Skip to content
Resources for the second meetup
Jupyter Notebook Other
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
2ndMeetup-Resources
.DS_Store
.gitattributes
LICENSE
README.md

README.md

School Of AI - Tools in the world of AI (2nd Meetup)

Hello world, Here is the comprehensive list of all the information we discussed today in our meetup.

Presenters

Presentation Links

What is NumPy

NumPy is the fundamental package for scientific computing in Python. It is a Python library that provides a multidimensional array object, various derived objects (such as masked arrays and matrices), and an assortment of routines for fast operations on arrays, including mathematical, logical, shape manipulation, sorting, selecting, I/O, discrete Fourier transforms, basic linear algebra, basic statistical operations, random simulation and much more.

Read more about NumPy in the documentation

Read the following documents for concise information to what you need to know about NumPy

Try it out yourself

What is Pandas

Pandas is an open source, BSD-licensed library providing high-performance, easy-to-use data structures and data analysis tools for the Python programming language.

Pandas is a NumFOCUS sponsored project. This will help ensure the success of development of pandas as a world-class open-source project, and makes it possible to donate to the project.

Read more about Pandas in the documentation

The following set of notebooks should help you learn pandas in detail. Source

The goal of the following cookbook is to give you some concrete examples forgetting started with pandas. The docs are really comprehensive. However, I've often had people tell me that they have some trouble getting started, so these are examples with real-world data, and all the bugs and weirdness that that entails.

How to use these notebooks

pip install ipython pandas numpy tornado pyzmq jinja2 matplotlib

Or better yet, while in conda environment use the conda command to install the dependencies.

Create a new environment

conda create -name pandasEnv
conda activate pandasEnv

Or go to the console and select, open with terminal and run the following command.

conda install ipython pandas numpy tornado pyzmq jinja2 matplotlib python=2.7 notebook jupyter jupyterlab_launcher jupyterlab

What is matplotlib

Matplotlib is a Python 2D plotting library which produces publication quality figures in a variety of hardcopy formats and interactive environments across platforms. Matplotlib can be used in Python scripts, the Python and IPython shells, the Jupyter notebook, web application servers, and four graphical user interface toolkits.

Matplotlib tries to make easy things easy and hard things possible. You can generate plots, histograms, power spectra, bar charts, errorcharts, scatterplots, etc., with just a few lines of code.

The following set of notebooks should help with learning matplotlib in more detail.

Other resources

What is TensorFlow

  • Need help with the installation? Please visit the installation documentation
    • If you to the environements tab in the anaconda application, and then select the libraries that are currently Not Installed you can add the TensorFlow library to your environment easily.

Example Notebooks

  • The first 3-4 notebooks would be aimed at giving you a taste of TensorFlow and how it can be used in real world application.
  • The source of the following notebooks gives a brief overview of the tensorflow libraries.
    • Please note that you do not have to know TensorFlow at all. Moreover, you're not expected to understand anything from the notebooks. It is there to just give you tase as to what can be done.
  • The first notebook is a basic Classification Notebook using the Fashion MNIST dataset which contains 70,000 grayscale images in 10 categories.
    • This guide trains a neural network model to classify images of clothing, like sneakers and shirts. It's okay if you don't understand all the details, this is a fast-paced overview of a complete TensorFlow program with the details explained as we go. The images show individual articles of clothing at low resolution (28 by 28 pixels), as seen here:
Fashion MNIST sprite
Figure 1. Fashion-MNIST samples (by Zalando, MIT License).
 
  • The second notebook is a text classification example that makes use of the reviews from IMBD dataset as positive or negative.
    • This notebook uses tf.keras, a high-level API to build and train models in TensorFlow. For a more advanced text classification tutorial using tf.keras, see the MLCC Text Classification Guide.
  • The third notebook is regressions notebook for the boston housing prices dataset.
    • This notebook builds a model to predict the median price of homes in a Boston suburb during the mid-1970s. To do this, we'll provide the model with some data points about the suburb, such as the crime rate and the local property tax rate.
  • The fourth notebook is focussed towards overfitting and underfitting data.
    • In this notebook, we'll explore two common regularization techniques—weight regularization and dropout—and use them to improve our IMDB movie review classification notebook.

Summary for TensorFlow

Just listing down the notebooks for easy reference.

Learn TensorFlow Basics

I've set up a series of notebook to get guys familiar with the world of TensorFlow from the very basics. In these notebooks you'll also find some simple questions based on what was done either in the previous notebooks or in the current notebook you're working.

:P

You can’t perform that action at this time.