From a1177e597de75f31507895540d2e6243dccafe27 Mon Sep 17 00:00:00 2001
From: Lasse <lasseh0310@gmail.com>
Date: Thu, 19 Jan 2023 12:08:31 +0100
Subject: [PATCH 01/10] feat: add out of vocabulary ratio to quality component

---
 src/textdescriptives/components/quality.py    | 44 ++++++++++++++++++-
 .../components/quality_data_classes.py        | 14 +++++-
 tests/test_quality.py                         | 12 +++++
 3 files changed, 68 insertions(+), 2 deletions(-)

diff --git a/src/textdescriptives/components/quality.py b/src/textdescriptives/components/quality.py
index e4860d9d..0f43e5f9 100644
--- a/src/textdescriptives/components/quality.py
+++ b/src/textdescriptives/components/quality.py
@@ -1,6 +1,7 @@
 """Component for calculating quality metrics."""
 from collections import Counter, defaultdict
-from typing import Callable, Dict, List, Optional, Tuple, Union
+from functools import partial
+from typing import Callable, Dict, List, Mapping, Optional, Tuple, Union
 
 import numpy as np
 from spacy.language import Language
@@ -334,6 +335,23 @@ def contains_string(span: Union[Span, Doc], string: str) -> bool:
     return string in span.text
 
 
+def oov_ratio(span: Union[Span, Doc], vocab: Optional[Mapping] = None) -> float:
+    """Calculates the out-of-vocabulary ratio.
+
+    Args:
+        span (Union[Span, Doc]): A spaCy Span or Doc object.
+        vocab (Optional[Mapping], optional): A vocabulary to check against.
+            If None, will use the spaCy vocab. Note that the spaCy vocab
+            is not defined for small models. Defaults to None.
+
+    Returns:
+        float: the out-of-vocabulary ratio
+    """
+    if vocab is None:
+        return len([token for token in span if token.is_oov]) / len(span)
+    return len([token for token in span if token.text not in vocab]) / len(span)
+
+
 class Quality:
     """spaCy component for adding text quality metrics to the `Doc` and `Span`
     objects.
@@ -351,6 +369,7 @@ def __init__(  # pylint: disable=dangerous-default-value
         top_ngram_range: Tuple[int, int],
         top_ngram_min_count: int,
         duplicate_n_gram_fraction_range: Tuple[int, int],
+        vocab: Optional[Mapping],
         quality_thresholds: Optional[QualityThresholds] = None,
         force: bool = False,
     ):  # noqa: D107
@@ -365,6 +384,7 @@ def __init__(  # pylint: disable=dangerous-default-value
         if quality_thresholds is None:
             quality_thresholds = QualityThresholds()
         self.quality_thresholds = quality_thresholds
+        self.vocab = vocab
 
         self.set_extensions()
 
@@ -453,6 +473,20 @@ def quality_setter(
             for n_gram, frac in duplicate_ngram_chr_fraction.items()
         }
 
+        # add oov_ratio if spacy model is not small or has a vocab
+        # vector length is 0 for small models
+        if span.vocab.vectors_length > 0 or self.vocab:
+            value_oov = oov_ratio(span, self.vocab)
+            thresholds_oov = threshold.oov_ratio
+        else:
+            value_oov = None
+            thresholds_oov = (None, None)
+
+        thresholds_outputs["oov_ratio"] = ThresholdsOutput(
+            value=value_oov,
+            threshold=thresholds_oov,
+        )
+
         return QualityOutput(**thresholds_outputs)
 
