From 40989bac545ee5ad2c1444fab06bff09a33df0f3 Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Mon, 29 Apr 2019 20:29:50 -0300
Subject: [PATCH 01/16] adding type check for corpus_file argument

---
 gensim/models/doc2vec.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py
index 9812dc5ef4..6a2f553626 100644
--- a/gensim/models/doc2vec.py
+++ b/gensim/models/doc2vec.py
@@ -794,6 +794,11 @@ def train(self, documents=None, corpus_file=None, total_examples=None, total_wor
 
         """
         kwargs = {}
+
+        # Check the type of corpus_file
+        if not isinstance(corpus_file, string_types):
+            raise TypeError("Parameter corpus_file of train() must be a string (path to a file).")
+
         if corpus_file is not None:
             # Calculate offsets for each worker along with initial doctags (doctag ~ document/line number in a file)
             offsets, start_doctags = self._get_offsets_and_start_doctags_for_corpusfile(corpus_file, self.workers)

From ad76b83653e23d760e378d471e5fc1f32e55418a Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Tue, 30 Apr 2019 20:33:48 -0300
Subject: [PATCH 02/16] fixes to handle different typeerror in train
 parameters, adding unittests

---
 gensim/test/test_doc2vec.py | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/gensim/test/test_doc2vec.py b/gensim/test/test_doc2vec.py
index d9af7070d3..279f7b0ef4 100644
--- a/gensim/test/test_doc2vec.py
+++ b/gensim/test/test_doc2vec.py
@@ -173,6 +173,23 @@ def testLoadOldModel(self):
             sims_to_infer = loaded_model.docvecs.most_similar([doc0_inferred], topn=len(loaded_model.docvecs))
             self.assertTrue(sims_to_infer)
 
+    def testDoc2vecTrainParameters(self):
+
+        model = doc2vec.Doc2Vec(vector_size=50)
+        model.build_vocab(documents=list_corpus)
+
+        # check if corpus_file is not a string
+        self.assertRaises(TypeError, model.train, corpus_file=11111)
+        # check if documents is an iterable (but not string)
+        self.assertRaises(TypeError, model.train, documents="blabla")
+        # check is both the parameters are provided
+        self.assertRaises(TypeError, model.train, documents=sentences, corpus_file='test')
+        # check if both the parameters are left empty
+        self.assertRaises(TypeError, model.train, documents=None, corpus_file=None)
+        # check if corpus_file is an iterable
+        self.assertRaises(TypeError, model.train, corpus_file=sentences)
+
+
     @unittest.skipIf(os.name == 'nt', "See another test for Windows below")
     def test_get_offsets_and_start_doctags(self):
         # Each line takes 6 bytes (including '\n' character)
@@ -387,7 +404,7 @@ def model_sanity(self, model, keep_training=True):
             tmpf = get_tmpfile('gensim_doc2vec.tst')
             model.save(tmpf)
             loaded = doc2vec.Doc2Vec.load(tmpf)
-            loaded.train(sentences, total_examples=loaded.corpus_count, epochs=loaded.epochs)
+            loaded.train(documents=sentences, total_examples=loaded.corpus_count, epochs=loaded.epochs)
 
     def test_training(self):
         """Test doc2vec training."""

From e1f32a2accdb49fa12d0fef62f34bba2e74b3cfc Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Tue, 30 Apr 2019 20:41:48 -0300
Subject: [PATCH 03/16] adding doc2vec with more typeerror checks

---
 gensim/models/doc2vec.py | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py
index 6a2f553626..7766d450ba 100644
--- a/gensim/models/doc2vec.py
+++ b/gensim/models/doc2vec.py
@@ -70,7 +70,7 @@
 except ImportError:
     from Queue import Queue  # noqa:F401
 
-from collections import namedtuple, defaultdict
+from collections import namedtuple, defaultdict, Iterable
 from timeit import default_timer
 
 from numpy import zeros, float32 as REAL, empty, ones, \
@@ -795,9 +795,21 @@ def train(self, documents=None, corpus_file=None, total_examples=None, total_wor
         """
         kwargs = {}
 
