Merge branch 'master' into spacy.io

bin/ud/ud_train.py

@@ -8,6 +8,7 @@ import plac
 from pathlib import Path
 import re
 import json
+import tqdm
 
 import spacy
 import spacy.util
@@ -486,9 +487,6 @@ def main(
     vectors_dir=None,
     use_oracle_segments=False,
 ):
-    # temp fix to avoid import issues cf https://github.com/explosion/spaCy/issues/4200
-    import tqdm
-
     Token.set_extension("get_conllu_lines", method=get_token_conllu)
     Token.set_extension("begins_fused", default=False)
     Token.set_extension("inside_fused", default=False)

bin/wiki_entity_linking/entity_linker_evaluation.py

@@ -1,6 +1,7 @@
 import logging
 import random
 
+from tqdm import tqdm
 from collections import defaultdict
 
 logger = logging.getLogger(__name__)
@@ -119,8 +120,6 @@ def get_eval_results(data, el_pipe=None):
     Only evaluate entities that overlap between gold and NER, to isolate the performance of the NEL.
     If the docs in the data require further processing with an entity linker, set el_pipe.
     """
-    from tqdm import tqdm
-
     docs = []
     golds = []
     for d, g in tqdm(data, leave=False):

bin/wiki_entity_linking/wikipedia_processor.py

@@ -6,6 +6,7 @@ import bz2
 import logging
 import random
 import json
+from tqdm import tqdm
 
 from functools import partial
 
@@ -457,9 +458,6 @@ def read_training(nlp, entity_file_path, dev, limit, kb, labels_discard=None):
     """ This method provides training examples that correspond to the entity annotations found by the nlp object.
      For training, it will include both positive and negative examples by using the candidate generator from the kb.
      For testing (kb=None), it will include all positive examples only."""
-
-    from tqdm import tqdm
-
     if not labels_discard:
         labels_discard = []
 

examples/training/conllu.py

@@ -7,6 +7,7 @@ import attr
 from pathlib import Path
 import re
 import json
+import tqdm
 
 import spacy
 import spacy.util
@@ -386,9 +387,6 @@ class TreebankPaths(object):
     limit=("Size limit", "option", "n", int),
 )
 def main(ud_dir, parses_dir, config, corpus, limit=0):
-    # temp fix to avoid import issues cf https://github.com/explosion/spaCy/issues/4200
-    import tqdm
-
     Token.set_extension("get_conllu_lines", method=get_token_conllu)
     Token.set_extension("begins_fused", default=False)
     Token.set_extension("inside_fused", default=False)

examples/training/pretrain_textcat.py

@@ -14,6 +14,7 @@ pre-train with the development data, but also not *so* terrible: we're not using
 the development labels, after all --- only the unlabelled text.
 """
 import plac
+import tqdm
 import random
 import spacy
 import thinc.extra.datasets
@@ -106,9 +107,6 @@ def create_pipeline(width, embed_size, vectors_model):
 
 
 def train_tensorizer(nlp, texts, dropout, n_iter):
-    # temp fix to avoid import issues cf https://github.com/explosion/spaCy/issues/4200
-    import tqdm
-
     tensorizer = nlp.create_pipe("tensorizer")
     nlp.add_pipe(tensorizer)
     optimizer = nlp.begin_training()
@@ -122,9 +120,6 @@ def train_tensorizer(nlp, texts, dropout, n_iter):
 
 
 def train_textcat(nlp, n_texts, n_iter=10):
-    # temp fix to avoid import issues cf https://github.com/explosion/spaCy/issues/4200
-    import tqdm
-
     textcat = nlp.get_pipe("textcat")
     tok2vec_weights = textcat.model.tok2vec.to_bytes()
     (train_texts, train_cats), (dev_texts, dev_cats) = load_textcat_data(limit=n_texts)

examples/vectors_tensorboard.py

@@ -8,6 +8,7 @@ from __future__ import unicode_literals
 
 from os import path
 
+import tqdm
 import math
 import numpy
 import plac
@@ -35,9 +36,6 @@ from tensorflow.contrib.tensorboard.plugins.projector import (
     ),
 )
 def main(vectors_loc, out_loc, name="spaCy_vectors"):
-    # temp fix to avoid import issues cf https://github.com/explosion/spaCy/issues/4200
-    import tqdm
-
     meta_file = "{}.tsv".format(name)
     out_meta_file = path.join(out_loc, meta_file)
 

requirements.txt

@@ -12,6 +12,7 @@ numpy>=1.15.0
 requests>=2.13.0,<3.0.0
 plac>=0.9.6,<1.2.0
 pathlib==1.0.1; python_version < "3.4"
+tqdm>=4.38.0,<5.0.0
 # Optional dependencies
 jsonschema>=2.6.0,<3.1.0
 # Development dependencies

