Merge branch 'feat/#5_implement_strategy_TFIDF_for_summary' into 'master'

Feat/#5 implement strategy tfidf for summary

See merge request !30

src/nlp/app/nlp_server.py

@@ -2,6 +2,7 @@ from fastapi import FastAPI, Request
 from app.utilities import generator
 from app.summary.simple_spacy_summarizer import SimpleSpacySummarizer
 from app.summary.summary_sentence_embedding import SentenceEmbeddingSummarizer
+from app.summary.summarization_with_strategy_TFIDF import SummaryTFIDF
 
 app = FastAPI(
     title="IntentFinder: NLP-API",
@@ -11,8 +12,10 @@ app = FastAPI(
                 " IntentFinder"
 )
 
-strategies = [SimpleSpacySummarizer(),
-              SentenceEmbeddingSummarizer()]
+strategies = [
+    SimpleSpacySummarizer(),
+    SentenceEmbeddingSummarizer(),
+    SummaryTFIDF()]
 
 
 @app.get("/")

src/nlp/app/summary/summarization_with_strategy_TFIDF.py

@@ -38,16 +38,15 @@ class SummaryTFIDF(ISummaryStrategy):
             stopWords = self.nlpEng.Defaults.stop_words
 
         for sent in summary:
-            # dictionary mit 'words' als Schlüssel und ihrer 'Häufigkeit' als
-            #   Wert
+            # dictionary with 'words' as the key
+            # and their 'frequency' as the value
             freq_table = {}
 
             words = [word.text.lower() for word in sent if word.text.isalnum()]
 
             for word in words:
-                word = self.lemmatizer.lemmatize(
-                    word)  # Lemmatisieren Sie das Wort
-                if word not in stopWords:            # Stoppwörter ablehnen
+                word = self.lemmatizer.lemmatize(word)  # Lemmatize the word
+                if word not in stopWords:               # Reject stopWords
                     if word in freq_table:
                         freq_table[word] += 1
                     else:
@@ -68,7 +67,7 @@ class SummaryTFIDF(ISummaryStrategy):
         tf_matrix = {}
 
         for sent, freq_table in freq_matrix.items():
-            # dictionary mit 'word' selbst als Schlüssel und dessen TF als Wert
+            # dictionary with 'word' itself as the key and its TF as the value
             tf_table = {}
 
             total_words_in_sentence = len(freq_table)