تبلیغات

آموزش اصولی یادگیری ماشینی و AI با پایتون و Jupyter Notebook

دسته بندی ها: یادگیری ماشینی (Machine Learning) ، هوش مصنوعی ، آموزش های INE ، آموزش پایتون (Python) ، آموزش Jupyter Notebook

این دوره ویدیویی 8 ساعته  نشان می دهد که چگونه AWS و Google Cloud Platform را می توان برای حل مشکلات تجاری واقعی در یادگیری ماشینی و AI مورد استفاده قرار داد. این دوره چگونگی شروع کار با پایتون را از طریق Jupyter Notebook آغاز می کند و پس از آن به جزئیات کتابخانه های علم داده در پایتون، از جمله Pandas، Seaborn، scikit-learn و تنسورفلو، بررسی EDA و نحوه انجام EDA در Python و Jupyter Notebook می پردازد.

سرفصل:

  • معرفی دوره
  • درس 1: معرفی برنامه نویسی علم داده با مبانی پایتون
  • درس 2: نوشتن و اعمال توابع
  • درس 3: استفاده از ساختارهای کنترل پایتون
  • درس 4: نوشتن، استفاده و استقرار کتابخانه ها در پایتون
  • درس 5: درک کلاس های پایتون
  • درس 6: عملیات IO در پایتون و Pandas
  • درس 7: یادگیری Software Carpentry
  • درس 8: ایجاد Data Engineering API با Flask و Pandas
  • درس 9: پروژه ML و قدرت اجتماعی NBA EDA
  • درس 10: درک یادگیری ماشینی متوسط
  • درس 11: خط لوله های AI و AWS Cloud ML مبتنی بر پایتون
  • درس 12: خط لوله های AI و Google Compute Platform ML مبتنی بر پایتون
  • درس 13: ایجاد ابزارهای یادگیری ماشینی خط فرمان
  • و غیره
آیا این نوشته را دوست داشتید؟
Essential Machine Learning and AI with Python and Jupyter Notebook Publisher:INE Author:Noah Gift Duration:8 h


