无监督学习

自动对输入数据进行分类或者分群

优点：
算法不受监督信息（偏见）的约束，可能考虑到新的信息
不需要标签数据，极大程度扩大数据样本

Kmeans 聚类

根据数据与中心点距离划分类别
基于类别数据更新中心点
重复过程直到收敛
特点：实现简单、收敛快；需要指定类别数量（需要告诉计算机要分成几类）

选择聚类的个数
确定聚类中心
根据点到聚类中心聚类确定各个点所属类别
更具各个类别数据更新聚类中心
重复以上步骤直到收敛（中心点不再变化）

均值漂移聚类 Meanshift

在中心点一定区域检索数据点
更新中心
重复流程到中心点稳定

DBSCAN算法(基于密度的空间聚类算法)

基于区域点密度筛选有效数据
基于有效数据向周边扩张，直到没有新点加入
特点：过滤噪音数据；不需要人为选择类别数量；数据密度不同时影响结果

KNN K邻近分类监督学习

给定一个训练数据集，对新的输入实例，在训练数据集中找到与该实例最邻近的K个实例，这K个实例的多数属于某个类，就把该输入实例分类到这个类中。

参考链接

https://blog.csdn.net/weixin_46344368/article/details/106036451?spm=1001.2014.3001.5502

code

#加载数据并预览
import pandas as pd
import numpy as np
data = pd.read_csv('data.csv')
data.head()
#定义X和y
X = data.drop(['labels'],axis=1)
y = data.loc[:,'labels']
y.head()#预览
pd.value_counts(y) #查看类别数(这里有0，1，2三个类别)以及每个类别对应的样本数
#导入数据以及数据可视化
%matplotlib inline
from matplotlib import pyplot as plt
fig1 = plt.figure()
plt.scatter(X.loc[:,'V1'],X.loc[:,'V2'])
plt.title("un-labled data")
plt.xlabel('V1')
plt.ylabel('V2')
plt.show()
#给出标签
fig1 = plt.figure()
label0 = plt.scatter(X.loc[:,'V1'][y==0],X.loc[:,'V2'][y==0])
label1 = plt.scatter(X.loc[:,'V1'][y==1],X.loc[:,'V2'][y==1])
label2 = plt.scatter(X.loc[:,'V1'][y==2],X.loc[:,'V2'][y==2])

plt.title("labled data")
plt.xlabel('V1')
plt.ylabel('V2')
plt.legend((label0,label1,label2),('label0','label1','label2'))
plt.show()

#建立模型
from sklearn.cluster import KMeans
KM = KMeans(n_clusters=3,random_state=0)
KM.fit(X)

#给出中心点
centers = KM.cluster_centers_

fig3 = plt.figure()
label0 = plt.scatter(X.loc[:,'V1'][y==0],X.loc[:,'V2'][y==0])
label1 = plt.scatter(X.loc[:,'V1'][y==1],X.loc[:,'V2'][y==1])
label2 = plt.scatter(X.loc[:,'V1'][y==2],X.loc[:,'V2'][y==2])

plt.title("labled data")
plt.xlabel('V1')
plt.ylabel('V2')
plt.legend((label0,label1,label2),('label0','label1','label2'))
plt.scatter(centers[:,0],centers[:,1])
plt.show()

#测试数据: V1=80,V2=60
y_predict_test = KM.predict([[80,60]])
print(y_predict_test)

y_predict = KM.predict(X)
print(pd.value_counts(y_predict),'\n',pd.value_counts(y))

from sklearn.metrics import accuracy_score
accuracy = accuracy_score(y,y_predict)
print(accuracy)

fig4 = plt.subplot(121)
label0 = plt.scatter(X.loc[:,'V1'][y_predict==0],X.loc[:,'V2'][y_predict==0])
label1 = plt.scatter(X.loc[:,'V1'][y_predict==1],X.loc[:,'V2'][y_predict==1])
label2 = plt.scatter(X.loc[:,'V1'][y_predict==2],X.loc[:,'V2'][y_predict==2])