+        # Check if both documents and corpus_file are None
+        if corpus_file is None and documents is None:
+            raise TypeError("Either one of corpus_file or documents value must be provided.")
+
+        # Check if both documents and corpus_file are not None
+        if not corpus_file is None and not documents is None:
+            raise TypeError("Instead provide value to either of corpus_file or documents parameter but not both.")
+
+        # Check if documents is not None and iterable but not string type
+        if not documents is None and isinstance(documents, Iterable) and isinstance(documents, string_types):
+            raise TypeError("Documents must be an iterable of list and not a string type.")
+
         # Check the type of corpus_file
-        if not isinstance(corpus_file, string_types):
-            raise TypeError("Parameter corpus_file of train() must be a string (path to a file).")
+        if corpus_file is not None and not isinstance(corpus_file, string_types):
+            raise TypeError(f"Parameter corpus_file of train() must be a string (path to a file) got {corpus_file} instead.")
 
         if corpus_file is not None:
             # Calculate offsets for each worker along with initial doctags (doctag ~ document/line number in a file)

From a9eeddfd579e83b92f2d7a88101500ff1c4269d3 Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Tue, 30 Apr 2019 20:53:15 -0300
Subject: [PATCH 04/16] fixing lint errors

---
 gensim/models/doc2vec.py    | 7 ++++---
 gensim/test/test_doc2vec.py | 1 -
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py
index 7766d450ba..61521c98ff 100644
--- a/gensim/models/doc2vec.py
+++ b/gensim/models/doc2vec.py
@@ -800,16 +800,17 @@ def train(self, documents=None, corpus_file=None, total_examples=None, total_wor
             raise TypeError("Either one of corpus_file or documents value must be provided.")
 
         # Check if both documents and corpus_file are not None
-        if not corpus_file is None and not documents is None:
+        if corpus_file is not None and documents is not None:
             raise TypeError("Instead provide value to either of corpus_file or documents parameter but not both.")
 
         # Check if documents is not None and iterable but not string type
-        if not documents is None and isinstance(documents, Iterable) and isinstance(documents, string_types):
+        if documents is not None and isinstance(documents, Iterable) and isinstance(documents, string_types):
             raise TypeError("Documents must be an iterable of list and not a string type.")
 
         # Check the type of corpus_file
         if corpus_file is not None and not isinstance(corpus_file, string_types):
-            raise TypeError(f"Parameter corpus_file of train() must be a string (path to a file) got {corpus_file} instead.")
+            raise TypeError(f"""Parameter corpus_file of train() must be a
+                             string (path to a file) got {corpus_file} instead.""")
 
         if corpus_file is not None:
             # Calculate offsets for each worker along with initial doctags (doctag ~ document/line number in a file)
diff --git a/gensim/test/test_doc2vec.py b/gensim/test/test_doc2vec.py
index 279f7b0ef4..7301f808cc 100644
--- a/gensim/test/test_doc2vec.py
+++ b/gensim/test/test_doc2vec.py
@@ -189,7 +189,6 @@ def testDoc2vecTrainParameters(self):
         # check if corpus_file is an iterable
         self.assertRaises(TypeError, model.train, corpus_file=sentences)
 
-
     @unittest.skipIf(os.name == 'nt', "See another test for Windows below")
     def test_get_offsets_and_start_doctags(self):
         # Each line takes 6 bytes (including '\n' character)

From 6639089fdc26e94751b133a365271e344e31c055 Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Tue, 30 Apr 2019 21:21:58 -0300
Subject: [PATCH 05/16] removing f-string use

---
 gensim/models/doc2vec.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py
index 61521c98ff..bebf261fa8 100644
--- a/gensim/models/doc2vec.py
+++ b/gensim/models/doc2vec.py
@@ -809,8 +809,8 @@ def train(self, documents=None, corpus_file=None, total_examples=None, total_wor
 
         # Check the type of corpus_file
         if corpus_file is not None and not isinstance(corpus_file, string_types):
-            raise TypeError(f"""Parameter corpus_file of train() must be a
-                             string (path to a file) got {corpus_file} instead.""")
+            raise TypeError("""Parameter corpus_file of train() must be a
+                             string (path to an existing file) got %s instead.""" % corpus_file)
 
         if corpus_file is not None:
             # Calculate offsets for each worker along with initial doctags (doctag ~ document/line number in a file)

