Placeholder Image

字幕表 動画を再生する

  • YUFENG GUO: On this episode of AI Adventures,

  • find out what Kaggle Kernels are and how to get

  • started using them.

  • Though there's no popcorn in this episode,

  • I can assure you that Kaggle Kernels are popping.

  • Kaggle is a platform for doing and sharing data science.

  • You may have heard about some of their competitions,

  • which often have cash prizes.

  • It's also a great place to practice data science

  • and learn from the community.

  • Kaggle Kernels are essentially Jupyter Notebooks

  • in the browser that can be run right before your eyes,

  • all free of charge.

  • Let me say that again in case you missed it, because this

  • is truly quite amazing.

  • Kaggle Kernels is a free platform

  • to run Jupyter Notebooks in your browser.

  • This means that you can save yourself

  • the hassle of setting up a local environment

  • and have a Jupyter Notebook environment

  • right inside your browser anywhere in the world

  • that you have an internet connection.

  • Not only that-- the processing power for the notebook

  • comes from servers up in the clouds, not your local machine.

  • So you can do a lot of data science and machine learning

  • without heating up your laptop.

  • Kaggle also recently upgraded all their kernels

  • to have more compute power and more memory,

  • as well as extending the length of time

  • that you can run a notebook cell to up to 60 minutes.

  • But OK.

  • Enough of me gushing about Kaggle Kernels.

  • Let's see what it actually looks like.

  • Once we create an account at Kaggle.com,

  • we can choose a dataset that we want

  • to play with and spin up a new kernel or notebook in just

  • a few clicks.

  • The dataset that we started in comes preloaded

  • in the environment of that kernel,

  • so there's no need to deal with pushing

  • a dataset into that machine or waiting for large datasets

  • to copy over a network.

  • Of course, you can still load additional files

  • into the kernel if you want.

  • In our case, we'll continue to play

  • with our fashion and this dataset.

  • It's a dataset that contains 10 categories of clothing

  • and accessory types--

  • things like pants, bags, heels, shirts, and so on.

  • There are 50,000 training samples and 10,000 evaluation

  • samples.

  • Let's explore the dataset in our Kaggle Kernel.

  • Looking at the dataset, it's provided on Kaggle

  • in the form of CSV files.

  • The original data was in a 28 by 28 pixel grayscale images

  • and they've been flattened to become 784 distinct columns

  • in the CSV file.

  • The file also contains a column representing

  • the index, 0 through 9, of that fashion item.

  • Since the dataset is already in the environment, in pandas--

  • this is already loaded--

  • let's use it to read these CSV files into panda's data frames.

  • Now that we've loaded the data into a data frame,

  • we can take advantage of all the features

  • that this brings, which we covered

  • in the previous episode.

  • We'll display the first five rows with Head,

  • and we can run Describe to learn more

  • about the structure of the dataset.

  • Additionally, it would be good to visualize

  • some of these images so that they

  • can have more meaning to us than just rows upon rows of numbers.

  • Let's use matplotlib to see what some of these images look like.

  • Here we'll use the matplotlib.pyplot library--

  • typically imported as PLT--

  • to display the arrays of pixel values as images.

  • We can see that these images, while fuzzy,

  • are indeed still recognizable as the clothing

  • and accessory items that they claim to be.

  • I really like that Kaggle Kernels

  • lets me visualize my data in addition to just processing it.

  • So Kaggle Kernels allows us to work

  • in a fully interactive notebook environment in the browser

  • with little to no setup.

  • And I really want to emphasize that we didn't

  • have to do any sort of Python environment configuration

  • or installation of libraries, which is really cool.

  • Thanks for watching this episode of Cloud AI Adventures.

  • Be sure to subscribe to the channel

  • to catch future episodes as they come out.

  • Now what are you waiting for?

  • Head on over to Kaggle.com and sign up for an account

  • to play with kernels today.

  • [BEEP]

  • Though there's no popcorn in this episode,

  • I can assure you that Kaggle Kernels--

  • [BEEP]

  • You've got to throw harder.

  • SPEAKER: That's horrible timing.

  • [BEEP]

  • YUFENG GUO: Wait, are you going to throw

  • it this way or this way?

  • [BEEP]

  • Though there's no popcorn in this episode,

  • I can assure you that [LAUGHING] Kaggle Kernels are popping.

YUFENG GUO: On this episode of AI Adventures,

字幕と単語

動画の操作 ここで「動画」の調整と「字幕」の表示を設定することができます

B1 中級

Kaggle カーネルの紹介 (Introduction to Kaggle Kernels)

  • 37 2
    alex に公開 2021 年 01 月 14 日
動画の中の単語