Update app.py

app.py

@@ -8,6 +8,7 @@ import matplotlib.pyplot as plt
 from datasets import load_dataset
 from langchain_groq import ChatGroq
 from langchain_openai import ChatOpenAI
+import time  
 
 # Load environment variables
 openai_api_key = os.getenv("OPENAI_API_KEY")
@@ -38,15 +39,23 @@ def load_repo_dataset(file_path):
     return pd.read_csv(file_path)
 
 @st.cache_data
-def load_huggingface_dataset(dataset_name):
+def load_huggingface_dataset(dataset_name, progress_callback):
     dataset = load_dataset(dataset_name, name="all", split="train", trust_remote_code=True, uniform_split=True)
     if hasattr(dataset, "to_pandas"):
-        return dataset.to_pandas()
+        progress_callback(50)  # Update progress bar
+        df = dataset.to_pandas()
+        progress_callback(100)  # Final progress update
+        return df
+    progress_callback(100)
     return pd.DataFrame(dataset)
 
 @st.cache_data
-def load_uploaded_csv(uploaded_file):
-    return pd.read_csv(uploaded_file)
+def load_uploaded_csv(uploaded_file, progress_callback):
+    time.sleep(1)  # Simulate processing delay
+    progress_callback(50)  # Update progress bar
+    df = pd.read_csv(uploaded_file)
+    progress_callback(100)  # Final progress update
+    return df
 
 # Dataset selection logic
 def load_dataset_into_session():
@@ -60,7 +69,8 @@ def load_dataset_into_session():
         file_path = "./source/test.csv"
         if st.button("Load Dataset"):
             try:
-                st.session_state.df = load_repo_dataset(file_path)
+                with st.spinner("Loading dataset from the repo directory..."):
+                    st.session_state.df = load_repo_dataset(file_path)
                 st.success(f"File loaded successfully from '{file_path}'!")
             except Exception as e:
                 st.error(f"Error loading dataset from the repo directory: {e}")
@@ -71,21 +81,31 @@ def load_dataset_into_session():
             "Enter Hugging Face Dataset Name:", value="HUPD/hupd"
         )
         if st.button("Load Dataset"):
+            progress_bar = st.progress(0)  # Initialize progress bar
+            def progress_callback(progress):
+                progress_bar.progress(progress)  # Update progress bar dynamically
+
             try:
-                st.session_state.df = load_huggingface_dataset(dataset_name)
+                st.session_state.df = load_huggingface_dataset(dataset_name, progress_callback)
                 st.success(f"Hugging Face Dataset '{dataset_name}' loaded successfully!")
             except Exception as e:
                 st.error(f"Error loading Hugging Face dataset: {e}")
+                progress_bar.progress(0)  # Reset progress bar on error
 
     # Option 3: Upload CSV File
     elif input_option == "Upload CSV File":
         uploaded_file = st.file_uploader("Upload a CSV File:", type=["csv"])
         if uploaded_file:
+            progress_bar = st.progress(0)  # Initialize progress bar
+            def progress_callback(progress):
+                progress_bar.progress(progress)  # Update progress bar dynamically
+
             try:
-                st.session_state.df = load_uploaded_csv(uploaded_file)
+                st.session_state.df = load_uploaded_csv(uploaded_file, progress_callback)
                 st.success("File uploaded successfully!")
             except Exception as e:
                 st.error(f"Error reading uploaded file: {e}")
+                progress_bar.progress(0)  # Reset progress bar on error
 
 # Load dataset into session
 load_dataset_into_session()
@@ -155,7 +175,6 @@ with st.sidebar:
         "   - Example: 'Predict if the patent will be accepted.'\n"
         "   - Example: 'What is the primary classification of this patent?'\n"
         "   - Example: 'Summarize the abstract of this patent.'\n"
-        #"4. Download the processed dataset as a CSV file."
     )
     st.markdown("---")
     st.header("References:")