Merge branch 'feature/prepare' of https://github.com/explosion/spaCy into feature/prepare

spacy/cli/init_pipeline.py

@@ -19,13 +19,18 @@ def init_vectors_cli(
     prune: int = Opt(-1, "--prune", "-p", help="Optional number of vectors to prune to"),
     truncate: int = Opt(0, "--truncate", "-t", help="Optional number of vectors to truncate to when reading in vectors file"),
     name: Optional[str] = Opt(None, "--name", "-n", help="Optional name for the word vectors, e.g. en_core_web_lg.vectors"),
+    verbose: bool = Opt(False, "--verbose", "-V", "-VV", help="Display more information for debugging purposes"),
     # fmt: on
 ):
+    """Convert word vectors for use with spaCy. Will export an nlp object that
+    you can use in the [initialize.vocab] block of your config to initialize
+    a model with vectors.
+    """
+    util.logger.setLevel(logging.DEBUG if verbose else logging.ERROR)
     msg.info(f"Creating blank nlp object for language '{lang}'")
     nlp = util.get_lang_class(lang)()
-    convert_vectors(
+    convert_vectors(nlp, vectors_loc, truncate=truncate, prune=prune, name=name)
-        nlp, vectors_loc, truncate=truncate, prune=prune, name=name, silent=False
+    msg.good(f"Successfully converted {len(nlp.vocab.vectors)} vectors")
-    )
     nlp.to_disk(output_dir)
     msg.good(
         "Saved nlp object with vectors to output directory. You can now use the "

spacy/language.py

@@ -18,6 +18,7 @@ from .tokens.underscore import Underscore
 from .vocab import Vocab, create_vocab
 from .pipe_analysis import validate_attrs, analyze_pipes, print_pipe_analysis
 from .training import Example, validate_examples
+from .training.initialize import init_vocab, init_tok2vec
 from .scorer import Scorer
 from .util import registry, SimpleFrozenList
 from .util import SimpleFrozenDict, combine_score_weights, CONFIG_SECTION_ORDER
@@ -27,7 +28,8 @@ from .lang.punctuation import TOKENIZER_INFIXES
 from .tokens import Doc
 from .tokenizer import Tokenizer
 from .errors import Errors, Warnings
-from .schemas import ConfigSchema, ConfigSchemaNlp, validate_init_settings
+from .schemas import ConfigSchema, ConfigSchemaNlp, ConfigSchemaInit
+from .schemas import ConfigSchemaPretrain, validate_init_settings
 from .git_info import GIT_VERSION
 from . import util
 from . import about
@@ -1161,7 +1163,6 @@ class Language:
         self,
         get_examples: Optional[Callable[[], Iterable[Example]]] = None,
         *,
-        settings: Dict[str, Dict[str, Any]] = SimpleFrozenDict(),
         sgd: Optional[Optimizer] = None,
     ) -> Optimizer:
         """Initialize the pipe for training, using data examples if available.
@@ -1198,28 +1199,38 @@ class Language:
         if not valid_examples:
             err = Errors.E930.format(name="Language", obj="empty list")
             raise ValueError(err)
+        # Make sure the config is interpolated so we can resolve subsections
+        config = self.config.interpolate()
+        # These are the settings provided in the [initialize] block in the config
+        I = registry.resolve(config["initialize"], schema=ConfigSchemaInit)
+        V = I["vocab"]
+        init_vocab(
+            self, data=V["data"], lookups=V["lookups"], vectors=V["vectors"],
+        )
+        pretrain_cfg = config.get("pretraining")
+        if pretrain_cfg:
+            P = registry.resolve(pretrain_cfg, schema=ConfigSchemaPretrain)
+            init_tok2vec(self, P, V)
         if self.vocab.vectors.data.shape[1] >= 1:
             ops = get_current_ops()
             self.vocab.vectors.data = ops.asarray(self.vocab.vectors.data)
-        self._optimizer = sgd
         if hasattr(self.tokenizer, "initialize"):
-            tok_settings = settings.get("tokenizer", {})
             tok_settings = validate_init_settings(
                 self.tokenizer.initialize,
-                tok_settings,
+                I["tokenizer"],
                 section="tokenizer",
                 name="tokenizer",
             )
             self.tokenizer.initialize(get_examples, nlp=self, **tok_settings)
-        proc_settings = settings.get("components", {})
         for name, proc in self.pipeline:
             if hasattr(proc, "initialize"):
-                p_settings = proc_settings.get(name, {})
+                p_settings = I["components"].get(name, {})
                 p_settings = validate_init_settings(
                     proc.initialize, p_settings, section="components", name=name
                 )
                 proc.initialize(get_examples, nlp=self, **p_settings)
         self._link_components()
+        self._optimizer = sgd
         if sgd is not None:
             self._optimizer = sgd
         elif self._optimizer is None:

spacy/tests/pipeline/test_initialize.py

@@ -9,34 +9,61 @@ from pydantic import StrictBool
 def test_initialize_arguments():
     name = "test_initialize_arguments"
 
