Package absolute imports

README.md

@@ -25,6 +25,7 @@ Synonym().raw_synonym(word = 'माया',word_vec=word_vec) #method: 1
 Synonym().filter_synonym(word = 'साथी',word_vec=word_vec) #method: 2
 #output -> 'भाइहरू','सहपाठी','प्रेमी','दाइ','प्रेमि','बहिनी'
 ```
+
 <h3>Word-spell corrector</h3>
 
 ```python
@@ -34,32 +35,37 @@ Corrector().corrector(word='सुशल') #In a very raw stage for now.
 Corrector().spell_correct("कस्त भको हेरौ है")
 #output-> "कस्तो भयो हेर है"
 ```
-<h3>Nepali text summerizer</h3>
+
+<h3>Nepali text Summarizer</h3>
 
 ```python
-from Nepali_nlp import Summerize
-Summerize().show_summary(word_vec,text, length_sentence_predict=5)
+from Nepali_nlp import Summarize
+Summarize().show_summary(word_vec,text, length_sentence_predict=5)
 ```
+
 <h3>Nepali unicode to Devnagiri Font</h3>
 
 ```python
 from Nepali_nlp import Unicode
 text = 'ma ghara jaanchhu'
 Unicode().unicode_word(text) #output-> 'म घर जान्छु'
 ```
+
 <h3>Preeti-font character to Devnagiri Font</h3>
 
 ```python
 from Nepali_nlp import preeti
 unicode_word = 'g]kfnL'
 print(preeti(unicode_word)) #output-> नेपाली
 ```
+
 <h3>OCR(optical character reader)</h3>
 
 ```python
 from Nepali_nlp import OCR
 text = OCR(image_location)
 ```
+
 <h3>Nepali Tokenizer</h3>
 
 ```python
@@ -94,22 +100,24 @@ from Nepali_nlp import extract_news
 news_link = 'https://www.onlinekhabar.com/2019/12/821094'
 title, news = extract_news(news_link) #onlinekhabar and ekantipur is supported at the moment.
 ```
+
 <h3>Show latest news summary</h3>
 