     def quality_getter(self, span: Union[Span, Doc]) -> QualityOutput:
@@ -545,6 +579,7 @@ def __call__(self, doc: Doc):
         "top_ngram_range": [2, 4],
         "top_ngram_min_count": 3,
         "duplicate_n_gram_fraction_range": [5, 10],
+        "vocab": None,
         "force": True,
     },
 )
@@ -556,6 +591,7 @@ def create_quality_component(
     top_ngram_range: Tuple[int, int],
     top_ngram_min_count: int,
     duplicate_n_gram_fraction_range: Tuple[int, int],
+    vocab: Optional[Mapping],
     force: bool = True,
 ) -> Callable[[Doc], Doc]:
     """Allows Quality to be added to a spaCy pipe using
@@ -600,6 +636,11 @@ def create_quality_component(
             be considered a top n-gram. Defaults to 3.
         duplicate_n_gram_fraction_range (Tuple[int]): range of n-grams to
             calculate the proportion of duplicate n-grams. Defaults to [5, 10].
+        vocab (Optional[Mapping]): vocabulary to use for calculating the
+            out-of-vocabulary rate. If none, will use the vocabulary of the
+            spaCy model. Note, that small spaCy models do not have a vocabulary.
+            The attribute will only be set if the vocabulary is not None or
+            the spaCy model is medium or large.
         force (bool): whether to overwrite existing extensions. Defaults to True.
 
 
@@ -626,5 +667,6 @@ def create_quality_component(
         top_ngram_min_count=top_ngram_min_count,
         duplicate_n_gram_fraction_range=duplicate_n_gram_fraction_range,
         quality_thresholds=None,
+        vocab=vocab,
         force=force,
     )
diff --git a/src/textdescriptives/components/quality_data_classes.py b/src/textdescriptives/components/quality_data_classes.py
index 840d203f..af33a12f 100644
--- a/src/textdescriptives/components/quality_data_classes.py
+++ b/src/textdescriptives/components/quality_data_classes.py
@@ -24,11 +24,13 @@ class Config:
         extra = Extra.forbid
 
     threshold: Union[Interval, bool, None]
-    value: float
+    value: Union[float, None]
 
     @property
     def passed(self) -> bool:
         """Return True if the value is within the thresholds."""
+        if self.value is None:
+            return True
         if self.threshold is None:
             return True
         if isinstance(self.threshold, bool):
@@ -151,6 +153,11 @@ class Config:
         + r"are contained within a duplicate for 2-grams, 18% for 3-grams and 16% "
         + "for 4-grams.",
     )
+    oov_ratio: Interval = Field(
+        (None, 0.2),
+        description="A range for the out-of-vocabulary ratio. Default: (None, 0.2)"
+        + r" i.e. no lower limit, but at most 20% of words are out-of-vocabulary.",
+    )
 
 
 class QualityOutput(BaseModel):
@@ -211,6 +218,10 @@ class Config:
         ...,
         description="The thresholds output for the top n-gram character fraction.",
     )
+    oov_ratio: ThresholdsOutput = Field(
+        ...,
+        description="The thresholds output for the out-of-vocabulary ratio.",
+    )
 
     @property
     def passed(self) -> bool:
@@ -232,6 +243,7 @@ def passed(self) -> bool:
                 self.duplicate_paragraph_chr_fraction.passed,
                 all(v.passed for v in self.duplicate_ngram_chr_fraction.values()),
                 all(v.passed for v in self.top_ngram_chr_fraction.values()),
+                self.oov_ratio.passed,
             ],
         )
 
diff --git a/tests/test_quality.py b/tests/test_quality.py
index 4778a4e8..3f88589d 100644
--- a/tests/test_quality.py
+++ b/tests/test_quality.py
@@ -4,12 +4,14 @@
 
 import pytest
 import spacy
+
 import textdescriptives as td
 from textdescriptives.components.quality import (
     alpha_ratio,
     duplicate_ngram_fraction,
     mean_word_length,
     n_stop_words,
+    oov_ratio,
     proportion_bullet_points,
     proportion_ellipsis,
     symbol_to_word_ratio,
@@ -190,6 +192,7 @@ def test_quality_component(nlp: spacy.Language):
     assert quality.duplicate_ngram_chr_fraction["5"] == 1
     assert abs(quality.top_ngram_chr_fraction["2"].value - 0.44) < 0.01
     assert doc._.passed_quality_check is False
+    assert quality.oov_ratio.value is None
     assert quality.passed is False
 
