feat(profiling): Add examples and setup

.gitignore

@@ -14,3 +14,6 @@ htmlcov
 .venv
 
 .DS_Store
+
+*.profile.*
+*results.txt

.vscode/launch.json

@@ -20,6 +20,13 @@
       "program": "${file}",
       "console": "integratedTerminal",
       "justMyCode": true
+    },
+    {
+      "name": "Profile current file",
+      "type": "debugpy",
+      "request": "launch",
+      "module": "cProfile",
+      "args": ["-o", "profile_data.prof", "${file}"]
     }
   ]
 }

README.md

@@ -11,7 +11,8 @@ For talks, presentations, workshops, demos.
 ```bash
 python3 -m venv .venv
 source .venv/bin/activate
-pip install -r requirements.lock -r requirements-dev.lock
+pip install pip --upgrade
+pip install -e ".[dev]"
 ```
 
 ### Option 2

pyproject.toml

@@ -109,4 +109,6 @@ dev-dependencies = [
     "ipython>=8.12.2",
     "pytest-cov>=5.0.0",
     "pytest-xdist>=3.6.1",
+    "pyinstrument>=4.7.3",
+    "snakeviz>=2.2.0",
 ]

src/profiling/README.md

@@ -0,0 +1,33 @@
+# Profiling Python code
+
+## Setup
+
+```bash
+python3 -m venv .venv
+source .venv/bin/activate
+pip install pip --upgrade
+pip install pyinstrument snakeviz
+```
+
+## Sources
+
+- https://docs.python.org/3/library/timeit.html
+- https://docs.python.org/3/library/profile.html
+- https://pyinstrument.readthedocs.io/en/latest/home.html
+- https://realpython.com/python-profiling/#pyinstrument-take-snapshots-of-the-call-stack
+
+## Profiling with pyinstrument
+
+```bash
+python -m pyinstrument --color --renderer=html --use-timing-thread --show-all --timeline --outfile _pyinstrument.profile.html src/profiling/primes.py
+python -m pyinstrument --color --renderer=html --use-timing-thread --show-all --outfile _pyinstrument.profile.html src/profiling/primes.py
+python -m pyinstrument --color --renderer=html --use-timing-thread --show-all --timeline src/profiling/primes.py
+python -m pyinstrument src/profiling/primes.py
+```
+
+## Profiling with cProfile
+
+```bash
+python -m cProfile -o _profile_data.profile.pstats src/profiling/primes.py
+python -m snakeviz _profile_data.profile.pstats
+```

src/profiling/primes.py

@@ -0,0 +1,93 @@
+import random
+import time
+
+RESULTS_FILE_NAME = "_results.txt"
+UNIQUE_RESULTS_FILE_NAME = "_unique_results.txt"
+
+
+def _slow_sort(arr):
+    n = len(arr)
+    for i in range(n):
+        for j in range(0, n - i - 1):
+            if arr[j] > arr[j + 1]:
+                arr[j], arr[j + 1] = arr[j + 1], arr[j]
+    return arr
+
+
+def sort(*args, **kwargs):
+    return _slow_sort(*args, **kwargs)
+
+
+def _slow_prime_check(n):
+    if n < 2:
+        return False
+    for i in range(2, int(n**0.5) + 1):
+        if n % i == 0:
+            return False
+    time.sleep(0.01)
+    return True
+
+
+def prime_check(*args, **kwargs):
+    return _slow_prime_check(*args, **kwargs)
+
+
+def _slow_make_unique(data):
+    unique = []
+    for item in data:
+        if item not in unique:
+            unique.append(item)
+    return unique
+
+
+def make_unique(*args, **kwargs):
+    return _slow_make_unique(*args, **kwargs)
+
+
+def _slow_save_items(results, file_name):
+    for item in results:
+        with open(file_name, "a") as f:
+            f.write(str(item) + "\n")
+
+
+def save_items(*args, **kwargs):
+    return _slow_save_items(*args, **kwargs)
+
+
+def process_data(data):
+    primes = []
+    result = []
+    for item in data:
+        if prime_check(item):
+            result.append(f"* {str(item).rjust(6)} is prime")
+            primes.append(item)
+        else:
+            result.append(f"  {str(item).rjust(6)}")
+
+    save_items(result, file_name=RESULTS_FILE_NAME)
+    save_items(make_unique(sort(primes)), file_name=UNIQUE_RESULTS_FILE_NAME)
+
+    return result
+
+
+def main():
+    with open(RESULTS_FILE_NAME, "w") as f:
+        f.write("")
+    with open(UNIQUE_RESULTS_FILE_NAME, "w") as f:
+        f.write("")
+
+    number = 1000
+    data = [random.randint(1, number) for _ in range(number)]
+
+    start_time = time.time()
+
+    sorted_data = sort(data)
+    processed_data = process_data(sorted_data)
+
+    end_time = time.time()
+
+    print(f"Time taken: {end_time - start_time:.2f}s")
+
+
+if __name__ == "__main__":
+    main()