From 2ca51ca4a18c7811f9e32115e2649d5906d63916 Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Wed, 1 May 2019 08:07:24 -0300
Subject: [PATCH 06/16] fixes as suggested

---
 gensim/models/doc2vec.py | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py
index bebf261fa8..90197c9cf1 100644
--- a/gensim/models/doc2vec.py
+++ b/gensim/models/doc2vec.py
@@ -803,14 +803,13 @@ def train(self, documents=None, corpus_file=None, total_examples=None, total_wor
         if corpus_file is not None and documents is not None:
             raise TypeError("Instead provide value to either of corpus_file or documents parameter but not both.")
 
-        # Check if documents is not None and iterable but not string type
-        if documents is not None and isinstance(documents, Iterable) and isinstance(documents, string_types):
+        # Check if documents is not None and not string type either
+        if documents is not None and isinstance(documents, string_types):
             raise TypeError("Documents must be an iterable of list and not a string type.")
 
         # Check the type of corpus_file
-        if corpus_file is not None and not isinstance(corpus_file, string_types):
-            raise TypeError("""Parameter corpus_file of train() must be a
-                             string (path to an existing file) got %s instead.""" % corpus_file)
+        if not isinstance(corpus_file, string_types) and documents is None:
+            raise TypeError("Parameter corpus_file must be a valid path to a file, got %s instead." % corpus_file)
 
         if corpus_file is not None:
             # Calculate offsets for each worker along with initial doctags (doctag ~ document/line number in a file)

From 6458aea3a1dfc8d8c400ccdc7543434dfaf9f542 Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Wed, 1 May 2019 08:51:05 -0300
Subject: [PATCH 07/16] remove unused imports

---
 gensim/models/doc2vec.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py
index 90197c9cf1..acff036577 100644
--- a/gensim/models/doc2vec.py
+++ b/gensim/models/doc2vec.py
@@ -70,7 +70,7 @@
 except ImportError:
     from Queue import Queue  # noqa:F401
 
-from collections import namedtuple, defaultdict, Iterable
+from collections import namedtuple, defaultdict
 from timeit import default_timer
 
 from numpy import zeros, float32 as REAL, empty, ones, \

From bc9dce66119d70efa372484835556ae4bc646bb2 Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Wed, 1 May 2019 21:36:20 -0300
Subject: [PATCH 08/16] using xor as suggested

---
 gensim/models/doc2vec.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py
index acff036577..b82da0afe2 100644
--- a/gensim/models/doc2vec.py
+++ b/gensim/models/doc2vec.py
@@ -800,12 +800,12 @@ def train(self, documents=None, corpus_file=None, total_examples=None, total_wor
             raise TypeError("Either one of corpus_file or documents value must be provided.")
 
         # Check if both documents and corpus_file are not None
-        if corpus_file is not None and documents is not None:
+        if not ((corpus_file is None) ^ (documents is None)):
             raise TypeError("Instead provide value to either of corpus_file or documents parameter but not both.")
 
         # Check if documents is not None and not string type either
         if documents is not None and isinstance(documents, string_types):
-            raise TypeError("Documents must be an iterable of list and not a string type.")
+            raise TypeError("documents must be an iterable of list and not a string type.")
 
         # Check the type of corpus_file
         if not isinstance(corpus_file, string_types) and documents is None:

From 97d56197833a428b99973ecfb24f457862c4f75d Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Wed, 1 May 2019 22:22:55 -0300
Subject: [PATCH 09/16] minor fixes

---
 gensim/models/doc2vec.py | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py
index b82da0afe2..961a0b661b 100644
--- a/gensim/models/doc2vec.py
+++ b/gensim/models/doc2vec.py
@@ -70,7 +70,7 @@
 except ImportError:
     from Queue import Queue  # noqa:F401
 
-from collections import namedtuple, defaultdict
+from collections import namedtuple, defaultdict, Iterable
 from timeit import default_timer
 
 from numpy import zeros, float32 as REAL, empty, ones, \
@@ -803,14 +803,14 @@ def train(self, documents=None, corpus_file=None, total_examples=None, total_wor
         if not ((corpus_file is None) ^ (documents is None)):
             raise TypeError("Instead provide value to either of corpus_file or documents parameter but not both.")
 