 
@@ -266,3 +269,12 @@ def test_quality_multi_process(nlp):
     docs = nlp.pipe(texts, n_process=2)
     for doc in docs:
         assert doc._.quality
+
+@pytest.mark.parametrize("vocab", [None, {"This", "is", "a", "test"}])
+def test_oov_ratio(vocab):
+    """Test the oov_ratio function."""
+    nlp = spacy.load("en_core_web_md")
+    doc = nlp("This is a test")
+    assert oov_ratio(doc, vocab) == 0
+    doc = nlp("This is a nonwrod")
+    assert oov_ratio(doc, vocab) == 0.25

From c3dea6c213890a17967a164286b76758a5956fdf Mon Sep 17 00:00:00 2001
From: Lasse <lasseh0310@gmail.com>
Date: Mon, 23 Jan 2023 16:39:54 +0100
Subject: [PATCH 02/10] chore: fixes after review

---
 src/textdescriptives/components/quality.py           |  2 +-
 .../components/quality_data_classes.py               |  8 +++++---
 src/textdescriptives/utils.py                        | 12 ++++++++++++
 tests/test_quality.py                                |  9 +++++++++
 4 files changed, 27 insertions(+), 4 deletions(-)

diff --git a/src/textdescriptives/components/quality.py b/src/textdescriptives/components/quality.py
index 0f43e5f9..df979fe8 100644
--- a/src/textdescriptives/components/quality.py
+++ b/src/textdescriptives/components/quality.py
@@ -637,7 +637,7 @@ def create_quality_component(
         duplicate_n_gram_fraction_range (Tuple[int]): range of n-grams to
             calculate the proportion of duplicate n-grams. Defaults to [5, 10].
         vocab (Optional[Mapping]): vocabulary to use for calculating the
-            out-of-vocabulary rate. If none, will use the vocabulary of the
+            out-of-vocabulary ratio (`oov_ratio`). If None, will use the vocabulary of the
             spaCy model. Note, that small spaCy models do not have a vocabulary.
             The attribute will only be set if the vocabulary is not None or
             the spaCy model is medium or large.
diff --git a/src/textdescriptives/components/quality_data_classes.py b/src/textdescriptives/components/quality_data_classes.py
index af33a12f..03e96205 100644
--- a/src/textdescriptives/components/quality_data_classes.py
+++ b/src/textdescriptives/components/quality_data_classes.py
@@ -3,6 +3,8 @@
 
 from pydantic import BaseModel, Extra, Field
 
+from textdescriptives.utils import all_true_or_none
+
 Interval = Tuple[Optional[float], Optional[float]]
 
 
@@ -27,10 +29,10 @@ class Config:
     value: Union[float, None]
 
     @property
-    def passed(self) -> bool:
+    def passed(self) -> Optional[bool]:
         """Return True if the value is within the thresholds."""
         if self.value is None:
-            return True
+            return None
         if self.threshold is None:
             return True
         if isinstance(self.threshold, bool):
@@ -229,7 +231,7 @@ def passed(self) -> bool:
         Returns:
             bool: Whether all thresholds have been passed.
         """
-        return all(
+        return all_true_or_none(
             [
                 self.n_stop_words.passed,
                 self.alpha_ratio.passed,
diff --git a/src/textdescriptives/utils.py b/src/textdescriptives/utils.py
index 741214fd..75968962 100644
--- a/src/textdescriptives/utils.py
+++ b/src/textdescriptives/utils.py
@@ -169,3 +169,15 @@ def _create_spacy_pipeline(
         msg.info(f"No spacy model provided. Inferring spacy model for {lang}.")
         spacy_model = _download_spacy_model(lang=lang, size=spacy_model_size)
     return spacy.load(spacy_model)
+
+
+def all_true_or_none(x: Iterable[bool]) -> bool:
+    """Check if all elements in an iterable are True or None.
+
+    Args:
+        x (Iterable[bool]): Iterable to check
+
+    Returns:
+        bool: True if all elements are True or None, False otherwise.
+    """
+    return all([i is None or i for i in x])
\ No newline at end of file
diff --git a/tests/test_quality.py b/tests/test_quality.py
index 3f88589d..814cb1cf 100644
--- a/tests/test_quality.py
+++ b/tests/test_quality.py
@@ -212,6 +212,7 @@ def test_quality_component_with_config(nlp: spacy.Language):
         top_ngram_chr_fraction={2: (None, 0.6), 3: (None, 0.6)},
         duplicate_ngram_chr_fraction={},
         contains={"lorem ipsum": False},
+        oov_ratio=(None, 0.3),
     )
 
