glitchlings 0.1.3__py3-none-any.whl → 0.1.4__py3-none-any.whl

glitchlings/dlc/prime.py

@@ -1,10 +1,59 @@
+"""Integration helpers for the optional verifiers prime DLC."""
+
+from __future__ import annotations
+
+from collections.abc import Iterable, Sequence
 from enum import Enum
-import functools as ft
 
 import verifiers as vf
-from datasets import Dataset
 
-from ..zoo import Glitchling, Gaggle, Mim1c, Typogre, summon
+try:
+    from datasets import Dataset
+except ModuleNotFoundError:  # pragma: no cover - optional dependency
+    Dataset = object  # type: ignore[assignment]
+
+from ..zoo import Gaggle, Glitchling, Mim1c, Typogre, summon
+
+
+def _resolve_environment(env: str | vf.Environment) -> vf.Environment:
+    """Return a fully-instantiated verifier environment."""
+
+    if isinstance(env, str):
+        env = vf.load_environment(env)
+
+    if not isinstance(env, vf.Environment):
+        raise TypeError("Invalid environment type")
+
+    return env
+
+
+def _resolve_columns(dataset: Dataset, columns: Sequence[str] | None) -> list[str]:
+    """Identify which dataset columns should be corrupted."""
+
+    available = set(dataset.column_names)
+
+    if columns is not None:
+        missing = sorted(set(columns) - available)
+        if missing:
+            missing_str = ", ".join(missing)
+            raise ValueError(f"Columns not found in dataset: {missing_str}")
+        return list(columns)
+
+    for candidate in ("prompt", "question"):
+        if candidate in available:
+            return [candidate]
+
+    sample = dataset[0] if len(dataset) else {}
+    inferred = [
+        name
+        for name in dataset.column_names
+        if isinstance(sample.get(name), str)
+    ]
+
+    if inferred:
+        return inferred
+
+    raise ValueError("Unable to determine which dataset columns to corrupt.")
 
 
 class Difficulty(Enum):
@@ -18,35 +67,47 @@ class Difficulty(Enum):
 
 
 def tutorial_level(
-    env: vf.Environment | str, seed=151, difficulty: Difficulty = Difficulty.Normal
+    env: vf.Environment | str,
+    seed: int = 151,
+    difficulty: Difficulty = Difficulty.Normal,
 ) -> vf.Environment:
-    """Create a low-corruption environment."""
+    """Create a low-corruption environment using tuned defaults."""
 
     tuned_mim1c = Mim1c(replacement_rate=0.01 * difficulty.value)
     tuned_typogre = Typogre(max_change_rate=0.025 * difficulty.value)
 
-    glitchlings: Gaggle = summon([tuned_mim1c, tuned_typogre], seed=seed)
+    return load_environment(
+        env,
+        glitchlings=[tuned_mim1c, tuned_typogre],
+        seed=seed,
+    )
 
-    if isinstance(env, str):
-        env = vf.load_environment(env)
 
-    assert isinstance(env, vf.Environment), "Invalid environment type"
+def load_environment(
+    env: str | vf.Environment,
+    glitchlings: Iterable[str | Glitchling] | Glitchling | str | Gaggle | None = None,
+    *,
+    seed: int = 151,
+    columns: Sequence[str] | None = None,
+) -> vf.Environment:
+    """Load an environment and optionally corrupt it with glitchlings."""
+
+    environment = _resolve_environment(env)
 
-    if "prompt" in env.dataset.column_names:
-        env.dataset = glitchlings.corrupt_dataset(env.dataset, ["prompt"])
-    elif "question" in env.dataset.column_names:
-        env.dataset = glitchlings.corrupt_dataset(env.dataset, ["question"])
-    else:
-        raise ValueError("Can't find prompt or question column")
+    if glitchlings is None:
+        return environment
 
-    return env
+    if isinstance(glitchlings, Gaggle):
+        gaggle = glitchlings
+    else:
+        if isinstance(glitchlings, (Glitchling, str)):
+            resolved = [glitchlings]
+        else:
+            resolved = list(glitchlings)
 
+        gaggle = summon(resolved, seed=seed)
 
-def load_environment(
-    env: str | vf.Environment,
-    seed=151,
-    difficulty: Difficulty = Difficulty.Normal,
-    loader=tutorial_level,
-) -> vf.Environment:
-    """Load an environment by name."""
-    return loader(env, seed=seed, difficulty=difficulty)
+    dataset = environment.dataset
+    corrupt_columns = _resolve_columns(dataset, columns)
+    environment.dataset = gaggle.corrupt_dataset(dataset, corrupt_columns)
+    return environment

{glitchlings-0.1.3.dist-info → glitchlings-0.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: glitchlings
-Version: 0.1.3
+Version: 0.1.4
 Summary: Monsters for your language games.
 Project-URL: Homepage, https://github.com/osoleve/glitchlings
 Project-URL: Repository, https://github.com/osoleve/glitchlings.git
@@ -225,6 +225,7 @@ Requires-Dist: datasets>=4.0.0
 Requires-Dist: jellyfish>=1.2.0
 Requires-Dist: nltk>=3.9.1
 Provides-Extra: dev
+Requires-Dist: hypothesis>=6.100.0; extra == 'dev'
 Requires-Dist: pytest>=8.0.0; extra == 'dev'
 Provides-Extra: prime
 Requires-Dist: verifiers>=0.1.3.post0; extra == 'prime'
@@ -283,6 +284,30 @@ print(gaggle(SAMPLE_TEXT))
 
 > Onҽ m‎ھ‎rning, wһen Gregor Samƽa woke from trouble𝐝 𝑑reams, he found himself transformed in his bed into a horrible vermin‎٠‎ He l   lay on his armour-like back, and if he lifted his head a little he could see his brown belly, slightlh domed and divided by arches ino stiff sections. The bedding was adly able to cover it and and seemed ready to slide off any  moment. His many legxs, pitifully thin compared with the size of the the rest of him, waved about helplessly ashe looked looked.
 
