implement shuffle benchmark

.gitignore

@@ -1,2 +1,3 @@
 .idea
-.DS_Store
+.DS_Store
+output

src/benchmark.py

@@ -4,6 +4,7 @@ import random
 from dataclasses import dataclass
 from statistics import mean, variance
 from enum import Enum
+from pathlib import Path
 
 @dataclass
 class Benchmark:
@@ -15,18 +16,18 @@ class ShuffleTypes(Enum):
     FULL_SHUFFLE = "FULL_SHUFFLE"
     SPLIT_SHUFFLE = "SPLIT_SHUFFLE"
 
-def observations(number_of_keys, properties_per_key, passcode_len, shuffle_type: ShuffleTypes = ShuffleTypes.SPLIT_SHUFFLE):
+def observations(number_of_keys, properties_per_key, passcode_len, complexity: int, disparity: int, shuffle_type: ShuffleTypes):
     k = number_of_keys
     p = properties_per_key
     n = passcode_len
-    nkode = [random.randint(0, k*p-1) for _ in range(n)]
+    passcode =  passcode_generator(k, p, n, complexity, disparity)
     keypad = Keypad.new_keypad(k, p)
 
     def obs_gen():
         for _ in range(100):  # finite number of yields
             yield Observation(
                 keypad=keypad.keypad.copy(),
-                key_selection=keypad.key_entry(target_passcode=nkode)
+                key_selection=keypad.key_entry(target_passcode=passcode)
             )
             match shuffle_type:
                 case ShuffleTypes.FULL_SHUFFLE:
@@ -38,25 +39,94 @@ def observations(number_of_keys, properties_per_key, passcode_len, shuffle_type:
 
     return obs_gen()
 
-def split_shuffle_benchmark(
+def passcode_generator(k: int, p: int, n: int, c: int, d: int) -> list[int]:
+    assert n >= c
+    assert p*k >= c
+
+    assert n >= d
+    assert p >= d
+    passcode_prop = []
+    passcode_set = []
+    valid_choices = {i for i in range(k*p)}
+    repeat_set = n-d
+    repeat_prop = n-c
+    prop_added = set()
+    set_added = set()
+
+    for _ in range(n):
+        prop = random.choice(list(valid_choices))
+        prop_set = prop//p
+        passcode_prop.append(prop)
+        passcode_set.append(prop_set)
+
+        if prop in prop_added:
+            repeat_prop -= 1
+        if prop_set in set_added:
+            repeat_set -= 1
+
+        prop_added.add(prop)
+        set_added.add(prop_set)
+
+        if repeat_prop <= 0:
+            valid_choices -= prop_added
+
+        if repeat_set <= 0:
+            for el in valid_choices.copy():
+                if el // p in set_added:
+                    valid_choices.remove(el)
+
+    return passcode_prop
+
+
+def shuffle_benchmark(
         number_of_keys: int,
         properties_per_key: int,
         passcode_len: int,
         max_tries_before_lockout: int,
         run_count: int,
+        complexity: int,
+        disparity: int,
+        shuffle_type: ShuffleTypes,
+        file_path: str = '../output',
+        overwrite: bool = False
 ) -> Benchmark:
+    file_name = f"{shuffle_type.name.lower()}-{number_of_keys}-{properties_per_key}-{passcode_len}-{max_tries_before_lockout}-{complexity}-{disparity}-{run_count}.txt"
+    full_path = Path(file_path) / file_name
+    if not overwrite and full_path.exists():
+        print(f"file exists {file_path}")
+
+        with open(full_path, "r") as fp:
+            runs = fp.readline()
+            runs = runs.split(',')
+            runs = [int(i) for i in runs]
+            return  Benchmark(
+                mean=mean(runs),
+                variance=variance(runs),
+                runs=runs
+            )
     runs = []
     for _ in range(run_count):
         evilkode = Evilkode(
-            observations=observations(number_of_keys, properties_per_key, passcode_len),
+            observations=observations(
+                number_of_keys=number_of_keys,
+                properties_per_key=properties_per_key,
+                passcode_len=passcode_len,
+                complexity=complexity,
+                disparity=disparity,
+                shuffle_type=shuffle_type,
+            ),
             number_of_keys=number_of_keys,
             properties_per_key=properties_per_key,
             passcode_len=passcode_len,
-            max_tries_before_lockout=max_tries_before_lockout
+            max_tries_before_lockout=max_tries_before_lockout,
         )
         evilout = evilkode.run()
         runs.append(evilout.iterations)
 
+    full_path.parent.mkdir(parents=True, exist_ok=True)
+    with open(full_path, "w") as fp:
+       fp.write(",".join([str(i) for i in runs])),
+
     return Benchmark(
         mean=mean(runs),
         variance=variance(runs),
@@ -70,15 +140,24 @@ def full_shuffle_benchmark(
         passcode_len: int,
         max_tries_before_lockout: int,
         run_count: int,
+        complexity: int,
+        disparity: int,
 ) -> Benchmark:
     runs = []
     for _ in range(run_count):
         evilkode = Evilkode(
-            observations=observations(number_of_keys, properties_per_key, passcode_len, shuffle_type=ShuffleTypes.FULL_SHUFFLE),
+            observations=observations(
+                number_of_keys=number_of_keys,
+                properties_per_key=properties_per_key,
+                passcode_len=passcode_len,
+                complexity=complexity,
+                disparity=disparity,
+                shuffle_type=ShuffleTypes.FULL_SHUFFLE,
+            ),
             number_of_keys=number_of_keys,
             properties_per_key=properties_per_key,
             passcode_len=passcode_len,
-            max_tries_before_lockout=max_tries_before_lockout
+            max_tries_before_lockout=max_tries_before_lockout,
         )
         evilout = evilkode.run()
         runs.append(evilout.iterations)

src/evilkode.py

@@ -1,6 +1,5 @@
 import math
 from dataclasses import dataclass
-from itertools import chain
 from typing import Iterator
 
 

tests/test_benchmark.py

@@ -0,0 +1,15 @@
+from src.benchmark import passcode_generator
+import pytest
+
+@pytest.mark.parametrize(
+    "k, p, n, c, d, runs",
+    [
+        (6, 9, 4, 4, 4, 100)
+    ]
+)
+def test_passcode_generator(k, p, n, c, d, runs):
+    for _ in range(runs):
+        passcode = passcode_generator(k=k, p=p, n=n, c=c, d=d)
+        passcode_sets = [el//p for el in passcode]
+        assert  c <= len(set(passcode))
+        assert d <= len(set(passcode_sets))