Data preprocessing is considered more important in the machine learning and deep learning field. Most of the time data is not normalized due to so much missing values. Presence of missing values make the data so skewed. Decision whether to estimate (Impute) those missing values or drop those missing values all depends upon missing values analysis. So, missing values handling is considered as primary importance while preprocessing or normalizing the data. I will do the following jobs in the respect of data cleaning and preprocessing: After necessary transformation i can also fed the prepared data to machine learning algorithms to evaluate the model in terms of Accuracy, Precision-Recall Curve, True positive rates (TPR), True Negative Rates (TNR), Area Under the Curve (AUC) and plotting the confusion matrix.