Jupyter下完成一个鸢尾花数据集的线性多分类、可视化显示与测试精度
一、Iris数据集的Fisher线性分类
(1)iris的数据来源:https://gitee.com/melicent/titantic_and_iris_dataset/blob/master/iris.csv
(2)完成Iris数据集的 Fisher线性分类判断准确率
实验代码:
2.1实验1:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
path=r'iris.csv'
df = pd.read_csv(path, header=0)
Iris1=df.values[0:50,0:4]
Iris2=df.values[50:100,0:4]
Iris3=df.values[100:150,0:4]
m1=np.mean(Iris1,axis=0)
m2=np.mean(Iris2,axis=0)
m3=np.mean(Iris3,axis=0)
s1=np.zeros((4,4))
s2=np.zeros((4,4))
s3=np.zeros((4,4))
for i in range(0,30,1):
a=Iris1[i,:]-m1
a=np.array([a])
b=a.T
s1=s1+np.dot(b,a)
for i in range(0,30,1):
c=Iris2[i,:]-m2
c=np.array([c])
d=c.T
s2=s2+np.dot(d,c)
#s2=s2+np.dot((Iris2[i,:]-m2).T,(Iris2[i,:]-m2))
for i in range(0,30,1):
a=Iris3[i,:]-m3
a=np.array([a])
b=a.T
s3=s3+np.dot(b,a)
sw12=s1+s2
sw13=s1+s3
sw23=s2+s3
#投影方向
a=np.array([m1-m2])
sw12=np.array(sw12,dtype='float')
sw13=np.array(sw13,dtype='float')
sw23=np.array(sw23,dtype='float')
#判别函数以及T
#需要先将m1-m2转化成矩阵才能进行求其转置矩阵
a=m1-m2
a=np.array([a])
a=a.T
b=m1-m3
b=np.array([b])
b=b.T
c=m2-m3
c=np.array([c])
c=c.T
w12=(np.dot(np.linalg.inv(sw12),a)).T
w13=(np.dot(np.linalg.inv(sw13),b)).T
w23=(np.dot(np.linalg.inv(sw23),c)).T
#print(m1+m2) #1x4维度 invsw12 4x4维度 m1-m2 4x1维度
T12=-0.5*(np.dot(np.dot((m1+m2),np.linalg.inv(sw12)),a))
T13=-0.5*(np.dot(np.dot((m1+m3),np.linalg.inv(sw13)),b))
T23=-0.5*(np.dot(np.dot((m2+m3),np.linalg.inv(sw23)),c))
kind1=0
kind2=0
kind3=0
newiris1=[]
newiris2=[]
newiris3=[]
for i in range(30,49):
x=Iris1[i,:]
x=np.array([x])
g12=np.dot(w12,x.T)+T12
g13=np.dot(w13,x.T)+T13
g23=np.dot(w23,x.T)+T23
if g12>0 and g13>0:
newiris1.extend(x)
kind1=kind1+1
elif g12<0 and g23>0:
newiris2.extend(x)
elif g13<0 and g23<0 :
newiris3.extend(x)
#print(newiris1)
for i in range(30,49):
x=Iris2[i,:]
x=np.array([x])
g12=np.dot(w12,x.T)+T12
g13=np.dot(w13,x.T)+T13
g23=np.dot(w23,x.T)+T23
if g12>0 and g13>0:
newiris1.extend(x)
elif g12<0 and g23>0:
newiris2.extend(x)
kind2=kind2+1
elif g13<0 and g23<0 :
newiris3.extend(x)
for i in range(30,50):
x=Iris3[i,:]
x=np.array([x])
g12=np.dot(w12,x.T)+T12
g13=np.dot(w13,x.T)+T13
g23=np.dot(w23,x.T)+T23
if g12>0 and g13>0:
newiris1.extend(x)
elif g12<0 and g23>0:
newiris2.extend(x)
elif g13<0 and g23<0 :
newiris3.extend(x)
kind3=kind3+1
#花瓣与花萼的长度散点图
plt.scatter(df.values[:50, 3], df.values[:50, 1], color='red', marker='o', label='setosa')
plt.scatter(df.values[50:100, 3], df.values[50: 100, 1], color='blue', marker='x', label='versicolor')
plt.scatter(df.values[100:150, 3], df.values[100: 150, 1], color='green', label='virginica')
plt.xlabel('petal length')
plt.ylabel('sepal length')
plt.title("花瓣与花萼长度的散点图")
plt.rcParams['font.sans-serif']=['SimHei'] #显示中文标签
plt.rcParams['axes.unicode_minus']=False
plt.legend(loc='upper left')
plt.show()
#花瓣与花萼的宽度度散点图
plt.scatter(df.values[:50, 4], df.values[:50, 2], color='red', marker='o', label='setosa')
plt.scatter(df.values[50:100, 4], df.values[50: 100, 2], color='blue', marker='x', label='versicolor')
plt.scatter(df.values[100:150, 4], df.values[100: 150, 2], color='green', label='virginica')
plt.xlabel('petal width')
plt.ylabel('sepal width')
plt.title("花瓣与花萼宽度的散点图")
plt.legend(loc='upper left')
plt.show()
correct=(kind1+kind2+kind3)/60
print("样本类内离散度矩阵S1:",s1,'\n')
print("样本类内离散度矩阵S2:",s2,'\n')
print("样本类内离散度矩阵S3:",s3,'\n')
print('-----------------------------------------------------------------------------------------------')
