update readme file

README.md

@@ -1,199 +1,110 @@
----
-license: apache-2.0
-tags:
-  - time-series
-  - anomaly-detection
-  - zero-shot
-  - pytorch
-  - transformers
-library_name: transformers
-pipeline_tag: time-series-classification
----
-
-# Time-RCD: Zero-Shot Time Series Anomaly Detection
-
-Time-RCD is a transformer-based model for zero-shot anomaly detection in time series data.
-
-## ⚠️ IMPORTANT: Custom Model Loading
-
-**This model uses a custom architecture not built into transformers.**  
-You **MUST** include `trust_remote_code=True` when loading:
-
-```python
-# ✅ CORRECT - Will work
-from transformers import AutoModel
-model = AutoModel.from_pretrained("your-repo/Time-RCD", trust_remote_code=True)
-
-# ❌ WRONG - Will throw KeyError: 'time_rcd'
-model = AutoModel.from_pretrained("your-repo/Time-RCD")  # Missing trust_remote_code=True
-```
+# Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy
 
-## Quick Start
-
-```python
-from transformers import AutoModel, AutoConfig
-import numpy as np
-
-# Load model (trust_remote_code=True is REQUIRED!)
-model = AutoModel.from_pretrained(
-    "thu-sail-lab/Time_RCD",
-    trust_remote_code=True
-)
-
-# Load processor
-from transformers import AutoProcessor
-processor = AutoProcessor.from_pretrained(
-    "thu-sail-lab/Time_RCD",
-    trust_remote_code=True
-)
-
-# Prepare data
-data = np.random.randn(10000, 1)  # [n_samples, n_features]
-
-# Process data
-processed = processor(
-    data,
-    return_tensors="pt"
-)
-
-# Get anomaly scores
-outputs = model(**processed)
-anomaly_scores = outputs.anomaly_scores.numpy()
-```
+This repository contains the implementation of Time-RCD for time series anomaly detection, integrated with the TSB-AD (Time Series Benchmark for Anomaly Detection) datasets.
 
-## Model Details
+## Project Structure
 
-- **Architecture:** Transformer encoder with patch embedding
-- **Parameters:** ~5M parameters
-- **Patch Size:** 4
-- **Hidden Dimension:** 512
-- **Projection Dimension:** 256
-- **Layers:** 8 transformer layers
-- **Attention Heads:** 8 heads
+```
+.
+├── checkpoints/          # Pre-trained model checkpoints
+├── datasets/            # TSB-AD datasets (univariate and multivariate)
+├── evaluation/          # Evaluation metrics and visualization tools
+├── models/              # Model implementations
+│   └── time_rcd/       # Time-RCD model components
+├── utils/               # Utility functions
+├── testing.py              # Main entry point
+├── model_wrapper.py     # Model wrapper for different algorithms
+└── README.md            # This file
+```
 
-## Features
+## Prerequisites
 
-✅ **Zero-shot detection** - No training required  
-✅ **Multi-variate support** - Handle multiple features  
-✅ **Flexible windows** - Configurable window sizes  
-✅ **Robust normalization** - Built-in preprocessing  
+- Python 3.10
+- conda (recommended for environment management)
+- Git
 
-## Usage Examples
+## Installation
 
-### Basic Anomaly Detection
+### 1. Create and Activate Conda Environment
 
-```python
-from transformers import AutoModel
-import numpy as np
+```bash
+conda create -n Time-RCD python=3.10
+conda activate Time-RCD
+```
 
-# IMPORTANT: trust_remote_code=True is required!
-model = AutoModel.from_pretrained("thu-sail-lab/Time_RCD", trust_remote_code=True)
+### 2. Download the Repository
 
-# Your time series (n_samples, n_features)
-data = np.random.randn(10000, 1)
+```bash
+wget https://anonymous.4open.science/api/repo/TimeRCD-5BE1/zip -O Time-RCD.zip
+unzip Time-RCD.zip -d Time-RCD
+```
+or dowload from the link: https://anonymous.4open.science/r/TimeRCD-5BE1 and unzip
 
-# Get anomaly scores using the zero_shot method
-scores, logits = model.zero_shot(data)
+### 3. Download TSB-AD Datasets
 
-# Flatten scores from list of batches
-import numpy as np
-all_scores = np.concatenate(scores, axis=0).flatten()
+Create the datasets directory and download the TSB-AD-U (univariate) and TSB-AD-M (multivariate) datasets:
 
