knn_classifier.py File Reference

Go to the source code of this file.

Classes
class	knn_classifier.HashEmbedder
class	knn_classifier.SentenceTransformerEmbedder
class	knn_classifier.LMStudioEmbedder
class	knn_classifier.Index
class	knn_classifier.FitCell
class	knn_classifier.Fit

Namespaces
namespace	knn_classifier

Functions
Any	knn_classifier._numpy ()
list[dict[str, str]]	knn_classifier.read_jsonl (Path path)
list[dict[str, str]]	knn_classifier.read_cases (Path path)
bytes	knn_classifier._npy_header (int rows, int dim)
bytes	knn_classifier._flat_float32 (Any matrix, int rows, int dim)
Path	knn_classifier.write_npy (Path path, Any matrix)
tuple[int, int, array]	knn_classifier.read_npy (Path path)
Any	knn_classifier._normalise_rows (Any matrix)
Path	knn_classifier.build_index (Path corpus_path, Any embedder, Path index_dir, int|None subset=None, int seed=SUBSET_SEED)
Index	knn_classifier.load_index (Path index_dir, Any embedder=None)
list[float]	knn_classifier.index_row (Index index, int position)
Any	knn_classifier._similarities (Index index, Sequence[float] query)
list[tuple[float, str]]	knn_classifier.top_neighbours (Index index, Sequence[float] query, int k)
dict[str, float]	knn_classifier.class_sums (Iterable[tuple[float, str]] neighbours)
dict[str, float]	knn_classifier.probabilities (dict[str, float] sums, float temperature, bool mask_absent=True)
tuple[str, bool]	knn_classifier.verdict_of (dict[str, float] probs)
list[float]	knn_classifier.embed_query (Index index, str command)
dict[str, float]	knn_classifier.classify (str command, Index index, int k=DEFAULT_K, float temperature=DEFAULT_TEMPERATURE, bool mask_absent=True)
list[list[tuple[float, str]]]	knn_classifier._neighbour_batches (Index index, Any vectors, int k)
list[float]	knn_classifier._normalise_one (Sequence[float] vector)
Fit	knn_classifier.fit (Path validation_path, Index index, Sequence[int] k_grid=DEFAULT_K_GRID, Sequence[float] temperature_grid=DEFAULT_TEMPERATURE_GRID, Sequence[bool] maskings=(True, False))
dict[str, Any]	knn_classifier.evaluate (Path cases_path, Index index, int k=DEFAULT_K, float temperature=DEFAULT_TEMPERATURE, bool mask_absent=True, str model_name="knn", Fit|None fitted=None)
Path	knn_classifier.write_result (dict[str, Any] payload, Path out_path)
str	knn_classifier.render_fit_table (Fit fitted, bool|None mask_absent=None)
str	knn_classifier.render_masking_table (Fit fitted)
Any	knn_classifier._make_embedder (str kind)
argparse.ArgumentParser	knn_classifier._build_parser ()
str	knn_classifier._leg_tag (argparse.Namespace args)
int	knn_classifier.main (list[str]|None argv=None)

Variables
tuple	knn_classifier.LABELS = ("allow", "confirm", "deny")
str	knn_classifier.TIE_BREAK = "deny"
tuple	knn_classifier.DEFAULT_K_GRID = (1, 5, 15, 51)
tuple	knn_classifier.DEFAULT_TEMPERATURE_GRID
int	knn_classifier.DEFAULT_K = 15
float	knn_classifier.DEFAULT_TEMPERATURE = 0.1
int	knn_classifier.SUBSET_ROWS = 1000
int	knn_classifier.SUBSET_SEED = 289
str	knn_classifier.JINA_MODEL_ID = "jinaai/jina-embeddings-v2-base-code"
int	knn_classifier.MAX_SEQ_LENGTH = 512
int	knn_classifier.THREADS = 8
str	knn_classifier.LMSTUDIO_URL = "http://127.0.0.1:1234/v1/embeddings"
str	knn_classifier.LMSTUDIO_MODEL = "text-embedding-qwen3-embedding-0.6b"
float	knn_classifier.LMSTUDIO_TIMEOUT = 30.0
int	knn_classifier.BUILD_BATCH = 128
int	knn_classifier.FIT_BATCH = 256
str	knn_classifier.NPY_MAGIC = b"\x93NUMPY"
int	knn_classifier.NPY_ALIGNMENT = 64
int	knn_classifier.NPY_PREAMBLE = 10
tuple	knn_classifier.HASH_NGRAM_SIZES = (1, 2, 3, 4)
Any	knn_classifier.NUMPY = _numpy()