Upload 5 files

app.py

@@ -0,0 +1,63 @@
+#gradio app 
+
+import gradio as gr
+import pandas as pd
+import pickle
+import numpy as np
+
+# 1. Load the Model
+with open("student_rf_pipeline.pkl", "rb") as f:
+    model = pickle.load(f)
+
+# 2. The Logic Function
+def predict_gpa(gender, age, address, famsize, 
+                Pstatus, M_Edu, F_Edu, M_Job, F_Job, 
+                relationship, smoker, tuition_fee, time_friends,
+                  ssc_result):
+    
+    # Pack inputs into a DataFrame
+    # The column names must match your CSV file exactly
+    input_df = pd.DataFrame([[
+        gender, age, address, famsize, Pstatus, 
+        M_Edu, F_Edu, M_Job, F_Job, relationship, 
+        smoker, tuition_fee, time_friends, ssc_result
+
+    ]],
+      columns=[
+        'gender', 'age', 'address', 'famsize', 'Pstatus', 'M_Edu', 'F_Edu', 'M_Job', 'F_Job', 'relationship', 'smoker', 'tuition_fee', 'time_friends', 'ssc_result'
+    ])
+    
+    # Predict
+    prediction = model.predict(input_df)[0]
+    
+    # Return formatted result (Clipped 0-5)
+    return f"Predicted HSC Result: {np.clip(prediction, 0, 5):.2f}"
+
+# 3. The App Interface
+# Defining inputs in a list to keep it clean
+inputs = [
+    gr.Radio(["M", "F"], label="Gender"),
+    gr.Number(label="Age", value=18),
+    gr.Radio(["Urban", "Rural"], label="Address"),
+    gr.Radio(["GT3", "LE3"], label="Family Size"),
+    gr.Radio(["Together", "Apart"], label="Parent Status"),
+    gr.Slider(0, 4, step=1, label="Mother's Edu"),
+    gr.Slider(0, 4, step=1, label="Father's Edu"),
+    gr.Dropdown(["At_home", "Health", "Other", "Services", "Teacher"], label="Mother's Job"),
+    gr.Dropdown(["Teacher", "Other", "Services", "Health", "Business", "Farmer"], label="Father's Job"),
+    gr.Radio(["Yes", "No"], label="Relationship"),
+    gr.Radio(["Yes", "No"], label="Smoker"),
+    gr.Number(label="Tuition Fee"),
+    gr.Slider(1, 5, step=1, label="Time with Friends"),
+    gr.Number(label="SSC Result (GPA)")
+]
+
+app = gr.Interface(
+    fn=predict_gpa,
+      inputs=inputs,
+        outputs="text", 
+        title="HSC Predictor")
+
+app.launch(share=True)
+
+

requirements.txt

@@ -0,0 +1,57 @@
+aiofiles==24.1.0
+annotated-doc==0.0.4
+annotated-types==0.7.0
+anyio==4.12.1
+audioop-lts==0.2.2
+brotli==1.2.0
+certifi==2026.1.4
+click==8.3.1
+colorama==0.4.6
+fastapi==0.128.0
+ffmpy==1.0.0
+filelock==3.20.3
+fsspec==2026.1.0
+gradio==6.3.0
+gradio_client==2.0.3
+groovy==0.1.2
+h11==0.16.0
+hf-xet==1.2.0
+httpcore==1.0.9
+httpx==0.28.1
+huggingface_hub==1.3.1
+idna==3.11
+Jinja2==3.1.6
+joblib==1.5.3
+markdown-it-py==4.0.0
+MarkupSafe==3.0.3
+mdurl==0.1.2
+numpy==2.4.1
+orjson==3.11.5
+packaging==25.0
+pandas==2.3.3
+pillow==12.1.0
+pydantic==2.12.5
+pydantic_core==2.41.5
+pydub==0.25.1
+Pygments==2.19.2
+python-dateutil==2.9.0.post0
+python-multipart==0.0.21
+pytz==2025.2
+PyYAML==6.0.3
+rich==14.2.0
+safehttpx==0.1.7
+scikit-learn==1.8.0
+scipy==1.17.0
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.17.0
+starlette==0.50.0
+threadpoolctl==3.6.0
+tomlkit==0.13.3
+tqdm==4.67.1
+typer==0.21.1
+typer-slim==0.21.1
+typing-inspection==0.4.2
+typing_extensions==4.15.0
+tzdata==2025.3
+uvicorn==0.40.0

rf_train.py

@@ -0,0 +1,99 @@
+
+import pandas as pd
+import numpy as np
+import pickle
+
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+from sklearn.impute import SimpleImputer
+from sklearn.compose import ColumnTransformer
+from sklearn.pipeline import Pipeline
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.metrics import mean_squared_error, r2_score
+
+# =====================
+# Load dataset
+# =====================
+df = pd.read_csv("bangladesh_student_performance_2018.csv")
+
+print(df)
+
+# Drop date column
+if 'date' in df.columns:
+    df.drop(columns=['date'], inplace=True)
+
+# Target and features
+X = df.drop('hsc_result', axis=1)
+y = df['hsc_result']
+
+# =====================
+# Column split
+# =====================
+numeric_features = X.select_dtypes(include=['int64', 'float64']).columns
+categorical_features = X.select_dtypes(include=['object']).columns
+
+# =====================
+# Preprocessing
+# =====================
+num_transformer = Pipeline(steps=[
+    ('imputer', SimpleImputer(strategy='median')),
+    ('scaler', StandardScaler())
+])
+
+cat_transformer = Pipeline(steps=[
+    ('imputer', SimpleImputer(strategy='most_frequent')),
+    ('encoder', OneHotEncoder(handle_unknown='ignore'))
+])
+
+preprocessor = ColumnTransformer(transformers=[
+    ('num', num_transformer, numeric_features),
+    ('cat', cat_transformer, categorical_features)
+])
+
+# =====================
+# Random Forest Model
+# =====================
+rf_model = RandomForestRegressor(
+    n_estimators=200,
+    max_depth=10,
+    min_samples_split=2,
+    random_state=42,
+    n_jobs=-1
+)
+
+# =====================
+# Full Pipeline
+# =====================
+rf_pipeline = Pipeline(steps=[
+    ('preprocessor', preprocessor),
+    ('model', rf_model)
+])
+
+# =====================
+# Train-test split
+# ====================
+X_train, X_test, y_train, y_test = train_test_split(
+    X, y, test_size=0.2, random_state=42
+)
+
+
+rf_pipeline.fit(X_train, y_train)
+
+# =====================
+# Evaluation
+# =====================
+y_pred = rf_pipeline.predict(X_test)
+rmse = np.sqrt(mean_squared_error(y_test, y_pred))
+r2 = r2_score(y_test, y_pred)
+
+print(f"RMSE: {rmse:.4f}")
+print(f"R2 Score: {r2:.4f}")
+
+# =====================
+# Save model (IMPORTANT)
+# =====================
+
+with open("student_rf_pipeline.pkl", "wb") as f:
+    pickle.dump(rf_pipeline, f)
+
+print("✅ Random Forest pipeline saved as student_rf_pipeline.pkl")

student_rf_pipeline.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8c9af2c107dd2061c705653d0f9b8d73aaf87d31f432249968114c097e7136
+size 14727571