There are numerous applications for GANs and many new applications are coming out all the time. But since this article i

Markdown cells in Notebook allow us to be more expressive in how we document our workflow compared to code comments. We could use headers of different font size, ordered or unordered list of items, tables, mathematical formulas, checkboxes, hyperlinks, images and many more with Markdown. Here’s a one-minute introduction to Markdown on its commonly used syntax:

You can have more or less number of Notebooks than the example. That is, the exact number of Notebook is not important. The key idea here is to have logical major tasks (it’s up to you how you define this) spread out, so it’s easier to see the overall workflow and find things. For instance, when writing production-ready code for deployment, we just have to refer to 5_final_pipeline.ipynb.

One popular use of pickling in Data Science is saving trained models or machine learning pipelines into .pkl files. In the following example, we can see that there are couple of models saved in pickle:

Instead of putting your workflow from exploratory data analysis to modelling in one giant Notebook, it’s good to separate them out into a few logical pieces and name each Notebook descriptively. Let’s look at an example:

You may have heard of the DRY principle: Don’t Repeat Yourself. If you haven’t heard of this software engineering principle before, it is about “not duplicating a piece of knowledge within a system”. One of my interpretation of this principle in Data Science is to create functions to abstract away the reoccurring tasks to reduce copy pasting. You can even use classes if it makes sense in your case.

Another good use for pickles is to save objects like lists, dictionaries and the like. For instance, if we assigned manual selection of categorical features to a list in one Notebook and plan to also use it in another Notebook, we can write the list to a pickle file and load it in other Notebooks. This way if we manually make changes to the list, then we only have to do it in one place. Here’s an example code to write or load a pickle file named categorical.pkl where categorical refers to an object in Python (e.g. list).

If we look at this example, we have a couple of Notebooks. From the name, we can see the sequence of Notebooks. For instance, we can guess that 3_base_models.ipynb precedes 4_gbm_model.ipynb while 4_gbm_model.ipynb and 4_rfc_model.ipynb are probably exploring two options in parallel. If we renamed these two to 4A_gbm_model.ipynb and 4B_rfc_model.ipynb, then we can hint an order in the name in a slightly different way as well.

Deep fakes I’m sure everybody has heard of deep fakes from the media. Deep fakes are also GANs where the generator is trained to perform the faking operation, and the critic is tasked with detecting the fake. The generator can be trained for long enough to fool most humans. This is a somewhat dangerous technology and something to be aware of on the internet.

Data scientists do lots of exploration and experimentation. Jupyter Notebook (Notebook from here onwards) is a great tool for exploring and experimenting. However, things can get cluttered and messy quickly when using Notebook. Keeping your workflow clean, organised and easy-to-understand is an important skill and will serve you well in your professional career. In this post, I will share a few of my tips on how to keep your Notebook and workflow more organised.

Here’s a simple way to assess if a function has an intuitive name: If you think a colleague who hasn’t seen the function before could roughly guess what the function does just by looking at its name, then you are on the right track. When documenting these functions, I have adapted a few different styles in a way it made more sense to me. While these examples serve as a working example function for Data Science, I highly encourage you to check out official guides such as below to learn the best practices in naming and documentation conventions, style guides and type hints:

Pickles are not only delicious, but when used in the context of Python, they allow us to save objects as .pkl files. The process of saving the object is referred to as pickling.

http://svt.munich.es/tvk/Video-Besiktas-caykur-Rizespor-v-en-gb-1dzw-3.php

http://agro.ruicasa.com/gms/videos-boca-juniors-v-santos-v-es-ar-1iab-1.php

http://skrs.vidrio.org/udo/Video-olympique-lyonnais-v-lens-v-fr-fr-1hhp-7.php

http://stream88.colomboserboli.com/lvi/videos-metz-v-bordeaux-v-fr-fr-1nvi-11.php