-# Detect anomalies (e.g., top 5%)
-threshold = np.percentile(all_scores, 95)
-anomalies = all_scores > threshold
+```bash
+mkdir -p "datasets" \
+  && wget -O "datasets/TSB-AD-U.zip" "https://www.thedatum.org/datasets/TSB-AD-U.zip" \
+  && wget -O "datasets/TSB-AD-M.zip" "https://www.thedatum.org/datasets/TSB-AD-M.zip" \
+  && cd datasets \
+  && unzip TSB-AD-U.zip && rm TSB-AD-U.zip \
+  && unzip TSB-AD-M.zip && rm TSB-AD-M.zip \
+  && cd ..
 ```
 
-### With Custom Processing
-
-```python
-from transformers import AutoModel
-from processing_time_rcd import TimeRCDProcessor
-import numpy as np
+### 4. Install Python Dependencies
 
-# IMPORTANT: trust_remote_code=True is required!
-model = AutoModel.from_pretrained("thu-sail-lab/Time_RCD", trust_remote_code=True)
+#### Option A: Fast Install (using uv)
 
-# Create and configure processor
-processor = TimeRCDProcessor(win_size=5000, normalize=True)
+```bash
+pip install uv
+uv pip install jaxtyping einops pandas numpy scikit-learn transformers torch torchvision statsmodels matplotlib seaborn -U "huggingface_hub[cli]"
+```
 
-# Process data
-data = np.random.randn(10000, 1)
-processed = processor(data, return_tensors="pt")
+#### Option B: Normal Install
 
-# Get predictions
-outputs = model(**processed)
-anomaly_scores = outputs.anomaly_scores
+```bash
+pip install jaxtyping einops pandas numpy scikit-learn transformers torch torchvision statsmodels matplotlib seaborn -U "huggingface_hub[cli]"
 ```
 
-## Configuration
+### 5. Download Pre-trained Checkpoints
 
-| Parameter | Default | Description |
-|-----------|---------|-------------|
-| patch_size | 4 | Patch size for embedding |
-| d_model | 512 | Model dimension |
-| d_proj | 256 | Projection dimension |
-| num_layers | 8 | Transformer layers |
-| num_heads | 8 | Attention heads |
-| use_rope | True | Rotary position embeddings |
+Download the pre-trained model checkpoints from Hugging Face:
 
-## Performance
+```bash
+huggingface-cli download thu-sail-lab/Time-RCD checkpoints.zip --local-dir ./
+unzip checkpoints.zip
+```
 
-Evaluated on various time series anomaly detection benchmarks.
+### Single Variable Time Series
 
-## Limitations
+To run anomaly detection on univariate time series:
 
-- Requires sufficient data (> window size)
-- Performance varies by domain
-- High-dimensional data may need preprocessing
+```bash
+python testing.py
+```
 
-## Troubleshooting
+### Multi-Variable Time Series
 
-### KeyError: 'time_rcd'
+To run anomaly detection on multivariate time series:
 
-If you see this error:
-```
-KeyError: 'time_rcd'
-The checkpoint you are trying to load has model type `time_rcd` but Transformers does not recognize this architecture.
+```bash
+python testing.py --mode multi
 ```
 
-**Solution:** Add `trust_remote_code=True` to your loading code:
+<!-- 
+### 6. Download Training Datasets
 
-```python
-# This will fix the error
-model = AutoModel.from_pretrained("your-repo/Time-RCD", trust_remote_code=True)
+Download Training Datasets (Optional -for retraining models)
+```bash
+mkdir training_data
+huggingface-cli download thu-sail-lab/Time-RCD training_data.zip --local-dir ./
+unzip training_data.zip
 ```
 
-This is required because Time-RCD is a custom architecture not built into the transformers library. The `trust_remote_code=True` flag tells transformers to load and execute the custom model code from the repository.
-
-### Other Common Issues
-
-**Issue:** `ModuleNotFoundError: No module named 'einops'`  
-**Solution:** Install einops: `pip install einops`
+ -->
 
-**Issue:** Model runs slowly on CPU  
-**Solution:** Move model to GPU: `model = model.to('cuda')`
-
-**Issue:** Out of memory errors  
-**Solution:** Reduce window size or batch size in the processor:
-```python
-processor = TimeRCDProcessor(win_size=2000, batch_size=32)
-```
-
-## Citation
-
-```bibtex
-@misc{lan2025foundationmodelszeroshottime,
-      title={Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy}, 
-      author={Tian Lan and Hao Duong Le and Jinbo Li and Wenjun He and Meng Wang and Chenghao Liu and Chen Zhang},
-      year={2025},
-      eprint={2509.21190},
-      archivePrefix={arXiv},
-      primaryClass={cs.LG},
-      url={https://arxiv.org/abs/2509.21190}, 
-}
-```
 
-## License
 
-Apache 2.0