Update lab/interim.py

lab/interim.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")
@@ -32,21 +33,39 @@ def initialize_llm(model_choice):
 model_choice = st.radio("Select LLM", ["GPT-4o", "llama-3.3-70b"], index=0, horizontal=True)
 llm = initialize_llm(model_choice)
 
-# Cache dataset loading
-@st.cache_data
-def load_repo_dataset(file_path):
-    return pd.read_csv(file_path)
-
-@st.cache_data
+# Dataset loading without caching to support progress bar
 def load_huggingface_dataset(dataset_name):
-    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()
-    return pd.DataFrame(dataset)
+    # Initialize progress bar
+    progress_bar = st.progress(0)
+    try:
+        # Incrementally update progress
+        progress_bar.progress(10)
+        dataset = load_dataset(dataset_name, name="sample", split="train", trust_remote_code=True, uniform_split=True)
+        progress_bar.progress(50)
+        if hasattr(dataset, "to_pandas"):
+            df = dataset.to_pandas()
+        else:
+            df = pd.DataFrame(dataset)
+        progress_bar.progress(100)  # Final update to 100%
+        return df
+    except Exception as e:
+        progress_bar.progress(0)  # Reset progress bar on failure
+        raise e
 
-@st.cache_data
 def load_uploaded_csv(uploaded_file):
-    return pd.read_csv(uploaded_file)
+    # Initialize progress bar
+    progress_bar = st.progress(0)
+    try:
+        # Simulate progress
+        progress_bar.progress(10)
+        time.sleep(1)  # Simulate file processing delay
+        progress_bar.progress(50)
+        df = pd.read_csv(uploaded_file)
+        progress_bar.progress(100)  # Final update
+        return df
+    except Exception as e:
+        progress_bar.progress(0)  # Reset progress bar on failure
+        raise e
 
 # Dataset selection logic
 def load_dataset_into_session():
@@ -60,7 +79,8 @@ 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 = pd.read_csv(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}")
@@ -155,10 +175,9 @@ 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:")
     st.markdown(
         "1. [Chat With Your CSV File With PandasAI - Prince Krampah](https://medium.com/aimonks/chat-with-your-csv-file-with-pandasai-22232a13c7b7)"
-    )
+    )