Messy data is organized and corrected (heterogeneous values, missing entries, large volume of errors) Parts of data in enterprise may be detected unreliable because of, missing values, incomplete, incorrect, inaccurate, irrelevant, etc. these issues will be corrupted the organizations vital data sources. It’s necessary to carry out the Process of replacing missing data with substituted values or modifying or deleting unreliable data. In the following paragraph we will be discussed briefly in some topics. Data cleansing must be considered as a prevent maintenance(PM) in the manufacturers, although there are some data frameworks in the market but we concentrate utilizing python and related technologies for data cleansing, Python’s rich libraries helps to solve many issues, for instance the solution to handle missing value in dataset using KNN (KNN imputer is a scikit-learn class used to fill out or predict the missing values in a dataset) or to handle data anomaly (Isolation Forest is an algorithm for data anomaly detection, It detects anomalies using isolation rather than modeling the normal points). Moreover, organization outlier and anomaly may be detected by utilizing Isolation Forest, one class SVM, local outlier factor, and/or outlier detection algorithms. for example, the One-class SVM is an unsupervised algorithm that learns a decision function for unusual data, or data that’s does not occur regularly, called novelty detection (classifying new data as similar or different to the training set). Practical methods for outlier detection, comprise distance and density of data points. By comparing the local density of an object to the local densities of its neighbors, one can identify regions of similar density, and points that have a substantially lower density than their neighbors, those are outliers. if the data set has many and difficult outliers, we might need to try, outliers’ univariate method (analysis of one variable, calculation of frequencies, central tendency, dispersion), the multivariate (analysis of more than one variable, multiple logistic regression, multivariate analysis of variance, cluster analysis, analysis of variance ANOVA) method and the Makowski error all together. Recommended model, building a model to predict data point distribution, and highlighting outliers which don’t meet a user-defined threshold. Cleaning Techniques comprise, X-Variable family, to apply custom functions, remove duplicates, as well as replace crucial values, Y-Variable sort, to sorts the variables in the active dataset based on the values of the selected data dictionary attributes.