     quality_pipe = nlp.add_pipe(
@@ -234,6 +235,7 @@ def test_quality_component_with_config(nlp: spacy.Language):
     assert doc._.quality.duplicate_ngram_chr_fraction["8"] == 1
     assert abs(doc._.quality.top_ngram_chr_fraction["3"].value - 0.57) < 0.01
     assert doc._.passed_quality_check is True
+    assert doc._.quality.oov_ratio.value is None
 
 
 @pytest.mark.parametrize(
@@ -278,3 +280,10 @@ def test_oov_ratio(vocab):
     assert oov_ratio(doc, vocab) == 0
     doc = nlp("This is a nonwrod")
     assert oov_ratio(doc, vocab) == 0.25
+
+
+def test_oov_ratio_small_model():
+    nlp = spacy.load("en_core_web_sm")
+    nlp.add_pipe("textdescriptives/quality")
+    doc = nlp("This is a test")
+    assert doc._.quality.oov_ratio.value is None
\ No newline at end of file

From a87a5eacfa1895caa5de5c9c775b5012df1f1267 Mon Sep 17 00:00:00 2001
From: Lasse <lasseh0310@gmail.com>
Date: Mon, 23 Jan 2023 16:43:27 +0100
Subject: [PATCH 03/10] chore: precommit

---
 src/textdescriptives/components/quality.py | 9 ++++-----
 src/textdescriptives/utils.py              | 4 ++--
 tests/test_quality.py                      | 3 ++-
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/src/textdescriptives/components/quality.py b/src/textdescriptives/components/quality.py
index df979fe8..c31b2dd2 100644
--- a/src/textdescriptives/components/quality.py
+++ b/src/textdescriptives/components/quality.py
@@ -1,6 +1,5 @@
 """Component for calculating quality metrics."""
 from collections import Counter, defaultdict
-from functools import partial
 from typing import Callable, Dict, List, Mapping, Optional, Tuple, Union
 
 import numpy as np
@@ -637,10 +636,10 @@ def create_quality_component(
         duplicate_n_gram_fraction_range (Tuple[int]): range of n-grams to
             calculate the proportion of duplicate n-grams. Defaults to [5, 10].
         vocab (Optional[Mapping]): vocabulary to use for calculating the
-            out-of-vocabulary ratio (`oov_ratio`). If None, will use the vocabulary of the
-            spaCy model. Note, that small spaCy models do not have a vocabulary.
-            The attribute will only be set if the vocabulary is not None or
-            the spaCy model is medium or large.
+            out-of-vocabulary ratio (`oov_ratio`). If None, will use the vocabulary
+            of the spaCy model. Note, that small spaCy models do not have a
+            vocabulary. The attribute will only be set if the vocabulary is not
+            None or the spaCy model is medium or large.
         force (bool): whether to overwrite existing extensions. Defaults to True.
 
 
diff --git a/src/textdescriptives/utils.py b/src/textdescriptives/utils.py
index 75968962..28044ab1 100644
--- a/src/textdescriptives/utils.py
+++ b/src/textdescriptives/utils.py
@@ -171,7 +171,7 @@ def _create_spacy_pipeline(
     return spacy.load(spacy_model)
 
 
-def all_true_or_none(x: Iterable[bool]) -> bool:
+def all_true_or_none(x: Iterable[Optional[bool]]) -> bool:
     """Check if all elements in an iterable are True or None.
 
