homework 3 .docx - To introduce we try to define which model between linear regression principal component regression and Partial list square regression

homework 3 .docx - To introduce we try to define which...

This preview shows page 1 - 6 out of 6 pages.

To introduce we try to define which model between linear regression , principal component regression and Partial list square regression matches the best to estimate the relation between solubility and chemical structure. >data(solubility) load solubility data set >ls() data transformation stored Fingerprints are binary sequence of numbers which represents the presence or not of specific molecular substructure. Here we are looking of columns without binary. Then grep search for matches to column name that contain the patern “FP”. After that we find a correlation among 20 predictors and display the chart that show a correlation between number of atoms and the mol weight. Remove predictors that have very high correlations greater than the threshold value of 0.9 the random number seed is set prior to modeling so that the results can be reproduced We created a control function using 10 fold cross validation resampling technique
Image of page 1

Subscribe to view the full document.

Image of page 2
Image of page 3

Subscribe to view the full document.

Image of page 4
Image of page 5

Subscribe to view the full document.

Image of page 6

Unformatted text preview: Create a linear regression model which fit with choose predictors lmTune tune is a function which hyperparameters of statistical methods using a grid search over supplied parameter ranges RMSE Rsquared show us that 87,93% of data is explained by the model. Build principal component model with tune function choose 35 rows on the grids RMSE is 0,73 and Rsquarred 0,8714 We ask to display PCR preventive model vs reality plsTune Run the function Partial Least Square To display RMSE and Rsquared of the ncomp choiced before. RMSE is 0,69 and Rsquared 0,88 with The plot show the correlation between predictive model and actual outcome. To conclude we can say that the PLS model which match the best with a prediction of 88.37% for only 20 components against PCR with Rsquared of 0,8714 with 35 components....
View Full Document

  • Spring '14

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern

Ask Expert Tutors You can ask You can ask ( soon) You can ask (will expire )
Answers in as fast as 15 minutes