Text-Classification
Text-Classification copied to clipboard
data_train in CNN.ipynb
Line 5 of block 6 has a variable data_train which comes out of blue.
Please see if it is the case of missing block of naming inconsistency.
Thanks R
What is the data format?
Thanks
"Shape of dataset (100, 2) Index(['message', 'class'], dtype='object') No. of unique classes 17"
It looks like 2 columns, text (message), and class_identifier (class) respectively. This is read into a pandas data frame. In this case it's read from an excel file/spreadsheet, but the same can be done with a csv, tsv, etc.