plt.title("predicted data")
plt.xlabel('V1')
plt.ylabel('V2')
plt.legend((label0,label1,label2),('label0','label1','label2'))
plt.scatter(centers[:,0],centers[:,1])

fig5 = plt.subplot(122)
label0 = plt.scatter(X.loc[:,'V1'][y==0],X.loc[:,'V2'][y==0])
label1 = plt.scatter(X.loc[:,'V1'][y==1],X.loc[:,'V2'][y==1])
label2 = plt.scatter(X.loc[:,'V1'][y==2],X.loc[:,'V2'][y==2])

plt.title("labled data")
plt.xlabel('V1')
plt.ylabel('V2')
plt.legend((label0,label1,label2),('label0','label1','label2'))
plt.scatter(centers[:,0],centers[:,1])
plt.show()

#矫正结果
y_corrected = []
for i in y_predict:
    if i==0:
        y_corrected.append(1)
    elif i==1:
        y_corrected.append(2)
    else:
        y_corrected.append(0)
print(pd.value_counts(y_corrected),pd.value_counts(y))

print(accuracy_score(y,y_corrected))

y_corrected = np.array(y_corrected)
print(type(y_corrected))

fig6 = plt.subplot(121)
label0 = plt.scatter(X.loc[:,'V1'][y_corrected==0],X.loc[:,'V2'][y_corrected==0])
label1 = plt.scatter(X.loc[:,'V1'][y_corrected==1],X.loc[:,'V2'][y_corrected==1])
label2 = plt.scatter(X.loc[:,'V1'][y_corrected==2],X.loc[:,'V2'][y_corrected==2])

plt.title("corrected data")
plt.xlabel('V1')
plt.ylabel('V2')
plt.legend((label0,label1,label2),('label0','label1','label2'))
plt.scatter(centers[:,0],centers[:,1])

fig7 = plt.subplot(122)
label0 = plt.scatter(X.loc[:,'V1'][y==0],X.loc[:,'V2'][y==0])
label1 = plt.scatter(X.loc[:,'V1'][y==1],X.loc[:,'V2'][y==1])
label2 = plt.scatter(X.loc[:,'V1'][y==2],X.loc[:,'V2'][y==2])

plt.title("labled data")
plt.xlabel('V1')
plt.ylabel('V2')
plt.legend((label0,label1,label2),('label0','label1','label2'))
plt.scatter(centers[:,0],centers[:,1])
plt.show()

# eatablish a KNN model
from sklearn.neighbors import KNeighborsClassifier
KNN = KNeighborsClassifier(n_neighbors = 3)
KNN.fit(X,y)

# predict based on the test data V1 = 80 V2 = 60
y_predict_knn_test = KNN.predict([[80,60]])
y_predict_knn = KNN.predict(X)
print(y_predict_knn_test)
print('Knn accuracy:',accuracy_score(y,y_predict_knn))

print(pd.value_counts(y_predict_knn),pd.value_counts(y))

fig8 = plt.subplot(121)
label0 = plt.scatter(X.loc[:,'V1'][y_predict_knn==0],X.loc[:,'V2'][y_predict_knn==0])
label1 = plt.scatter(X.loc[:,'V1'][y_predict_knn==1],X.loc[:,'V2'][y_predict_knn==1])
label2 = plt.scatter(X.loc[:,'V1'][y_predict_knn==2],X.loc[:,'V2'][y_predict_knn==2])

plt.title("knn predict data")
plt.xlabel('V1')
plt.ylabel('V2')
plt.legend((label0,label1,label2),('label0','label1','label2'))
plt.scatter(centers[:,0],centers[:,1])

fig9 = plt.subplot(122)
label0 = plt.scatter(X.loc[:,'V1'][y==0],X.loc[:,'V2'][y==0])
label1 = plt.scatter(X.loc[:,'V1'][y==1],X.loc[:,'V2'][y==1])
label2 = plt.scatter(X.loc[:,'V1'][y==2],X.loc[:,'V2'][y==2])

plt.title("labled data")
plt.xlabel('V1')
plt.ylabel('V2')
plt.legend((label0,label1,label2),('label0','label1','label2'))
plt.scatter(centers[:,0],centers[:,1])
plt.show()

