PyData Chicago 2016<\/p>\n
Slides: https:\/\/mheilman.github.io\/pydata_chicago_2016\/#\/<\/a><\/p>\n Grid search over hyperparameters is an important but computationally expensive process in machine learning, particularly for deep learning and tree ensembles. In this talk, I will describe how one can use joblib's recently added custom backend functionality to do distributed grid search on Amazon EC2 for a TensorFlow deep text classifier that follows the scikit-learn estimator API.<\/p>\n","pubDate":"Sun, 28 Aug 2016 00:00:00 +0000","guid":"tag:pyvideo.org,2016-08-28:\/pydata-chicago-2016\/implementing-distributed-grid-search-for-deep-learning-using-scikit-learn-and-joblib.html","category":["PyData Chicago 2016","deep learning","distributed","learning","scikit","search"]},{"title":"High Frequency Trading in MMORPG Markets using Luigi, Pandas, and Scikit learn","link":"https:\/\/pyvideo.org\/pydata-chicago-2016\/high-frequency-trading-in-mmorpg-markets-using-luigi-pandas-and-scikit-learn.html","description":" PyData Chicago 2016<\/p>\n In this talk I\u2019ll describe the system I developed to implement a basic algorithmic trading strategy in the in-game market of an online, multi-player video game. Using this toy model, I\u2019ll walk through the steps involved in setting up a data pipeline with Luigi, analyzing the resulting data with pandas, and identifying important factors and features with scikit-learn.<\/p>\n","pubDate":"Sat, 27 Aug 2016 00:00:00 +0000","guid":"tag:pyvideo.org,2016-08-27:\/pydata-chicago-2016\/high-frequency-trading-in-mmorpg-markets-using-luigi-pandas-and-scikit-learn.html","category":["PyData Chicago 2016","scikit"]},{"title":"Mind the Gap! Bridging the pandas - scikit learn dtype divide","link":"https:\/\/pyvideo.org\/pydata-chicago-2016\/mind-the-gap-bridging-the-pandas-scikit-learn-dtype-divide.html","description":" PyData Chicago 2016<\/p>\n Github: https:\/\/github.com\/TomAugspurger\/mtg\/blob\/master\/MTG.pdf<\/a><\/p>\n This talk briefly introduces the two different data models used by Scikit-Learn (NumPy arrays) and pandas DataFrames. We see why this can cause problems for users of these libraries. Finally, we discuss strategies for managing the differences.<\/p>\n","pubDate":"Sat, 27 Aug 2016 00:00:00 +0000","guid":"tag:pyvideo.org,2016-08-27:\/pydata-chicago-2016\/mind-the-gap-bridging-the-pandas-scikit-learn-dtype-divide.html","category":["PyData Chicago 2016","pandas","scikit"]},{"title":"Learning scikit learn - An Introduction to Machine Learning in Python","link":"https:\/\/pyvideo.org\/pydata-chicago-2016\/learning-scikit-learn-an-introduction-to-machine-learning-in-python.html","description":" PyData Chicago 2016<\/p>\n This tutorial provides you with a comprehensive introduction to machine learning in Python using the popular scikit-learn library. We will learn how to tackle common problems in predictive modeling and clustering analysis that can be used in real-world problems, in business and in research applications. And we will implement certain algorithms as scratch as well, to internalize the inner workings<\/p>\n This tutorial will teach you the basics of scikit-learn. We will learn how to leverage powerful algorithms from the two main domains of machine learning: supervised and unsupervised learning. In this talk, I will give you a brief overview of the basic concepts of classification and regression analysis, how to build powerful predictive models from labeled data. Furthermore, we will go over the basics of clustering analysis to discover hidden structures in unlabeled data. Although it's not a requirement for attending this tutorial, I highly recommend you to check out the accompanying GitHub repository at https:\/\/github.com\/rasbt\/pydata-chicago2016-ml-tutorial<\/a> 1-2 days before the tutorial. During the session, we will not only talk about scikit-learn, but we will also go over some live code examples and code simple machine-learning algorithms from scratch to get the knack of scikit-learn's API.<\/p>\n","pubDate":"Fri, 26 Aug 2016 00:00:00 +0000","guid":"tag:pyvideo.org,2016-08-26:\/pydata-chicago-2016\/learning-scikit-learn-an-introduction-to-machine-learning-in-python.html","category":["PyData Chicago 2016","learning","machine learning","scikit"]},{"title":"Machine Learning with Text in scikit learn","link":"https:\/\/pyvideo.org\/pydata-dc-2016\/machine-learning-with-text-in-scikit-learn.html","description":" PyData DC 2016<\/p>\n Github: https:\/\/github.com\/justmarkham\/pydata-dc-2016-tutorial<\/a><\/p>\n Although numeric data is easy to work with in Python, most knowledge created by humans is actually raw, unstructured text. By learning how to transform text into data that is usable by machine learning models, you drastically increase the amount of data that your models can learn from. In this tutorial, we'll build and evaluate predictive models from real-world text using scikit-learn.