-        # Check if documents is not None and not string type either
-        if documents is not None and isinstance(documents, string_types):
-            raise TypeError("documents must be an iterable of list and not a string type.")
-
-        # Check the type of corpus_file
+        # Check if corpus_file is string type
         if not isinstance(corpus_file, string_types) and documents is None:
             raise TypeError("Parameter corpus_file must be a valid path to a file, got %s instead." % corpus_file)
 
+        # Check if documents is iterable and not string type
+        if isinstance(documents, Iterable) and isinstance(documents, string_types):
+            raise TypeError("documents must be an iterable of list and not a string type.")
+
         if corpus_file is not None:
             # Calculate offsets for each worker along with initial doctags (doctag ~ document/line number in a file)
             offsets, start_doctags = self._get_offsets_and_start_doctags_for_corpusfile(corpus_file, self.workers)

From cdaff9ff3985d497f540ea38d332dbbac1db8044 Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Wed, 1 May 2019 22:33:06 -0300
Subject: [PATCH 10/16] only check for iterable

---
 gensim/models/doc2vec.py    | 6 +++---
 gensim/test/test_doc2vec.py | 4 ++--
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py
index 961a0b661b..84959a59a3 100644
--- a/gensim/models/doc2vec.py
+++ b/gensim/models/doc2vec.py
@@ -807,9 +807,9 @@ def train(self, documents=None, corpus_file=None, total_examples=None, total_wor
         if not isinstance(corpus_file, string_types) and documents is None:
             raise TypeError("Parameter corpus_file must be a valid path to a file, got %s instead." % corpus_file)
 
-        # Check if documents is iterable and not string type
-        if isinstance(documents, Iterable) and isinstance(documents, string_types):
-            raise TypeError("documents must be an iterable of list and not a string type.")
+        # Check if documents is iterable
+        if not isinstance(documents, Iterable):
+            raise TypeError("documents must be an iterable of list, got %s instead." % documents)
 
         if corpus_file is not None:
             # Calculate offsets for each worker along with initial doctags (doctag ~ document/line number in a file)
diff --git a/gensim/test/test_doc2vec.py b/gensim/test/test_doc2vec.py
index 7301f808cc..60e59e278f 100644
--- a/gensim/test/test_doc2vec.py
+++ b/gensim/test/test_doc2vec.py
@@ -180,8 +180,8 @@ def testDoc2vecTrainParameters(self):
 
         # check if corpus_file is not a string
         self.assertRaises(TypeError, model.train, corpus_file=11111)
-        # check if documents is an iterable (but not string)
-        self.assertRaises(TypeError, model.train, documents="blabla")
+        # check if documents is an iterable
+        self.assertRaises(TypeError, model.train, documents=11111)
         # check is both the parameters are provided
         self.assertRaises(TypeError, model.train, documents=sentences, corpus_file='test')
         # check if both the parameters are left empty

From b04629229c8d975ae6cb63b249b0c577c93f1169 Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Wed, 1 May 2019 23:42:06 -0300
Subject: [PATCH 11/16] minor fix - 2

---
 gensim/models/doc2vec.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py
index 84959a59a3..4f68bbb6a7 100644
--- a/gensim/models/doc2vec.py
+++ b/gensim/models/doc2vec.py
@@ -804,11 +804,11 @@ def train(self, documents=None, corpus_file=None, total_examples=None, total_wor
             raise TypeError("Instead provide value to either of corpus_file or documents parameter but not both.")
 
