remove outliers python pandas
#------------------------------------------------------------------------------ # accept a dataframe, remove outliers, return cleaned data in a new dataframe # see http://www.itl.nist.gov/div898/handbook/prc/section1/prc16.htm #------------------------------------------------------------------------------ def remove_outlier(df_in, col_name): q1 = df_in[col_name].quantile(0.25) q3 = df_in[col_name].quantile(0.75) iqr = q3-q1 #Interquartile range fence_low = q1-1.5*iqr fence_high = q3+1.5*iqr df_out = df_in.loc[(df_in[col_name] > fence_low) & (df_in[col_name] < fence_high)] return df_out