The popular K-Nearest Neighbors (KNN) algorithm is used for regression and classification in many applications such as recommender systems, image classification, and financial data forecasting. It is the basis of many advanced machine learning techniques (e.g., in information retrieval). There is no doubt that understanding KNN is an important building block of your proficient computer … Read more
If there is one clustering algorithm you need to know – whether you are a computer scientist, data scientist, or machine learning expert – it’s the K-Means algorithm. In this tutorial drawn from my book Python One-Liners, you’ll learn the general idea and when and how to use it in a single line of Python … Read more
Problem Formulation Given a TensorFlow variable created with tf.Variable(). As this variable may have changed during the training process (e.g., using assign()), you want to get the current value of it. How to accomplish this in TensorFlow? Sessions Are Gone in TensorFlow 2 In TensorFlow 1, computations were performed within Sessions. That’s why many people … Read more
Scikit-learn has a library of transformers to preprocess a data set. These transformers clean, generate, reduce or expand the feature representation of the data set. These transformers provide the fit(), transform() and fit_transform() methods. The fit() method identifies and learns the model parameters from a training data set. For example, standard deviation and mean for … Read more
Summary: The best way to plot a Confusion Matrix with labels, is to use the ConfusionMatrixDisplay object from the sklearn.metrics module. Another simple and elegant way is to use the seaborn.heatmap() function. Note: All the solutions provided below have been verified using Python 3.9.0b5. Problem Formulation Imagine the following lists of Actual and Predicted values … Read more
There are two ways to convert a Tensor to a NumPy array: TensorFlow version 2.x — use tensor.numpy() TensorFlow version 1.x — use tensor.eval(session=tf.compat.v1.Session()) Let’s dive into these two methods in greater detail. Method 1: Explicit Tensor to NumPy Array Conversion in TensorFlow 2.x To convert a tensor t to a NumPy array in TensorFlow … Read more
To check your TensorFlow version in your Jupyter Notebook such as Google’s Colab, use the following two commands: import tensorflow as tf This imports the TensorFlow library and stores it in the variable named tf. print(tf.__version__) This prints the installed TensorFlow version number in the format x.y.z. The following code example uses the dunder attribute … Read more
A couple of years ago, I fell into the habit of creating cheat sheets when exploring certain areas in the programming space. Over time, hundreds of thousands of Finxters have downloaded and used them in their own learning journeys. However, the cheat sheets are largely scattered around many different locations on the Finxter ecosystem. And … Read more
This article is a collection of useful machine learning cheat sheets focusing on the Python libraries such as Theano, Keras, TensorFlow, PyTorch, NetworkX, and other ML-related Python libraries. You may want to check out these great resources that cover many of these topics at once: https://becominghuman.ai/cheat-sheets-for-ai-neural-networks-machine-learning-deep-learning-big-data-science-pdf-f22dc900d2d7 https://gto76.github.io/python-cheatsheet/ https://www.pythonsheets.com/ Theano Cheat Sheets Theano is a Library … Read more
? This tutorial will show you the most simple and straightforward way to implement linear regression in Python—by using scikit-learn’s linear regression functionality. I have written this tutorial as part of my book Python One-Liners where I present how expert coders accomplish a lot in a little bit of code. Feel free to bookmark and download … Read more
Minute 1: Install Dash Type the following command in your terminal/shell. Windows, macOS: Linux, Ubuntu: Minute 2: Create Minimal Dash Project File “app.py” Copy&paste the code into a new file called “app.py” in a folder – with path /path/to/dash_app/app.py: Minute 3: Run Dash App Open a terminal or shell in the /path/to/dash_app/ and run python … Read more
AI is hard! Transforming tensors, cleaning data, building complicated networks- these are all specialized skills that can take months or even years to learn. But the times are a-changin’. Businesses understand that adopting state-of-the-art AI is no longer a choice. Of course, those burdened with actually implementing that AI are the software devs. High-level talk … Read more