鸢尾花（iris）训练测试

# 需要导入的模块
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

# 加载数据集
iris = pd.read_csv('./Iris.csv')


# 查看数据是否加载成功
ris.head()
# 与上面步骤相同，查看数据是否加载成功
iris.info()
# 删除无关的列
iris.drop('Id',axis=1,inplace=True)
# 查看是否删除成功
iris.info()
# 数据可视化（数据探查）
## 下面这段代码是花萼在不同类别下的分布散点图

fig = iris[iris.Species=='Iris-setosa'].plot(kind='scatter',x='SepalLengthCm',y='SepalWidthCm',color='orange', label='Setosa')
iris[iris.Species=='Iris-versicolor'].plot(kind='scatter',x='SepalLengthCm',y='SepalWidthCm',color='blue', label='versicolor',ax=fig)
iris[iris.Species=='Iris-virginica'].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()
# 同上对数据进行可视化
# 下面这段代码是对花瓣的长度和宽度特征的散点图
fig = iris[iris.Species=='Iris-setosa'].plot.scatter(x='PetalLengthCm',y='PetalWidthCm',color='orange', label='Setosa')
iris[iris.Species=='Iris-versicolor'].plot.scatter(x='PetalLengthCm',y='PetalWidthCm',color='blue', label='versicolor',ax=fig)
iris[iris.Species=='Iris-virginica'].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")
# 用直方图展示花萼和花瓣的长度和宽度
iris.hist(edgecolor='black', linewidth=1.2)
# 导入本实验需要用到的一些算法
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn import svm
from sklearn import metrics
from sklearn.tree import DecisionTreeClassifier
# 查看数据类型
iris.shape
# 数据集划分为训练集和测试集
train, test = train_test_split(iris, test_size = 0.3)
print(train.shape)
print(test.shape)
# 分别对训练集和测试集进行输入
train_X = train[['SepalLengthCm','SepalWidthCm','PetalLengthCm','PetalWidthCm']]
train_y=train.Species
test_X= test[['SepalLengthCm','SepalWidthCm','PetalLengthCm','PetalWidthCm']]
test_y =test.Species
# 查看是否成功
train_X.head(2)
# 支持向量机的算法对其进行测试
model = svm.SVC()
model.fit(train_X,train_y)
prediction=model.predict(test_X)
print('The accuracy of the SVM is:',metrics.accuracy_score(prediction,test_y))
# 采用逻辑回归的算法对其进行测试
model = LogisticRegression()
model.fit(train_X,train_y)
prediction=model.predict(test_X)
print('The accuracy of the Logistic Regression is',metrics.accuracy_score(prediction,test_y))
# 采用决策树算法对其进行测试
model=DecisionTreeClassifier()
model.fit(train_X,train_y)
prediction=model.predict(test_X)
print('The accuracy of the Decision Tree is',metrics.accuracy_score(prediction,test_y))
# 采用K邻近算法对其进行测试
model=KNeighborsClassifier(n_neighbors=3)
model.fit(train_X,train_y)
prediction=model.predict(test_X)
print('The accuracy of the KNN is',metrics.accuracy_score(prediction,test_y))
# 输出以K邻近算法对其进行测试的模型
a_index=list(range(1,11))
#a=pd.Series()
a=pd.Series(dtype='float64')
x=[1,2,3,4,5,6,7,8,9,10]
for i in list(range(1,11)):
    model=KNeighborsClassifier(n_neighbors=i) 
    model.fit(train_X,train_y)
    prediction=model.predict(test_X)
    a=a.append(pd.Series(metrics.accuracy_score(prediction,test_y)))
plt.plot(a_index, a)
plt.xticks(x)
# 在上面的模型中，我们是用了鸢尾花所有的特征值来给算法进行训练
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
# SVM算法
model=svm.SVC()
model.fit(train_x_p,train_y_p) 
prediction=model.predict(test_x_p) 
print('The accuracy of the SVM using Petals is:',metrics.accuracy_score(prediction,test_y_p))

model=svm.SVC()
model.fit(train_x_s,train_y_s) 
prediction=model.predict(test_x_s) 
print('The accuracy of the SVM using Sepal is:',metrics.accuracy_score(prediction,test_y_s))
# 逻辑回归算法
model = LogisticRegression()
model.fit(train_x_p,train_y_p) 
prediction=model.predict(test_x_p) 
print('The accuracy of the Logistic Regression 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 Logistic Regression using Sepals is:',metrics.accuracy_score(prediction,test_y_s))# 决策树算法
model=DecisionTreeClassifier()
model.fit(train_x_p,train_y_p) 
prediction=model.predict(test_x_p) 
print('The accuracy of the Decision Tree 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 Decision Tree using Sepals is:',metrics.accuracy_score(prediction,test_y_s))
# K邻近算法
model=KNeighborsClassifier(n_neighbors=3) 
model.fit(train_x_p,train_y_p) 
prediction=model.predict(test_x_p) 
print('The accuracy of the KNN 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 KNN using Sepals is:',metrics.accuracy_score(prediction,test_y_s))

以上代码是本次实验的全部代码，需要者自行复制运行即可，前提你已经把环境以及需要安装的库安装好。