Udemy

Learning Path: From Python Programming to Data Science

立即報名
  • 420 名學生
  • 更新於 5/2017
3.4
(39 個評分)
CTgoodjobs 嚴選優質課程,為職場人士提升競爭力。透過本站連結購買Udemy課程,本站將獲得推廣佣金,有助未來提供更多實用進修課程資訊給讀者。

課程資料

報名日期
全年招生
課程級別
學習模式
修業期
20 小時 55 分鐘
教學語言
英語
授課導師
Packt Publishing
評分
3.4
(39 個評分)

課程簡介

Learning Path: From Python Programming to Data Science

Unleash the true potential of Python by learning basic programming and high-end data science techniques.

Python has become the language of choice for most data analysts/data scientists to perform various tasks of data science. If you’re looking forward to implementing Python in your data science projects to enhance data discovery, then this is the perfect Learning Path is for you. Starting out at the basic level, this Learning Path will take you through all the stages of data science in a step-by-step manner.


Packt’s Video Learning Paths are a series of individual video products put together in a logical and stepwise manner such that each video builds on the skills learned in the video before it.


We begin this journey with nailing down the fundamentals of Python. You’ll be introduced to basic and advanced programming concepts of Python before moving on to data science topics. Then, you’ll learn how to perform data analysis by taking advantage of the core data science libraries in the Python ecosystem. You’ll also understand the data visualization concepts better, learn how to apply them and overcome any challenges that you might face while implementing them. Moving ahead, you’ll learn to use a wide variety of machine learning algorithms to solve real-world problems. Finally, you’ll learn deep learning along with a brief introduction to TensorFlow.


By the end of the Learning Path, you’ll be able to improve the efficiency of your data science projects using Python.


Meet Your Experts:


We have combined the best works of the following esteemed authors to ensure that your learning journey is smooth:


Daniel Arbuckle got his Ph.D. in Computer Science from the University of Southern California.


Benjamin Hoff spent 3 years working as a software engineer and team leader doing graphics processing, desktop application development, and scientific facility simulation using a mixture of C++ and Python.


Dimitry Foures is a data scientist with a background in applied mathematics and theoretical physics.


Giuseppe Vettigli is a data scientist who has worked in the research industry and academia for many years.


Igor Milovanović is an experienced developer, with strong background in Linux system knowledge and software engineering education.


Prateek Joshi is an artificial intelligence researcher, published author of five books, and TEDx speaker.



Eder Santana is a PhD candidate on Electrical and Computer Engineering. His thesis topic is on Deep and Recurrent neural networks.

課程章節

  • 5 個章節
  • 240 堂課
  • 第 1 章 Mastering Python - Second Edition
  • 第 2 章 Learning Python Data Analysis
  • 第 3 章 Python Data Visualization Solutions
  • 第 4 章 Python Machine Learning Solutions
  • 第 5 章 Deep Learning with Python

課程內容

  • Familiarize yourself with Python, Learn data analysis using modern processing techniques with NumPy, SciPy, and Pandas, Determine different approaches to data visualization, and how to choose the most appropriate one for your needs, Make 3D visualizations mainly using mplot3d, Work with image data and build systems for image recognition and biometric face recognition, Grasp how to use deep neural networks to build an optical character recognition system


評價

  • C
    Chadwick
    5.0

    clear speaking and simple examples

  • S
    Stephan Michaud
    2.5

    First speaker sounded like a choppy robot. Needed to follow with the transcript instead of voice. The example code is quickly jumped over so badly that it sometimes took me a couple of minutes jumping through / pausing the video to actually see where the stub of code is talked about. Would of appreciated a repo link on Github in order to skip some of the basic parts that contain the boilerplate for the actually interesting sections.

  • M
    Mike Kertser
    3.5

    At the first part of the course, the recorded lecture is done by machine voice instead of human, which is annoying. The visualization is very mechanical. Second part of the course is more humanized, but a little bit unfocused.

  • R
    Robert Schemmel
    2.0

    The instructor doesn't really explain much. He just reads the code out load saying "we're going to go ahead and "blah , blah, blah,..." and then we're going to "blah, blah, blah" but never explains why he's doing anything. I could just as easily read his code from the resources file out loud and I still would have no idea why any of that code is what it is. It makes no sense whatsoever. The whole point of taking a course is to learn why things are done a certain way. I didn't learn any of that. The only value of the course was the downloadable source code in the resources.

立即關注瀏覽更多

本網站使用Cookies來改善您的瀏覽體驗,請確定您同意及接受我們的私隱政策使用條款才繼續瀏覽。

我已閱讀及同意