Update app.py

app.py

@@ -1,37 +1,24 @@
-import spaces
-
-@spaces.GPU
-def train_and_predict():
-    model.fit(x_train, y_train.values.ravel())
-    return model.predict(x_test)
-
-y_pred = train_and_predict()
 import os
 import numpy as np
 import pandas as pd
 import gradio as gr
+import spaces
 from sklearn.model_selection import train_test_split
 from sklearn.linear_model import LogisticRegression
 from sklearn import metrics
 
 ### ------------------------------ ###
-###       Data & File Check       ###
+###       Data Transformation      ###
 ### ------------------------------ ###
 
-# Ensure data.csv exists
-if not os.path.exists('data.csv'):
-    raise FileNotFoundError("Missing 'data.csv'! Please upload data.csv to your Hugging Face Space files.")
-
+# Load dataset
 uncleaned_data = pd.read_csv('data.csv')
 
-# Verify column count
-if uncleaned_data.shape[1] < 2:
-    raise ValueError("'data.csv' must contain at least 2 columns (a timestamp/ID column and at least one feature or target column).")
-
-# Remove timestamp column (first column)
+# Remove timestamp from dataset (first column)
 uncleaned_data = uncleaned_data.iloc[:, 1:]
 data = pd.DataFrame()
 
+# Track categorical mappings
 cat_value_dicts = {}
 final_colname = uncleaned_data.columns[-1]
 
@@ -67,8 +54,14 @@ y = data[final_colname]
 
 x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=42)
 
-model = LogisticRegression(max_iter=1000)
-model.fit(x_train, y_train.values.ravel())
+# ZeroGPU decorator on startup model training
+@spaces.GPU
+def train_model(x_tr, y_tr):
+    clf = LogisticRegression(max_iter=1000)
+    clf.fit(x_tr, y_tr.values.ravel())
+    return clf
+
+model = train_model(x_train, y_train)
 y_pred = model.predict(x_test)
 
 acc = str(round(metrics.accuracy_score(y_test, y_pred) * 100, 1)) + "%"
@@ -101,6 +94,8 @@ if os.path.exists('info.md'):
 ###        Interface Creation       ###
 ### ------------------------------- ###
 
+# ZeroGPU decorator on prediction function
+@spaces.GPU
 def general_predictor(*args):
     features = []
     for colname, arg in zip(feature_cols, args):
@@ -149,5 +144,4 @@ with gr.Blocks() as demo:
         with gr.Column():
             gr.Markdown(body_text)
 
-# Launch without Node.js SSR proxy to prevent instant shutdowns
-demo.launch(server_name="0.0.0.0", server_port=7860, ssr_mode=False)
+demo.launch()