Tag

Python

Reading and discussion group: Spatial Analysis in Social Sciences

By |

This reading group moderated by consultants from CSCAR will focus on spatial analysis especially as practiced in social sciences. We will meet for 1.5 to 2 hours every month on the fourth Thursday and discuss one or two chapters from relevant graduate level textbooks. We will focus on the concepts and applications but will also try to discuss the technical details. The format is open-ended, and the key objective is to support learning at different knowledge and skill levels. If there is interest, we will also cover software implementation of techniques in R or Python. We will select reading material that is available via U-M library or freely accessible online.

Readings – We will discuss the following chapters:

(2) Chapter 3: Global and local indicators of spatial association (from Spatial Analysis using Big Data by Yoshiki Yamagata and Hajime Seya)

(3) Chapter 3: Spatial autocorrelation and statistical inference (from Spatial Analysis for Social Science by David Darmofal)

Digital versions of the above two books are available from the UM Library.

CSCAR/MIDAS Workshop on Data, Methodology, and Covid

By |

Zoom link:  https://umich.zoom.us/j/99072338239

 

The second CSCAR/MIDAS workshop on Data, Methodology, and Covid will focus on Covid testing and mortality data from the Covid Tracking Project (covidtracking.com) and Worldometer (worldometer.com).  We will develop insight into how the reported PCR testing data from various US states, and from different countries, can be informative about Covid deaths in those localities.  We will also discuss some of the challenges of estimating the “infection fatality ratio” with this type of data, and conduct some sensitivity analyses to see what the IFR would be in different settings.

The workshop will use intermediate statistical methods (to be reviewed in the workshop), and computations will be done in Python.  Notebooks and links to data will be provided.

Introduction to Deep Neural Networks with Keras/TensorFlow

By |

Deep Neural Networks (DNNs) are used as a machine learning method for both regression and classification problems. Keras is a high-level, Python interface running on top of multiple neural network libraries, including the popular library TensorFlow. In this workshop, participants will learn how to quickly use the Keras interface to perform nonlinear regression and classification with standard fully-connected DNNs, as well as image classification using Convolutional Neural Networks (CNNs). We will also look at regularization techniques and how to deal with under- and over-fitting. All examples will use Python; some familiarity with Python is recommended. Computers will be available to complete exercises. We will run the models using Google Colab, which requires a Google account.

Introduction to Python’s NumPy library

By |

This workshop will introduce you to the NumPy library in Python, which is useful in scientific computing. We will cover NumPy’s n-dimensional array object and associated functions in depth, along with related linear algebra and random number capabilities. Some familiarity with Python is expected. Computers will be available to complete exercises.

Introduction to Deep Neural Networks with Keras/TensorFlow

By |

Deep Neural Networks (DNNs) are used as a machine learning method for both regression and classification problems. Keras is a high-level, Python interface running on top of multiple neural network libraries, including the popular library TensorFlow. In this workshop, participants will learn how to quickly use the Keras interface to perform nonlinear regression and classification with standard fully-connected DNNs, as well as image classification using Convolutional Neural Networks (CNNs). We will also look at regularization techniques and how to deal with under- and over-fitting. All examples will use Python; some familiarity with Python is recommended. Computers will be available to complete exercises. We will run the models using Google Colab, which requires a Google account.

Introduction to Deep Neural Networks with Keras/TensorFlow

By |

Deep Neural Networks (DNNs) are used as a machine learning method for both regression and classification problems. Keras is a high-level, Python interface running on top of multiple neural network libraries, including the popular library TensorFlow. In this workshop, participants will learn how to quickly use the Keras interface to perform nonlinear regression and classification with standard fully-connected DNNs, as well as image classification using Convolutional Neural Networks (CNNs). We will also look at regularization techniques and how to deal with under- and over-fitting. All examples will use Python; some familiarity with Python is recommended. Computers will be available to complete exercises. We will run the models using Google Colab, which requires a Google account.

Introduction to NumPy (Python)

By |

This workshop will introduce you to the NumPy library in Python, which is useful in scientific computing. We will cover NumPy’s n-dimensional array object and associated functions in depth, along with related linear algebra and random number capabilities. Some familiarity with Python is expected. Computers will be available to complete exercises.

Web Scraping with Python

By |

This workshop will provide an overview of how to scrape data from html pages and website APIs using Python. This will mostly be accomplished using the requests, beautifulsoup, and retry modules with the browser developer tools. The workshop is intended for users with basic Python knowledge. Anaconda Python 3 will be used.

Introduction to Deep Neural Networks with Keras/TensorFlow

By |

Deep Neural Networks (DNNs) are used as a machine learning method for both regression and classification problems. Keras is a high-level, Python interface running on top of multiple neural network libraries, including the popular library TensorFlow. In this workshop, participants will learn how to quickly use the Keras interface to perform nonlinear regression and classification with standard fully-connected DNNs, as well as image classification using Convolutional Neural Networks (CNNs). We will also look at regularization techniques and how to deal with under- and over-fitting. All examples will use Python; some familiarity with Python is recommended. Computers will be available to complete exercises. We will run the models using Google Colab, which requires a Google account.

Web Scraping with Python

By |

This workshop will provide an overview of how to scrape data from html pages and website APIs using Python. This will mostly be accomplished using the Python requests, beautifulsoup, retry modules and the browser developer tools. The workshop is intended for users with basic Python knowledge. Anaconda Python 3.5 will be used.