From 56070fbb772259d434af957f46b4cda8954f4927 Mon Sep 17 00:00:00 2001 From: Laubeee Date: Mon, 13 Aug 2018 11:17:21 +0200 Subject: [PATCH 1/9] update documentation to match actual code Change "default" to "auto" since there is no handling on the value "default". --- gensim/models/ldamodel.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gensim/models/ldamodel.py b/gensim/models/ldamodel.py index 2f8fca4768..1f8a8d42c4 100755 --- a/gensim/models/ldamodel.py +++ b/gensim/models/ldamodel.py @@ -369,7 +369,7 @@ def __init__(self, corpus=None, num_topics=100, id2word=None, Alternatively default prior selecting strategies can be employed by supplying a string: * 'asymmetric': Uses a fixed normalized asymmetric prior of `1.0 / topicno`. - * 'default': Learns an asymmetric prior from the corpus. + * 'auto': Learns an asymmetric prior from the corpus. eta : {float, np.array, str}, optional A-priori belief on word probability, this can be: From 35b9106a2173ffceea7fa50c607c32279813e7fc Mon Sep 17 00:00:00 2001 From: Laubeee Date: Mon, 13 Aug 2018 11:40:21 +0200 Subject: [PATCH 2/9] Update ldamodel.py --- gensim/models/ldamodel.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gensim/models/ldamodel.py b/gensim/models/ldamodel.py index 1f8a8d42c4..e866386ba0 100755 --- a/gensim/models/ldamodel.py +++ b/gensim/models/ldamodel.py @@ -531,7 +531,7 @@ def init_dir_prior(self, prior, name): * an 1D array of length equal to the number of expected topics, * 'asymmetric': Uses a fixed normalized assymetric prior of `1.0 / topicno`. - * 'default': Learns an assymetric prior from the corpus. + * 'auto': Learns an assymetric prior from the corpus. name : {'alpha', 'eta'} Whether the `prior` is parameterized by the alpha vector (1 parameter per topic) or by the eta (1 parameter per unique term in the vocabulary). From 8a0835735332af07c125402d595e70530a9e715a Mon Sep 17 00:00:00 2001 From: Laubeee Date: Mon, 13 Aug 2018 11:45:55 +0200 Subject: [PATCH 3/9] Update ldamulticore.py --- gensim/models/ldamulticore.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gensim/models/ldamulticore.py b/gensim/models/ldamulticore.py index d32a709f80..74831ea495 100644 --- a/gensim/models/ldamulticore.py +++ b/gensim/models/ldamulticore.py @@ -129,7 +129,7 @@ def __init__(self, corpus=None, num_topics=100, id2word=None, workers=None, Alternatively default prior selecting strategies can be employed by supplying a string: * 'asymmetric': Uses a fixed normalized assymetric prior of `1.0 / topicno`. - * 'default': Learns an assymetric prior from the corpus. + * 'auto': Learns an assymetric prior from the corpus. eta : {float, np.array, str}, optional A-priori belief on word probability, this can be: From b1ba3d865bc62b36ffd409329779368c8363f0e0 Mon Sep 17 00:00:00 2001 From: Laubeee Date: Mon, 13 Aug 2018 11:47:03 +0200 Subject: [PATCH 4/9] Update ldamodel.py --- gensim/sklearn_api/ldamodel.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gensim/sklearn_api/ldamodel.py b/gensim/sklearn_api/ldamodel.py index 3e5d65dcc6..4ef515aeeb 100644 --- a/gensim/sklearn_api/ldamodel.py +++ b/gensim/sklearn_api/ldamodel.py @@ -61,7 +61,7 @@ def __init__(self, num_topics=100, id2word=None, chunksize=2000, passes=1, updat Alternatively default prior selecting strategies can be employed by supplying a string: * 'asymmetric': Uses a fixed normalized assymetric prior of `1.0 / topicno`. - * 'default': Learns an assymetric prior from the corpus. + * 'auto': Learns an assymetric prior from the corpus. eta : {float, np.array, str}, optional A-priori belief on word probability, this can be: From 7ba8a7a8f5f747abf74d1d328dd0fe25668c3742 Mon Sep 17 00:00:00 2001 From: Laubeee Date: Mon, 13 Aug 2018 11:50:35 +0200 Subject: [PATCH 5/9] Update atmodel.py --- gensim/sklearn_api/atmodel.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gensim/sklearn_api/atmodel.py b/gensim/sklearn_api/atmodel.py index 69397833c0..a111e45f77 100644 --- a/gensim/sklearn_api/atmodel.py +++ b/gensim/sklearn_api/atmodel.py @@ -83,7 +83,7 @@ def __init__(self, num_topics=100, id2word=None, author2doc=None, doc2author=Non Alternatively default prior selecting strategies can be employed by supplying a string: * 'asymmetric': Uses a fixed normalized assymetric prior of `1.0 / topicno`. - * 'default': Learns an assymetric prior from the corpus. + * 'auto': Learns an assymetric prior from the corpus. eta : {float, np.array, str}, optional A-priori belief on word probability, this can be: From 2b20f67914c471aa5eeefe5117950a387758a70a Mon Sep 17 00:00:00 2001 From: Laubeee Date: Mon, 13 Aug 2018 16:10:53 +0200 Subject: [PATCH 6/9] correct assymetric -> asymmetric --- gensim/models/ldamodel.