https://github.com/bm777/predictive-maintenance

Predictive maintenance using ML, hosted by FastAPI and Kafka
https://github.com/bm777/predictive-maintenance

anomaly-detection api-rest fastapi kafka-consumer kafka-producer predictive-maintenance

Last synced: 13 days ago
JSON representation

Predictive maintenance using ML, hosted by FastAPI and Kafka

• Host: GitHub
• URL: https://github.com/bm777/predictive-maintenance
• Owner: bm777
• License: mit
• Created: 2022-03-03T11:00:50.000Z (almost 3 years ago)
• Default Branch: master
• Last Pushed: 2022-03-06T18:48:23.000Z (almost 3 years ago)
• Last Synced: 2024-11-09T18:46:16.609Z (2 months ago)
• Topics: anomaly-detection, api-rest, fastapi, kafka-consumer, kafka-producer, predictive-maintenance
• Language: Python
• Homepage:
• Size: 413 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Predictive-maintenance

Predictive maintenance using ML, hosted by FastAPI and Kafka

# Settings

Try to clone the repo.

```

git clone https://github.com/bm777/predictive-maintenance.git

```

#### 0. Set up the kafka env

```

cd kafka

bin/zookeeper-server-start.sh config/zookeeper.properties

bin/kafka-server-start.sh config/server.properties

```

#### 1. Create the transactions, anomalies and normals topics in Kafka Consumer

```

cd kafka

bin/kafka-topics.sh --create --topic transactions --bootstrap-server localhost:9092

bin/kafka-topics.sh --create --topic anomalies --bootstrap-server localhost:9092

bin/kafka-topics.sh --create --topic normals --bootstrap-server localhost:9092

```

We can check our created topics by this command `kafka-topics.sh --bootstrap-server localhost:9092 --list`, the result should be three topics.

#### 2. The predictive maintenance thread & the topics

- The predictive maintenance thread is started automatically in fastapi's startup event. So no need to run `python streaming_kafka/predictive_maintenance.py`

- [optional] watch the topic of your choice {`transactions`, `anomalies`, and `normals` } in the consumer

```

bin/kafka-console-consumer.sh --topic transactions --from-beginning --bootstrap-server localhost:9092

bin/kafka-console-consumer.sh --topic anomalies --from-beginning --bootstrap-server localhost:9092

bin/kafka-console-consumer.sh --topic normals --from-beginning --bootstrap-server localhost:9092

```

![alt](assets/topics.png)

#### 3. Start the producer (from our distributed users)

- Static producer: in making event in cascade :)

```

python streaming_kafka/producer.py

```

- Dynamic producer: using REST FastAPI

 ```

http://localhost:5500/event?data=11

 ```

  ![alt](assets/transaction-api.png)

#### 4. Alerts bot to slack

![alt](assets/rt.png)