Spelling

Doc2Vec.ipynb

@@ -222,7 +222,7 @@
     "\n",
     "def remove_punctuation(data):\n",
     "    \"\"\"\n",
-    "    Removes various punctation from Hebrew text.\n",
+    "    Removes various punctuation from Hebrew text.\n",
     "    :param data: String of Hebrew Text\n",
     "    :return: String without punctuation\n",
     "    \"\"\"\n",
@@ -281,7 +281,7 @@
     "\n",
     "def get_segments(filename):\n",
     "    \"\"\"\n",
-    "    Combs through the entire Sefaris Hebrew Library and cleans the text for Doc2Vec.\n",
+    "    Combs through the entire Sefaria Hebrew Library and cleans the text for Doc2Vec.\n",
     "    Creates a dict:\n",
     "        Key:  Ref\n",
     "        Value:  The text of that ref cleaned and ready for Doc2Vec\n",

Hebrew Spellcheck.ipynb

@@ -68,7 +68,7 @@
     "\n",
     "def determine_beginning_stopword(beginning_stopword):\n",
     "    \"\"\"\n",
-    "    Appends the approproate beginning stopword.  There are three possibilites, \n",
+    "    Appends the appropriate beginning stopword.  There are three possibilities, \n",
     "    therefore the correct option needs to be determine\n",
     "    :param beginning_stopword: The modified word\n",
     "    :return: Appropriate beginning stopword\n",

RAKE Hebrew.ipynb

@@ -1078,7 +1078,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# This just gets a list of every word and the number of occurences within the entire corpus.  Used to help build a stopword list"
+    "# This just gets a list of every word and the number of occurrences within the entire corpus.  Used to help build a stopword list"
    ]
   },
   {

create_docs_for_doc2vec.py

@@ -168,7 +168,7 @@ def remove_dicta_prefix(string, marker):
 
 def remove_punctuation(data):
     """
-    Removes various punctation from Hebrew text.
+    Removes various punctuation from Hebrew text.
     :param data: String of Hebrew Text
     :return: String without punctuation
     """
@@ -236,9 +236,9 @@ def extract_reference(data):
     return data.split(u'~')[0]
 
 
-def concatenate_sematically_linked_segments(topic_ranged_refs, ranged_to_segment):
+def concatenate_semantically_linked_segments(topic_ranged_refs, ranged_to_segment):
     """
-    Combines multiple Sefaria Segments into one larger segment based on sematical meaning
+    Combines multiple Sefaria Segments into one larger segment based on semantical meaning
     :param topic_ranged_refs: List of ranged trefs that define the semantic separation
     :param ranged_to_segment: Nested dict.  First layer points from Ranged Refs to all sub-seg-refs.  The nested dict points from the sub_seg_ref to the text of said sub_seg_ref
     :return: Dict containing semantically define ranged refs corresponding to their concatenated text
@@ -294,8 +294,8 @@ def get_segments(filename):
         else:
             all_data[ref] = data
 
-    all_data.update(concatenate_sematically_linked_segments(tanakh_topic_ranged_refs, tanakh_ranged_to_segment))
-    all_data.update(concatenate_sematically_linked_segments(talmud_topic_ranged_refs, talmud_ranged_to_segment))
+    all_data.update(concatenate_semantically_linked_segments(tanakh_topic_ranged_refs, tanakh_ranged_to_segment))
+    all_data.update(concatenate_semantically_linked_segments(talmud_topic_ranged_refs, talmud_ranged_to_segment))
 
     return all_data
 

hebrew_spellcheck.py

@@ -47,7 +47,7 @@ def we_havent_added_prefix_or_suffix(word):
 
 def determine_beginning_stopword(beginning_stopword):
     """
-    Appends the approproate beginning stopword.  There are three possibilites,
+    Appends the appropriate beginning stopword.  There are three possibilities,
     therefore the correct option needs to be determine
     :param beginning_stopword: The modified word
     :return: Appropriate beginning stopword

high_conf_links.json

@@ -55691,7 +55691,7 @@
   ], 
   [
     "Daniel 7:9", 
-    "Likutei Halachot, Yoreh Deah, Laws of Fobidden Fabric Blends 3:2:1", 
+    "Likutei Halachot, Yoreh Deah, Laws of Forbidden Fabric Blends 3:2:1", 
     146.76882352941178
   ], 
   [
@@ -279761,7 +279761,7 @@
   ], 
   [
     "Chagigah 13a:9", 
-    "Likutei Halachot, Yoreh Deah, Laws of Fobidden Fabric Blends 4:3:1", 
+    "Likutei Halachot, Yoreh Deah, Laws of Forbidden Fabric Blends 4:3:1", 
     163.4555
   ], 
   [
@@ -389716,7 +389716,7 @@
   ], 
   [
     "Berakhot 6a:5", 
-    "Likutei Halachot, Yoreh Deah, Laws of Fobidden Fabric Blends 2:2:1", 
+    "Likutei Halachot, Yoreh Deah, Laws of Forbidden Fabric Blends 2:2:1", 
     83.0
   ], 
   [
@@ -391401,7 +391401,7 @@
   ], 
   [
     "Proverbs 25:2", 
-    "Likutei Halachot, Yoreh Deah, Laws of Fobidden Fabric Blends 3:5:1", 
+    "Likutei Halachot, Yoreh Deah, Laws of Forbidden Fabric Blends 3:5:1", 
     66.27947368421053
   ], 
   [
@@ -563561,7 +563561,7 @@
   ], 
   [
     "Psalms 99:6", 
-    "Divrei Emet, Divrei Emet on Torah, A Collection on Sciptures 5", 
+    "Divrei Emet, Divrei Emet on Torah, A Collection on Scriptures 5", 
     102.61833333333334
   ], 
   [

test_topics.json

@@ -695,7 +695,7 @@
       0.7636483311653137
     ], 
     [
-      "Siddur Sefard, Additional Prayers , Six Rememberances 10", 
+      "Siddur Sefard, Additional Prayers , Six Remembrances 10", 
       0.7589909434318542
     ], 
     [