+## Usage
+
+Glitchlings slot into evaluation pipelines just as easily as they corrupt stray strings.
+
+- **Direct invocation** – Instantiate a glitchling (or `Gaggle`) and call it on strings, iterables, or datasets. Keep the seed stable to make every run deterministic.
+- **Dataset corruption** – Use a `Gaggle`'s `.corrupt_dataset` helper to perturb a Hugging Face `datasets.Dataset` and return a corrupted copy for training or evaluation.
+
+### Prime Intellect environments
+
+After `pip install -e .[prime]`, the `glitchlings.dlc.prime.load_environment` helper mirrors `verifiers.load_environment` for Prime Intellect scenarios while optionally applying glitchlings before returning the environment:
+
+```python
+from glitchlings import Mim1c, Typogre
+from glitchlings.dlc.prime import load_environment
+
+env = load_environment(
+    "osoleve/syllabify-en",
+    glitchlings=[Mim1c(replacement_rate=0.01), Typogre(max_change_rate=0.02)],
+    seed=404,
+)
+```
+
+Skip the `glitchlings` argument to receive an untouched verifier dataset.
+
 ## Motivation
 
 If your model performs well on a particular task, but not when `Glitchling`s are present, it's a sign that it hasn't actually generalized to the problem.

{glitchlings-0.1.3.dist-info → glitchlings-0.1.4.dist-info}/RECORD

@@ -2,7 +2,7 @@ glitchlings/__init__.py,sha256=yD0BaldUpcc_QlHVca1z1iwpOp8ne1H9YVQHc85d1So,580
 glitchlings/__main__.py,sha256=EOiBgay0x6B9VlSDzSQvMuoq6bHJdSvFSgcAVGGKkd4,121
 glitchlings/main.py,sha256=1pdVqytcrkh_GxOb0UPnZ0NzYKMoUnXmAWQB4cY5SEg,6199
 glitchlings/dlc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-glitchlings/dlc/prime.py,sha256=WnLIon2WbdPGx_PK4vF6nOwJICXudZ6zKGR1hVES4Oc,1452
+glitchlings/dlc/prime.py,sha256=3ugrF7SQTh64JTiH3F3Xii2m1eybRaVRX5sqd1WxrME,3078
 glitchlings/util/__init__.py,sha256=OCpWFtloU-sATBv2XpBGlkR7UFR6RemUtuCheuRA4yw,4018
 glitchlings/zoo/__init__.py,sha256=hXQci2tysMoRHXiR6NDkWtGkKgcO0xxsMB91eiM_Llc,1344
 glitchlings/zoo/core.py,sha256=5f9pWBZZSDADiUSs-xUahIqCEb9EUq-YcR_N5HzBAw0,8021
@@ -13,8 +13,8 @@ glitchlings/zoo/reduple.py,sha256=ML4TLQNfOkSaF7G9Sjy_i9ILB4FIl1I101CIppNGmOw,27
 glitchlings/zoo/rushmore.py,sha256=FH-pHnj1XKFzLRRQIHOojTkbkCpipNKnxSfxP9UGYZI,2528
 glitchlings/zoo/scannequin.py,sha256=4QP_dpReUxno0mk5Hnn2uCfd3B6eDa7ZGePuW1dyqBU,4630
 glitchlings/zoo/typogre.py,sha256=8aYULO4nvdyFDsknAfrlQYKeWz_Tgh5uXAkF3omHe0o,5358
-glitchlings-0.1.3.dist-info/METADATA,sha256=fwqJfu1FrQwJfAnc5UQIaaN3L7er_FWek0cMzRFSVuw,24978
-glitchlings-0.1.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-glitchlings-0.1.3.dist-info/entry_points.txt,sha256=kGOwuAsjFDLtztLisaXtOouq9wFVMOJg5FzaAkg-Hto,54
-glitchlings-0.1.3.dist-info/licenses/LICENSE,sha256=YCvGip-LoaRyu6h0nPo71q6eHEkzUpsE11psDJOIRkw,11337
-glitchlings-0.1.3.dist-info/RECORD,,
+glitchlings-0.1.4.dist-info/METADATA,sha256=tbagFiEgfGaqU2DrARiOsUJKlwGWaUFXVIk7Flcgd7M,26059
+glitchlings-0.1.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+glitchlings-0.1.4.dist-info/entry_points.txt,sha256=kGOwuAsjFDLtztLisaXtOouq9wFVMOJg5FzaAkg-Hto,54
+glitchlings-0.1.4.dist-info/licenses/LICENSE,sha256=YCvGip-LoaRyu6h0nPo71q6eHEkzUpsE11psDJOIRkw,11337
+glitchlings-0.1.4.dist-info/RECORD,,