Update app.py

app.py

@@ -13,15 +13,12 @@ import time
 
 openai_api_key = os.getenv("OPENAI_API_KEY")
 
-def chat_with_csv(df, prompt):
-    llm = OpenAI(api_token=openai_api_key)
-    pandas_ai = PandasAI(llm)
-    result = pandas_ai.run(df, prompt=prompt)
-    return result
-
+# Dataset loading without caching to support progress bar
 def load_huggingface_dataset(dataset_name):
+    # 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)
@@ -29,33 +26,35 @@ def load_huggingface_dataset(dataset_name):
             df = dataset.to_pandas()
         else:
             df = pd.DataFrame(dataset)
-        progress_bar.progress(100)
+        progress_bar.progress(100)  # Final update to 100%
         return df
     except Exception as e:
-        progress_bar.progress(0)
+        progress_bar.progress(0)  # Reset progress bar on failure
         raise e
 
 def load_uploaded_csv(uploaded_file):
+    # Initialize progress bar
     progress_bar = st.progress(0)
     try:
+        # Simulate progress
         progress_bar.progress(10)
-        time.sleep(1)
+        time.sleep(1)  # Simulate file processing delay
         progress_bar.progress(50)
         df = pd.read_csv(uploaded_file)
-        progress_bar.progress(100)
+        progress_bar.progress(100)  # Final update
         return df
     except Exception as e:
-        progress_bar.progress(0)
+        progress_bar.progress(0)  # Reset progress bar on failure
         raise e
 
+# Dataset selection logic
 def load_dataset_into_session():
     input_option = st.radio(
         "Select Dataset Input:",
-        ["Use Repo Directory Dataset", "Use Hugging Face Dataset", "Upload CSV File"],
-        index=1,
-        horizontal=True
+        ["Use Repo Directory Dataset", "Use Hugging Face Dataset", "Upload CSV File"], index=1, horizontal=True
     )
 
+    # Option 1: Load dataset from the repo directory
     if input_option == "Use Repo Directory Dataset":
         file_path = "./source/test.csv"
         if st.button("Load Dataset"):
@@ -66,8 +65,11 @@ def load_dataset_into_session():
             except Exception as e:
                 st.error(f"Error loading dataset from the repo directory: {e}")
 
+    # Option 2: Load dataset from Hugging Face
     elif input_option == "Use Hugging Face Dataset":
-        dataset_name = st.text_input("Enter Hugging Face Dataset Name:", value="HUPD/hupd")
+        dataset_name = st.text_input(
+            "Enter Hugging Face Dataset Name:", value="HUPD/hupd"
+        )
         if st.button("Load Dataset"):
             try:
                 st.session_state.df = load_huggingface_dataset(dataset_name)
@@ -75,6 +77,7 @@ def load_dataset_into_session():
             except Exception as e:
                 st.error(f"Error loading Hugging Face dataset: {e}")
 
+    # 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:
@@ -84,13 +87,28 @@ def load_dataset_into_session():
             except Exception as e:
                 st.error(f"Error reading uploaded file: {e}")
 
+# Load dataset into session
+load_dataset_into_session()
+
+if "df" in st.session_state and llm:
+    df = st.session_state.df
+
+    # Display dataset metadata
+    st.write("### Dataset Metadata")
+    st.text(f"Number of Rows: {df.shape[0]}")
+    st.text(f"Number of Columns: {df.shape[1]}")
+    st.text(f"Column Names: {', '.join(df.columns)}")
+
+    # Display dataset preview
+    st.write("### Dataset Preview")
+    num_rows = st.slider("Select number of rows to display:", min_value=5, max_value=50, value=10)
+    st.dataframe(df.head(num_rows))
+
+
 # Streamlit app main
 st.set_page_config(layout='wide')
 st.title("ChatCSV powered by LLM")
 
-# Ensure session state for the dataframe
-if "df" not in st.session_state:
-    st.session_state.df = pd.DataFrame()  # Initialize with an empty dataframe
 
 st.header("Load Your Dataset")
 load_dataset_into_session()