标签：KNN knn np 算法 train test import sklearn Sklearn
KNN鸢尾花分类
import matplotlib.pyplot as plt
from sklearn.neighbors import KNeighborsClassifier
from sklearn import datasets
import numpy as np
X,y = datasets.load_iris(True) #返回x、y
X = X[:,:2]
plt.scatter(X[:,0],X[:,1],c=y)
knn = KNeighborsClassifier(n_neighbors = 5)
knn.fit(X,y)
x1 = np.linspace(4,8,100) #横坐标4到8
y1 = np.linspace(2,4.5,80) #纵坐标2到4.5
X1,Y1 = np.meshgrid(x1,y1)
X1 =X1.reshape(-1,1)
Y1 =Y1.reshape(-1,1)
X_test = np.concatenate([X1,Y1],axis = 1) #shape为(8000,2)
from matplotlib.colors import ListedColormap
lc1 = ListedColormap(["#FFAAAA","#AAFFAA","#AAAAFF"])
lc2 = ListedColormap(["#FF0000","#00FF00","#0000FF"])
y_ = knn.predict(X_test)
plt.scatter(X_test[:,0],X_test[:,1], c=y_ ,cmap=lc1)
plt.scatter(X[:,0],X[:,1], c=y,cmap=lc2)
KNN参数的筛选
import numpy as np
from sklearn.neighbors import KNeighborsClassifier
from sklearn import datasets
from sklearn.model_selection import cross_val_score
X,y = datasets.load_iris(True)
knn = KNeighborsClassifier()
score = cross_val_score(knn,X,y,scoring="accuracy",cv=6)
print(score)
erros = []
for i in range(1,14): #150开根号
knn = KNeighborsClassifier(n_neighbors=i)
score = cross_val_score(knn,X,y,scoring="accuracy",cv=6).mean()
erros.append(1-score)
import matplotlib.pyplot as plt
plt.plot(np.arange(1,14),erros)
weights = ["uniform","distance"]
for w in weights:
knn = KNeighborsClassifier(n_neighbors = 12,weights = w)
print(cross_val_score(knn,X,y,scoring="accuracy",cv = 6).mean())0.98
0.9733333333333333
result = {}
for k in range(1,14):
for w in weights:
knn = KNeighborsClassifier(n_neighbors = k,weights = w)
sm = cross_val_score(knn,X,y,scoring="accuracy",cv = 6).mean()
result[w + str(k)] = sm
result{'uniform1': 0.96,
'distance1': 0.96,
'uniform2': 0.94,
'distance2': 0.96,
'uniform3': 0.9666666666666667,
'distance3': 0.9666666666666667,
'uniform4': 0.9666666666666667,
'distance4': 0.9666666666666667,
'uniform5': 0.9666666666666667,
'distance5': 0.9666666666666667,
'uniform6': 0.9666666666666667,
'distance6': 0.96,
'uniform7': 0.9733333333333333,
'distance7': 0.9733333333333333,
'uniform8': 0.9666666666666667,
'distance8': 0.9666666666666667,
'uniform9': 0.9733333333333333,
'distance9': 0.9733333333333333,
'uniform10': 0.96,
'distance10': 0.96,
'uniform11': 0.9733333333333333,
'distance11': 0.9733333333333333,
'uniform12': 0.98,
'distance12': 0.9733333333333333,
'uniform13': 0.9733333333333333,
'distance13': 0.9733333333333333}np.array(list(result.values())).argmax()
list(result)[22]22
'uniform12'KNN癌症诊断
import numpy as np
import pandas as pd
from pandas import Series,DataFrame
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
cancer = pd.read_csv("/Users/zhucan/Desktop/cancer.csv",sep = "\t")
cancer.drop("ID",axis = 1, inplace=True)
X = cancer.iloc[:,1:]
y = cancer["Diagnosis"]
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.2)
knn = KNeighborsClassifier()
params = {"n_neighbors":[i for i in range(1,30)],"weights":["distance","uniform"],"p":[1,2]}
gcv = GridSearchCV(knn,params,scoring = "accuracy",cv = 6)
gcv.fit(X_train,y_train)
gcv.best_estimator_
gcv.best_score_
gcv.best_params_
y_ = gcv.predict(X_test)
gcv.score(X_test,y_test) #此时的gcv就是gcv.best_estimator_
pd.crosstab(index = y_test,columns = y_,rownames=["True"],colnames=["Predict"])
#输出混淆矩阵
KNeighborsClassifier(n_neighbors=4, p=1, weights='distance')
0.9516666666666667
{'n_neighbors': 4, 'p': 1, 'weights': 'distance'}
0.9385964912280702from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
confusion_matrix(y_,y_test)
print(classification_report(y_test,y_,target_names = ["B","M"]))78/(78+5) = 0.94 78/(78+2) = 0.97