http://svt.munich.es/tvk/Video-Besiktas-caykur-Rizespor-v-en-gb-1bta-1.php

http://old.cocir.org/media/sja/Video-olot-v-osasuna-v-es-es-1vui-16.php

http://agro.ruicasa.com/gms/v-ideos-boca-juniors-v-santos-v-es-ar-1cig-16.php

http://stream88.colomboserboli.com/lvi/videos-metz-v-bordeaux-v-fr-fr-1bah-18.php

http://skrs.vidrio.org/udo/Video-athletic-bilbao-v-barcelona-v-es-es-1wdj-15.php

http://svt.munich.es/tvk/video-Wydad-Athletic-Club-Stade-Malien-v-en-gb-1iyc-.php

http://skrs.vidrio.org/udo/v-ideos-athletic-bilbao-v-barcelona-v-es-es-1oyr-27.php

http://agro.ruicasa.com/gms/Video-boca-juniors-v-santos-v-es-ar-1czl-3.php

http://stream88.colomboserboli.com/lvi/Video-metz-v-bordeaux-v-fr-fr-1hah-7.php

http://old.cocir.org/media/sja/videos-olot-v-osasuna-v-es-es-1rld-7.php

http://svt.munich.es/tvk/Video-Wydad-Athletic-Club-Stade-Malien-v-en-gb-1ygu30122020-5.php

http://vert.actiup.com/eil/videos-Horoya-Racing-Club-Dabidjan-v-en-gb-1qiy30122020-9.php

http://svt.munich.es/tvk/Video-Wydad-Athletic-Club-Stade-Malien-v-en-gb-1anc-24.php

http://skrs.vidrio.org/udo/Video-athletic-bilbao-v-barcelona-v-es-es-1miy-6.php

http://old.cocir.org/media/sja/v-ideos-olot-v-osasuna-v-es-es-1rwn-23.php

http://agro.ruicasa.com/gms/v-ideos-boca-juniors-v-santos-v-es-ar-1nrg-21.php

ics, and these themes are all items we must contend with during our Saturn Returns: the bones, boredom, brutality, business, calculation, celibacy, chronic ailments, common sense, construction, conventionality, debts, depression, deprivation, diligence, discipline, duty, endurance, envy, failure, fasting, foundations, habits, hibernation, hindsight, humility, inferiority, integrity, isolation, kinks, losses, materialism, monogamy, mortality, neglect, obstacles, old age, oppression, dull and heavy pains, patience, the past, patterns, perseverance, pessimism, poverty, the practical, privacy, rejection, remorse, responsibility, rigidity, sadness, self-control, sobriety, stabilization, stagnation, stillness, structure, time, trials, tribulations, troubles, unhappiness, vocations, want, wealth, woes, work, and worry.

#### Headers # Header 1 ## Header 2 #### Styles *Italic*, **bold**, _underscore_, ~~strikethrough~~ #### Hyperlink [hyperlink](https://www.markdownguide.org/) #### Table | Default | Left-aligned | Center-aligned | Right-aligned | |---------|:-------------|:--------------:|--------------:| | Default | Left | Center | Right | #### Others * Bulleted item 1 * Bulleted subitem 1 * Bulleted item 2 *** 1. Ordered item 1 1.1. Ordered subitem 1 2. Ordered item 2 *** - [ ] Unchecked box - [x] Checked box

Super-resolution Super-resolution refers to taking a low-quality image and generating a high-quality image from it. Nvidia’s new DLSS could be using this technique. Jeremey Howard from fast.ai has an extremely interesting approach called the noGAN approach for super-resolution. This process is a sort of pretraining for GANs, where high-quality images are converted to lower quality images for training data of the Generator, and the critic is pre-trained on the generated images. This way, both the generator and critic have a head start, and this method is found to significantly improve training time for GANs.

Deep fakes I’m sure everybody has heard of deep fakes from the media. Deep fakes are also GANs where the generator is trained to perform the faking operation, and the critic is tasked with detecting the fake. The generator can be trained for long enough to fool most humans. This is a somewhat dangerous technology and something to be aware of on the internet.