<\/p>\n","pubDate":"Fri, 07 Oct 2016 00:00:00 +0000","guid":"tag:pyvideo.org,2016-10-07:\/pydata-dc-2016\/machine-learning-with-text-in-scikit-learn.html","category":["PyData DC 2016","learning","machine learning","scikit"]},{"title":"Image analysis in Python with scipy and scikit image 4","link":"https:\/\/pyvideo.org\/scipy-2014\/image-analysis-in-python-with-scipy-and-scikit-im.html","description":" From telescopes to satellite cameras to electron microscopes, scientists\nare producing more images than they can manually inspect. This tutorial\nwill introduce automated image analysis using the "images as numpy\narrays" abstraction, run through various fundamental image analysis\noperations (filters, morphology, segmentation), and finally complete one\nor two more advanced real-world examples.<\/p>\n Image analysis is central to a boggling number of scientific endeavors.\nGoogle needs it for their self-driving cars and to match satellite\nimagery and mapping data. Neuroscientists need it to understand the\nbrain. NASA needs it to map\nasteroids<\/a> and save\nthe human race. It is, however, a relatively underdeveloped area of\nscientific computing. Attendees will leave this tutorial confident of\ntheir ability to extract information from their images in Python.<\/p>\n Attendees will need a working knowledge of numpy arrays, but no further\nknowledge of images or voxels or other doodads. After a brief\nintroduction to the idea that images are just arrays and vice versa, we\nwill introduce fundamental image analysis operations: filters, which can\nbe used to extract features such as edges, corners, and spots in an\nimage; morphology, inferring shape properties by modifying the image\nthrough local operations; and segmentation, the division of an image\ninto meaningful regions.<\/p>\n We will then combine all these concepts and apply them to several\nreal-world examples of scientific image analysis: given an image of a\npothole, measure its size in pixels compare the fluorescence intensity\nof a protein of interest in the centromeres vs the rest of the\nchromosome. observe the distribution of cells invading a wound site<\/p>\n Attendees will also be encouraged to bring their own image analysis\nproblems to the session for guidance, and, if time allows, we will cover\nmore advanced topics such as image registration and stitching.<\/p>\n The entire tutorial will be coordinated with the IPython notebook, with\nvarious code cells left blank for attendees to fill in as exercises.<\/p>\n","pubDate":"Wed, 09 Jul 2014 00:00:00 +0000","guid":"tag:pyvideo.org,2014-07-09:\/scipy-2014\/image-analysis-in-python-with-scipy-and-scikit-im.html","category":["SciPy 2014","scikit"]},{"title":"Image analysis in Python with scipy and scikit image, Part 1","link":"https:\/\/pyvideo.org\/scipy-2014\/image-analysis-with-scikit-image-part-1.html","description":" From telescopes to satellite cameras to electron microscopes, scientists\nare producing more images than they can manually inspect. This tutorial\nwill introduce automated image analysis using the "images as numpy\narrays" abstraction, run through various fundamental image analysis\noperations (filters, morphology, segmentation), and finally complete one\nor two more advanced real-world examples.<\/p>\n Image analysis is central to a boggling number of scientific endeavors.\nGoogle needs it for their self-driving cars and to match satellite\nimagery and mapping data. Neuroscientists need it to understand the\nbrain. NASA needs it to map\nasteroids<\/a> and save\nthe human race. It is, however, a relatively underdeveloped area of\nscientific computing. Attendees will leave this tutorial confident of\ntheir ability to extract information from their images in Python.<\/p>\n Attendees will need a working knowledge of numpy arrays, but no further\nknowledge of images or voxels or other doodads. After a brief\nintroduction to the idea that images are just arrays and vice versa, we\nwill introduce fundamental image analysis operations: filters, which can\nbe used to extract features such as edges, corners, and spots in an\nimage; morphology, inferring shape properties by modifying the image\nthrough local operations; and segmentation, the division of an image\ninto meaningful regions.<\/p>\n We will then combine all these concepts and apply them to several\nreal-world examples of scientific image analysis: given an image of a\npothole, measure its size in pixels compare the fluorescence intensity\nof a protein of interest in the centromeres vs the rest of the\nchromosome. observe the distribution of cells invading a wound site<\/p>\n Attendees will also be encouraged to bring their own image analysis\nproblems to the session for guidance, and, if time allows, we will cover\nmore advanced topics such as image registration and stitching.<\/p>\n The entire tutorial will be coordinated with the IPython notebook, with\nvarious code cells left blank for attendees to fill in as exercises.