# try meanshift model
from sklearn.cluster import MeanShift,estimate_bandwidth
# obtain the bandwidth
bw = estimate_bandwidth(X, n_samples=500)
print(bw)

# establish the meanshift model
ms = MeanShift(bandwidth=bw)
ms.fit(X)

y_predict_ms = ms.predict(X)
print(pd.value_counts(y_predict_ms), pd.value_counts(y))

fig10 = plt.subplot(121)
label0 = plt.scatter(X.loc[:,'V1'][y_predict_ms==0],X.loc[:,'V2'][y_predict_ms==0])
label1 = plt.scatter(X.loc[:,'V1'][y_predict_ms==1],X.loc[:,'V2'][y_predict_ms==1])
label2 = plt.scatter(X.loc[:,'V1'][y_predict_ms==2],X.loc[:,'V2'][y_predict_ms==2])

plt.title("meanshift predict data")
plt.xlabel('V1')
plt.ylabel('V2')
plt.legend((label0,label1,label2),('label0','label1','label2'))
plt.scatter(centers[:,0],centers[:,1])

fig11 = plt.subplot(122)
label0 = plt.scatter(X.loc[:,'V1'][y==0],X.loc[:,'V2'][y==0])
label1 = plt.scatter(X.loc[:,'V1'][y==1],X.loc[:,'V2'][y==1])
label2 = plt.scatter(X.loc[:,'V1'][y==2],X.loc[:,'V2'][y==2])

plt.title("labled data")
plt.xlabel('V1')
plt.ylabel('V2')
plt.legend((label0,label1,label2),('label0','label1','label2'))
plt.scatter(centers[:,0],centers[:,1])
plt.show()

#矫正结果
y_corrected_ms = []
for i in y_predict_ms:
    if i==0:
        y_corrected_ms.append(2)
    elif i==1:
        y_corrected_ms.append(1)
    else:
        y_corrected_ms.append(0)
print(pd.value_counts(y_corrected_ms),pd.value_counts(y))

# convert the results to numpy array
y_corrected_ms = np.array(y_corrected_ms)
print(type(y_corrected_ms))

fig12 = plt.subplot(121)
label0 = plt.scatter(X.loc[:,'V1'][y_corrected_ms==0],X.loc[:,'V2'][y_corrected_ms==0])
label1 = plt.scatter(X.loc[:,'V1'][y_corrected_ms==1],X.loc[:,'V2'][y_corrected_ms==1])
label2 = plt.scatter(X.loc[:,'V1'][y_corrected_ms==2],X.loc[:,'V2'][y_corrected_ms==2])

plt.title("meanshift predict data")
plt.xlabel('V1')
plt.ylabel('V2')
plt.legend((label0,label1,label2),('label0','label1','label2'))
plt.scatter(centers[:,0],centers[:,1])

fig13 = plt.subplot(122)
label0 = plt.scatter(X.loc[:,'V1'][y==0],X.loc[:,'V2'][y==0])
label1 = plt.scatter(X.loc[:,'V1'][y==1],X.loc[:,'V2'][y==1])
label2 = plt.scatter(X.loc[:,'V1'][y==2],X.loc[:,'V2'][y==2])

plt.title("labled data")
plt.xlabel('V1')
plt.ylabel('V2')
plt.legend((label0,label1,label2),('label0','label1','label2'))
plt.scatter(centers[:,0],centers[:,1])
plt.show()

无监督学习 Kmeans

无监督学习

Kmeans 聚类

均值漂移聚类 Meanshift

DBSCAN算法(基于密度的空间聚类算法)

KNN K邻近分类监督学习

参考链接

code

image

node js 版本更新

left join 和 where 區別

?? js 語法糖

顯示歐拉法求解 y' = y 問題

GIT重新學習

Mac下配置sublime實現LaTeX

https://yachay.unat.edu.pe/blog/index.php?comment_area=format_blog&comment_component=blog&comment_co

linux以太網驅動總結