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/gensim/models/ldamodel.py b/gensim/models/ldamodel.py index e866386ba0..2f66f30c52 100755 --- a/gensim/models/ldamodel.py +++ b/gensim/models/ldamodel.py @@ -530,8 +530,8 @@ def init_dir_prior(self, prior, name): If `name` == 'alpha', then the prior can be: * an 1D array of length equal to the number of expected topics, - * 'asymmetric': Uses a fixed normalized assymetric prior of `1.0 / topicno`. - * 'auto': Learns an assymetric prior from the corpus. + * 'asymmetric': Uses a fixed normalized asymmetric prior of `1.0 / topicno`. + * 'auto': Learns an asymmetric prior from the corpus. name : {'alpha', 'eta'} Whether the `prior` is parameterized by the alpha vector (1 parameter per topic) or by the eta (1 parameter per unique term in the vocabulary). From 497ac5d5d257035ba434e23a255a18c811f379fd Mon Sep 17 00:00:00 2001 From: Laubeee Date: Mon, 13 Aug 2018 16:12:21 +0200 Subject: [PATCH 7/9] Update ldamulticore.py --- gensim/models/ldamulticore.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/gensim/models/ldamulticore.py b/gensim/models/ldamulticore.py index 74831ea495..168a2752c0 100644 --- a/gensim/models/ldamulticore.py +++ b/gensim/models/ldamulticore.py @@ -128,8 +128,8 @@ def __init__(self, corpus=None, num_topics=100, id2word=None, workers=None, our a-priori belief for the each topics' probability. Alternatively default prior selecting strategies can be employed by supplying a string: - * 'asymmetric': Uses a fixed normalized assymetric prior of `1.0 / topicno`. - * 'auto': Learns an assymetric prior from the corpus. + * 'asymmetric': Uses a fixed normalized asymmetric prior of `1.0 / topicno`. + * 'auto': Learns an asymmetric prior from the corpus. eta : {float, np.array, str}, optional A-priori belief on word probability, this can be: From 10262cfdc8a05e8d6e663c40b493d153e83a15f7 Mon Sep 17 00:00:00 2001 From: Laubeee Date: Mon, 13 Aug 2018 16:13:01 +0200 Subject: [PATCH 8/9] Update atmodel.py --- gensim/sklearn_api/atmodel.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/gensim/sklearn_api/atmodel.py b/gensim/sklearn_api/atmodel.py index a111e45f77..085ed9a745 100644 --- a/gensim/sklearn_api/atmodel.py +++ b/gensim/sklearn_api/atmodel.py @@ -82,8 +82,8 @@ def __init__(self, num_topics=100, id2word=None, author2doc=None, doc2author=Non our a-priori belief for the each topics' probability. Alternatively default prior selecting strategies can be employed by supplying a string: - * 'asymmetric': Uses a fixed normalized assymetric prior of `1.0 / topicno`. - * 'auto': Learns an assymetric prior from the corpus. + * 'asymmetric': Uses a fixed normalized asymmetric prior of `1.0 / topicno`. + * 'auto': Learns an asymmetric prior from the corpus. eta : {float, np.array, str}, optional A-priori belief on word probability, this can be: From 00733db5613cb42daf3798ff36897e09f3533706 Mon Sep 17 00:00:00 2001 From: Laubeee Date: Mon, 13 Aug 2018 16:13:31 +0200 Subject: [PATCH 9/9] Update ldamodel.py --- gensim/sklearn_api/ldamodel.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/gensim/sklearn_api/ldamodel.py b/gensim/sklearn_api/ldamodel.py index 4ef515aeeb..33f2575acc 100644 --- a/gensim/sklearn_api/ldamodel.py +++ b/gensim/sklearn_api/ldamodel.py @@ -60,8 +60,8 @@ def __init__(self, num_topics=100, id2word=None, chunksize=2000, passes=1, updat our a-priori belief for the each topics' probability. Alternatively default prior selecting strategies can be employed by supplying a string: - * 'asymmetric': Uses a fixed normalized assymetric prior of `1.0 / topicno`. - * 'auto': Learns an assymetric prior from the corpus. + * 'asymmetric': Uses a fixed normalized asymmetric prior of `1.0 / topicno`. + * 'auto': Learns an asymmetric prior from the corpus. eta : {float, np.array, str}, optional A-priori belief on word probability, this can be: