I am relative newbie to data science so please excuse me if its a trivial question.
I have 6 features and want to predict the 'y'. These features are related to y in the training data-set as follows; (x-axis being the feature data points and y axis being the value to be learnt to predict) Feature1 vs y
Feature2 vs y
Feature3 vs y Feature4 vs y
Feature5 vs y
Feature6 vs y Just on observing this it seems that my y can be predicted by using Linear Regression using only Feature 1 & 6. Even if I wanted to use the other features;
a) Can I ?
b) Feature 3,5 & 2,4 can be combined ?

The correlation matrix looks like this;

varCorr = featureMatrix.corr()
sns.heatmap(varCorr, xticklabels=varCorr.columns, yticklabels=varCorr.columns, annot=True)

Correlation matrix

How can include other features for regression or is my dataset such that I have limited options (linear regression using 2 features) and should I look for more/better features ?


You have some pretty obvious colinearity. This has been discussed here a lot (see the colinearity tag) and if you then have additional questions, ask a new question.

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.