机器学习分类-鸢尾花数据分类

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from  sklearn.cluster import KMeans
from sklearn.model_selection import train_test_split 
from sklearn import metrics 

iris = pd.read_csv('E:/练习/Iris.csv')

iris.head()

	id	SepalLengthCm	SepalWidthCm	PetalLengthCm	PetalWidthCm	Species
0	1	5.1	3.5	1.4	0.2	0
1	2	4.9	3.0	1.4	0.2	0
2	3	4.7	3.2	1.3	0.2	0
3	4	4.6	3.1	1.5	0.2	0
4	5	5.0	3.6	1.4	0.2	0

iris.drop('id',axis=1,inplace=True)

iris.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 150 entries, 0 to 149
Data columns (total 5 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   SepalLengthCm  150 non-null    float64
 1   SepalWidthCm   150 non-null    float64
 2   PetalLengthCm  150 non-null    float64
 3   PetalWidthCm   150 non-null    float64
 4   Species        150 non-null    int64  
dtypes: float64(4), int64(1)
memory usage: 6.0 KB

iris.head()

	SepalLengthCm	SepalWidthCm	PetalLengthCm	PetalWidthCm	Species
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

fig = iris[iris.Species==0].plot(kind='scatter',x='SepalLengthCm',y='SepalWidthCm',color='orange', label='Setosa')
iris[iris.Species==1].plot(kind='scatter',x='SepalLengthCm',y='SepalWidthCm',color='blue', label='versicolor',ax=fig)
iris[iris.Species==2].plot(kind='scatter',x='SepalLengthCm',y='SepalWidthCm',color='green', label='virginica', ax=fig)
fig.set_xlabel("Sepal Length")
fig.set_ylabel("Sepal Width")
fig.set_title("Sepal Length VS Width")
fig=plt.gcf()
fig.set_size_inches(10,6)
plt.show()

fig = iris[iris.Species==0].plot.scatter(x='PetalLengthCm',y='PetalWidthCm',color='orange', label='Setosa')
iris[iris.Species==1].plot.scatter(x='PetalLengthCm',y='PetalWidthCm',color='blue', label='versicolor',ax=fig)
iris[iris.Species==2].plot.scatter(x='PetalLengthCm',y='PetalWidthCm',color='green', label='virginica', ax=fig)
fig.set_xlabel("Petal Length")
fig.set_ylabel("Petal Width")
fig.set_title(" Petal Length VS Width")
fig=plt.gcf()
fig.set_size_inches(10,6)
plt.show()

plt.figure(figsize=(7,4))  #计算相关系数
sns.heatmap(iris.corr(),annot=True,cmap='cubehelix_r')
plt.show()

train, test = train_test_split(iris, test_size = 0.3)
print(train.shape)
print(test.shape)

(105, 5)
(45, 5)

train_X = train[['SepalLengthCm','SepalWidthCm','PetalLengthCm','PetalWidthCm']]
train_y=train.Species# output of our training data
test_X= test[['SepalLengthCm','SepalWidthCm','PetalLengthCm','PetalWidthCm']]
test_y =test.Species

train_X.head(2)

	SepalLengthCm	SepalWidthCm	PetalLengthCm	PetalWidthCm
98	5.1	2.5	3.0	1.1
89	5.5	2.5	4.0	1.3

test_X.head(2)

	SepalLengthCm	SepalWidthCm	PetalLengthCm	PetalWidthCm
110	6.5	3.2	5.1	2.0
124	6.7	3.3	5.7	2.1

train_y.head()

98     1
89     1
55     1
111    2
117    2
Name: Species, dtype: int64

x = iris.iloc[:, [0, 1, 2, 3]].values
kmeans = KMeans(n_clusters = 3, init = 'k-means++', max_iter = 300, n_init = 10, random_state = 0)
y_kmeans = kmeans.fit_predict(x)

#Visualising the clusters
plt.scatter(x[y_kmeans == 0, 0], x[y_kmeans == 0, 1], s = 100, c = 'purple', label = '0')
plt.scatter(x[y_kmeans == 1, 0], x[y_kmeans == 1, 1], s = 100, c = 'orange', label = '1')
plt.scatter(x[y_kmeans == 2, 0], x[y_kmeans == 2, 1], s = 100, c = 'green', label = '2')

#Plotting the centroids of the clusters
plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:,1], s = 100, c = 'red', label = 'Centroids')

plt.legend()

<matplotlib.legend.Legend at 0x1b0d536c8b0>

model = KMeans(n_clusters=3)
model.fit(train_X,train_y)
prediction=model.predict(test_X)
print('The accuracy of the KMeans is',metrics.accuracy_score(prediction,test_y))

The accuracy of the KMeans is 0.9111111111111111

r1 = pd.Series(model.labels_).value_counts() 

r2 = pd.DataFrame(model.cluster_centers_) #找出聚类中心

r = pd.concat([r2, r1], axis = 1) #横向连接(0是纵向), 得到聚类中心对应的类别下的数目

print(r)

          0         1         2         3   0
0  5.063636  3.472727  1.500000  0.251515  33
1  5.817500  2.722500  4.340000  1.447500  40
2  6.881250  3.053125  5.746875  2.015625  32

petal=iris[['PetalLengthCm','PetalWidthCm','Species']]
sepal=iris[['SepalLengthCm','SepalWidthCm','Species']]

train_p,test_p=train_test_split(petal,test_size=0.3,random_state=0)  #petals
train_x_p=train_p[['PetalWidthCm','PetalLengthCm']]
train_y_p=train_p.Species
test_x_p=test_p[['PetalWidthCm','PetalLengthCm']]
test_y_p=test_p.Species


train_s,test_s=train_test_split(sepal,test_size=0.3,random_state=0)  #Sepal
train_x_s=train_s[['SepalWidthCm','SepalLengthCm']]
train_y_s=train_s.Species
test_x_s=test_s[['SepalWidthCm','SepalLengthCm']]
test_y_s=test_s.Species

model=KMeans(n_clusters=3)
model.fit(train_x_p,train_y_p) 
prediction=model.predict(test_x_p) 
print('The accuracy of the KMeans using Petals is:',metrics.accuracy_score(prediction,test_y_p))

model.fit(train_x_s,train_y_s) 
prediction=model.predict(test_x_s) 
print('The accuracy of the KMeans using Sepals is:',metrics.accuracy_score(prediction,test_y_s))

The accuracy of the KMeans using Petals is: 0.4
The accuracy of the KMeans using Sepals is: 0.13333333333333333

r1 = pd.Series(model.labels_).value_counts() 
r2 = pd.DataFrame(model.cluster_centers_) #找出聚类中心
r = pd.concat([r2, r1], axis = 1) #横向连接(0是纵向), 得到聚类中心对应的类别下的数目
print(r)

          0         1   0
0  3.108571  6.885714  35
1  3.330556  4.988889  36
2  2.676471  5.829412  34