2026-rff_mp/SorokinAD/[1]lab_1/MP_hash-table.py

456 lines
16 KiB
Python
Raw Normal View History

from MP_records import records
import string
import random as rd
import time
import csv
import codecs
def polynomial_hash(word):
p=11111
m=(10**9)+9
hashh=0
for i in range(len(word)):
hashh+=ord(word[i])*(p**i)
hashh=hashh%m
return hashh
def hash_to_index(hashh,length):
#print(hashh)
#if len(str(hashh))>4:
#hashh=int(str(hashh)[3:])
while hashh>length:
hashh=hashh%(length)
return hashh
def ll_insert(table,name,phone,index):
if table[index]==None:
entry={"name":name,"phone":phone,"next":None}
table[index]=entry
return table
else:
entry={"name":name,"phone":phone,"next":None}
if table[index]["phone"]==phone:
table[index]["name"]=name
return table
if table[index]["next"]==None:
table[index]["next"]=entry
return table
else:
nexxt=table[index]["next"]
if nexxt["phone"]==phone:
nexxt["name"]=name
return table
while nexxt["next"]!=None:
nexxt=nexxt["next"]
if nexxt["phone"]==phone:
nexxt["name"]=name
return table
nexxt["next"]=entry
return table
def ht_insert(table,name,phone):
index=hash_to_index(polynomial_hash(name), len(table))
ll_insert(table,name,phone,index)
return table
def ht_find(table, name):
index=hash_to_index(polynomial_hash(name), len(table))
if table[index]!=None:
if table[index]["name"]==name:
return table[index]["phone"]
elif table[index]["next"]!=None:
if table[index]["next"]["name"]==name:
return table[index]["next"]["phone"]
else:
nexxt=table[index]["next"]
while nexxt["next"]!=None:
nexxt=nexxt["next"]
if nexxt["name"]==name:
return nexxt["phone"]
return None
def ht_delete(table,name):
index=hash_to_index(polynomial_hash(name), len(table))
if len(table)>0:
if table[index]["name"]==name:
if table[index]["next"]!=None:
table[index]=table[index]["next"]
return table
else:
table[index]=None
return table
elif table[index]["next"]!=None:
if table[index]["next"]["name"]==name:
if table[index]["next"]["next"]!=None:
table[index]["next"]=table[index]["next"]["next"]
return table
else:
table[index]["next"]=None
return table
elif table[index]["next"]["next"]!=None:
nexxt1=table[index]["next"]
nexxt2=nexxt1["next"]
if nexxt2["name"]==name:
if nexxt2["next"]!=None:
nexxt1["next"]=nexxt2["next"]
return table
else:
nexxt1["next"]=None
return table
while nexxt2["next"]!=None:
nexxt1=nexxt2
nexxt2=nexxt1["next"]
if nexxt2["name"]==name:
if nexxt2["next"]!=None:
nexxt1["next"]=nexxt2["next"]
return table
else:
nexxt1["next"]=None
return table
def bad_sort(names,phones):
names1=[]
phones1=[]
while len(names)>0:
min_=names[0].encode()
ph=phones[0]
for i in range(len(names)):
nm=names[i].encode()
if nm<min_:
min_=nm
ph=phones[i]
#print(min_.decode()," - ",ph)
names1.append(min_.decode())
phones1.append(ph)
names.remove(min_.decode())
phones.remove(ph)
#print(names1,"\n",phones1)
return names1, phones1
def Shell(names,phones):
N = len(names)
n = N // 2
while n>0:
for i in range (0,N-n):
j=i
while j+n<N:
if (names[j].encode())>(names[j+n].encode()):
t=names[j]
t1=phones[j]
names[j]=names[j+n]
phones[j]=phones[j+n]
names[j+n]=t
phones[j+n]=t1
j=i
else:
j+=n
n=n//2
return names,phones
def ht_listall(table):
names=[]
phones=[]
pointer=0
while pointer<len(table):
if table[pointer]!=None:
names.append(table[pointer]["name"])
phones.append(table[pointer]["phone"])
if table[pointer]["next"]!=None:
names.append(table[pointer]["next"]["name"])
phones.append(table[pointer]["next"]["phone"])
nexxt=table[pointer]["next"]
while nexxt["next"]!=None:
nexxt=nexxt["next"]
names.append(nexxt["name"])
phones.append(nexxt["phone"])
pointer+=1
names1, phones1 = bad_sort(names, phones)
#names1, phones1 = Shell(names, phones)
for i in range(len(names1)):
print(names1[i]," - ",phones1[i],end='')