spacy/cli/init_model.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 
 import plac
 import math
+from tqdm import tqdm
 import numpy
 from ast import literal_eval
 from pathlib import Path
@@ -116,9 +117,6 @@ def open_file(loc):
 
 
 def read_attrs_from_deprecated(freqs_loc, clusters_loc):
-    # temp fix to avoid import issues cf https://github.com/explosion/spaCy/issues/4200
-    from tqdm import tqdm
-
     if freqs_loc is not None:
         with msg.loading("Counting frequencies..."):
             probs, _ = read_freqs(freqs_loc)
@@ -201,9 +199,6 @@ def add_vectors(nlp, vectors_loc, prune_vectors, name=None):
 
 
 def read_vectors(vectors_loc):
-    # temp fix to avoid import issues cf https://github.com/explosion/spaCy/issues/4200
-    from tqdm import tqdm
-
     f = open_file(vectors_loc)
     shape = tuple(int(size) for size in next(f).split())
     vectors_data = numpy.zeros(shape=shape, dtype="f")
@@ -220,9 +215,6 @@ def read_vectors(vectors_loc):
 
 
 def read_freqs(freqs_loc, max_length=100, min_doc_freq=5, min_freq=50):
-    # temp fix to avoid import issues cf https://github.com/explosion/spaCy/issues/4200
-    from tqdm import tqdm
-
     counts = PreshCounter()
     total = 0
     with freqs_loc.open() as f:
@@ -252,9 +244,6 @@ def read_freqs(freqs_loc, max_length=100, min_doc_freq=5, min_freq=50):
 
 
 def read_clusters(clusters_loc):
-    # temp fix to avoid import issues cf https://github.com/explosion/spaCy/issues/4200
-    from tqdm import tqdm
-
     clusters = {}
     if ftfy is None:
         user_warning(Warnings.W004)

spacy/cli/profile.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals, division, print_function
 
 import plac
+import tqdm
 from pathlib import Path
 import srsly
 import cProfile
@@ -46,9 +47,6 @@ def profile(model, inputs=None, n_texts=10000):
 
 
 def parse_texts(nlp, texts):
-    # temp fix to avoid import issues cf https://github.com/explosion/spaCy/issues/4200
-    import tqdm
-
     for doc in nlp.pipe(tqdm.tqdm(texts), batch_size=16):
         pass
 

spacy/cli/train.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals, division, print_function
 
 import plac
 import os
+import tqdm
 from pathlib import Path
 from thinc.neural._classes.model import Model
 from timeit import default_timer as timer
@@ -85,10 +86,6 @@ def train(
     JSON format. To convert data from other formats, use the `spacy convert`
     command.
     """
-
-    # temp fix to avoid import issues cf https://github.com/explosion/spaCy/issues/4200
-    import tqdm
-
     util.fix_random_seed()
     util.set_env_log(verbose)
 
@@ -516,9 +513,6 @@ def _score_for_model(meta):
 
 @contextlib.contextmanager
 def _create_progress_bar(total):
-    # temp fix to avoid import issues cf https://github.com/explosion/spaCy/issues/4200
-    import tqdm
-
     if int(os.environ.get("LOG_FRIENDLY", 0)):
         yield
     else:

spacy/errors.py

@@ -53,7 +53,9 @@ class Warnings(object):
     W009 = ("Custom factory '{name}' provided by entry points of another "
             "package overwrites built-in factory.")
     W010 = ("As of v2.1.0, the PhraseMatcher doesn't have a phrase length "
-            "limit anymore, so the max_length argument is now deprecated.")
+            "limit anymore, so the max_length argument is now deprecated. "
+            "If you did not specify this parameter, make sure you call the "
+            "constructor with named arguments instead of positional ones.")
     W011 = ("It looks like you're calling displacy.serve from within a "
             "Jupyter notebook or a similar environment. This likely means "
             "you're already running a local web server, so there's no need to "

website/docs/api/phrasematcher.md

@@ -38,6 +38,7 @@ be shown.
 | Name                                    | Type            | Description                                                                                 |
 | --------------------------------------- | --------------- | ------------------------------------------------------------------------------------------- |
 | `vocab`                                 | `Vocab`         | The vocabulary object, which must be shared with the documents the matcher will operate on. |
+| `max_length`                            | int             | Deprecated argument -  the `PhraseMatcher` does not have a phrase length limit anymore.     |
 | `attr` <Tag variant="new">2.1</Tag>     | int / unicode   | The token attribute to match on. Defaults to `ORTH`, i.e. the verbatim token text.          |
 | `validate` <Tag variant="new">2.1</Tag> | bool            | Validate patterns added to the matcher.                                                     |
 | **RETURNS**                             | `PhraseMatcher` | The newly constructed object.                                                               |