Helping patients know whether they are diabetic or not using Machine Learning

Random Forest Classifier:

Random Forest Classifier is an ensemble algorithm which works with multiple algorithms parallelly. This is a supervised algorithm and it can be used with both classification and regression problems. The output of the new data is estimated either by using majority voting or average voting technique. Since the algorithm works with bagging technique, multiple decision trees are used to provide the output for the specific input. This is a key difference between decision trees and random forests. While decision trees consider all the possible feature splits, random forests only select a subset of those features. Random forest works best with large datasets and high dimensional.

References:

1. https://www.geeksforgeeks.org/random-forest-regression-in-python/

Decision Tree Classifier:

A decision tree is a tool for making decisions and the process for making decisions is in a tree like structure, decision tree is a supervised machine learning algorithm mainly used for predicting the outcome after computing all the attributes. The process flow of Decision tree goes from Root node to leave node i.e., the decision node.

References:

1. https://www.ibm.com/topics/decision-trees
2. https://www.mastersindatascience.org/learning/introduction-to-machine-learning-algorithms/decision-tree/

Logistic Regression:

Logistic Regression is a Supervised algorithm which mostly works in the case of binary classification problems. Logistic regression is a sophisticated algorithm where the data to be trained using this algorithm should be properly presented i.e., Normalized/Scaled, Columns should be Converted to numerical and data should be neat and clean. The output is presented in the form of logit score, where this helps us to predict the likelihood of an event occurring of a given problem. The main reason of getting a S curve in the below chart is that the sigmoid function does the trick of converting the given number in the range between 0 and 1.

Sigmoid(x) = Y = 1 / 1+e -z

References: 

1. https://www.geeksforgeeks.org/understanding-logistic-regression/
2. https://www.ibm.com/topics/logistic-regression

Gradient Boosting Classifier:

Gradient Boosting is a boosting algorithm which consists of ensemble of classification and regression trees. In GB each predictor tries to correct the error made by its predecessor. Unlike the Adaboost algorithm here we don’t change the training instances, instead each predictor/tree is trained by the residual errors caused by the previous trees. All the leaners/trees in the gradient boosting have the same equal weights, since the weights are referred as learning rate which is small in magnitude.