 ```python
 from Nepali_nlp import UpdateNews
-title, links, summerized_news = UpdateNews().show_latest(word_vec=word_vec,portal='onlinekhabar',number_of_news=5) #ekantipur portal is also supported
+title, links, Summarized_news = UpdateNews().show_latest(word_vec=word_vec,portal='onlinekhabar',number_of_news=5) #ekantipur portal is also supported
 ```
 
 TODOs:</br>
-- [x] Nepali Embeddings 
-- [x] Tokenizers (sentence, word, character) 
+
+- [x] Nepali Embeddings
+- [x] Tokenizers (sentence, word, character)
 - [x] Stop Words
-- [x] Nepali Words Collection 
+- [x] Nepali Words Collection
 - [x] Nepali Word synonym
 - [x] Roman Nepali to Nepali
 - [x] Nepali OCR
-- [x] Summerization 
+- [x] summarization
 - [x] Pos_tag
 - [x] Nepali stemming
 - [x] Sentence similarity score

nepali_nlp/__init__.py

@@ -0,0 +1,12 @@
+from nepali_nlp.embedding import Embeddings
+from nepali_nlp.synonym import Synonym
+from nepali_nlp.spellcheck import Corrector
+from nepali_nlp.summarization import Summarize
+from nepali_nlp.unicode_nepali import Unicode
+from nepali_nlp.preeti_unicode import preeti
+from nepali_nlp.ocr import OCR
+from nepali_nlp.nepali_tokenizer import Tokenizer
+from nepali_nlp.sentence_similar import Avg_vector_similar
+from nepali_nlp.news_scrap import extract_news
+from nepali_nlp.news_latest import UpdateNews
+from nepali_nlp.stemmer import Stem

Nepali_nlp/Embedding.py → nepali_nlp/embedding.py

@@ -1,10 +1,9 @@
+from nepali_nlp.download_embedding import Download
+from gensim.models.keyedvectors import KeyedVectors
+import gensim
 import os
 import sys
-sys.path.append('..')
 
-import gensim
-from gensim.models.keyedvectors import KeyedVectors
-from .Download_embedding import Download
 
 class Embeddings:
     """This class helps to load embedding in keyedvector format."""
@@ -19,23 +18,26 @@ def load_large_vector(self):
             [keyedVectors] -- [Custom Nepali word Embedding]
         """
         download = Download()
-        download.download_file_from_google_drive('1ik38vahOmzhiU2DBi78VOqDt7YFPsk5w', 'word_vector.sg')
-        word_vector = KeyedVectors.load_word2vec_format('word_vector.sg', binary=False)
+        download.download_file_from_google_drive(
+            '1ik38vahOmzhiU2DBi78VOqDt7YFPsk5w', 'word_vector.sg')
+        word_vector = KeyedVectors.load_word2vec_format(
+            'word_vector.sg', binary=False)
         os.remove("word_vector.sg")
 
         return word_vector
 
     def load_vector(self):
         """Returns a large Nepali word embedding. Creator: https://github.com/rabindralamsal/Word2Vec-Embeddings-for-Nepali-Language
-        
+
         Returns:
             [keyedVectors] -- [Custom Nepali word Embedding]
         """
         download = Download()
-        download.download_file_from_google_drive('1KnAZ2Eeqwz3S9VrAuzTLWysAaRB6Ch7e', 'nepali_embeddings_word2vec.txt')
+        download.download_file_from_google_drive(
+            '1KnAZ2Eeqwz3S9VrAuzTLWysAaRB6Ch7e', 'nepali_embeddings_word2vec.txt')
         word_vector = KeyedVectors.load('nepali_embeddings_word2vec.txt')
         os.remove("nepali_embeddings_word2vec.txt")
-        
+
         return word_vector
 
     def __str__(self):

Nepali_nlp/n_gram.py → nepali_nlp/n_gram.py

@@ -1,7 +1,6 @@
+from nepali_nlp.nepali_tokenizer import Tokenizer
 import sys
-sys.path.append('..')
 
-from .Nepali_tokenizer import Tokenizer
 
 class NgramGenerator(Tokenizer):
 
@@ -10,11 +9,11 @@ def __init__(self, n_gram):
 
     def generate_n_gram(self, token_text):
         """This function generate ngram token list
-        
+
             Arguments:
                 sentence {list} -- list of tokenized text
                 n_gram {int} -- value of n-gram
-        
+
             Returns:
                 list --  multi array list of n-gram tokenized words
             """

nepali_nlp/news_latest.py

@@ -0,0 +1,36 @@
+from nepali_nlp.summarization import Summarize
+from nepali_nlp.news_scrap import extract_news
+from nepali_nlp.utils import top_news_link
+import sys
+
+
+class UpdateNews:
+    def __init__(self):
+        pass
+
+    def show_latest(self, word_vec, portal='onlinekhabar', number_of_news=5):
+        """This function returns tile of latest news, link for latest news and Summarize news 
+
+        Keyword Arguments:
+            portal {str} -- [news portal sites; for now either 'onlinekhabar' or 'ekantipur'] (default: {'onlinekhabar'})
+            number_of_news {int} -- [Number of top trending news] (default: {5})
+
+        Returns:
+            [tuple] -- [tuple of (titles, links, news_summaries)]
+        """
+        assert portal in [
+            'onlinekhabar', 'ekantipur'], "we currently support only ekantipur and onlinekhabar"
+        extracted_link = top_news_link(portal=portal, top_n=number_of_news)
+        summary_ = Summarize()
+        links = []
+        titles = []
+        news_summaries = []
+        for link in extracted_link:
+            title, text = extract_news(link)
+            summary_news = summary_.show_summary(
+                word_vec, text, length_sentence_predict=7)
+            links.append(link)
+            titles.append(title)
+            news_summaries.append(summary_news)
+
+        return (titles, links, news_summaries)