Merge pull request nltk#3080 from tomaarsen/enhancement/lm_warn_vocab

Throw warning when `LanguageModel` is initialized with incorrect vocabulary

Author: stevenbird

nltk/lm/api.py

@@ -7,6 +7,7 @@
 """Language Model Interface."""
 
 import random
+import warnings
 from abc import ABCMeta, abstractmethod
 from bisect import bisect
 from itertools import accumulate
@@ -83,14 +84,20 @@ def __init__(self, order, vocabulary=None, counter=None):
             of creating a new one when training.
         :type vocabulary: `nltk.lm.Vocabulary` or None
         :param counter: If provided, use this object to count ngrams.
-        :type vocabulary: `nltk.lm.NgramCounter` or None
+        :type counter: `nltk.lm.NgramCounter` or None
         :param ngrams_fn: If given, defines how sentences in training text are turned to ngram
             sequences.
         :type ngrams_fn: function or None
         :param pad_fn: If given, defines how sentences in training text are padded.
         :type pad_fn: function or None
         """
         self.order = order
+        if vocabulary and not isinstance(vocabulary, Vocabulary):
+            warnings.warn(
+                f"The `vocabulary` argument passed to {self.__class__.__name__!r} "
+                "must be an instance of `nltk.lm.Vocabulary`.",
+                stacklevel=3,
+            )
         self.vocab = Vocabulary() if vocabulary is None else vocabulary
         self.counts = NgramCounter() if counter is None else counter