if i%4==0:
print("\n")
else:
print(", ",end='')
print("\n")
def test():
table=[]
for i in range(8):
table.append(None)
ht_insert(table, "Zyky", 1)
ht_insert(table, "Abba", 2)
ht_insert(table, "Babba", 3)
ht_insert(table, "Aaaaa", 4)
ht_insert(table, "Aakk", 5)
ht_insert(table, "Bfaw", 6)
ht_insert(table, "Uno", 7)
ht_insert(table, "Uk", 8)
ht_insert(table, "Uaa", 9)
ht_insert(table, "h", 10)
print(table)
print(ht_find(table,"Aakk"))
# ht_delete(table, "Aakk")
#ht_delete(table, "Aaaaa")
#print(table)
#ht_delete(table, "Uaa")
#ht_delete(table, "Zyky")
print(table)
ht_listall(table)
def run_shuffled(records_shuffled):
insertion_times=[]
finding_times=[]
deletion_times1=[]
print("Shuffled list: ")
for k in range(5):
lisst=[]
for i in range(5000):
lisst.append(None)
rd.shuffle(records_shuffled)
#А. Вставка всех записей
start=time.perf_counter()
for i in range(len(records_shuffled)):
ht_insert(lisst, records_shuffled[i][0], records_shuffled[i][1])
end=time.perf_counter()
insertion_times.append(end-start)
#Б. Поиск 100 случайных записей
names=[]
index=rd.randint(0,9899)
for i in range(100):
names.append(records_shuffled[index][0])
index+=1
for i in range(10):
names.append("A")
rd.shuffle(names)
start=time.perf_counter()
for i in range(len(names)):
ht_find(lisst,names[i])
end=time.perf_counter()
finding_times.append(end-start)
#В. Удаление 50 случайных записей
for i in range(10):
names.remove("A")
rd.shuffle(names)
deletion_times=[]
for i in range(50):
start=time.perf_counter()
ht_delete(lisst,names[i])
end=time.perf_counter()
ttt=end-start
deletion_times.append(ttt)
deletion_times1.append(deletion_times)
print("Run number ",k+1)
print("Insertion time: ",insertion_times[k])
print("Finding time: ",finding_times[k])
print("Deletion times: ","\n",deletion_times)
print("\n")
temp=0
for i in range(5):
temp+=insertion_times[i]
temp=temp/5
results = [
[u"Структура", u"Режим", u"Операция", u"Время (сек)"],
["HashTable", u"случайный", u"вставка", insertion_times[0]],
["HashTable", u"случайный", u"вставка", insertion_times[1]],
["HashTable", u"случайный", u"вставка", insertion_times[2]],
["HashTable", u"случайный", u"вставка", insertion_times[3]],
["HashTable", u"случайный", u"вставка", insertion_times[4]],
[u"Структура", u"Режим", u"Операция", u"Среднее время (сек)"],
["HashTable", u"случайный", u"вставка", temp,]
]
with codecs.open("results.csv", "a+", "utf-16") as f:
writer = csv.writer(f)
writer.writerows(results)
writer.writerows("\n")
temp=0
for i in range(5):
temp+=finding_times[i]
temp=temp/5
results = [
[u"Структура", u"Режим", u"Операция", u"Время (сек)"],
["HashTable", u"случайный", u"поиск", finding_times[0]],
["HashTable", u"случайный", u"поиск", finding_times[1]],
["HashTable", u"случайный", u"поиск", finding_times[2]],
["HashTable", u"случайный", u"поиск", finding_times[3]],
["HashTable", u"случайный", u"поиск", finding_times[4]],
[u"Структура", u"Режим", u"Операция", u"Среднее время (сек)"],
["HashTable", u"случайный", u"поиск", temp,]
]
with codecs.open("results.csv", "a+", "utf-16") as f:
writer = csv.writer(f)
writer.writerows(results)
writer.writerows("\n")
temp=0
del_times=[]
for i in range(5):
for j in range(50):
temp+=deletion_times1[i][j]
temp=temp/50
del_times.append(temp)
temp=0
temp=0
for i in range(5):
temp+=del_times[i]
temp=temp/5
results = [
[u"Структура", u"Режим", u"Операция", u"Время (сек)"],
["HashTable", u"случайный", u"удаление", del_times[0]],
["HashTable", u"случайный", u"удаление", del_times[1]],
["HashTable", u"случайный", u"удаление", del_times[2]],
["HashTable", u"случайный", u"удаление", del_times[3]],
["HashTable", u"случайный", u"удаление", del_times[4]],
[u"Структура", u"Режим", u"Операция", u"Среднее время (сек)"],