29/(29+2) = 0.94 29/(29+5) = 0.85
找健康的比找生病的要强
KNN数据归一化操作
#归一化操作
X_norm1 = (X-X.min())/(X.max()-X.min())
X_train,X_test,y_train,y_test = train_test_split(X_norm1,y,test_size = 0.2)
knn = KNeighborsClassifier()
params = {"n_neighbors":[i for i in range(1,30)],"weights":["distance","uniform"],"p":[1,2]}
gcv = GridSearchCV(knn,params,scoring = "accuracy",cv = 6)
gcv.fit(X_train,y_train)from sklearn.metrics import accuracy_score
y_ = gcv.predict(X_test)
accuracy_score(y_test,y_)0.9649122807017544#另外的方法
#标准化
X_norm2 = (X - X.mean())/X.std()
from sklearn.preprocessing import MinMaxScaler,StandardScaler
mms = MinMaxScaler()
mms.fit(X)
X2 = mms.transform(X) #和归一化效果一样
ss = StandardScaler()
X3=ss.fit_transform(X)
X3 #和标准化效果一样sklearn中数据拆分
import numpy as np
import pandas as pd
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score,GridSearchCV
from sklearn.model_selection import KFold,StratifiedKFold #KFold、StratifiedKFold将数据分成多少份
data = np.random.randint(0,10,size=(8,2))
target = np.array([0,0,1,0,1,1,1,0])# train,test是索引，只要有索引就可以获取数据
KFold = KFold(n_splits=4)
for train,test in KFold.split(data,target):
print(target[train],target[test])[1 0 1 1 1 0] [0 0]
[0 0 1 1 1 0] [1 0]
[0 0 1 0 1 0] [1 1]
[0 0 1 0 1 1] [1 0]#分成4分，每一份数据特征，数据样本比例和原来一样
sKFold = StratifiedKFold(n_splits=4)
for train,test in sKFold.split(data,target):
print(target[train],target[test])[0 0 1 1 1 0] [0 1]
[0 1 0 1 1 0] [0 1]
[0 0 1 1 1 0] [0 1]
[0 0 1 0 1 1] [1 0]#train_test_split,KFold,StratifiedKFold作用都是将数据拆分
str类型数据的转变与训练预测
data = pd.read_csv("/Users/zhucan/Desktop/salary.txt")
data.drop(labels=["final_weight","education","capital_gain","capital_loss"],axis = 1,inplace=True)
X = data.iloc[:,0:-1]
y = data.iloc["salary"]
#方法将数据中str转换int，float从而算法可以计算
#map方法，apply，transform
u = X["workclass"].unique()
uarray(['State-gov', 'Self-emp-not-inc', 'Private', 'Federal-gov',
'Local-gov', '?', 'Self-emp-inc', 'Without-pay', 'Never-worked'],
dtype=object)np.argwhere(u=='Local-gov')[0,0]4def convert(x): #利用数字进行映射
return np.argwhere(u==x)[0,0]
X["workclass"]=X["workclass"].map(convert)
cols = ['marital_status', 'occupation','relationship', 'race', 'sex','native_country']
for col in cols:
u = X[col].unique()
def convert(x):
return np.argwhere(u==x)[0,0]
X[col] = X[col].map(convert)
import numpy as np
import pandas as pd
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score,GridSearchCV
from sklearn.model_selection import KFold,StratifiedKFold
data = pd.read_csv("/Users/zhucan/Desktop/salary.txt")
data.head()
data.drop(labels=["final_weight","education","capital_gain","capital_loss"],axis = 1,inplace=True)
X = data.iloc[:,0:-1]
y = data["salary"]
u = X["workclass"].unique()
def convert(x):
return np.argwhere(u==x)[0,0]
X["workclass"]=X["workclass"].map(convert)
cols = ['marital_status','occupation','relationship','race','sex','native_country']
for col in cols:
u = X[col].unique()
def convert(x):
return np.argwhere(u==x)[0,0]
X[col] = X[col].map(convert)
knn = KNeighborsClassifier()
kFold = KFold(10)
knn = KNeighborsClassifier()
accuracy = 0
for train,test in kFold.split(X,y):
knn.fit(X.loc[train],y[train])
acc = knn.score(X.loc[test],y[test])
accuracy += acc/10
print(accuracy)0.7973345728987424标签：KNN,knn,np,算法,train,test,import,sklearn,Sklearn 来源： https://blog.csdn.net/Grateful_Dead424/article/details/120556408
本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享； 2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关； 3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关； 4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除； 5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。