Update pages/1_Classification.py

pages/1_Classification.py

@@ -1,8 +1,14 @@
+#importing the libraries needed
+#for the classification
 import streamlit as st
 import pandas as pd
-import matplotlib.pyplot as plt
 from transformers import pipeline
+#for the pre-processing of uploaded data
+import string 
+import nltk
+nltk.download("stopwords")
 
+#calling and loading the fine tuned model from the hugging face account
 @st.cache_resource
 def load_classifier():
     return pipeline(
@@ -11,31 +17,63 @@ def load_classifier():
         truncation=True
     )
 
+#saving the loaded model for convience in a variable 
 classifier = load_classifier()
 
+#writing the text content in the page
 st.title("News Classifier")
+st.write("""In this page the user can upload a CSV file which contains a content 
+        column which includes a text, then the model will use text pre-processing (anlysis step for more details) 
+        and then label the data based on 5 categories,
+        - Business 
+        - Opinions
+        - Political_gossip 
+        - Sports 
+        - Worlds_news
+          """)
+
+#uploading the file 
 uploaded_file = st.file_uploader("Upload CSV", type=["csv"])
 
+#loop to carry out the transformation
 if uploaded_file is not None:
     try:
-        df = pd.read_csv(uploaded_file)
-
-        if "content" not in df.columns:
+        uploaded_content = pd.read_csv(uploaded_file)
+        #detect if a content coloumn is present
+        if "content" not in uploaded_content.columns:
             st.error("The uploaded CSV must contain a column named `content`.")
         else:
-            df["content"] = df["content"].fillna("").astype(str)
-
+            #removing empty strings
+            uploaded_content["content"] = uploaded_content["content"].fillna("").astype(str)
+            uploaded_content["pre-processed"] = uploaded_content["content"]
+            #showing the loading message to user 
             with st.spinner("Classifying records..."):
-                preds = classifier(df["content"].tolist(), batch_size=8)
 
-            df["class"] = [pred["label"] for pred in preds]
+                #processing the data
+                #removing punctuations
+                string.punctuation
+                punct_to_remove = string.punctuation.replace("'",'').replace("-",'')
+                def remove_punctuation(text):
+                    return text.translate(str.maketrans('', '', string.punctuation))
+                uploaded_content["pre-processed"] = uploaded_content["pre-processed"].apply(remove_punctuation)
+
+                #removing stop words
+                stop_words = set(stopwords.words('english'))
+                def remove_stopwords(text):
+                    return " ".join([word for word in str(text).split() if word not in stop_words])
+                uploaded_content["pre-processed"] = uploaded_content["pre-processed"].apply(lambda text: remove_stopwords(text))
+
+                #constructing the labels
+                preds = classifier(uploaded_content["pre-processed"].tolist(), batch_size=8)
+
+            uploaded_content["class"] = [pred["label"] for pred in preds]
 
             # save for other pages
-            st.session_state["df"] = df
+            st.session_state["uploaded_content"] = uploaded_content
             st.session_state["uploaded_filename"] = uploaded_file.name
 
             st.success("Classification complete.")
-            st.dataframe(df.head())
+            st.dataframe(uploaded_content.head())
 
     except Exception as e:
         st.error(f"Error reading or processing file: {e}")