Update README.md

README.md

@@ -1,59 +1,65 @@
-# Model Card for Lego Brick Classification (Classical AutoML)
+---
+language: 
+- en
+license: mit
+tags:
+- automl
+- tabular
+- classification
+- sklearn
+datasets:
+- aedupuga/lego-sizes
+metrics:
+- accuracy
+- f1
+model-index:
+- name: Lego Brick Classification (Classical AutoML)
+  results:
+  - task:
+      type: classification
+      name: Tabular Classification
+    dataset:
+      name: aedupuga/lego-sizes
+      type: classification
+      split: augmented
+    metrics:
+    - type: accuracy
+      value: 0.97
+    - type: f1
+      value: 0.96
+---
 
-## Model Details
-- **Model type**: Classical AutoML ensemble (AutoGluon Tabular)
-- **Framework**: [AutoGluon](https://auto.gluon.ai/stable/index.html)
-- **Task**: Multiclass Classification  
-- **Classes**:  
-  - Standard  
-  - Flat  
-  - Sloped  
+# Lego Brick Classification (Classical AutoML)
 
-The model was trained using AutoGluon Tabular with automated feature engineering, model selection, and hyperparameter tuning under a fixed budget.
+This model was trained using **AutoGluon Tabular (Classical AutoML)** on the dataset [aedupuga/lego-sizes](https://huggingface.co/datasets/aedupuga/lego-sizes).  
+The task is to classify LEGO bricks into three categories: **Standard, Flat, Sloped**, given their measured dimensions (length, height, width, studs).  
 
-## Intended Use
-- **Direct use**: Classify LEGO bricks into `Standard`, `Flat`, or `Sloped` types based on their dimensions.  
-- **Educational use**: Demonstrate classical AutoML techniques on a small synthetic dataset.  
-- **Not intended for**: Industrial-scale LEGO piece classification or manufacturing quality control.  
+## Model Details
+- **Framework**: AutoGluon (TabularPredictor)
+- **Algorithms searched**: Random Forest, Gradient Boosting Trees, XGBoost, LightGBM, CatBoost
+- **Best model**: LightGBM (selected by AutoML)
+- **Training data**: 300 augmented + 30 original samples
+- **Evaluation metric**: Accuracy, Weighted F1
+
+## Results
+- Accuracy: **0.97**
+- Weighted F1: **0.96**
 
 ## Dataset
-- **Dataset name**: [aedupuga/lego-sizes](https://huggingface.co/datasets/aedupuga/lego-sizes)  
-- **Description**: Contains dimensions and stud count of LEGO bricks, with labels indicating piece type.  
-- **Splits**:
-  - Original: 30 measured samples
-  - Augmented: 300 synthetically generated samples
-- **Features**:
-  - Max Length (cm)
-  - Max Height (cm)
-  - Width (cm)
-  - Studs
-  - Type (Standard/Flat/Sloped)
-
-## Training Procedure
-- **Train/Val/Test split**: 80/10/10 (stratified) on augmented dataset
-- **External validation**: Performed on original dataset
-- **AutoML settings**:
-  - Preset: `best_quality`
-  - Metric: Accuracy
-  - Time budget: ~30 minutes
-
-## Evaluation Results
-- **Augmented Test Set**:
-  - Accuracy: 0.97
-  - Weighted F1: 0.96
-- **Original External Validation Set**:
-  - Accuracy: 0.93
-  - Weighted F1: 0.92
+- Name: [aedupuga/lego-sizes](https://huggingface.co/datasets/aedupuga/lego-sizes)  
+- Original: 30 manually measured LEGO bricks  
+- Augmented: 300 synthetically generated samples (jittered dimensions)  
+- Features: `Length`, `Height`, `Width`, `Studs`  
+- Target: `Type (Standard / Flat / Sloped)`
 
-## Limitations
-- The dataset is very small (only 30 original samples).
-- Synthetic augmentation may not capture full real-world variability.
-- Model may not generalize beyond this toy dataset.
+## Intended Use
+This model is intended for **educational practice** in AutoML and tabular classification.  
+It is **not suitable for industrial use**, given the small sample size and synthetic data.  
 
-## Recommendations
-- Use primarily for **demonstration and coursework**.  
-- Do not deploy in real-world LEGO production environments.  
+## Limitations
+- Very small real dataset (30 samples)  
+- Synthetic augmentation may not capture all real-world variations  
 
-## Model Card Contact
-Author: *Xinxuan Tang (Carnegie Mellon University)* – xinxuant@andrew.cmu.edu
-Dataset curator: Anuhya Edupuganti (CMU) – aedupuga@andrew.cmu.edu
+## Contact
+Dataset by: Anuhya Edupuganti (CMU)  
+Model by: Xinxuan Tang (CMU) - xinxuant@andrew.cmu.edu