From 2e728cb4fd70519ffbe05c910d0de240d49e3e07 Mon Sep 17 00:00:00 2001 From: Michael Penkov Date: Sat, 26 Jan 2019 17:13:23 +1100 Subject: [PATCH] deprecate the iter parameter to the FastText constructor --- gensim/models/fasttext.py | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/gensim/models/fasttext.py b/gensim/models/fasttext.py index c062e599a5..095ba4fdd7 100644 --- a/gensim/models/fasttext.py +++ b/gensim/models/fasttext.py @@ -353,7 +353,7 @@ class FastText(BaseWordEmbeddingsModel): """ def __init__(self, sentences=None, corpus_file=None, sg=0, hs=0, size=100, alpha=0.025, window=5, min_count=5, max_vocab_size=None, word_ngrams=1, sample=1e-3, seed=1, workers=3, min_alpha=0.0001, - negative=5, ns_exponent=0.75, cbow_mean=1, hashfxn=hash, iter=5, null_word=0, min_n=3, max_n=6, + negative=5, ns_exponent=0.75, cbow_mean=1, hashfxn=hash, iter=None, null_word=0, min_n=3, max_n=6, sorted_vocab=1, bucket=2000000, trim_rule=None, batch_words=MAX_WORDS_IN_BATCH, callbacks=(), compatible_hash=True): """ @@ -416,7 +416,7 @@ def __init__(self, sentences=None, corpus_file=None, sg=0, hs=0, size=100, alpha hashfxn : function, optional Hash function to use to randomly initialize weights, for increased training reproducibility. iter : int, optional - Number of iterations (epochs) over the corpus. + Deprecated. trim_rule : function, optional Vocabulary trimming rule, specifies whether certain words should remain in the vocabulary, be trimmed away, or handled using the default (discard if word count < min_count). @@ -471,6 +471,12 @@ def __init__(self, sentences=None, corpus_file=None, sg=0, hs=0, size=100, alpha >>> of_vector = model.wv['of'] # get vector for out-of-vocab word """ + if iter is not None: + logging.warn( + 'The iter parameter is deprecated. Pass the epochs keyword ' + 'parameter to the train method instead.' + ) + self.load = call_on_class_only self.load_fasttext_format = call_on_class_only self.callbacks = callbacks @@ -487,7 +493,7 @@ def __init__(self, sentences=None, corpus_file=None, sg=0, hs=0, size=100, alpha self.wv.bucket = self.trainables.bucket super(FastText, self).__init__( - sentences=sentences, corpus_file=corpus_file, workers=workers, vector_size=size, epochs=iter, + sentences=sentences, corpus_file=corpus_file, workers=workers, vector_size=size, callbacks=callbacks, batch_words=batch_words, trim_rule=trim_rule, sg=sg, alpha=alpha, window=window, seed=seed, hs=hs, negative=negative, cbow_mean=cbow_mean, min_alpha=min_alpha, fast_version=FAST_VERSION)