Update app.py

app.py

@@ -5,9 +5,6 @@ from sklearn.model_selection import train_test_split
 from sklearn.ensemble import RandomForestRegressor
 import gradio as gr
 import openai
-from gradio import inputs as gr_inputs
-from gradio import outputs as gr_outputs
-from gradio import components as gr_components
 
 # Set up OpenAI API credentials
 openai.api_key = "YOUR_OPENAI_API_KEY"
@@ -54,66 +51,35 @@ def ask_openai(question):
     answer = response.choices[0].text.strip()
     return answer
 
-iface = gr.Interface(
-    fn=train_and_predict,
-    inputs=[
-        gr_inputs.Dataframe(label="Upload CSV"),
-        gr_inputs.Number(label="Qwater"),
-        gr_inputs.Number(label="Qgas"),
-        gr_inputs.Number(label="BHP"),
-        gr_inputs.Number(label="WHP"),
-        gr_inputs.Number(label="WHT"),
-        gr_inputs.Number(label="Tsep"),
-        gr_inputs.Number(label="Psep"),
-        gr_inputs.Number(label="Choke_in"),
-    ],
-    outputs=gr_outputs.Textbox(label="Prediction"),
-    title="Oil Production Prediction",
-    description="""This application is the interface of a machine learning model that allows Oil and Gas executives with no coding knowledge or experience to enter inputs related to oil production and predict the number of barrels that will be produced per day given those inputs. Upload the oil production dataset. Enter the input values (Qwater, Qgas, BHP, WHP, WHT, Tsep, Psep, Choke_in) and then click Submit. The model will initiate and complete its training in the background using the dataset provided and then return the output value (Qoil) to you.
-
-    Input Features:
-    Qwater: Water Flow Rate
-    Qgas: Gas Flow Rate
-    BHP: Bottom Hole Pressure
-    WHP: Wellhead Pressure
-    WHT: Wellhead Temperature
-    Tsep: Separator Temperature
-    Psep: Separator Pressure
-    Choke_in: Choke Valve Opening
-
-    Target Variable:
-    Qoil: Oil Flow Rate (measured in barrels per day)"""
-)
-
-# Chatbot components
-question_input = gr_inputs.Textbox(label="Ask a Question")
-chat_output = gr_outputs.Textbox(label="Chatbot Response")
-submit_button = gr_components.Button(label="Submit")
-reset_button = gr_components.Button(label="Reset")
-
-# Function to handle chatbot submission
 def handle_submit(data, Qwater, Qgas, BHP, WHP, WHT, Tsep, Psep, Choke_in, question):
     prediction = train_and_predict(data, Qwater, Qgas, BHP, WHP, WHT, Tsep, Psep, Choke_in)
     answer = ask_openai(question)
     return prediction, answer
 
-# Function to handle reset button
 def handle_reset():
     iface.clear_input()
 
-# Interface layout
-interface_layout = [
-    [iface.inputs[0]],
-    [iface.inputs[1], iface.inputs[2], iface.inputs[3], iface.inputs[4], iface.inputs[5], iface.inputs[6], iface.inputs[7], iface.inputs[8]],
-    [submit_button, reset_button],
-    [iface.outputs[0]],
-    [question_input],
-    [chat_output]
-]
-
-# Interface callback functions
-iface.input_callback = handle_submit
-iface.reset_callback = handle_reset
+iface = gr.Interface(
+    fn=handle_submit,
+    inputs=[
+        gr.inputs.File(label="Upload CSV"),
+        gr.inputs.Number(label="Qwater"),
+        gr.inputs.Number(label="Qgas"),
+        gr.inputs.Number(label="BHP"),
+        gr.inputs.Number(label="WHP"),
+        gr.inputs.Number(label="WHT"),
+        gr.inputs.Number(label="Tsep"),
+        gr.inputs.Number(label="Psep"),
+        gr.inputs.Number(label="Choke_in"),
+        gr.inputs.Textbox(label="Ask a Question")
+    ],
+    outputs=[
+        gr.outputs.Textbox(label="Prediction"),
+        gr.outputs.Textbox(label="Chatbot Response")
+    ],
+    title="Oil Production Prediction",
+    description="""This application is the interface of a machine learning model that allows Oil and Gas executives with no coding knowledge or experience to enter inputs related to oil production and predict the number of barrels that will be produced per day given those inputs. Upload the oil production dataset and enter the input values (Qwater, Qgas, BHP, WHP, WHT, Tsep, Psep, Choke_in). You can also ask questions about the dataset or the meaning of inputs. The model will initiate and complete its training in the background using the dataset provided and then return the output value (Qoil) along with an answer from the chatbot to you.
+    """
+)
 
-iface.interface_layout = interface_layout
 iface.launch()