+    class CustomTokenizer:
+        def __init__(self, tokenizer):
+            self.tokenizer = tokenizer
+            self.from_initialize = None
+
+        def __call__(self, text):
+            return self.tokenizer(text)
+
+        def initialize(self, get_examples, nlp, custom: int):
+            self.from_initialize = custom
+
     class Component:
         def __init__(self):
-            ...
+            self.from_initialize = None
 
         def initialize(
             self, get_examples, nlp, custom1: str, custom2: StrictBool = False
         ):
-            ...
+            self.from_initialize = (custom1, custom2)
 
     Language.factory(name, func=lambda nlp, name: Component())
 
     nlp = English()
+    nlp.tokenizer = CustomTokenizer(nlp.tokenizer)
     example = Example.from_dict(nlp("x"), {})
     get_examples = lambda: [example]
     nlp.add_pipe(name)
     # The settings here will typically come from the [initialize] block
+    init_cfg = {"tokenizer": {"custom": 1}, "components": {name: {}}}
+    nlp.config["initialize"].update(init_cfg)
     with pytest.raises(ConfigValidationError) as e:
-        # Empty settings, no required custom1 argument
+        # Empty config for component, no required custom1 argument
-        nlp.initialize(get_examples, settings={"components": {name: {}}})
+        nlp.initialize(get_examples)
     errors = e.value.errors
     assert len(errors) == 1
     assert errors[0]["loc"] == ("custom1",)
     assert errors[0]["type"] == "value_error.missing"
+    init_cfg = {
+        "tokenizer": {"custom": 1},
+        "components": {name: {"custom1": "x", "custom2": 1}},
+    }
+    nlp.config["initialize"].update(init_cfg)
     with pytest.raises(ConfigValidationError) as e:
-        # Wrong type
+        # Wrong type of custom 2
-        settings = {"components": {name: {"custom1": "x", "custom2": 1}}}
+        nlp.initialize(get_examples)
-        nlp.initialize(get_examples, settings=settings)
     errors = e.value.errors
     assert len(errors) == 1
     assert errors[0]["loc"] == ("custom2",)
     assert errors[0]["type"] == "value_error.strictbool"
+    init_cfg = {
+        "tokenizer": {"custom": 1},
+        "components": {name: {"custom1": "x", "custom2": True}},
+    }
+    nlp.config["initialize"].update(init_cfg)
+    nlp.initialize(get_examples)
+    assert nlp.tokenizer.from_initialize == 1
+    pipe = nlp.get_pipe(name)
+    assert pipe.from_initialize == ("x", True)

spacy/training/initialize.py

@@ -1,8 +1,7 @@
-from typing import Union, Dict, Optional, Any, List, IO
+from typing import Union, Dict, Optional, Any, List, IO, TYPE_CHECKING
 from thinc.api import Config, fix_random_seed, set_gpu_allocator
 from thinc.api import ConfigValidationError
 from pathlib import Path
-from wasabi import Printer
 import srsly
 import numpy
 import tarfile
@@ -11,17 +10,18 @@ import zipfile
 import tqdm
 
 from .loop import create_before_to_disk_callback
-from ..language import Language
 from ..lookups import Lookups
 from ..vectors import Vectors
 from ..errors import Errors
-from ..schemas import ConfigSchemaTraining, ConfigSchemaInit, ConfigSchemaPretrain
+from ..schemas import ConfigSchemaTraining
-from ..util import registry, load_model_from_config, resolve_dot_names
+from ..util import registry, load_model_from_config, resolve_dot_names, logger
 from ..util import load_model, ensure_path, OOV_RANK, DEFAULT_OOV_PROB
 