     Args:
@@ -180,4 +180,4 @@ def all_true_or_none(x: Iterable[bool]) -> bool:
     Returns:
         bool: True if all elements are True or None, False otherwise.
     """
-    return all([i is None or i for i in x])
\ No newline at end of file
+    return all([i is None or i for i in x])
diff --git a/tests/test_quality.py b/tests/test_quality.py
index 814cb1cf..35d08530 100644
--- a/tests/test_quality.py
+++ b/tests/test_quality.py
@@ -272,6 +272,7 @@ def test_quality_multi_process(nlp):
     for doc in docs:
         assert doc._.quality
 
+
 @pytest.mark.parametrize("vocab", [None, {"This", "is", "a", "test"}])
 def test_oov_ratio(vocab):
     """Test the oov_ratio function."""
@@ -286,4 +287,4 @@ def test_oov_ratio_small_model():
     nlp = spacy.load("en_core_web_sm")
     nlp.add_pipe("textdescriptives/quality")
     doc = nlp("This is a test")
-    assert doc._.quality.oov_ratio.value is None
\ No newline at end of file
+    assert doc._.quality.oov_ratio.value is None

From 8eb070e3887a69eb20198af464ba0b52609be751 Mon Sep 17 00:00:00 2001
From: Lasse <lasseh0310@gmail.com>
Date: Mon, 23 Jan 2023 16:57:18 +0100
Subject: [PATCH 04/10] tests: add spacy medium to test requirements

---
 tests/requirements.txt | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tests/requirements.txt b/tests/requirements.txt
index 32d74dea..6842e71a 100644
--- a/tests/requirements.txt
+++ b/tests/requirements.txt
@@ -1,5 +1,6 @@
 # only for requirements which can't be specified in the pyproject.toml file
 # e.g. links to wheels which is not allowed in pyproject.toml on pypi
 
-# spacy pipeline
-https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.2.0/en_core_web_sm-3.2.0.tar.gz
\ No newline at end of file
+# spacy pipelines
+https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.2.0/en_core_web_sm-3.2.0.tar.gz
+https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.2.0/en_core_web_md-3.2.0.tar.gz
\ No newline at end of file

From ea05cf3d9e511bd1e1404be568557a32f6d83062 Mon Sep 17 00:00:00 2001
From: Lasse <lasseh0310@gmail.com>
Date: Mon, 23 Jan 2023 17:16:14 +0100
Subject: [PATCH 05/10] chore: fix type

---
 tests/requirements.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/requirements.txt b/tests/requirements.txt
index 6842e71a..acd705ca 100644
--- a/tests/requirements.txt
+++ b/tests/requirements.txt
@@ -3,4 +3,4 @@
 
 # spacy pipelines
 https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.2.0/en_core_web_sm-3.2.0.tar.gz
-https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.2.0/en_core_web_md-3.2.0.tar.gz
\ No newline at end of file
+https://github.com/explosion/spacy-models/releases/download/en_core_web_md-3.4.0/en_core_web_md-3.4.0.tar.gz
\ No newline at end of file

From 2559c97a8c90bcdce4b2eacf029b8e095fe48ba1 Mon Sep 17 00:00:00 2001
From: Lasse <lasseh0310@gmail.com>
Date: Mon, 23 Jan 2023 17:18:45 +0100
Subject: [PATCH 06/10] chore: update after review

