Create app.py

app.py

@@ -0,0 +1,25 @@
+import gradio as gr
+import pandas as pd
+
+def predict_quality(fixed_acidity = None, volatile_acidity = None, citric_acid = None, residual_sugar = None, chlorides = None, free_sulfur_dioxide = None, total_sulfur_dioxide = None, density = None, pH = None, sulphates = None, alcohol = None):
+  model_input = [fixed_acidity, volatile_acidity, citric_acid, residual_sugar, chlorides, free_sulfur_dioxide, total_sulfur_dioxide, density, pH, sulphates, alcohol]
+  if 0 in model_input:
+    return_message = "Error: Invalid Input \n Please Input: \n"
+    model_input_name = ['fixed_acidity', 'volatile_acidity', 'citric_acid', 'residual_sugar', 'chlorides', 'free_sulfur_dioxide', 'total_sulfur_dioxide', 'density', 'pH', 'sulphates', 'alcohol']
+    for i in range(len(model_input)):
+      if model_input[i] == 0:
+        return_message = return_message + " " + model_input_name[i]
+    return return_message
+  else:
+    prediction = predict_model(loaded_best_pipeline, data = pd.DataFrame([model_input], columns = white_wine.columns[:-1]))
+    return_message = "Predicted Quality: " + str(prediction['prediction_label'][0]) + "\nConfidence: " + str(prediction['prediction_score'][0])
+    return return_message
+
+demo = gr.Interface(
+    fn = predict_quality,
+    inputs = ['number', 'number', 'number', 'number', 'number', 'number', 'number', 'number', 'number', 'number', 'number'],
+    outputs = [gr.Textbox(label= "Result", lines=8)], api_name = 'predict_quality',
+    title = "🍾 White Wine Quality Predictor 🍾",
+    description="🍾 This is a white wine quality predicting machine learning model based on a random forest classifier. 🍾"
+    )
+demo.launch(share=True)