Multipipeline #wip

Dockerfile

@@ -1,4 +1,4 @@
-FROM ubuntu:20.04
+FROM ubuntu:latest
 
 RUN apt update && apt install -y python3 python3-pip
 

main.py

@@ -1,6 +1,20 @@
 import string
 import pandas as pd
 from sklearn.model_selection import train_test_split
+import nltk
+nltk.download('stopwords')
+from nltk.corpus import stopwords
+
+
+def remove_punct(text):
+    translator = str.maketrans("", "", string.punctuation)
+    return text.translate(translator)
+
+
+stop = set(stopwords.words("english"))
+def remove_stopwords(text):
+    filtered_words = [word.lower() for word in text.split() if word.lower() not in stop]
+    return " ".join(filtered_words)
 
 
 def main():