+if TYPE_CHECKING:
+    from ..language import Language  # noqa: F401
 
-def init_nlp(config: Config, *, use_gpu: int = -1, silent: bool = True) -> Language:
+
-    msg = Printer(no_print=silent)
+def init_nlp(config: Config, *, use_gpu: int = -1) -> "Language":
     raw_config = config
     config = raw_config.interpolate()
     if config["training"]["seed"] is not None:
@@ -32,39 +32,29 @@ def init_nlp(config: Config, *, use_gpu: int = -1, silent: bool = True) -> Langu
     # Use original config here before it's resolved to functions
     sourced_components = get_sourced_components(config)
     nlp = load_model_from_config(raw_config, auto_fill=True)
-    msg.good("Set up nlp object from config")
+    logger.info("Set up nlp object from config")
     config = nlp.config.interpolate()
     # Resolve all training-relevant sections using the filled nlp config
     T = registry.resolve(config["training"], schema=ConfigSchemaTraining)
     dot_names = [T["train_corpus"], T["dev_corpus"]]
     train_corpus, dev_corpus = resolve_dot_names(config, dot_names)
-    I = registry.resolve(config["initialize"], schema=ConfigSchemaInit)
-    V = I["vocab"]
-    init_vocab(
-        nlp, data=V["data"], lookups=V["lookups"], vectors=V["vectors"], silent=silent
-    )
     optimizer = T["optimizer"]
     before_to_disk = create_before_to_disk_callback(T["before_to_disk"])
     # Components that shouldn't be updated during training
     frozen_components = T["frozen_components"]
     # Sourced components that require resume_training
     resume_components = [p for p in sourced_components if p not in frozen_components]
-    msg.info(f"Pipeline: {nlp.pipe_names}")
+    logger.info(f"Pipeline: {nlp.pipe_names}")
     if resume_components:
         with nlp.select_pipes(enable=resume_components):
-            msg.info(f"Resuming training for: {resume_components}")
+            logger.info(f"Resuming training for: {resume_components}")
             nlp.resume_training(sgd=optimizer)
     with nlp.select_pipes(disable=[*frozen_components, *resume_components]):
-        nlp.initialize(lambda: train_corpus(nlp), sgd=optimizer, settings=I)
+        nlp.initialize(lambda: train_corpus(nlp), sgd=optimizer)
-        msg.good("Initialized pipeline components")
+        logger.info("Initialized pipeline components")
     # Verify the config after calling 'initialize' to ensure labels
     # are properly initialized
     verify_config(nlp)
-    if "pretraining" in config and config["pretraining"]:
-        P = registry.resolve(config["pretraining"], schema=ConfigSchemaPretrain)
-        loaded = add_tok2vec_weights(nlp, P, V)
-        if loaded and P["component"]:
-            msg.good(f"Loaded pretrained weights into component '{P['component']}'")
     nlp = before_to_disk(nlp)
     return nlp
 
@@ -75,17 +65,15 @@ def must_reinitialize(train_config: Config, init_config: Config) -> bool:
 
 
 def init_vocab(
-    nlp: Language,
+    nlp: "Language",
     *,
     data: Optional[Path] = None,
     lookups: Optional[Lookups] = None,
     vectors: Optional[str] = None,
-    silent: bool = True,
+) -> "Language":
-) -> Language:
-    msg = Printer(no_print=silent)
     if lookups:
         nlp.vocab.lookups = lookups
-        msg.good(f"Added vocab lookups: {', '.join(lookups.tables)}")
+        logger.info(f"Added vocab lookups: {', '.join(lookups.tables)}")
     data_path = ensure_path(data)
     if data_path is not None:
         lex_attrs = srsly.read_jsonl(data_path)
@@ -101,15 +89,15 @@ def init_vocab(
         else:
             oov_prob = DEFAULT_OOV_PROB
         nlp.vocab.cfg.update({"oov_prob": oov_prob})
-        msg.good(f"Added {len(nlp.vocab)} lexical entries to the vocab")
+        logger.info(f"Added {len(nlp.vocab)} lexical entries to the vocab")
-    msg.good("Created vocabulary")
+    logger.info("Created vocabulary")
     if vectors is not None:
         load_vectors_into_model(nlp, vectors)
-        msg.good(f"Added vectors: {vectors}")
+        logger.info(f"Added vectors: {vectors}")
 
 
 def load_vectors_into_model(
-    nlp: Language, name: Union[str, Path], *, add_strings: bool = True
+    nlp: "Language", name: Union[str, Path], *, add_strings: bool = True
 ) -> None:
     """Load word vectors from an installed model or path into a model instance."""
     try:
@@ -132,8 +120,8 @@ def load_vectors_into_model(
                 nlp.vocab.strings.add(vectors_nlp.vocab.strings[key])
 
 
-def add_tok2vec_weights(
+def init_tok2vec(
-    nlp: Language, pretrain_config: Dict[str, Any], vocab_config: Dict[str, Any]
+    nlp: "Language", pretrain_config: Dict[str, Any], vocab_config: Dict[str, Any]
 ) -> bool:
     # Load pretrained tok2vec weights - cf. CLI command 'pretrain'
     P = pretrain_config
@@ -171,7 +159,7 @@ def add_tok2vec_weights(
     return False
 
