[UI] Clarify dataset requirement (#140)

Co-authored-by: YUAN TIAN <[email protected]>

src/autogluon/assistant/ui/constants.py

@@ -123,9 +123,13 @@
 DATASET_OPTIONS = ["Sample Dataset", "Upload Dataset"]
 
 # Captions under DataSet Options
-CAPTIONS = ["Run with sample dataset", "Upload Train, Test and Output (Optional) Dataset"]
+CAPTIONS = ["Run with sample dataset", "Upload Train (Required), Test (Required) and Output (Optional) Dataset"]
 
 DEMO_URL = "https://automl-mm-bench.s3.amazonaws.com/autogluon-assistant/aga-kaggle-demo.mp4"
 
 SAMPLE_DATASET_DESCRIPTION = """You are solving this data science tasks:The dataset presented here (knot theory) comprises a lot of numerical features. Some of the features may be missing, with nan value. Your task is to predict the 'signature', which has 18 unique integers. The evaluation metric is the classification accuracy."""
 LOGO_PATH = "static/page_icon.png"
+SUCCESS_MESSAGE = """
+        🎉🎉Task completed successfully! If you found this useful, please consider:
+        ⭐ [Starring our repository](https://github.com/autogluon/autogluon-assistant)
+        """

src/autogluon/assistant/ui/log_processor.py

@@ -1,7 +1,7 @@
 import re
 
 import streamlit as st
-from constants import STAGE_COMPLETE_SIGNAL, STAGE_MESSAGES, STATUS_BAR_STAGE, TIME_LIMIT_MAPPING
+from constants import STAGE_COMPLETE_SIGNAL, STAGE_MESSAGES, STATUS_BAR_STAGE, SUCCESS_MESSAGE, TIME_LIMIT_MAPPING
 
 
 def parse_model_path(log):
@@ -50,7 +50,7 @@ def show_logs():
     if st.session_state.logs:
         status_container = st.empty()
         if st.session_state.return_code == 0:
-            status_container.success("Task completed successfully!")
+            status_container.success(SUCCESS_MESSAGE)
         else:
             status_container.error("Error detected in the process...Check the logs for more details")
         tab1, tab2 = st.tabs(["Messages", "Logs"])
@@ -149,9 +149,10 @@ def messages():
                 if model_path:
                     st.session_state.model_path = model_path
             if "Prediction complete" in line:
-                status_container.success("Task completed successfully!")
+                status_container.success(SUCCESS_MESSAGE)
                 progress.progress(100)
                 process_realtime_logs(line)
+                st.toast("Task completed successfully! 🎉", icon="✅")
                 break
             else:
                 for stage, progress_value in STATUS_BAR_STAGE.items():

src/autogluon/assistant/ui/pages/task.py

@@ -153,7 +153,7 @@ def display_description():
 
 @st.fragment
 def show_output_download_button(data, file_name):
-    st.download_button(label="💾  Download Output", data=data, file_name=file_name, mime="text/csv")
+    st.download_button(label="💾  Download Predictions", data=data, file_name=file_name, mime="text/csv")
 
 
 def show_cancel_task_button():

src/autogluon/assistant/ui/pages/tutorial.py

@@ -58,12 +58,13 @@ def main():
         </div>
         <div class="right-section">
             <div class="get-started-title">Get Started</div>
-            <div class="description">AutoGluon Assistant (AG-A) provides users a simple interface where they can upload their data, describe their problem, and receive a highly accurate and competitive ML solution — without writing any code. By leveraging the state-of-the-art AutoML capabilities of AutoGluon and integrating them with a Large Language Model (LLM), AG-A automates the entire data science pipeline. AG-A takes AutoGluon’s automation from three lines of code to zero, enabling users to solve new supervised learning tabular problems using only natural language descriptions.</div>
+            <div class="description">AutoGluon Assistant (AG-A) provides users a simple interface where they can upload their data, describe their problem, and receive a highly accurate and competitive ML solution — without writing any code. By leveraging the state-of-the-art AutoML capabilities of AutoGluon and integrating them with a Large Language Model (LLM), AG-A automates the entire data science pipeline.</div>
             <div class="steps">
                 <ol>
                     <li>Upload dataset files (CSV,XLSX)</li>
-                    <li>Provide dataset description</li>
+                    <li>Define your machine learning task</li>
                     <li>Launch AutoGluon Assistant</li>
+                    <li>Get accurate predictions</li>
                 </ol>
             </div>    
         </div> 

src/autogluon/assistant/ui/utils/utils.py

@@ -45,7 +45,7 @@ def generate_output_filename():
     timestamp = pd.Timestamp.now().strftime("%Y%m%d_%H%M%S")
     directory_path = os.path.join(user_data_dir, timestamp)
     os.makedirs(directory_path, exist_ok=True)
-    output_filepath = os.path.join(directory_path, "output.csv")
+    output_filepath = os.path.join(directory_path, "predictions.csv")
     return output_filepath