Category Archives: Machine Learning

Normal distribution and exercise

In normal distribution standard deviation will be one and mean will be greater than zero, where in standard normal distribution mean will be zero and standard deviation will be one. We can very well convert normal distribution to standard/Z distribution with below formula.Because Z table is very easy to find the probability area. We haveContinue reading “Normal distribution and exercise”

Factorials and Combination

We might have heard about Factorials right from our childhood and also one of the best example learning any programming language. In mathematics, the factorial of a non-negative integer n, denoted by n!, is the product of all positiveintegers less than or equal to n. For example, 5 ! = 5 * 4 * 3 * 2 * 1 = 120 4!Continue reading “Factorials and Combination”

Types of Regression

When I ask what are the types of regression for the beginners, the expected answer will be  linear regression and Logistic regression, because these are the two algorithms that all beginners will start with. Now coming to the point we have five types of regression. Linear regression Logistic regression Polynomial regression Ridge Regression Lasso RegressionContinue reading “Types of Regression”

Deriving Logistic regression equation

Lets derive logistic regression equation. oops we know if we use linear regression we will get continuous values, but we need binary results. We are still not done to find the final logistic regression function. Step 1: we apply some algebra knowledge here to find equation. If we move log function to another side itContinue reading “Deriving Logistic regression equation”

Logistic regression assumptions

Binary Output Variable: Logistic regression is intended for binary (two-class) classification problems. It will predict the probability of an instance belonging to the default class, which can be snapped into a 0 or 1 classification.ˆRemove Noise: Logistic regression assumes no error in the output variable (y), consider removing outliers and possibly misclassified instances from your Continue reading “Logistic regression assumptions”

Synthetic Minority Over-sampling Technique (SMOTE)

Imbalanced data is one of the main issue in classification problem. Why we will have imbalanced data? Let’s say if I have 100 customer who is holding credit card, may be maximum I may have 2 or 3% defaulters and remaining 95 to 97% are perfect payers (This is called presence of minority class ),Continue reading “Synthetic Minority Over-sampling Technique (SMOTE)”

Liner regression assumptions

Linear Assumption. Linear regression assumes that the relationship between your input/independent and output/depended is linear.We can use pearson correlation to check the linearity.if we found there is no linearity between input and output variables We need to transform data to make the relationship linear (e.g. log transform,Box-cox etc..). Data Cleaning. Linear regression assumes that yourContinue reading “Liner regression assumptions”

Parametric Machine Learning

I have a finite number of parameters for example in case of linear regression, we need to find slope(m) and intercept(c), where ever we need to find the parameters we can say it parametric Machine learning algorithm. We can also say, when we work with assumptions like data should be normally distributed, multi collinearity etc…Continue reading “Parametric Machine Learning”

Hyper parameter tuning

Before going to this blog make sure you are aware about any one of the algorithms like Decision tree, Random forest.etc…. Below are the few  parameters that we need for most of the algorithms. Maximum number of leaves per tree Depth of trees. Number of trees in Random forest Learning rate L1 and L2 regularizationContinue reading “Hyper parameter tuning”