Data completion method based on inverse probability and computer equipment

Abstract

The invention belongs to the technical field of data filling, and particularly relates to a data completion method based on inverse probability and computer equipment, and the method comprises the following steps: filling a missing data set by using a trained improved machine learning filling model, the improvement comprises that a loss function used for training the machine learning filling model is an improved loss function, a data set in the improved loss function is a data set obtained by weighting each piece of data, the weighted weight of the data is obtained according to a corresponding inverse probability, and the lower the inverse probability of the data is, the larger the corresponding weight is; the process of calculating the inverse probability of the data comprises the following steps: carrying out preliminary filling on a data set for training, calculating the missing probability of each piece of data in the data set subjected to preliminary filling, and calculating the inverse probability of each piece of data according to the missing probability of each piece of data in the data set. The filling capability of the machine learning filling model for non-random missing data is enhanced, and the filling precision of the machine learning filling model is improved.

Images