print('Transparent Window in Package: ',
Counter(ProductTable['Transparent Window in Package']))
print('Processing Agent Stability Index: ',
Counter(ProductTable['Processing Agent Stability Index']))
#---------------------------------------------------------------------------------------------------------------------
#CLEAN DATA
#---------------------------------------------------------------------------------------------------------------------
#Remove Transparent Window in Package from further consideration as non-null values belong to only one category
print(
"Remove Transparent Window in Package from further consideration as non-null values belong to only one category"
)
ProductTable = ProductTable.drop('Transparent Window in Package')
#Also Residual Oxygen, Moisture (%) and Hexanal (ppm) are charecteristics of aged samples.
#Hence is of little use for prediction of shelf life. hence droping those columns also from further analysis
print(
"Also Residual Oxygen, Moisture (%) and Hexanal (ppm) are charecteristics of aged samples. Hence is of little use for prediction of shelf life. hence droping those columns also from further analysis"
)
ProductTable = ProductTable.drop('Moisture (%)')
ProductTable = ProductTable.drop('Residual Oxygen (%)')
ProductTable = ProductTable.drop('Hexanal (ppm)')
#Also drop colomn Study Number/Sample ID as this is not affecting shelf life in anyway
'''ProductTable=ProductTable.drop('Study Number')
ProductTable=ProductTable.drop('Sample ID')'''
#Drop Duplicate Entries iF there are any
pandasDF = ProductTable.to_df()
def drop(self, *args, **kwargs):
return self._fix_(Table.drop(self, *args, **kwargs))
