In this article, we’ll look at how we can save a model that we have trained in Keras. First, we’ll create a very simple CNN model using Keras and train that model on the Fashion MNIST data set. Then I will show you how to save and subsequently restore that trained model and perform the prediction. I understand that saving a model for a very basic problem like fashion MNIST might sound trivial. However, think of a situation where we are training a very complex model which takes a tremendous amount of time, like hours, or even days, to train. In such cases, it is often useful to save the model ..read more

Matplotlib is one of the most commonly used tools for plotting in Python. In this article, we’ll look at how to use matplotlib to create some basic plots, such as line plots, pie chart, histograms, bar and scatter plots. So, let’s get started with the line plot. Line Plots: This is the most basic type of plot. A line plot is typically used to plot the relationship between two numerical variables. Below is a code snippet for plotting the number of ice creams sold during a week. import pandas as pd import matplotlib.pyplot as plt #number of ice creams sold during a week ice_cream = [35,33 ..read more

In this article, we’ll discuss some of the NLP preprocessing techniques while handling the text data. As you have guessed from the title we’ll use spaCy for most of our tasks in this article. So, if you don’t have it installed see the spaCy installation instructions to get spaCy on your computer. Tokenization: When we are working with text data, the first thing we have to do is to divide the text into list of tokens. This is called tokenization. Tokenization is the process of breaking up a text sequence into tokens which can be sentences, words, numbers or punctuation marks. Per ..read more

In this article, we’ll discuss some of the NLP preprocessing techniques while handling the text data. As you have guessed from the title we’ll use spaCy for most of our tasks in this article. So, if you don’t have it installed see the spaCy installation instructions to get spaCy on your computer. Tokenization: When we are working with text data, the first thing we have to do is to divide the text into list of tokens. This is called tokenization. Tokenization is the process of breaking up a text sequence into tokens which can be sentences, words, numbers or punctuation marks. Per ..read more

In this article we’ll learn some of the commonly used math functions in Pandas. Let’s get started. The abs() function: The first one we are going to see is the abs() function. This function returns the absolute values for the elements in the data frame. import pandas as pd import numpy as np df = pd.DataFrame() df['A'] = np.random.randint(-100,100, size=10) print(df) A 0 -57 1 -49 2 -8 3 9 4 72 5 -57 6 -72 7 3 8 80 9 13 There are few negative values. Let’s apply the abs function. df['A'] = df['A'].abs() print(df) A 0 57 1 49 2 8 3 9 4 72 5 57 6 72 7 3 8 80 9 13 Th ..read more

In the Part 1 of Introduction to Neural Networks we learned about one of the simplest artificial neuron called McCulloch-Pitts neuron and implemented it in python. The problem with M-P neuron is that there is actually no learning involved. The weights are set manually. In this article we’ll see Perceptron which is an improvement from the M-P neuron. Unlike M-P neuron the perceptron can learn the weights over time. We will also see how to train a Perceptron from scratch to classify logical operations like AND or OR. Perceptron: A perceptron is basically a binary classifier. It is an algorithm f ..read more

In this article we’ll see how to perform Brain tumor segmentation from MRI images. We’ll try different architectures which are popular for image segmentation problems. Let’s start off by defining what our business problem is. Business Problem: A brain tumor is an abnormal mass of tissue in which cells grow and multiply abruptly, which remains unchecked by the mechanisms that control normal cells. Brain tumors are classified into benign tumors or low grade (grade I or II ) and malignant or high grade (grade III and IV).Benign tumors are non-cancerous and are considered to be non-progressive, th ..read more

A neural network is an algorithm whose design was inspired by the functioning of the human brain. It tries to emulate the basic functions of the brain. Due to the intentional design of ANNs as conceptual model of human brain let’s first understand how biological neurons work. Later we can extrapolate that idea into mathematical models. The below diagram is a model of the biological neuron   It consists of three primary parts, viz., the dendrites, soma, and the axon.  Dendrites are the receiver of the signals for the neuron. The dendrites collect the signal and pass it to soma, which ..read more

Table Of Contents:     1) Business Problem     2) Data description     3) Exploratory Data Analysis     4) Data preparation/Feature engineering     5) Model Building     6) Submit model on Kaggle  1. Business Problem  1.1) Problem Description: Elo Merchant Category Recommendation” challenge that is about helping understand customer loyalty using machine learning. Elo, a large Brazilian payment brand (focused on debit and credit cards), has built machine learning models t ..read more

Decision trees are one of the most powerful and widely used supervised models that can either perform regression or classification. In this tutorial, we’ll concentrate only on the classification setting. A decision tree consists of rules that we use to formulate a decision on the prediction of a data point. Basically, it’s a sequence of simple if/else rulings. We can visualize the decision tree as a structure based on a sequence of decision processes on which a different outcome can be expected.   Source: Machine learning Quick Reference Beginning at the root node of a tree, the decision n ..read more