removed unnecessary functions

textclassifier/TextClassifier.py

@@ -73,149 +73,6 @@ class TextClassifier:
 
         return classification_clean
 
-    def classify_sentiment(self, text: str):
-        """
-        Classifies the sentiment of a text.
-        """
-        assert isinstance(text, str)
-
-        prompt_string = "Classify one sentiment for this tweet:\n \""
-        prompt_string += text
-        prompt_string += "\" \nFor example:\nSupport,\nOpposition,\nCriticism,\nPraise,\nDisagreement," \
-                         "\nAgreement,\nSkepticism,\nAdmiration,\nAnecdotes,\nJokes,\nMemes,\nSarcasm,\nSatire," \
-                         "\nQuestions,\nStatements,\nOpinions,\nPredictions.\nSENTIMENT="
-
-        response = openai.Completion.create(
-            model=self.model_name,
-            prompt=prompt_string,
-            temperature=0.0,
-            max_tokens=256,
-            top_p=1,
-            frequency_penalty=0,
-            presence_penalty=0,
-            logprobs=5
-        )
-        classification_unclean = response.choices[0]['text']
-        classification_clean = self.cleanup_sentiment_results(classification_unclean)
-
-        return classification_clean.lower()
-
-    def classify_sentiment_of_tweets(self):
-        """
-        Classifies the sentiment of a user's tweets.
-        """
-        df_sentiment = self.df.copy()
-
-        df_sentiment['sentiment'] = df_sentiment['tweet'].apply(self.classify_sentiment)
-        self.df = df_sentiment
-        return self.df
-
-    def analyze_sentiment(self, text: str, sentiment: str):
-        """
-        Analyzes the sentiment of a text using OpenAI.
-        :param text: string of the tweet text.
-        :param sentiment: string of the sentiment.
-        :return:
-        """
-        # assert 1 == 2, "Måste fixa prompt innan denna metod körs"
-        prompt_string = "Who is the TARGET of this "
-        prompt_string += sentiment
-        prompt_string += " TWEET?\\nTWEET=\""
-        prompt_string += text
-        prompt_string += "\"\\n.TARGET should consist of less than 5 words.\\nTARGET="
-
-        response = openai.Completion.create(
-            model=self.model_name,
-            prompt=prompt_string,
-            temperature=0,
-            max_tokens=256,
-            top_p=1,
-            frequency_penalty=0,
-            presence_penalty=0
-        )
-
-        analyzed_sentiment = response.choices[0]['text']
-        # Remove spaces at the start/end of the response
-        if analyzed_sentiment.startswith(' '):
-            analyzed_sentiment = analyzed_sentiment[1:]
-        if analyzed_sentiment.endswith(' '):
-            analyzed_sentiment = analyzed_sentiment[:-1]
-
-        # Sometimes GPT-3 gives faulty results, so a simple filter is introduced
-        # If the prediction is bad
-        # -> set target value to N/A (not applicable)
-        if len(analyzed_sentiment) > 50:
-            analyzed_sentiment = "N/A"
-
-        # An attempt to merge target responses that should be the same
-        analyzed_sentiment = re.sub("\(", "", analyzed_sentiment)
-        analyzed_sentiment = re.sub("\)", "", analyzed_sentiment)
-
-        s_list = ["s", "the swedish social democratic party"]
-        m_list = ["m", "the swedish moderate party", "the moderate party"]
-        mp_list = ["mp", "the swedish green party"]
-
-        if analyzed_sentiment.lower() == "v":
-            analyzed_sentiment = "Vänsterpartiet"
-        elif analyzed_sentiment.lower() == "mp":
-            analyzed_sentiment = "Miljöpartiet"
-        elif analyzed_sentiment.lower() in s_list:
-            analyzed_sentiment = "Socialdemokraterna"
-        elif analyzed_sentiment.lower() == "c":
-            analyzed_sentiment = "Centerpartiet"
-        elif analyzed_sentiment.lower() == "l":
-            analyzed_sentiment = "Liberalerna"
-        elif analyzed_sentiment.lower() == "kd":
-            analyzed_sentiment = "Kristdemokraterna"
-        elif analyzed_sentiment.lower() in m_list:
-            analyzed_sentiment = "Moderaterna"
-        elif analyzed_sentiment.lower() == "sd":
-            analyzed_sentiment = "Sverigedemokraterna"
-        elif analyzed_sentiment.lower() == "the swedish government":
-            analyzed_sentiment = "Regeringen"
-
-        analyzed_sentiment = self.cleanup_sentiment_results(analyzed_sentiment)
-        return analyzed_sentiment
-
-    def analyze_sentiment_of_tweets(self):
-        """
-        Analyzes the sentiment of a user's tweets.
-        """
-        # check if 'sentiment' column exists, raise exception if not
-        assert 'sentiment' in self.df.columns, \
-            "'sentiment' column does not exist. Please run classify_sentiment_of_tweets first."
-
-        df_sentiment = self.df.copy()
-        df_sentiment['target'] = df_sentiment.apply(lambda row: self.analyze_sentiment(row['tweet'], row['sentiment']),
-                                                    axis=1)
-        self.df = df_sentiment
-        return self.df
-
-    def classify_topic(self, text: str):
-        """
-        Classifies the topics of a text.
-        :param text: string of the tweet text.
-        """
-        assert isinstance(text, str)
-
-        prompt_string = "Classify this tweet with a general topic and two sub-topics:\n\""
-        prompt_string += text
-        prompt_string += "\".\nGeneral topic: \nSub topic 1: \nSub topic 2:\n. The classifications should not be " \
-                         "more than 5 words. Numerate each topic in the output. END "
-        response = openai.Completion.create(
-            model="text-davinci-002",
-            prompt=prompt_string,
-            temperature=0,
-            max_tokens=892,
-            top_p=1,
-            frequency_penalty=0,
-            presence_penalty=0
-        )
-        classification_unclean = response.choices[0]['text']
-        classification_clean = self.cleanup_topic_results(classification_unclean)
-
-        return classification_clean.lower()
-
     def classify_topics_of_tweets(self):
         """
         Classifies the topics of a user's tweets.
@@ -308,18 +165,6 @@ class TextClassifier:
         self.df = df
         self.df_to_csv(filename)
 
-    def split_topics_into_columns(self):
-        """
-        Splits the topics into columns.
-        :return: None
-        """
-        df_topic = self.df.copy()
-        df_topic['topics_temp'] = df_topic['topics'].apply(lambda x: f.separate_string(x))
-        df_topic_split = pd.DataFrame(df_topic['topics_temp'].tolist(),
-                                      columns=['main_topic', 'sub_topic_1', 'sub_topic_2'])
-        self.df = df_topic.merge(df_topic_split, how='left', left_index=True, right_index=True)
-        self.df.drop(['topics_temp'], axis=1, inplace=True)
-
     def split_tuple_into_columns(self):
         """
         Splits the topics (topic, subtopic, sentiment, target) into columns.