---
 .../components/quality_data_classes.py        | 34 +++++++++----------
 src/textdescriptives/utils.py                 | 11 ------
 2 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/src/textdescriptives/components/quality_data_classes.py b/src/textdescriptives/components/quality_data_classes.py
index 03e96205..2c565660 100644
--- a/src/textdescriptives/components/quality_data_classes.py
+++ b/src/textdescriptives/components/quality_data_classes.py
@@ -231,23 +231,23 @@ def passed(self) -> bool:
         Returns:
             bool: Whether all thresholds have been passed.
         """
-        return all_true_or_none(
-            [
-                self.n_stop_words.passed,
-                self.alpha_ratio.passed,
-                self.mean_word_length.passed,
-                self.doc_length.passed,
-                all(v.passed for v in self.symbol_to_word_ratio.values()),
-                self.proportion_ellipsis.passed,
-                self.proportion_bullet_points.passed,
-                all(v.passed for v in self.contains.values()),
-                self.duplicate_line_chr_fraction.passed,
-                self.duplicate_paragraph_chr_fraction.passed,
-                all(v.passed for v in self.duplicate_ngram_chr_fraction.values()),
-                all(v.passed for v in self.top_ngram_chr_fraction.values()),
-                self.oov_ratio.passed,
-            ],
-        )
+        passed_or_none = [
+            self.n_stop_words.passed,
+            self.alpha_ratio.passed,
+            self.mean_word_length.passed,
+            self.doc_length.passed,
+            all(v.passed for v in self.symbol_to_word_ratio.values()),
+            self.proportion_ellipsis.passed,
+            self.proportion_bullet_points.passed,
+            all(v.passed for v in self.contains.values()),
+            self.duplicate_line_chr_fraction.passed,
+            self.duplicate_paragraph_chr_fraction.passed,
+            all(v.passed for v in self.duplicate_ngram_chr_fraction.values()),
+            all(v.passed for v in self.top_ngram_chr_fraction.values()),
+            self.oov_ratio.passed,
+        ]
+
+        return all(i is None or i for i in passed_or_none)
 
     def __repr_str__(self, join_str: str) -> str:
         return join_str.join(
diff --git a/src/textdescriptives/utils.py b/src/textdescriptives/utils.py
index 28044ab1..327e97aa 100644
--- a/src/textdescriptives/utils.py
+++ b/src/textdescriptives/utils.py
@@ -170,14 +170,3 @@ def _create_spacy_pipeline(
         spacy_model = _download_spacy_model(lang=lang, size=spacy_model_size)
     return spacy.load(spacy_model)
 
-
-def all_true_or_none(x: Iterable[Optional[bool]]) -> bool:
-    """Check if all elements in an iterable are True or None.
-
-    Args:
-        x (Iterable[bool]): Iterable to check
-
-    Returns:
-        bool: True if all elements are True or None, False otherwise.
-    """
-    return all([i is None or i for i in x])

From 9c0671178f8fbdd187e909a09916591edd0e200a Mon Sep 17 00:00:00 2001
From: Lasse <lasseh0310@gmail.com>
Date: Mon, 23 Jan 2023 17:23:17 +0100
Subject: [PATCH 07/10] tests: fix spacy model req for tests

---
 tests/requirements.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/requirements.txt b/tests/requirements.txt
index acd705ca..f3f8df6b 100644
--- a/tests/requirements.txt
+++ b/tests/requirements.txt
@@ -3,4 +3,4 @@
 
 # spacy pipelines
 https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.2.0/en_core_web_sm-3.2.0.tar.gz
-https://github.com/explosion/spacy-models/releases/download/en_core_web_md-3.4.0/en_core_web_md-3.4.0.tar.gz
\ No newline at end of file
+https://github.com/explosion/spacy-models/releases/download/en_core_web_md-3.2.0/en_core_web_md-3.2.0.tar.gz
\ No newline at end of file

From 2628ec6f7694198d1c5f0128dd4d95cf92d1a499 Mon Sep 17 00:00:00 2001
From: Lasse <lasseh0310@gmail.com>
Date: Mon, 23 Jan 2023 17:24:16 +0100
Subject: [PATCH 08/10] chore: precommit

