Principal Component Analysis Demystified

We see that column "Post Weekday" has less variance and column "Lifetime Post Total Reach" has comparatively more variance. Therefore, if we apply PCA without standardization of data then more weightage will be given to the "Lifetime Post Total Reach" column during the calculation of "eigenvectors" and "eigenvalues" and we will get biased principal components. Now we will standardize the dataset using RobustScaler of sklearn library. Other ways of standardizing data are provided in sklearn like StandardScaler and MinMaxScaler and can be chosen as per the requirement. Unless specified, the number of principal components will be equal to the number of attributes.