refactor: move NLP processing out of server file

server/nlp_processor.py

@@ -0,0 +1,28 @@
+import torch
+import pandas as pd
+
+from transformers import pipeline
+
+emotion_classifier = pipeline(
+    "text-classification",
+    model="j-hartmann/emotion-english-distilroberta-base",
+    top_k=None,
+    truncation=True,
+    device=0 if torch.cuda.is_available() else -1
+)
+
+def add_emotion_cols(df: pd.Dataframe, content_col: str) -> None:
+    texts = df[content_col].astype(str).str.slice(0, 512).tolist()
+
+    results = emotion_classifier(
+        texts,
+        batch_size=64
+    )
+
+    labels = [r["label"] for r in results[0]]
+
+    for label in labels:
+        df[f"emotion_{label}"] = [
+            next(item["score"] for item in row if item["label"] == label)
+            for row in results
+        ]

server/stat_gen.py

@@ -2,19 +2,10 @@ import pandas as pd
 import re
 import nltk
 import datetime
-import torch
 
 from nltk.corpus import stopwords
 from collections import Counter
-from transformers import pipeline
+from server.nlp_processor import add_emotion_cols
-
-emotion_classifier = pipeline(
-    "text-classification",
-    model="j-hartmann/emotion-english-distilroberta-base",
-    top_k=None,
-    truncation=True,
-    device=0 if torch.cuda.is_available() else -1
-)
 
 DOMAIN_STOPWORDS = {
     "www", "https", "http",
@@ -39,7 +30,6 @@ class StatGen:
 
         self.df = pd.concat([posts_df, comments_df])
         self._add_extra_cols(self.df)
-        self._add_emotion_cols(self.df)
 
         self.original_df = self.df.copy(deep=True)
 
@@ -50,21 +40,8 @@ class StatGen:
         df["hour"] = df["dt"].dt.hour
         df["weekday"] = df["dt"].dt.day_name()
         
-    def _add_emotion_cols(self, df: pd.DataFrame) -> None:
+        add_emotion_cols(df, "content")
-        texts = df["content"].astype(str).str.slice(0, 512).tolist()
 
-        results = emotion_classifier(
-            texts,
-            batch_size=64
-        )
-
-        labels = [r["label"] for r in results[0]]
-
-        for label in labels:
-            df[f"emotion_{label}"] = [
-                next(item["score"] for item in row if item["label"] == label)
-                for row in results
-            ]
 
     def _tokenize(self, text: str):
         tokens = re.findall(r"\b[a-z]{3,}\b", text)