Update train_model.py

train_model.py

@@ -1,61 +1,33 @@
-# -*- coding: utf-8 -*-
-"""train_model.py
-
-Automatically generated by Colab.
-
-Original file is located at
-    https://colab.research.google.com/drive/1Oq8iUsTw8pCPeB1qLiaYLCI6QRVjO05g
-"""
-
-pip install joblib
-
+# train_model.py
 import pandas as pd
-import numpy as np
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.preprocessing import LabelEncoder
-from sklearn.model_selection import train_test_split
 import joblib
 import os
 
-# Sample dataset (replace with your actual data)
+# 1. Load/Sample Data
 data = {
-    'face_shape': ['Oval', 'Round', 'Square', 'Oval', 'Round', 'Square'] * 10,
-    'skin_tone': ['Fair', 'Medium', 'Dark', 'Medium', 'Dark', 'Fair'] * 10,
-    'face_size': ['Small', 'Medium', 'Large', 'Medium', 'Large', 'Small'] * 10,
-    'mask_style': ['Glitter', 'Animal', 'Floral', 'Animal', 'Glitter', 'Floral'] * 10
+    'face_shape': ['Oval', 'Round', 'Square']*10,
+    'skin_tone': ['Fair', 'Medium', 'Dark']*10,
+    'face_size': ['Small', 'Medium', 'Large']*10,
+    'mask_style': ['StyleA', 'StyleB', 'StyleC']*10
 }
 df = pd.DataFrame(data)
 
-# Initialize LabelEncoders
+# 2. Create and Save Encoders
 encoders = {
-    'face_shape': LabelEncoder().fit(df['face_shape']),
-    'skin_tone': LabelEncoder().fit(df['skin_tone']),
-    'face_size': LabelEncoder().fit(df['face_size']),
-    'mask_style': LabelEncoder().fit(df['mask_style'])
+    col: LabelEncoder().fit(df[col].unique()) 
+    for col in ['face_shape', 'skin_tone', 'face_size', 'mask_style']
 }
 
-# Encode features
-X = pd.DataFrame({
-    'face_shape': encoders['face_shape'].transform(df['face_shape']),
-    'skin_tone': encoders['skin_tone'].transform(df['skin_tone']),
-    'face_size': encoders['face_size'].transform(df['face_size'])
-})
+# 3. Train Model
+X = pd.DataFrame({col: encoders[col].transform(df[col]) for col in encoders if col != 'mask_style'})
 y = encoders['mask_style'].transform(df['mask_style'])
 
-# Train-test split
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+model = RandomForestClassifier()
+model.fit(X, y)
 
-# Train Random Forest
-model = RandomForestClassifier(n_estimators=100, random_state=42)
-model.fit(X_train, y_train)
-
-# Create model directory
+# 4. Save to model/ directory
 os.makedirs('model', exist_ok=True)
-
-# Save model and encoders
 joblib.dump(model, 'model/random_forest.pkl')
-joblib.dump(encoders, 'model/label_encoders.pkl')
-
-print("Model trained and saved successfully!")
-print(f"Test Accuracy: {model.score(X_test, y_test):.2f}")
-
+joblib.dump(encoders, 'model/label_encoders.pkl')