---
 src/textdescriptives/components/quality_data_classes.py | 2 --
 src/textdescriptives/utils.py                           | 1 -
 2 files changed, 3 deletions(-)

diff --git a/src/textdescriptives/components/quality_data_classes.py b/src/textdescriptives/components/quality_data_classes.py
index 2c565660..f0daa8b4 100644
--- a/src/textdescriptives/components/quality_data_classes.py
+++ b/src/textdescriptives/components/quality_data_classes.py
@@ -3,8 +3,6 @@
 
 from pydantic import BaseModel, Extra, Field
 
-from textdescriptives.utils import all_true_or_none
-
 Interval = Tuple[Optional[float], Optional[float]]
 
 
diff --git a/src/textdescriptives/utils.py b/src/textdescriptives/utils.py
index 327e97aa..741214fd 100644
--- a/src/textdescriptives/utils.py
+++ b/src/textdescriptives/utils.py
@@ -169,4 +169,3 @@ def _create_spacy_pipeline(
         msg.info(f"No spacy model provided. Inferring spacy model for {lang}.")
         spacy_model = _download_spacy_model(lang=lang, size=spacy_model_size)
     return spacy.load(spacy_model)
-

From 7338488731bf6cd9ede0b33df8b0a86c49ccbc20 Mon Sep 17 00:00:00 2001
From: Lasse <lasseh0310@gmail.com>
Date: Thu, 26 Jan 2023 11:43:40 +0100
Subject: [PATCH 09/10] tests: parameterize oov ratio further

---
 tests/test_quality.py | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/tests/test_quality.py b/tests/test_quality.py
index 35d08530..26428321 100644
--- a/tests/test_quality.py
+++ b/tests/test_quality.py
@@ -273,14 +273,20 @@ def test_quality_multi_process(nlp):
         assert doc._.quality
 
 
-@pytest.mark.parametrize("vocab", [None, {"This", "is", "a", "test"}])
-def test_oov_ratio(vocab):
+@pytest.mark.parametrize(
+    "text,expected,vocab",
+    [
+        ("This is a test", 0, None),
+        ("This is a nonwrod", 0.25, None),
+        ("This is a test", 0, {"This", "is", "a", "test"}),
+        ("This is a nonwrod", 0.25, {"This", "is", "a", "test"}),
+    ],
+)
+def test_oov_ratio(text, expected, vocab):
     """Test the oov_ratio function."""
     nlp = spacy.load("en_core_web_md")
-    doc = nlp("This is a test")
-    assert oov_ratio(doc, vocab) == 0
-    doc = nlp("This is a nonwrod")
-    assert oov_ratio(doc, vocab) == 0.25
+    doc = nlp(text)
+    assert oov_ratio(doc, vocab) == expected
 
 
 def test_oov_ratio_small_model():

From 74c22b143fae43227feea28f74f19eff439a3240 Mon Sep 17 00:00:00 2001
From: Lasse <lasseh0310@gmail.com>
Date: Thu, 26 Jan 2023 11:47:58 +0100
Subject: [PATCH 10/10] docs: update quality docs with oov_ratio

---
 docs/quality.rst | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/docs/quality.rst b/docs/quality.rst
index fa2619ca..6d2d4a08 100644
--- a/docs/quality.rst
+++ b/docs/quality.rst
@@ -13,6 +13,7 @@ Heuristic quality metrics:
 * Proportion of bullet points (:code:`proportion_bullet_points`): Proportion of lines in a documents which start with a bullet point.
 * Symbol to word ratio (:code:`symbol_{symbol}_2_word_ratio`): Ratio of specified symbols to words, could e.g. include ratio of hashtags or curly brackets.
 * Contains string (:code:`contains_{string}`): Whether the document contains a specified string. For instance documents containing the string "lorem ipsum".
+* Out of vocabulary ratio (:code:`oov_ratio`): Ratio of out of vocabulary words to total words.
 
 Repetitious text metrics:
 
@@ -90,6 +91,7 @@ If you want to specify the thresholds for the quality metrics, you can do so by
             "10": (None, 0.1),
         },
         top_ngram_chr_fraction={"2": (None, 0.2), "3": (None, 0.18), "4": (None, 0.16)},
+        oov_ratio=(None, 0.2)
     )