问题描述
程序实现
# coding: utf-8
import numpy as np
import matplotlib.pyplot as plt
import time
def read_data(dataFile):
with open(dataFile, 'r') as file:
data_list = []
for line in file.readlines():
line = line.strip().split()
# add x0=1.0
data_list.append([1.0] + [float(l) for l in line])
num_data = len(data_list)
data_array = np.array(data_list)
return (num_data,data_array)
def sign(n):
if(n>0):
return 1
else:
return -1
# define PLA class
class PLA(object):
def __init__(self,num_data,data_array,training_epochs=2000,ita=1.0,qID=15):
self.num_data=num_data
self.data_array=data_array
self.training_epochs=training_epochs
self.ita=ita
self.qID=qID
def train(self,w=np.zeros([5])):
self.update_counts_list=[]
self.last_error_id_list=[]
for k in range(self.training_epochs):
if self.training_epochs==1:
id_array=np.array([m for m in range(self.num_data)])
else:
np.random.seed(k)
id_array = np.random.permutation([m for m in range(self.num_data)])
update_counts = 0
total_counts = 0
self.w=np.array(w)
id = 0
error_point_id = -1
while (total_counts <= self.num_data):
g = 0
g += np.dot(self.w, self.data_array[id_array[id]][:5])
if sign(g) == self.data_array[id_array[id]][5]:
total_counts += 1
else:
self.w += self.ita*self.data_array[id_array[id]][5] * self.data_array[id_array[id]][:5]
error_point_id = id_array[id]
update_counts += 1
total_counts = 0
id += 1
id = id % self.num_data
self.update_counts_list.append(update_counts)
self.last_error_id_list.append(error_point_id)
return
def show_results(self):
print("\n",self.qID,"...")
print("training:")
if self.training_epochs==1:
print("the number of updates: ", self.update_counts_list[0])
print("the final error point id: ", self.last_error_id_list[0])
print("-----------------------")
return
else:
print("the list of update counts: ",self.update_counts_list)
print("the list of last error point id: ",self.last_error_id_list)
print("the average number of updates:", sum(self.update_counts_list) / self.training_epochs)
print("-----------------------")
plt.figure()
plt.hist(self.update_counts_list)
plt.xlabel("the number of updates")
plt.ylabel("frequency")
plt.title(self.qID)
plt.savefig("%s_train.png"%self.qID)
return
def total_error_counts(w,data_array,num_data):
total_error_counts=0
for i in range(num_data):
if sign(np.dot(w, data_array[i][:5])) != data_array[i][5]:
total_error_counts+=1
return total_error_counts
# define PA class
class PA(PLA):
def __init__(self,num_data,data_array,num_test,test_array,
training_epochs=2000,given_updates=50,ita=1.0,pla_flag=False,qID=18):
PLA.__init__(self,num_data,data_array,training_epochs,ita,qID)
self.num_test=num_test
self.test_array=test_array
self.given_updates=given_updates
self.pla_flag=pla_flag
def train_and_test(self,w=np.zeros([5])):
self.last_error_id_list=[]
self.test_error_rate_list=[]
for k in range(self.training_epochs):
# train
if self.training_epochs==1:
id_array=np.array([m for m in range(self.num_data)])
else:
np.random.seed(k)
id_array = np.random.permutation([m for m in range(self.num_data)])
update_counts = 0
id = 0
self.pocket_w = np.array(w) # create a copy of w and give it to self.w
w=np.array(w)
error_point_id = -1
while (update_counts <= self.given_updates):
g = 0
g += np.dot(w, self.data_array[id_array[id]][:5])
if sign(g) != self.data_array[id_array[id]][5]:
w += self.ita*self.data_array[id_array[id]][5] * self.data_array[id_array[id]][:5]
if(self.pla_flag or (total_error_counts(w,self.data_array,self.num_data)
运行结果及分析
15
16
17
对比16与17的结果:
16中步长1.0,17中步长0.5,看似步长对更新次数无影响?
16.1
17.1
对比16.1与17.1的结果:
16.1中步长1.0,17.1中步长0.5,可见步长对更新次数有影响;
再看16 vs 16.1、17 vs 17.1,前者初始值[0,0,0,0,0],后者初始值[1,0,0,0,0],可见初始值对更新次数有影响。
18
19
对比18与19的结果:
可见PA(18)速度明显慢于PLA(19);但在数据线性不可分的情况下,PA表现比PLA好。
20
18.1
20.1
分别对比18与20、18.1与20.1、18与18.1、20与20.1的结果:
结论与PLA处类似,
W初始值、更新步长对分类器表现有影响。