gravatar

datascientiest

amit bhatia

Recently Published

Random Forest
Application of Random Forest algorithm on two datasets (Spam and Cpus). This assignment also includes how to decide the optimum number of trees and predictors ( find the best mtry among sqrt(p)+-1 and ntree among 500, 1000, 2000)
Decision trees and Generalized additive model
Application of Decision trees and Generalized additive model on spam data and cpus data
Ridge and Lasso regression application (Baseball dataset-Hitters)
In this example, I have applied Ridge and Lasso regression on Hitters Baseball dataset. This also captures best Lambda and plot of coefficient vs Lambda (using plot_glmnet)
Application of Lasso (linear) regresssion
Application of Lasso linear regression
Cross validation
Application of cross validation on QDA,LDA, KNN and Linear regression
Linear Regression Model
This post uses a linear regression model to assist in preparing a marketing plan for next year that will result in high product sales.
Gradient descent
In this code I have used the concept of gradient descent using 2d and 3d plots using image and contour function
LDA,QDA, KNN and logistic regression
Application of linear and quadratic discriminant analysis, KNN and logistic regression (ISLR chapter 4)
Publish Document
Social Media Analytics for Marketing strategy
Application of Sapply and other functions
In this assignment, I have used sapply and other functions to derive a matrix from a list
Application of Regression model on Wine data
Regression model using Logistic, Support vector Machine, Multinomial, Ordinal Logistic Regression
PCA analysis of Wine Data
PCA analysis of Wine Data
Petco Facebook sentiment analysis
Petco Facebook sentiment analysis
Diabetes Readmission analysis using decision trees and Random Forest
Approach for imbalanced classification problem Also see http://2bdatascientiest.blogspot.com/2016/12/how-misleading-can-performance-metric.html