Dealing with Raw DataRaw data often contains inconsistencies, missing values, and outliers. Data cleaning therefore is a crucial prerequiste for making accurate and informative visualizations.There are several common strategies to deal with missing values.First, you can identify the missing datapoints using:$$data$.$isnull$().$sum$()$Delete $($try dropna$)$data$.$dropna$($inplace$=$True$)$If there are just a few missing data points, you may want to delete them directly. If there is no data for a particular feature across many samples, you may want to delete that whole feature.Replace by mean$/$median$/$majority $($try fillna$)$data$.$fillna$($data$.$mean$(),$ inplace$=$True$)$The method of using mean$/$median to replace missing values is applicable to integers $($int$)$ and floating point numbers $($float$).$ For these types of data, the mean can be directly calculated and used to fill in missing values.If the data is categorical $($e$.$g$.,$ strings denoting different categories$),$ the mode can be used to replace the missing values.By model $($nearest neighbor method$)$A more sophisticated method for data imputation. Determine the K samples closest to the sample with missing data based on Euclidean distance or correlation analysis, and then use the weighted average of these K values to estimate the missing data of the sample.