         # Check if corpus_file is string type
-        if not isinstance(corpus_file, string_types) and documents is None:
+        if documents is None and not isinstance(corpus_file, string_types):
             raise TypeError("Parameter corpus_file must be a valid path to a file, got %s instead." % corpus_file)
 
         # Check if documents is iterable
-        if not isinstance(documents, Iterable):
+        if documents is not None and not isinstance(documents, Iterable):
             raise TypeError("documents must be an iterable of list, got %s instead." % documents)
 
         if corpus_file is not None:

From 298e8f0ea9e915fed80a8adcf631f86fa887e056 Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Thu, 2 May 2019 09:38:41 -0300
Subject: [PATCH 12/16] checking corpus_file path, removing xor

---
 gensim/models/doc2vec.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py
index 4f68bbb6a7..5a901b5962 100644
--- a/gensim/models/doc2vec.py
+++ b/gensim/models/doc2vec.py
@@ -800,11 +800,11 @@ def train(self, documents=None, corpus_file=None, total_examples=None, total_wor
             raise TypeError("Either one of corpus_file or documents value must be provided.")
 
         # Check if both documents and corpus_file are not None
-        if not ((corpus_file is None) ^ (documents is None)):
+        if corpus_file is not None and documents is not None:
             raise TypeError("Instead provide value to either of corpus_file or documents parameter but not both.")
 
         # Check if corpus_file is string type
-        if documents is None and not isinstance(corpus_file, string_types):
+        if documents is None and not os.path.isfile(corpus_file):
             raise TypeError("Parameter corpus_file must be a valid path to a file, got %s instead." % corpus_file)
 
         # Check if documents is iterable

From 4fb01f420cda7b12af4fb7bf046fbe23fca3e1d6 Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Sat, 4 May 2019 07:48:11 -0300
Subject: [PATCH 13/16] fixing nitpiks

---
 gensim/models/doc2vec.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py
index 5a901b5962..99954bba93 100644
--- a/gensim/models/doc2vec.py
+++ b/gensim/models/doc2vec.py
@@ -797,19 +797,19 @@ def train(self, documents=None, corpus_file=None, total_examples=None, total_wor
 
         # Check if both documents and corpus_file are None
         if corpus_file is None and documents is None:
-            raise TypeError("Either one of corpus_file or documents value must be provided.")
+            raise TypeError("Either one of corpus_file or documents value must be provided")
 
         # Check if both documents and corpus_file are not None
         if corpus_file is not None and documents is not None:
-            raise TypeError("Instead provide value to either of corpus_file or documents parameter but not both.")
+            raise TypeError("Both corpus_file and documents must not be provided at the same time")
 
         # Check if corpus_file is string type
         if documents is None and not os.path.isfile(corpus_file):
-            raise TypeError("Parameter corpus_file must be a valid path to a file, got %s instead." % corpus_file)
+            raise TypeError("Parameter corpus_file must be a valid path to a file, got %r instead" % corpus_file)
 
         # Check if documents is iterable
         if documents is not None and not isinstance(documents, Iterable):
-            raise TypeError("documents must be an iterable of list, got %s instead." % documents)
+            raise TypeError("documents must be an iterable of list, got %r instead" % documents)
 
         if corpus_file is not None:
             # Calculate offsets for each worker along with initial doctags (doctag ~ document/line number in a file)

From 07a7d5d3a0b28363379d095e6fbc26d9ec3edd54 Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Sat, 4 May 2019 14:36:29 -0300
Subject: [PATCH 14/16] parameters check in fasttext module

---
 gensim/models/fasttext.py    | 19 +++++++++++++++++++
 gensim/test/test_fasttext.py | 16 ++++++++++++++++
 2 files changed, 35 insertions(+)

diff --git a/gensim/models/fasttext.py b/gensim/models/fasttext.py
index 8978d3d2ff..53a7c96162 100644
--- a/gensim/models/fasttext.py
+++ b/gensim/models/fasttext.py
@@ -280,10 +280,12 @@
 """
 
 import logging
+import os
 
 import numpy as np
 from numpy import ones, vstack, float32 as REAL, sum as np_sum
 import six
+from collections import Iterable
 
 import gensim.models._fasttext_bin
 
@@ -901,6 +903,23 @@ def train(self, sentences=None, corpus_file=None, total_examples=None, total_wor
             >>> model.train(sentences, total_examples=model.corpus_count, epochs=model.epochs)
 