This 8-hour LiveLesson video course shows how AWS and Google Cloud Platform can be used to solve real-world business problems in Machine Learning and AI. Noah Gift covers how to get started with Python via Jupyter Notebook, and then proceeds to dive into nuts and bolts of Data Science libraries in Python, including Pandas, Seaborn, scikit-learn, and TensorFlow.
EDA, or exploratory data analysis, is at the heart of the Machine Learning; therefore, this series also highlights how to perform EDA in Python and Jupyter Notebook. Software engineering fundamentals tie the series together, with key instruction on linting, testing, command-line tools, data engineering APIs, and more.
Table of Contents
Introduction
Essential Machine Learning and AI with Python and Jupyter Notebook: Introduction 00:02:52
Lesson 1: Introducing Data Science Coding with Python Fundamentals
Learning objectives 00:01:00
1.1 Use IPython, Jupyter, and Python REPL 00:03:00
1.2 Write procedural statements 00:04:08
1.3 Use strings and string formatting 00:07:02
1.4 Use numbers and arithmetic operations 00:09:27
1.5 Interact with data structures 00:09:59
1.6 Write and run scripts 00:04:37
1.7 Summary 00:01:09
Lesson 2: Writing and Applying Functions
Learning objectives 00:01:04
2.1 Write functions 00:09:04
2.2 Utilize functional programming concepts 00:07:32
2.3 Utilize lazy evaluated functions 00:03:52
2.4 Utilize decorators 00:03:33
2.5 Make classes behave like functions 00:02:18
2.6 Apply a function to a Pandas DataFrame 00:06:38
2.7 Use Python lambdas 00:02:35
2.8 Summary 00:01:26
Lesson 3: Using Python Control Structures
Learning objectives 00:01:01
3.1 Create loops 00:03:42
3.2 Use if/else/break/continue/pass statements 00:05:46
3.3 Understand try/except 00:04:32
3.4 Understand generator expressions 00:06:39
3.5 Understand list comprehensions 00:03:18
3.6 Understand sorting 00:04:22
3.7 Understand Python regular expressions 00:03:03
3.8 Summary 00:01:02
Lesson 4: Writing, Using, and Deploying Libraries in Python
Learning objectives 00:00:42
4.1 Write and use libraries in Python 00:02:12
4.2 Use pipenv, pip, virtualenv and conda 00:04:09
4.3 Deploy Python code to production 00:07:30
4.4 Summary 00:00:36
Lesson 5: Understanding Python Classes
Learning objectives 00:00:51
5.1 Understand differences between classes and functions 00:02:08
5.2 Make and interact with simple objects 00:02:52
5.3 Understand class inheritance 00:05:25
5.4 Interact with special class methods 00:02:01
5.5 Create metaclasses 00:02:37
5.6 Summary 00:00:55
Lesson 6: IO Operations in Python and Pandas
Learning objectives 00:01:05
6.1 Use write file operations 00:03:15
6.2 Use read file operations 00:01:43
6.3 Use serialization techniques 00:09:24
6.4 Use Pandas DataFrames 00:08:35
6.5 Use Google Sheets with Pandas DataFrames 00:04:07
6.6 Use concurrency methods in Python 00:14:03
6.7 Summary 00:01:24
Lesson 7: Learning Software Carpentry
Learning objectives 00:00:39
7.1 Build a new Data Science Github project layout 00:05:17
7.2 Use git and Github to manage changes 00:08:22
7.3 Use CircleCI and AWS Code Build to build and test a project sourced from Github 00:06:29
7.4 Use static analysis and testing tools: pylint, pytest, and coverage 00:06:00
7.5 Test Jupyter Notebooks 00:02:26
7.6 Summary 00:03:14
Lesson 8: Creating a Data Engineering API with Flask and Pandas
Learning objectives 00:00:58
8.1 Make a project layout 00:03:36
8.2 Lay out a Makefile for a project 00:01:33
8.3 Create a command-line tool for Pandas aggregation 00:04:00
8.4 Make plugins to pass to Pandas 00:02:42
8.5 Write the Flask API 00:07:23
8.6 Integrate Swagger documentation 00:03:21
8.7 Benchmark Python projects 00:03:12
8.8 Integrate testing and linting 00:05:35
8.9 Summary 00:00:46
Lesson 9: Walking through Social Power NBA EDA and ML Project
Learning objectives 00:01:21
9.1 Data Collection of Social Media Data 00:08:07
9.2 Import and merge DataFrames in Pandas 00:04:02
9.3 Understand correlation heatmaps and pairplots 00:04:39
9.4 Use linear regression in Python 00:10:30
9.5 Use ggplot in Python 00:01:47
9.6 Use k-means clustering 00:12:27
9.7 Use PCA with scikit-learn 00:02:04
9.8 Use ML classification prediction with scikit-learn 00:01:32
9.9 Use ML regression prediction with scikit-learn 00:01:34
9.10 Use Plotly for interactive data visualization 00:12:55
9.11 Summary 00:02:52
Lesson 10: Understanding Intermediate Machine Learning
Learning objectives 00:00:34
10.1 Overview of AI, Machine Learning and Deep Learning 00:03:18
10.2 Big Data 00:06:06
10.3 Working with recommendation systems 00:04:46
10.4 Summary 00:01:44
Lesson 11: Python based AWS Cloud ML and AI Pipelines
Learning objectives (or Topics) 00:01:23
11.1 Use AWS Web Services 00:12:51
11.2 Use Boto 00:06:31
11.3 Use AWS Lambda development with Chalice 00:13:03
11.4 Use AWS DynamoDB 00:07:36
11.5 Use AWS Step functions 00:04:57
11.6 Use AWS Batch for ML jobs 00:08:27
11.7 Use AWS Sagemaker 00:10:28
11.8 Use AWS Comprehend for NLP 00:07:24
11.9 Use AWS Rekognition API 00:04:36
11.10 Summary 00:01:27
Lesson 12: Python based Google Compute Platform ML and AI Pipelines
Learning objectives (or Topics) 00:01:06
12.1 Perform Colaboratory basics 00:03:40
12.2 Use Advanced Colab Features 00:20:34
12.3 Perform Datalab basics 00:03:21
12.4 Use TPUS for deep learning 00:03:35
12.5 Use Google Big Query 00:03:15
12.6 Use Google Machine Learning Services 00:02:37
12.7 Use Google Sentiment Analysis API 00:04:26
12.8 Use Google Computer Vision API 00:01:50
12.9 Summary 00:03:02
Lesson 13: Creating Command-line Machine Learning Tools
Learning objectives 00:00:17
13.1 Walk through Spot Price Machine Learning 00:05:43
13.2 Walk through DevML 00:07:17
13.3 Summary 00:00:46
Lesson 14: Datascience: Case Study Social Power in the NBA
14.1 Datascience: Case Study Social Power in the NBA 00:18:35
Summary
Essential Machine Learning and AI with Python and Jupyter Notebook: Summary 00:00:50

پیشنهاد فرادرس