<\/p>\n","pubDate":"Wed, 09 Jul 2014 00:00:00 +0000","guid":"tag:pyvideo.org,2014-07-09:\/scipy-2014\/image-analysis-with-scikit-image-part-1.html","category":["SciPy 2014","scikit"]},{"title":"Image analysis in Python with scipy and scikit image, Part 2","link":"https:\/\/pyvideo.org\/scipy-2014\/image-analysis-with-scikit-image-part-2.html","description":" From telescopes to satellite cameras to electron microscopes, scientists\nare producing more images than they can manually inspect. This tutorial\nwill introduce automated image analysis using the "images as numpy\narrays" abstraction, run through various fundamental image analysis\noperations (filters, morphology, segmentation), and finally complete one\nor two more advanced real-world examples.<\/p>\n Image analysis is central to a boggling number of scientific endeavors.\nGoogle needs it for their self-driving cars and to match satellite\nimagery and mapping data. Neuroscientists need it to understand the\nbrain. NASA needs it to map\nasteroids<\/a> and save\nthe human race. It is, however, a relatively underdeveloped area of\nscientific computing. Attendees will leave this tutorial confident of\ntheir ability to extract information from their images in Python.<\/p>\n Attendees will need a working knowledge of numpy arrays, but no further\nknowledge of images or voxels or other doodads. After a brief\nintroduction to the idea that images are just arrays and vice versa, we\nwill introduce fundamental image analysis operations: filters, which can\nbe used to extract features such as edges, corners, and spots in an\nimage; morphology, inferring shape properties by modifying the image\nthrough local operations; and segmentation, the division of an image\ninto meaningful regions.<\/p>\n We will then combine all these concepts and apply them to several\nreal-world examples of scientific image analysis: given an image of a\npothole, measure its size in pixels compare the fluorescence intensity\nof a protein of interest in the centromeres vs the rest of the\nchromosome. observe the distribution of cells invading a wound site<\/p>\n Attendees will also be encouraged to bring their own image analysis\nproblems to the session for guidance, and, if time allows, we will cover\nmore advanced topics such as image registration and stitching.<\/p>\n The entire tutorial will be coordinated with the IPython notebook, with\nvarious code cells left blank for attendees to fill in as exercises.<\/p>\n","pubDate":"Wed, 09 Jul 2014 00:00:00 +0000","guid":"tag:pyvideo.org,2014-07-09:\/scipy-2014\/image-analysis-with-scikit-image-part-2.html","category":["SciPy 2014","scikit"]},{"title":"Image analysis in Python with scipy and scikit image, Part 3","link":"https:\/\/pyvideo.org\/scipy-2014\/image-analysis-with-scikit-image-part-3.html","description":" From telescopes to satellite cameras to electron microscopes, scientists\nare producing more images than they can manually inspect. This tutorial\nwill introduce automated image analysis using the "images as numpy\narrays" abstraction, run through various fundamental image analysis\noperations (filters, morphology, segmentation), and finally complete one\nor two more advanced real-world examples.<\/p>\n Image analysis is central to a boggling number of scientific endeavors.\nGoogle needs it for their self-driving cars and to match satellite\nimagery and mapping data. Neuroscientists need it to understand the\nbrain. NASA needs it to map\nasteroids<\/a> and save\nthe human race. It is, however, a relatively underdeveloped area of\nscientific computing. Attendees will leave this tutorial confident of\ntheir ability to extract information from their images in Python.<\/p>\n Attendees will need a working knowledge of numpy arrays, but no further\nknowledge of images or voxels or other doodads. After a brief\nintroduction to the idea that images are just arrays and vice versa, we\nwill introduce fundamental image analysis operations: filters, which can\nbe used to extract features such as edges, corners, and spots in an\nimage; morphology, inferring shape properties by modifying the image\nthrough local operations; and segmentation, the division of an image\ninto meaningful regions.<\/p>\n We will then combine all these concepts and apply them to several\nreal-world examples of scientific image analysis: given an image of a\npothole, measure its size in pixels compare the fluorescence intensity\nof a protein of interest in the centromeres vs the rest of the\nchromosome. observe the distribution of cells invading a wound site<\/p>\n Attendees will also be encouraged to bring their own image analysis\nproblems to the session for guidance, and, if time allows, we will cover\nmore advanced topics such as image registration and stitching.<\/p>\n The entire tutorial will be coordinated with the IPython notebook, with\nvarious code cells left blank for attendees to fill in as exercises.<\/p>\n","pubDate":"Wed, 09 Jul 2014 00:00:00 +0000","guid":"tag:pyvideo.org,2014-07-09:\/scipy-2014\/image-analysis-with-scikit-image-part-3.html","category":["SciPy 2014","scikit"]}]}}Description<\/h3>
Description<\/h3>
Description<\/h3>
Description<\/h3>
Summary<\/h3>
Description<\/h3>
Summary<\/h3>
Description<\/h3>
Summary<\/h3>
Description<\/h3>
Summary<\/h3>
Description<\/h3>