         """
+
+        # Check if both sentences and corpus_file are None
+        if corpus_file is None and sentences is None:
+            raise TypeError("Either one of corpus_file or sentences value must be provided")
+
+        # Check if both sentences and corpus_file are not None
+        if corpus_file is not None and sentences is not None:
+            raise TypeError("Both corpus_file and sentences must not be provided at the same time")
+
+        # Check if corpus_file is string type
+        if sentences is None and not os.path.isfile(corpus_file):
+            raise TypeError("Parameter corpus_file must be a valid path to a file, got %r instead" % corpus_file)
+
+        # Check if sentences is iterable
+        if sentences is not None and not isinstance(sentences, Iterable):
+            raise TypeError("sentences must be an iterable of list, got %r instead" % sentences)
+
         super(FastText, self).train(
             sentences=sentences, corpus_file=corpus_file, total_examples=total_examples, total_words=total_words,
             epochs=epochs, start_alpha=start_alpha, end_alpha=end_alpha, word_count=word_count,
diff --git a/gensim/test/test_fasttext.py b/gensim/test/test_fasttext.py
index 50cacaefdf..d6cb7e51b9 100644
--- a/gensim/test/test_fasttext.py
+++ b/gensim/test/test_fasttext.py
@@ -95,6 +95,22 @@ def test_training(self):
         oov_vec = model.wv['minor']  # oov word
         self.assertEqual(len(oov_vec), 10)
 
+    def testFastTextTrainParameters(self):
+
+        model =  FT_gensim(size=10, min_count=1, hs=1, negative=0, seed=42, workers=1)
+        model.build_vocab(sentences=sentences)
+
+        # check if corpus_file is not a string
+        self.assertRaises(TypeError, model.train, corpus_file=11111)
+        # check if sentences is an iterable
+        self.assertRaises(TypeError, model.train, sentences=11111)
+        # check is both the parameters are provided
+        self.assertRaises(TypeError, model.train, sentences=sentences, corpus_file='test')
+        # check if both the parameters are left empty
+        self.assertRaises(TypeError, model.train, sentences=None, corpus_file=None)
+        # check if corpus_file is an iterable
+        self.assertRaises(TypeError, model.train, corpus_file=sentences)
+
     @unittest.skipIf(os.name == 'nt' and six.PY2, "corpus_file training is not supported on Windows + Py27")
     def test_training_fromfile(self):
         with temporary_file(get_tmpfile('gensim_fasttext.tst')) as corpus_file:

From 8821b92c27a9274ce4530d2e87d9aab076174ab4 Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Sat, 4 May 2019 14:53:04 -0300
Subject: [PATCH 15/16] extra space fix

---
 gensim/test/test_fasttext.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/gensim/test/test_fasttext.py b/gensim/test/test_fasttext.py
index d6cb7e51b9..1e200ffdc7 100644
--- a/gensim/test/test_fasttext.py
+++ b/gensim/test/test_fasttext.py
@@ -97,7 +97,7 @@ def test_training(self):
 
     def testFastTextTrainParameters(self):
 
-        model =  FT_gensim(size=10, min_count=1, hs=1, negative=0, seed=42, workers=1)
+        model = FT_gensim(size=10, min_count=1, hs=1, negative=0, seed=42, workers=1)
         model.build_vocab(sentences=sentences)
 
         # check if corpus_file is not a string

From bfc43605147ca29203a1aba58f690f70c70281c9 Mon Sep 17 00:00:00 2001
From: manish saraswat <manisara0000@gmail.com>
Date: Sat, 4 May 2019 23:25:54 -0300
Subject: [PATCH 16/16] remove comments

---
 gensim/models/doc2vec.py     | 4 ----
 gensim/models/fasttext.py    | 4 ----
 gensim/test/test_doc2vec.py  | 5 -----
 gensim/test/test_fasttext.py | 5 -----
 4 files changed, 18 deletions(-)

diff --git a/gensim/models/doc2vec.py b/gensim/models/doc2vec.py
index 99954bba93..3e690380f9 100644
--- a/gensim/models/doc2vec.py
+++ b/gensim/models/doc2vec.py
@@ -795,19 +795,15 @@ def train(self, documents=None, corpus_file=None, total_examples=None, total_wor
         """
         kwargs = {}
 
