Skip to content

do setup only once #89

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
JostMigenda wants to merge 2 commits into from
Closed

do setup only once #89

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5e6cb1f
do setup only once
JostMigenda Jul 7, 2025
4df35e5
remove pRNG seeds
JostMigenda Jul 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
50 changes: 18 additions & 32 deletions episodes/optimisation-data-structures-algorithms.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -238,41 +238,35 @@ If you reduce the value of `repeats` it will run faster, how does changing the n
import random
from timeit import timeit

def generateInputs(N = 25000):
random.seed(12) # Ensure every list is the same
return [random.randint(0,int(N/2)) for i in range(N)]

N = 25000 # Number of elements in the list
data = [random.randint(0, int(N/2)) for i in range(N)]

def uniqueSet():
ls_in = generateInputs()
set_out = set(ls_in)
set_out = set(data)

def uniqueSetAdd():
ls_in = generateInputs()
set_out = set()
for i in ls_in:
for i in data:
set_out.add(i)

def uniqueList():
ls_in = generateInputs()
ls_out = []
for i in ls_in:
for i in data:
if not i in ls_out:
ls_out.append(i)

def uniqueListSort():
ls_in = generateInputs()
ls_in.sort()
ls_in = sorted(data)
ls_out = [ls_in[0]]
for i in ls_in:
if ls_out[-1] != i:
ls_out.append(i)

repeats = 1000
gen_time = timeit(generateInputs, number=repeats)
print(f"uniqueSet: {timeit(uniqueSet, number=repeats)-gen_time:.2f}ms")
print(f"uniqueSetAdd: {timeit(uniqueSetAdd, number=repeats)-gen_time:.2f}ms")
print(f"uniqueList: {timeit(uniqueList, number=repeats)-gen_time:.2f}ms")
print(f"uniqueListSort: {timeit(uniqueListSort, number=repeats)-gen_time:.2f}ms")
print(f"uniqueSet: {timeit(uniqueSet, number=repeats):.2f}ms")
print(f"uniqueSetAdd: {timeit(uniqueSetAdd, number=repeats):.2f}ms")
print(f"uniqueList: {timeit(uniqueList, number=repeats):.2f}ms")
print(f"uniqueListSort: {timeit(uniqueListSort, number=repeats):.2f}ms")
```

:::::::::::::::::::::::: hint
Expand Down Expand Up @@ -325,41 +319,33 @@ from bisect import bisect_left
N = 25000 # Number of elements in list
M = 2 # N*M == Range over which the elements span

def generateInputs():
random.seed(12) # Ensure every list is the same
st = set([random.randint(0, int(N*M)) for i in range(N)])
ls = list(st)
ls.sort() # Sort required for binary
return st, ls # Return both set and list
st = set([random.randint(0, int(N*M)) for i in range(N)])
ls = list(st)
ls.sort() # Sort required for binary search

def search_set():
st, _ = generateInputs()
j = 0
for i in range(0, int(N*M), M):
if i in st:
j += 1

def linear_search_list():
_, ls = generateInputs()
j = 0
for i in range(0, int(N*M), M):
if i in ls:
j += 1

def binary_search_list():
_, ls = generateInputs()
j = 0
for i in range(0, int(N*M), M):
k = bisect_left(ls, i)
if k != len(ls) and ls[k] == i:
j += 1


repeats = 1000
gen_time = timeit(generateInputs, number=repeats)
print(f"search_set: {timeit(search_set, number=repeats)-gen_time:.2f}ms")
print(f"linear_search_list: {timeit(linear_search_list, number=repeats)-gen_time:.2f}ms")
print(f"binary_search_list: {timeit(binary_search_list, number=repeats)-gen_time:.2f}ms")
print(f"search_set: {timeit(search_set, number=repeats):.2f}ms")
print(f"linear_search_list: {timeit(linear_search_list, number=repeats):.2f}ms")
print(f"binary_search_list: {timeit(binary_search_list, number=repeats):.2f}ms")
```

Searching the set is fastest performing 25,000 searches in 0.04ms.
Expand Down
13 changes: 4 additions & 9 deletions episodes/optimisation-using-python.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,16 +111,13 @@ The function `manualSearch()` manually iterates through the list (`ls`) and chec

```python
import random
from timeit import timeit

N = 2500 # Number of elements in list
M = 2 # N*M == Range over which the elements span

def generateInputs():
random.seed(12) # Ensure every list is the same
return [random.randint(0, int(N*M)) for i in range(N)]
ls = [random.randint(0, int(N*M)) for i in range(N)]

def manualSearch():
ls = generateInputs()
ct = 0
for i in range(0, int(N*M), M):
for j in range(0, len(ls)):
Expand All @@ -129,16 +126,14 @@ def manualSearch():
break

def operatorSearch():
ls = generateInputs()
ct = 0
for i in range(0, int(N*M), M):
if i in ls:
ct += 1

repeats = 1000
gen_time = timeit(generateInputs, number=repeats)
print(f"manualSearch: {timeit(manualSearch, number=repeats)-gen_time:.2f}ms")
print(f"operatorSearch: {timeit(operatorSearch, number=repeats)-gen_time:.2f}ms")
print(f"manualSearch: {timeit(manualSearch, number=repeats):.2f}ms")
print(f"operatorSearch: {timeit(operatorSearch, number=repeats):.2f}ms")
```

This results in the manual Python implementation being 5x slower, doing the exact same operation!
Expand Down
Loading