["HashTable", u"случайный", u"удаление", temp,]
]
with codecs.open("results.csv", "a+", "utf-16") as f:
writer = csv.writer(f)
writer.writerows(results)
writer.writerows("\n")
writer.writerows("\n")
def run_sorted(records_shuffled):
insertion_times=[]
finding_times=[]
deletion_times1=[]
print("Sorted list: ")
for k in range(5):
lisst=[]
for i in range(5000):
lisst.append(None)
#А. Вставка всех записей
start=time.perf_counter()
for i in range(len(records_shuffled)):
ht_insert(lisst, records_shuffled[i][0], records_shuffled[i][1])
end=time.perf_counter()
insertion_times.append(end-start)
#Б. Поиск 100 случайных записей
names=[]
index=rd.randint(0,9899)
for i in range(100):
names.append(records_shuffled[index][0])
index+=1
for i in range(10):
names.append("A")
rd.shuffle(names)
start=time.perf_counter()
for i in range(len(names)):
ht_find(lisst,names[i])
end=time.perf_counter()
finding_times.append(end-start)
#В. Удаление 50 случайных записей
for i in range(10):
names.remove("A")
rd.shuffle(names)
deletion_times=[]
for i in range(50):
start=time.perf_counter()
ht_delete(lisst,names[i])
end=time.perf_counter()
ttt=end-start
deletion_times.append(ttt)
deletion_times1.append(deletion_times)
print("Run number ",k+1)
print("Insertion time: ",insertion_times[k])
print("Finding time: ",finding_times[k])
print("Deletion average:", sum(deletion_times))
print("\n")
temp=0
for i in range(5):
temp+=insertion_times[i]
temp=temp/5
results = [
[u"Структура", u"Режим", u"Операция", u"Время (сек)"],
["HashTable", u"отсортированный", u"вставка", insertion_times[0]],
["HashTable", u"отсортированный", u"вставка", insertion_times[1]],
["HashTable", u"отсортированный", u"вставка", insertion_times[2]],
["HashTable", u"отсортированный", u"вставка", insertion_times[3]],
["HashTable", u"сотсортированный", u"вставка", insertion_times[4]],
[u"Структура", u"Режим", u"Операция", u"Среднее время (сек)"],
["HashTable", u"отсортированный", u"вставка", temp,]
]
with codecs.open("results.csv", "a+", "utf-16") as f:
writer = csv.writer(f)
writer.writerows(results)
writer.writerows("\n")
temp=0
for i in range(5):
temp+=finding_times[i]
temp=temp/5
results = [
[u"Структура", u"Режим", u"Операция", u"Время (сек)"],
["HashTable", u"отсортированный", u"поиск", finding_times[0]],
["HashTable", u"отсортированный", u"поиск", finding_times[1]],
["HashTable", u"отсортированный", u"поиск", finding_times[2]],
["HashTable", u"отсортированный", u"поиск", finding_times[3]],
["HashTable", u"отсортированный", u"поиск", finding_times[4]],
[u"Структура", u"Режим", u"Операция", u"Среднее время (сек)"],
["HashTable", u"отсортированный", u"поиск", temp,]
]
with codecs.open("results.csv", "a+", "utf-16") as f:
writer = csv.writer(f)
writer.writerows(results)
writer.writerows("\n")
temp=0
del_times=[]
for i in range(5):
for j in range(50):
temp+=deletion_times1[i][j]
temp=temp/50
del_times.append(temp)
temp=0
temp=0
for i in range(5):
temp+=del_times[i]
temp=temp/5
results = [
[u"Структура", u"Режим", u"Операция", u"Время (сек)"],
["HashTable", u"отсортированный", u"удаление", del_times[0]],
["HashTable", u"отсортированный", u"удаление", del_times[1]],
["HashTable", u"отсортированный", u"удаление", del_times[2]],
["HashTable", u"отсортированный", u"удаление", del_times[3]],
["HashTable", u"отсортированный", u"удаление", del_times[4]],
[u"Структура", u"Режим", u"Операция", u"Среднее время (сек)"],
["HashTable", u"отсортированный", u"удаление", temp,]
]
with codecs.open("results.csv", "a+", "utf-16") as f:
writer = csv.writer(f)
writer.writerows(results)
writer.writerows("\n")
writer.writerows("\n")
records_shuffled, records_sorted = records()
run_shuffled(records_shuffled)
run_sorted(records_sorted)