc__gamma': 0.1, 'svc__kernel': 'rbf'}

# 方式2：随机网格搜索RandomizedSearchCV()
from sklearn.model_selection import RandomizedSearchCV
from sklearn.svm import SVC
import time

start_time = time.time()
pipe_svc = make_pipeline(StandardScaler(),SVC(random_state=1))
param_range = [0.0001,0.001,0.01,0.1,1.0,10.0,100.0,1000.0]
param_grid = [{'svc__C':param_range,'svc__kernel':['linear']},{'svc__C':param_range,'svc__gamma':param_range,'svc__kernel':['rbf']}]
# param_grid = [{'svc__C':param_range,'svc__kernel':['linear','rbf'],'svc__gamma':param_range}]
gs = RandomizedSearchCV(estimator=pipe_svc, param_distributions=param_grid,scoring='accuracy',cv=10,n_jobs=-1)
gs = gs.fit(X,y)
end_time = time.time()
print("随机网格搜索经历时间：%.3f S" % float(end_time-start_time))
print(gs.best_score_)
print(gs.best_params_)

随机网格搜索经历时间：0.135 S
0.9733333333333334
{'svc__kernel': 'rbf', 'svc__gamma': 0.0001, 'svc__C': 1000.0}

# 混淆矩阵：
# 加载数据
df = pd.read_csv("http://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data",header=None)
'''
乳腺癌数据集：569个恶性和良性肿瘤细胞的样本，M为恶性，B为良性
'''
# 做基本的数据预处理
from sklearn.preprocessing import LabelEncoder

X = df.iloc[:,2:].values
y = df.iloc[:,1].values
le = LabelEncoder()    #将M-B等字符串编码成计算机能识别的0-1
y = le.fit_transform(y)
le.transform(['M','B'])
# 数据切分8：2
from sklearn.model_selection import train_test_split

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,stratify=y,random_state=1)
from sklearn.svm import SVC
pipe_svc = make_pipeline(StandardScaler(),SVC(random_state=1))
from sklearn.metrics import confusion_matrix

pipe_svc.fit(X_train,y_train)
y_pred = pipe_svc.predict(X_test)
confmat = confusion_matrix(y_true=y_test,y_pred=y_pred)
fig,ax = plt.subplots(figsize=(2.5,2.5))
ax.matshow(confmat, cmap=plt.cm.Blues,alpha=0.3)
for i in range(confmat.shape[0]):
    for j in range(confmat.shape[1]):
        ax.text(x=j,y=i,s=confmat[i,j],va='center',ha='center')
plt.xlabel('predicted label')
plt.ylabel('true label')
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-izD63mN8-1616577548334)(output_33_0.png)]

# 绘制ROC曲线：
from sklearn.metrics import roc_curve,auc
from sklearn.metrics import make_scorer,f1_score
scorer = make_scorer(f1_score,pos_label=0)
gs = GridSearchCV(estimator=pipe_svc,param_grid=param_grid,scoring=scorer,cv=10)
y_pred = gs.fit(X_train,y_train).decision_function(X_test)
#y_pred = gs.predict(X_test)
fpr,tpr,threshold = roc_curve(y_test, y_pred) ###计算真阳率和假阳率
roc_auc = auc(fpr,tpr) ###计算auc的值
plt.figure()
lw = 2
plt.figure(figsize=(7,5))
plt.plot(fpr, tpr, color='darkorange',
         lw=lw, label='ROC curve (area = %0.2f)' % roc_auc) ###假阳率为横坐标，真阳率为纵坐标做曲线
plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
plt.xlim([-0.05, 1.0])
plt.ylim([-0.05, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic ')
plt.legend(loc="lower right")
plt.show()

<Figure size 432x288 with 0 Axes>

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-QIbjMlnU-1616577548336)(output_34_1.png)]