print("总体类内离散度矩阵Sw12:",sw12,'\n')
print("总体类内离散度矩阵Sw13:",sw13,'\n')
print("总体类内离散度矩阵Sw23:",sw23,'\n')
print('-----------------------------------------------------------------------------------------------')
print('判断出来的综合正确率:',correct*100,'%')
实验结果:
2.2.实验2:
import numpy as np
from sklearn.linear_model import LogisticRegression
import matplotlib.pyplot as plt
import matplotlib as mpl
from sklearn import preprocessing
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
df=pd.read_csv(r'iris.csv')
x = df.values[:, :-1]
y = df.values[:, -1]
print('x = \n', x)
print('y = \n', y)
le = preprocessing.LabelEncoder()
le.fit(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'])
print(le.classes_)
y = le.transform(y)
print('Last Version, y = \n', y)
x = x[:, :2]
print(x)
print(y)
x = StandardScaler().fit_transform(x)
lr = LogisticRegression() # Logistic回归模型
lr.fit(x, y.ravel()) # 根据数据[x,y],计算回归参数N, M = 500, 500 # 横纵各采样多少个值
x1_min, x1_max = x[:, 0].min(), x[:, 0].max() # 第0列的范围
x2_min, x2_max = x[:, 1].min(), x[:, 1].max() # 第1列的范围
t1 = np.linspace(x1_min, x1_max, N)
t2 = np.linspace(x2_min, x2_max, M)
x1, x2 = np.meshgrid(t1, t2) # 生成网格采样点
x_test = np.stack((x1.flat, x2.flat), axis=1) # 测试点
cm_light = mpl.colors.ListedColormap(['#77E0A0', '#FF8080', '#A0A0FF'])
cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
y_hat = lr.predict(x_test) # 预测值
y_hat = y_hat.reshape(x1.shape) # 使之与输入的形状相同
plt.pcolormesh(x1, x2, y_hat, cmap=cm_light) # 预测值的显示
plt.scatter(x[:, 0], x[:, 1], c=y.ravel(), edgecolors='k', s=50, cmap=cm_dark)
plt.xlabel('petal length')
plt.ylabel('petal width')
plt.xlim(x1_min, x1_max)
plt.ylim(x2_min, x2_max)
plt.grid()
plt.savefig('2.png')
plt.show()
y_hat = lr.predict(x)
y = y.reshape(-1)
result = y_hat == y
print(y_hat)
print(result)
acc = np.mean(result)
print('准确度: %.2f%%' % (100 * acc))
实验结果:
2.3实验3:
import numpy as np
from sklearn.linear_model import LogisticRegression
import matplotlib.pyplot as plt
import matplotlib as mpl
from sklearn import preprocessing
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
df = pd.read_csv('http://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data', header=0)
x = df.values[:, :-1]
y = df.values[:, -1]
print('x = \n', x)
print('y = \n', y)
le = preprocessing.LabelEncoder()
le.fit(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'])
print(le.classes_)
y = le.transform(y)
print('Last Version, y = \n', y)
x = x[:, :2]
print(x)
print(y)
x = StandardScaler().fit_transform(x)
lr = LogisticRegression() # Logistic回归模型
lr.fit(x, y.ravel()) # 根据数据[x,y],计算回归参数N, M = 500, 500 # 横纵各采样多少个值
x1_min, x1_max = x[:, 0].min(), x[:, 0].max() # 第0列的范围
x2_min, x2_max = x[:, 1].min(), x[:, 1].max() # 第1列的范围
t1 = np.linspace(x1_min, x1_max, N)
t2 = np.linspace(x2_min, x2_max, M)
x1, x2 = np.meshgrid(t1, t2) # 生成网格采样点
x_test = np.stack((x1.flat, x2.flat), axis=1) # 测试点
cm_light = mpl.colors.ListedColormap(['#77E0A0', '#FF8080', '#A0A0FF'])
cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
y_hat = lr.predict(x_test) # 预测值
y_hat = y_hat.reshape(x1.shape) # 使之与输入的形状相同
plt.pcolormesh(x1, x2, y_hat, cmap=cm_light) # 预测值的显示
plt.scatter(x[:, 0], x[:, 1], c=y.ravel(), edgecolors='k', s=50, cmap=cm_dark)
plt.xlabel('petal length')
plt.ylabel('petal width')
plt.xlim(x1_min, x1_max)
plt.ylim(x2_min, x2_max)
plt.grid()
plt.savefig('2.png')
plt.show()
实验结果: