• I3_757344
    了解作者
  • 35.6MB
    文件大小
  • zip
    文件格式
  • 0
    收藏次数
  • VIP专享
    资源类型
  • 0
    下载次数
  • 2022-04-21 03:22
    上传日期
项目概况 在这个项目(使用AWS和Kubernetes进行大规模微服务)中,我应用了在本课程中获得的技能来运行机器学习微服务API,并且在所有项目工作中都使用了AWS cloud9 IDE。 有一个经过预先训练的sklearn模型,已经过训练,可以根据几个功能来预测波士顿的房价,例如房屋中的平均房间和有关高速公路通行性的数据,师生比例等等。要了解有关数据的更多信息,该数据最初来自Kaggle,位于。该项目测试了在提供的文件app.py中运行Python flask应用程序的能力,该文件通过API调用提供了有关房价的预测(推断)。该项目可以扩展到任何预先训练的机器学习模型,例如用于图像识别和数据标记的模型。 项目任务 该项目的目标是使用来运行这种工作的机器学习微服务,这是一个用于自动化容器化应用程序管理的开源系统。在此项目中,将应用以下概念: 使用linting测试您的项目代码 完成一个Do
devops-master.zip
  • devops-master
  • model_data
  • boston_housing_prediction.joblib
    665.5KB
  • housing.csv
    47.9KB
  • .circleci
  • config.yml
    1.1KB
  • output_txt_files
  • kubernetes_out.txt
    902B
  • docker_out.txt
    642B
  • resize.sh
    1.6KB
  • upload_docker.sh
    339B
  • app.py
    1.1KB
  • minikube-linux-amd64
    57MB
  • Dockerfile
    232B
  • requirements.txt
    218B
  • my.profile
    155B
  • shortcut.sh
    438B
  • README.md
    2.3KB
  • Makefile
    252B
  • make_prediction.sh
    384B
  • run_docker.sh
    249B
  • my_credential.txt
    9B
  • run_kubernetes.sh
    575B
  • kubectl
    38.4MB
内容介绍
[![smita-hub](https://circleci.com/gh/smita-hub/devops.svg?style=svg)](https://circleci.com/gh/smita-hub/devops) ### Project Overview In this project(Microservices at scale using AWS and Kubernetes), I have applied the skills I have acquired in this course to operationalize a Machine Learning Microservice API and I have used AWS cloud9 IDE for all my project work. There is a pre-trained, `sklearn` model that has been trained to predict housing prices in Boston according to several features, such as average rooms in a home and data about highway access, teacher-to-pupil ratios, and so on. To read more about the data, which was initially taken from Kaggle, on [the data source site](https://www.kaggle.com/c/boston-housing). This project tests the ability to operationalize a Python flask app—in a provided file, `app.py`—that serves out predictions (inference) about housing prices through API calls. This project could be extended to any pre-trained machine learning model, such as those for image recognition and data labeling. ### Project Tasks The project goal is to operationalize this working, machine learning microservice using [kubernetes](https://kubernetes.io/), which is an open-source system for automating the management of containerized applications. In this project below concepts are applied: * Test your project code using linting * Complete a Dockerfile to containerize this application * Deploy your containerized application using Docker and make a prediction * Improve the log statements in the source code for this application * Configure Kubernetes and create a Kubernetes cluster * Deploy a container using Kubernetes and make a prediction * Upload a complete Github repo with CircleCI to indicate that your code has been tested ## Setup the Environment * Create a virtualenv and activate it. * Run `make install` to install the necessary dependencies required for running the application like Hadoling and from requirements.txt ### Running `app.py` in different cases. 1. Standalone in my local: `python app.py` 2. To run in Docker: `./run_docker.sh` 3. To run in Kubernetes: `./run_kubernetes.sh` ### Kubernetes Steps * Setup and Configure Docker locally * Setup and Configure Kubernetes locally * Setup and Configure Minikube locally * Create Flask app in Container * Run via kubectl
评论
    相关推荐