 
-def verify_config(nlp: Language) -> None:
+def verify_config(nlp: "Language") -> None:
     """Perform additional checks based on the config, loaded nlp object and training data."""
     # TODO: maybe we should validate based on the actual components, the list
     # in config["nlp"]["pipeline"] instead?
@@ -182,7 +170,7 @@ def verify_config(nlp: Language) -> None:
             verify_textcat_config(nlp, pipe_config)
 
 
-def verify_textcat_config(nlp: Language, pipe_config: Dict[str, Any]) -> None:
+def verify_textcat_config(nlp: "Language", pipe_config: Dict[str, Any]) -> None:
     # if 'positive_label' is provided: double check whether it's in the data and
     # the task is binary
     if pipe_config.get("positive_label"):
@@ -211,15 +199,13 @@ def get_sourced_components(config: Union[Dict[str, Any], Config]) -> List[str]:
 
 
 def convert_vectors(
-    nlp: Language,
+    nlp: "Language",
     vectors_loc: Optional[Path],
     *,
     truncate: int,
     prune: int,
     name: Optional[str] = None,
-    silent: bool = True,
 ) -> None:
-    msg = Printer(no_print=silent)
     vectors_loc = ensure_path(vectors_loc)
     if vectors_loc and vectors_loc.parts[-1].endswith(".npz"):
         nlp.vocab.vectors = Vectors(data=numpy.load(vectors_loc.open("rb")))
@@ -228,9 +214,9 @@ def convert_vectors(
                 nlp.vocab.vectors.add(lex.orth, row=lex.rank)
     else:
         if vectors_loc:
-            with msg.loading(f"Reading vectors from {vectors_loc}"):
+            logger.info(f"Reading vectors from {vectors_loc}")
-                vectors_data, vector_keys = read_vectors(vectors_loc, truncate)
+            vectors_data, vector_keys = read_vectors(vectors_loc, truncate)
-            msg.good(f"Loaded vectors from {vectors_loc}")
+            logger.info(f"Loaded vectors from {vectors_loc}")
         else:
             vectors_data, vector_keys = (None, None)
         if vector_keys is not None:
@@ -247,7 +233,6 @@ def convert_vectors(
     nlp.meta["vectors"]["name"] = nlp.vocab.vectors.name
     if prune >= 1:
         nlp.vocab.prune_vectors(prune)
-    msg.good(f"Successfully converted {len(nlp.vocab.vectors)} vectors")
 
 
 def read_vectors(vectors_loc: Path, truncate_vectors: int):

spacy/training/loop.py

@@ -1,5 +1,5 @@
 from typing import List, Callable, Tuple, Dict, Iterable, Iterator, Union, Any
-from typing import Optional
+from typing import Optional, TYPE_CHECKING
 from pathlib import Path
 from timeit import default_timer as timer
 from thinc.api import Optimizer, Config, constant, fix_random_seed, set_gpu_allocator
@@ -9,13 +9,15 @@ from wasabi import Printer
 
 from .example import Example
 from ..schemas import ConfigSchemaTraining
-from ..language import Language
 from ..errors import Errors
 from ..util import resolve_dot_names, registry
 
+if TYPE_CHECKING:
+    from ..language import Language  # noqa: F401
+
 
 def train(
-    nlp: Language,
+    nlp: "Language",
     output_path: Optional[Path] = None,
     *,
     use_gpu: int = -1,
@@ -110,7 +112,7 @@ def train(
 
 
 def train_while_improving(
-    nlp: Language,
+    nlp: "Language",
     optimizer: Optimizer,
     train_data,
     evaluate,
@@ -233,7 +235,7 @@ def subdivide_batch(batch, accumulate_gradient):
 
 
 def create_evaluation_callback(
-    nlp: Language, dev_corpus: Callable, weights: Dict[str, float]
+    nlp: "Language", dev_corpus: Callable, weights: Dict[str, float]
 ) -> Callable[[], Tuple[float, Dict[str, float]]]:
     weights = {key: value for key, value in weights.items() if value is not None}
 
@@ -277,7 +279,7 @@ def create_train_batches(
 
 
 def update_meta(
-    training: Union[Dict[str, Any], Config], nlp: Language, info: Dict[str, Any]
+    training: Union[Dict[str, Any], Config], nlp: "Language", info: Dict[str, Any]
 ) -> None:
     nlp.meta["performance"] = {}
     for metric in training["score_weights"]:
@@ -288,8 +290,10 @@ def update_meta(
 
 
 def create_before_to_disk_callback(
-    callback: Optional[Callable[[Language], Language]]
+    callback: Optional[Callable[["Language"], "Language"]]
-) -> Callable[[Language], Language]:
+) -> Callable[["Language"], "Language"]:
+    from ..language import Language  # noqa: F811
+
     def before_to_disk(nlp: Language) -> Language:
         if not callback:
             return nlp