adding docs

docs/_notebooks/train_tonnage_anomaly_detection.markdown

@@ -0,0 +1,107 @@
+---
+# This is the Front Matter section where you can set variables used by Jekyll
+layout: post
+title: "Train Tonnage Anomaly Detection"
+date:   2024-03-16 19:26:31 +0000
+categories: notebooks
+---
+
+## Prerequisites
+* Configure RHODS workspace has been completed.
+
+## Run Jupyter notebooks 
+1. Accessing an AWS S3 bucket & downloading multiple JSON files - [advanceddownloadData.ipynb](https://github.com/tosin2013/edge-anomaly-detection-notebooks/blob/main/advanceddownloadData.ipynb)
+
+**Data Collection**
+Change the following to notebook
+```python
+AWS_ACCESS_KEY_ID = 'YOUR_ACCESS_KEY'
+AWS_SECRET_ACCESS_KEY = 'YOUR_SECRET_KEY'
+bucket_name = 'edge-anomaly-detection-bucket-name'
+# List of file names to download
+file_names = [
+    'edge-datalake-bullet--Wed Oct 04 13:56:26 GMT 2023.txt',
+    'edge-datalake-bullet--Wed Oct 04 13:57:26 GMT 2023.txt',
+    # Add more file names here if needed
+]
+```
+Example Bucket contents
+![20240318160248](https://i.imgur.com/Ie9u1JO.png)
+
+![20240318160350](https://i.imgur.com/piewUAs.png)
+
+### Train Tonnage Anomaly Detection Model - [TrainTonnage.ipynb](https://github.com/tosin2013/edge-anomaly-detection-notebooks/blob/main/TrainTonnage.ipynb)
+
+**Data Exploration**
+![20240318160746](https://i.imgur.com/QvAvfc3.png)
+**Preprocess the data (remove rows with missing values)**
+![20240318160826](https://i.imgur.com/epkYtgu.png)
+
+**Make an Isolation Forest Model**
+![20240318161314](https://i.imgur.com/vFhmhbf.png)
+
+**Show Anomalies**
+![20240318161351](https://i.imgur.com/9B2nMEM.png)
+
+**Check the Correlations in the Data**
+![20240318161420](https://i.imgur.com/7VA62H1.png)
+
+**Check fo Missing Data in the Dataset**
+![20240318161455](https://i.imgur.com/Y89ll2F.png)
+
+**Detect Negative Values in the 'TrainSpeed' Column**
+![20240318161529](https://i.imgur.com/jsiudcG.png)
+
+**Print the Anomaly Scores and Correlation Matrix**
+![20240318161605](https://i.imgur.com/iDBBnRn.png)
+
+**Train Tonnage Over Time with Anomalies Highlighted**
+![20240318161633](https://i.imgur.com/b5o2gUx.png)
+
+**List Detected Anomalies in Train Tonnage Data**
+![20240318161705](https://i.imgur.com/UaGNTrC.png)
+
+**Visualize of All Dataframe Columns**
+![20240318161922](https://i.imgur.com/PLjcIj0.png)
+
+**Visualize All Anomalies Dataframe Columns**
+![20240318161950](https://i.imgur.com/q7FV9HF.png)
+
+**Correlation Heatmap**
+![20240318162010](https://i.imgur.com/zXGYS7M.png)
+
+**Review Box Plot of Key Features**
+![20240318162037](https://i.imgur.com/fZOPfHA.png)
+
+**Pairwise Scatter Plot of Key Features**
+![20240318162107](https://i.imgur.com/Xa62nYe.png)
+
+**Scatter Plot of Primary Suspension Stiffness vs. Train Acceleration**
+![20240318162134](https://i.imgur.com/SjQpBRm.png)
+
+**Scatter Plot of Train Tonnage vs. Elapsed Time**
+![20240318162205](https://i.imgur.com/BLUvhML.png)
+
+**Scatter Plot of Train Tonnage vs. Anomaly Scores**
+![20240318162230](https://i.imgur.com/wSuNPsM.png)
+
+**Scatter Plot of Anomaly vs. Anomaly Scores**
+![20240318162252](https://i.imgur.com/mISPuIX.png)
+
+**Scatter Plot of TrainSpeed vs. TrainAcceleration with Correlation Line**
+![20240318162331](https://i.imgur.com/tackNTQ.png)
+
+**Model Conversion to ONNX Format**
+
+**Load an ONNX Model for Inference**
+
+**List Features in a Sample DataFrame**
+![20240318163307](https://i.imgur.com/3ySqXky.png)
+
+**Feature Extraction and Inference**
+
+**Inference using ONNX Model**
+
+**Visualizing Model Output with a Bar Chart**
+
+**Visualizing Anomaly Scores with a Bar Chart**