ntam0001 commited on
Commit
b05123e
·
verified ·
1 Parent(s): 5dadf25

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +42 -4
app.py CHANGED
@@ -3,7 +3,7 @@ import gradio as gr
3
  import numpy as np
4
 
5
  # Load the saved Random Forest model
6
- model = joblib.load('best_model.pkl')
7
 
8
  # Define the feature names (as per your dataset)
9
  feature_names = [
@@ -17,9 +17,25 @@ feature_names = [
17
  ]
18
 
19
  # Define the prediction function
20
- def predict(*args):
 
 
 
 
 
 
 
 
21
  # Create a numpy array from the input features
22
- input_data = np.array(args).reshape(1, -1)
 
 
 
 
 
 
 
 
23
 
24
  # Make a prediction
25
  prediction = model.predict(input_data)[0]
@@ -35,7 +51,29 @@ def predict(*args):
35
  return "Unknown"
36
 
37
  # Create a Gradio interface
38
- inputs = [gr.inputs.Number(label=name) for name in feature_names]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  outputs = gr.outputs.Textbox(label="Prediction")
40
 
41
  # Launch the Gradio app
 
3
  import numpy as np
4
 
5
  # Load the saved Random Forest model
6
+ model = joblib.load('random_forest_model.pkl')
7
 
8
  # Define the feature names (as per your dataset)
9
  feature_names = [
 
17
  ]
18
 
19
  # Define the prediction function
20
+ def predict(
21
+ marital_status, application_mode, application_order, course,
22
+ attendance, previous_qualification, nationality,
23
+ mother_qualification, mother_occupation, displaced,
24
+ special_needs, debtor, tuition_fees,
25
+ gender, scholarship_holder, curricular_units_credited,
26
+ curricular_units_without_evaluations, unemployment_rate,
27
+ inflation_rate, gdp
28
+ ):
29
  # Create a numpy array from the input features
30
+ input_data = np.array([
31
+ marital_status, application_mode, application_order, course,
32
+ attendance, previous_qualification, nationality,
33
+ mother_qualification, mother_occupation, displaced,
34
+ special_needs, debtor, tuition_fees,
35
+ gender, scholarship_holder, curricular_units_credited,
36
+ curricular_units_without_evaluations, unemployment_rate,
37
+ inflation_rate, gdp
38
+ ]).reshape(1, -1)
39
 
40
  # Make a prediction
41
  prediction = model.predict(input_data)[0]
 
51
  return "Unknown"
52
 
53
  # Create a Gradio interface
54
+ inputs = [
55
+ gr.inputs.Number(label="Marital status"),
56
+ gr.inputs.Number(label="Application mode"),
57
+ gr.inputs.Number(label="Application order"),
58
+ gr.inputs.Number(label="Course"),
59
+ gr.inputs.Number(label="Daytime/evening attendance"),
60
+ gr.inputs.Number(label="Previous qualification"),
61
+ gr.inputs.Number(label="Nacionality"),
62
+ gr.inputs.Number(label="Mother's qualification"),
63
+ gr.inputs.Number(label="Mother's occupation"),
64
+ gr.inputs.Number(label="Displaced"),
65
+ gr.inputs.Number(label="Educational special needs"),
66
+ gr.inputs.Number(label="Debtor"),
67
+ gr.inputs.Number(label="Tuition fees up to date"),
68
+ gr.inputs.Number(label="Gender"),
69
+ gr.inputs.Number(label="Scholarship holder"),
70
+ gr.inputs.Number(label="Curricular units 1st sem (credited)"),
71
+ gr.inputs.Number(label="Curricular units 1st sem (without evaluations)"),
72
+ gr.inputs.Number(label="Unemployment rate"),
73
+ gr.inputs.Number(label="Inflation rate"),
74
+ gr.inputs.Number(label="GDP"),
75
+ ]
76
+
77
  outputs = gr.outputs.Textbox(label="Prediction")
78
 
79
  # Launch the Gradio app