-        # Check if both documents and corpus_file are None
         if corpus_file is None and documents is None:
             raise TypeError("Either one of corpus_file or documents value must be provided")
 
-        # Check if both documents and corpus_file are not None
         if corpus_file is not None and documents is not None:
             raise TypeError("Both corpus_file and documents must not be provided at the same time")
 
-        # Check if corpus_file is string type
         if documents is None and not os.path.isfile(corpus_file):
             raise TypeError("Parameter corpus_file must be a valid path to a file, got %r instead" % corpus_file)
 
-        # Check if documents is iterable
         if documents is not None and not isinstance(documents, Iterable):
             raise TypeError("documents must be an iterable of list, got %r instead" % documents)
 
diff --git a/gensim/models/fasttext.py b/gensim/models/fasttext.py
index 53a7c96162..9dce98083e 100644
--- a/gensim/models/fasttext.py
+++ b/gensim/models/fasttext.py
@@ -904,19 +904,15 @@ def train(self, sentences=None, corpus_file=None, total_examples=None, total_wor
 
         """
 
-        # Check if both sentences and corpus_file are None
         if corpus_file is None and sentences is None:
             raise TypeError("Either one of corpus_file or sentences value must be provided")
 
-        # Check if both sentences and corpus_file are not None
         if corpus_file is not None and sentences is not None:
             raise TypeError("Both corpus_file and sentences must not be provided at the same time")
 
-        # Check if corpus_file is string type
         if sentences is None and not os.path.isfile(corpus_file):
             raise TypeError("Parameter corpus_file must be a valid path to a file, got %r instead" % corpus_file)
 
-        # Check if sentences is iterable
         if sentences is not None and not isinstance(sentences, Iterable):
             raise TypeError("sentences must be an iterable of list, got %r instead" % sentences)
 
diff --git a/gensim/test/test_doc2vec.py b/gensim/test/test_doc2vec.py
index 60e59e278f..6ac510ea8e 100644
--- a/gensim/test/test_doc2vec.py
+++ b/gensim/test/test_doc2vec.py
@@ -178,15 +178,10 @@ def testDoc2vecTrainParameters(self):
         model = doc2vec.Doc2Vec(vector_size=50)
         model.build_vocab(documents=list_corpus)
 
-        # check if corpus_file is not a string
         self.assertRaises(TypeError, model.train, corpus_file=11111)
-        # check if documents is an iterable
         self.assertRaises(TypeError, model.train, documents=11111)
-        # check is both the parameters are provided
         self.assertRaises(TypeError, model.train, documents=sentences, corpus_file='test')
-        # check if both the parameters are left empty
         self.assertRaises(TypeError, model.train, documents=None, corpus_file=None)
-        # check if corpus_file is an iterable
         self.assertRaises(TypeError, model.train, corpus_file=sentences)
 
     @unittest.skipIf(os.name == 'nt', "See another test for Windows below")
diff --git a/gensim/test/test_fasttext.py b/gensim/test/test_fasttext.py
index 1e200ffdc7..f2c8f39c5c 100644
--- a/gensim/test/test_fasttext.py
+++ b/gensim/test/test_fasttext.py
@@ -100,15 +100,10 @@ def testFastTextTrainParameters(self):
         model = FT_gensim(size=10, min_count=1, hs=1, negative=0, seed=42, workers=1)
         model.build_vocab(sentences=sentences)
 
-        # check if corpus_file is not a string
         self.assertRaises(TypeError, model.train, corpus_file=11111)
-        # check if sentences is an iterable
         self.assertRaises(TypeError, model.train, sentences=11111)
-        # check is both the parameters are provided
         self.assertRaises(TypeError, model.train, sentences=sentences, corpus_file='test')
-        # check if both the parameters are left empty
         self.assertRaises(TypeError, model.train, sentences=None, corpus_file=None)
-        # check if corpus_file is an iterable
         self.assertRaises(TypeError, model.train, corpus_file=sentences)
 
     @unittest.skipIf(os.name == 'nt' and six.PY2, "corpus_file training is not supported on Windows + Py27")