rtnjt commited on
Commit
25a4fd3
·
verified ·
1 Parent(s): 627ce6d

updated app.py

Browse files
Files changed (1) hide show
  1. app.py +7 -15
app.py CHANGED
@@ -12,11 +12,9 @@ models = {
12
  "Decision Tree": joblib.load('decision_tree_model.joblib'),
13
  "XGBoost": joblib.load('xgboost_model.joblib'),
14
  "AdaBoost": joblib.load('adaboost_model.joblib')
15
- }
16
 
17
  # --- BACKGROUND MAPPINGS ---
18
- # These dictionaries map the "Friendly Text" -> "Model Number"
19
- # You MUST ensure these numbers match exactly what your LabelEncoder/OneHotEncoder used during training.
20
  mappings = {
21
  "Gender": {"Male": 1, "Female": 0},
22
  "YesNo": {"Yes": 1, "No": 0},
@@ -35,7 +33,6 @@ mappings = {
35
  "80% - 89.9%": 4,
36
  "90% and above": 5
37
  },
38
- # Add mappings for Social Category and Domicile if your model needs numbers
39
  "Social_Category": {"General": 0, "OBC": 1, "SC": 2, "ST": 3, "EWS": 4},
40
  "Domicile_Type": {"Urban": 0, "Semi-Urban": 1, "Rural": 2}
41
  }
@@ -47,8 +44,7 @@ def predict_risk(model_name, gender, age, social_category, domicile_type, first_
47
  # 1. Select the model
48
  model = models[model_name]
49
 
50
- # 2. SILENT CONVERSION (Text -> Number)
51
- # We use .get() to safely grab the number. Default to 0 if something goes wrong.
52
  encoded_gender = mappings["Gender"].get(gender, 0)
53
  encoded_first_gen = mappings["YesNo"].get(first_gen, 0)
54
  encoded_disability = mappings["YesNo"].get(disability_status, 0)
@@ -57,13 +53,9 @@ def predict_risk(model_name, gender, age, social_category, domicile_type, first_
57
  encoded_income = mappings["Income"].get(income_bracket, 0)
58
  encoded_class10 = mappings["Grades"].get(class10, 0)
59
  encoded_class12 = mappings["Grades"].get(class12, 0)
60
-
61
- # Handle the ones that might have caused the "could not convert string" error
62
- # If your model used OneHotEncoder for these, you might need a different approach,
63
- # but if it used LabelEncoder, this is perfect.
64
  encoded_social = mappings["Social_Category"].get(social_category, 0)
65
  encoded_domicile = mappings["Domicile_Type"].get(domicile_type, 0)
66
-
67
  # 3. Create the numeric DataFrame
68
  input_data = pd.DataFrame({
69
  'Gender_bin': [encoded_gender],
@@ -88,7 +80,7 @@ def predict_risk(model_name, gender, age, social_category, domicile_type, first_
88
  prediction = model.predict(input_data)[0]
89
  result = "At Risk" if prediction >= 2 else "Not At Risk"
90
 
91
- # 5. Confidence
92
  try:
93
  probabilities = model.predict_proba(input_data)
94
  confidence = float(np.max(probabilities)) * 100
@@ -102,7 +94,7 @@ def predict_risk(model_name, gender, age, social_category, domicile_type, first_
102
  "risk_score": float(prediction)
103
  }
104
 
105
- # Create Gradio interface (Users see Text, Code sees Numbers)
106
  iface = gr.Interface(
107
  fn=predict_risk,
108
  inputs=[
@@ -131,7 +123,7 @@ iface = gr.Interface(
131
  title="SETU Student At-Risk Prediction",
132
  description="AI-powered student dropout risk assessment system with multiple ML models",
133
  api_name="predict"
134
- )
135
 
136
  if __name__ == "__main__":
137
- iface.launch()
 
12
  "Decision Tree": joblib.load('decision_tree_model.joblib'),
13
  "XGBoost": joblib.load('xgboost_model.joblib'),
14
  "AdaBoost": joblib.load('adaboost_model.joblib')
15
+ } # ← This closing brace was MISSING!
16
 
17
  # --- BACKGROUND MAPPINGS ---
 
 
18
  mappings = {
19
  "Gender": {"Male": 1, "Female": 0},
20
  "YesNo": {"Yes": 1, "No": 0},
 
33
  "80% - 89.9%": 4,
34
  "90% and above": 5
35
  },
 
36
  "Social_Category": {"General": 0, "OBC": 1, "SC": 2, "ST": 3, "EWS": 4},
37
  "Domicile_Type": {"Urban": 0, "Semi-Urban": 1, "Rural": 2}
38
  }
 
44
  # 1. Select the model
45
  model = models[model_name]
46
 
47
+ # 2. Convert text to numbers
 
48
  encoded_gender = mappings["Gender"].get(gender, 0)
49
  encoded_first_gen = mappings["YesNo"].get(first_gen, 0)
50
  encoded_disability = mappings["YesNo"].get(disability_status, 0)
 
53
  encoded_income = mappings["Income"].get(income_bracket, 0)
54
  encoded_class10 = mappings["Grades"].get(class10, 0)
55
  encoded_class12 = mappings["Grades"].get(class12, 0)
 
 
 
 
56
  encoded_social = mappings["Social_Category"].get(social_category, 0)
57
  encoded_domicile = mappings["Domicile_Type"].get(domicile_type, 0)
58
+
59
  # 3. Create the numeric DataFrame
60
  input_data = pd.DataFrame({
61
  'Gender_bin': [encoded_gender],
 
80
  prediction = model.predict(input_data)[0]
81
  result = "At Risk" if prediction >= 2 else "Not At Risk"
82
 
83
+ # 5. Calculate confidence
84
  try:
85
  probabilities = model.predict_proba(input_data)
86
  confidence = float(np.max(probabilities)) * 100
 
94
  "risk_score": float(prediction)
95
  }
96
 
97
+ # Create Gradio interface
98
  iface = gr.Interface(
99
  fn=predict_risk,
100
  inputs=[
 
123
  title="SETU Student At-Risk Prediction",
124
  description="AI-powered student dropout risk assessment system with multiple ML models",
125
  api_name="predict"
126
+ ) # ← This closing parenthesis was MISSING!
127
 
128
  if __name__ == "__main__":
129
+ iface.launch()