Update app.py

app.py

@@ -31,6 +31,7 @@ login(token=hf_token)
 model = HfApiModel("mistralai/Mixtral-8x7B-Instruct-v0.1", token=hf_token)
 
 df_global = None
+target_column_global = None
 
 def clean_data(df):
     df = df.dropna(how='all', axis=1).dropna(how='all', axis=0)
@@ -50,6 +51,12 @@ def upload_file(file):
     df_global = df
     return df.head()
 
+def set_target_column(col_name):
+    global target_column_global
+    target_column_global = col_name
+    return f"✅ Target column set to: {col_name}"
+
+
 def format_analysis_report(raw_output, visuals):
     try:
         if isinstance(raw_output, dict):
@@ -161,7 +168,8 @@ def compare_models():
     if df_global is None:
         return pd.DataFrame({"Error": ["Please upload and preprocess a dataset first."]}), None
 
-    target = df_global.columns[-1]
+    global target_column_global
+    target = target_column_global
     X = df_global.drop(target, axis=1)
     y = df_global[target]
 
@@ -212,15 +220,16 @@ def compare_models():
 
     
 # 1. prepare_data should come first
-def prepare_data(df, target_column=None):
+def prepare_data(df):
+    global target_column_global
     from sklearn.model_selection import train_test_split
 
     # If no target column is specified, select the first object column or the last column
     if target_column is None:
-        target_column = df.select_dtypes(include=['object']).columns[0] if len(df.select_dtypes(include=['object']).columns) > 0 else df.columns[-1]
+        raise ValueError("Target column not set.")
     
-    X = df.drop(columns=[target_column])
-    y = df[target_column]
+    X = df.drop(columns=[target_column_global])
+    y = df[target_column_global]
     
     return train_test_split(X, y, test_size=0.3, random_state=42)
 
@@ -286,7 +295,8 @@ def explainability(_):
     import warnings
     warnings.filterwarnings("ignore")
 
-    target = df_global.columns[-1]
+    global target_column_global
+    target = target_column_global
     X = df_global.drop(target, axis=1)
     y = df_global[target]
 
@@ -357,6 +367,11 @@ def explainability(_):
 
     return shap_path, lime_path
 
+# Define this BEFORE the Gradio app layout
+def update_target_choices():
+    global df_global
+    return gr.update(choices=df_global.columns.tolist())
+
 with gr.Blocks() as demo:
     gr.Markdown("## 📊 AI-Powered Data Analysis with Hyperparameter Optimization")
 
@@ -364,7 +379,12 @@ with gr.Blocks() as demo:
         with gr.Column():
             file_input = gr.File(label="Upload CSV or Excel", type="filepath")
             df_output = gr.DataFrame(label="Cleaned Data Preview")
+            target_dropdown = gr.Dropdown(label="Select Target Column", choices=[], interactive=True)
+            target_status = gr.Textbox(label="Target Column Status", interactive=False)
+
             file_input.change(fn=upload_file, inputs=file_input, outputs=df_output)
+            file_input.change(fn=update_target_choices, inputs=[], outputs=target_dropdown)
+            target_dropdown.change(fn=set_target_column, inputs=target_dropdown, outputs=target_status)
 
         with gr.Column():
             insights_output = gr.HTML(label="Insights from SmolAgent")
@@ -391,5 +411,4 @@ with gr.Blocks() as demo:
     explain_btn.click(fn=explainability, inputs=[], outputs=[shap_img, lime_img])
     compare_btn.click(fn=compare_models, inputs=[], outputs=[compare_output, compare_img])
 
-
-demo.launch(debug=True)
+demo.launch(debug=True)