Upload 3 files

app.py

@@ -0,0 +1,121 @@
+import joblib
+import pandas as pd
+import numpy as np
+import gradio as gr
+
+# Load your trained model
+model = joblib.load('trained_model.joblib')
+
+# Define grade to numeric conversion (same as before)
+def grade_to_numeric(grade):
+    if pd.isna(grade) or grade == "":
+        return np.nan
+    grade_map = {
+        "A1": 1, "B2": 2, "B3": 3, "C4": 4, "C5": 5, "C6": 6,
+        "D7": 7, "E8": 8, "F9": 9
+    }
+    return grade_map.get(grade, np.nan)
+
+# Define your preprocessing function
+def preprocess_input(desired_career, aggregate, english, core_maths, science, 
+                    social_studies, electives, elective_maths=None, 
+                    business_management=None, government=None, chemistry=None,
+                    physics=None, economics=None, visual_arts=None, geography=None,
+                    e_ict=None, literature=None, biology=None):
+    
+    # Create a dictionary with all inputs
+    input_data = {
+        "Desired_Career": desired_career,
+        "Aggregate": aggregate,
+        "English": english,
+        "Core Maths": core_maths,
+        "Science": science,
+        "Social Studies": social_studies,
+        "Electives": electives,
+        "Elective Maths": elective_maths,
+        "Business Management": business_management,
+        "Government": government,
+        "Chemistry": chemistry,
+        "Physics": physics,
+        "Economics": economics,
+        "Visual Arts": visual_arts,
+        "Geography": geography,
+        "E-ICT": e_ict,
+        "Literature": literature,
+        "Biology": biology
+    }
+    
+    # Convert to DataFrame
+    student_df = pd.DataFrame([input_data])
+    
+    # Convert grades to numerical
+    grade_cols = ['English', 'Core Maths', 'Science', 'Social Studies',
+                 'Elective Maths', 'Business Management', 'Government',
+                 'Chemistry', 'Physics', 'Economics', 'Visual Arts',
+                 'Geography', 'E-ICT', 'Literature', 'Biology']
+    
+    for col in grade_cols:
+        if col in student_df.columns:
+            student_df[col] = student_df[col].apply(grade_to_numeric)
+    
+    return student_df
+
+def predict_career(desired_career, aggregate, english, core_maths, science, 
+                  social_studies, electives, elective_maths=None, 
+                  business_management=None, government=None, chemistry=None,
+                  physics=None, economics=None, visual_arts=None, geography=None,
+                  e_ict=None, literature=None, biology=None):
+    
+    # Preprocess input
+    processed_input = preprocess_input(
+        desired_career, aggregate, english, core_maths, science,
+        social_studies, electives, elective_maths, business_management,
+        government, chemistry, physics, economics, visual_arts, geography,
+        e_ict, literature, biology
+    )
+    
+    # Make prediction
+    prediction = model.predict(processed_input)
+    probabilities = model.predict_proba(processed_input)[0]
+    
+    # Get top 3 recommendations
+    class_indices = np.argsort(probabilities)[::-1][:3]
+    classes = model.classes_
+    recommendations = [
+        (classes[idx], float(probabilities[idx])) 
+        for idx in class_indices
+    ]
+    
+    # Format output
+    output = "\n".join(
+        [f"{course}: {prob*100:.1f}%" for course, prob in recommendations]
+    )
+    
+    return output
+
+# Create Gradio interface
+inputs = [
+    gr.Dropdown(["Medicine", "Pharmacy", "Law", "Computer Science", "Engineering", 
+                "Business", "Nursing", "Agriculture", "Journalism", "Education"], 
+               label="Desired Career"),
+    gr.Number(label="Aggregate Score"),
+    gr.Dropdown(["A1", "B2", "B3", "C4", "C5", "C6", "D7", "E8", "F9"], label="English"),
+    gr.Dropdown(["A1", "B2", "B3", "C4", "C5", "C6", "D7", "E8", "F9"], label="Core Maths"),
+    gr.Dropdown(["A1", "B2", "B3", "C4", "C5", "C6", "D7", "E8", "F9"], label="Science"),
+    gr.Dropdown(["A1", "B2", "B3", "C4", "C5", "C6", "D7", "E8", "F9"], label="Social Studies"),
+    gr.Textbox(label="Electives (comma separated)"),
+    gr.Dropdown(["A1", "B2", "B3", "C4", "C5", "C6", "D7", "E8", "F9", None], label="Elective Maths (optional)"),
+    # Add other optional subjects similarly
+]
+
+outputs = gr.Textbox(label="Recommended Courses")
+
+interface = gr.Interface(
+    fn=predict_career,
+    inputs=inputs,
+    outputs=outputs,
+    title="Career Path Recommender",
+    description="Enter your academic information to get career recommendations"
+)
+
+interface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+gradio==3.50.2
+pandas==1.5.3
+numpy==1.23.5
+scikit-learn==1.2.2
+joblib==1.2.0

trained_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:572ea685ee5d87389cd0e370ed4db6d85415cc2e94396459a40cab5fdba64b94
+size 88291291