From c6b16b9ccf3106db76594198bfc0ed90f448e7ae Mon Sep 17 00:00:00 2001
From: rnsrk <rbrt.nsrk@posteo.de>
Date: Fri, 13 Jan 2023 20:26:04 +0100
Subject: [PATCH] Optimized text cleanup and function parameters

---
 Main.py        |  6 +++---
 SentiTooter.py | 10 +++++-----
 TootCrawler.py | 26 +++++++++++++-------------
 3 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/Main.py b/Main.py
index 879e487..8fbf829 100644
--- a/Main.py
+++ b/Main.py
@@ -93,7 +93,7 @@ axes[1].tick_params(which='minor', length=0)
 plotFileUrl = f'./plots/{TodayDate}.png'
 plt.savefig(plotFileUrl)
 
-"""
-media = mastodonInstance.media_post(plotFileUrl, mime_type="image/png", description=f"Sentiment analysis of local timeline on fedihum.org, showing the moods of the toots on, and the compounds up to {TodayDate}.")
+
+media = mastodonInstance.media_post(plotFileUrl, mime_type="image/png", description=f"Sentiment analysis of local timeline on fedihum.org, showing the moods of the toots on, and the sentiment mean up to {TodayDate}.")
 mastodonInstance.status_post(f'The moods of the toots on and up to {TodayDate}.', media_ids=media, language='en')
-"""
+
diff --git a/SentiTooter.py b/SentiTooter.py
index 1d89ab6..26b7a47 100644
--- a/SentiTooter.py
+++ b/SentiTooter.py
@@ -28,14 +28,14 @@ class SentiTooter:
         self.labels = ['negative', 'neutral', 'positive']
         self.sia = SentimentIntensityAnalyzer()
 
-    def analyze(self, toot):
-        match toot.language:
+    def analyze(self, language, content):
+        match language:
             case 'de':
-                sentiment = self.deModel.predict_sentiment([toot.content])
+                sentiment = self.deModel.predict_sentiment([content])
                 sentiment.append('germanSentiment')
                 return sentiment
             case 'en':
-                text = preprocess(toot.content)
+                text = preprocess(content)
                 encoded_input = self.enTokenizer(text, return_tensors='pt')
                 output = self.enModel(**encoded_input)
                 scores = output[0][0].detach().numpy()
@@ -45,7 +45,7 @@ class SentiTooter:
                 sentiment = [sentimentLabel, 'twitter-roberta-base-sentiment']
                 return sentiment
             case _:
-                compound = self.sia.polarity_scores(toot.content)['compound']
+                compound = self.sia.polarity_scores(content)['compound']
                 if compound > (1 / 3):
                     return ['positive', 'vaderSentiment']
                 elif compound < (-1 / 3):
diff --git a/TootCrawler.py b/TootCrawler.py
index 5d51b75..1b081c2 100644
--- a/TootCrawler.py
+++ b/TootCrawler.py
@@ -31,18 +31,18 @@ class TootCrawler():
             timelinePagination = self.mastodonInstance.fetch_previous(timelinePagination)
         for i in allTimelineResults:
             content = self.cleanhtml(i.content)
-            sentiment = self.sentiTooter.analyze(i)
-            toots.append(
-                    {
-                            "sentiment": sentiment[0],
-                            "model": sentiment[1],
-                            "userName": i.account.display_name,
-                            "userId": i.account.id,
-                            "toot": content,
-                            "datetime": i.created_at.astimezone(self.localTimezone),
-                            "language": detect(content),
-                            "tootId": i.id
-                    }
-                )
+            language = detect(content)
+            sentiment = self.sentiTooter.analyze(language, content)
+            toot = {
+                "sentiment": sentiment[0],
+                "model": sentiment[1],
+                "toot": content,
+                "datetime": i.created_at.astimezone(self.localTimezone),
+                "language": language,
+                "userName": i.account.display_name,
+                "userId": i.account.id,
+                "tootId": i.id
+            }
+            toots.append(toot)
         toots.sort(key=lambda item:item.get('datetime'))
         return pd.DataFrame.from_records(toots)
\ No newline at end of file