Text Error while trying to train the data - nlp

Question

Getting ValueError: "text" while trying to read and feed csv data BasicClassificationDatasetReader from deeppavlov model
from deeppavlov import dataset_readers
dat = dataset_readers.basic_classification_reader.BasicClassificationDatasetReader()
l=dat.read("C:\Users\Anna\Desktop\NLP\test", url=None, format = 'csv', sep=',', header = 1)
TypeError Traceback (most recent call last)
~\Anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_value(self, series, key)
4380 try:
-> 4381 return libindex.get_value_box(s, key)
4382 except IndexError:
pandas/_libs/index.pyx in pandas._libs.index.get_value_box()
pandas/_libs/index.pyx in pandas._libs.index.get_value_at()
pandas/_libs/util.pxd in pandas._libs.util.get_value_at()
pandas/_libs/util.pxd in pandas._libs.util.validate_indexer()
TypeError: 'str' object cannot be interpreted as an integer
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
in
2
3 dat = dataset_readers.basic_classification_reader.BasicClassificationDatasetReader()
----> 4 l=dat.read("C:\Users\Anna\Desktop\NLP\test", url=None, format = 'csv', sep=',', header = 1, names = ['x','y'])
~\Anaconda3\lib\site-packages\deeppavlov\dataset_readers\basic_classification_reader.py in read(self, data_path, url, format, class_sep, *args, **kwargs)
100 if class_sep is None:
101 # each sample is a tuple ("text", "label")
--> 102 data[data_type] = [(row[x], str(row[y])) for _, row in df.iterrows()]
103 else:
104 # each sample is a tuple ("text", ["label", "label", ...])
~\Anaconda3\lib\site-packages\deeppavlov\dataset_readers\basic_classification_reader.py in (.0)
100 if class_sep is None:
101 # each sample is a tuple ("text", "label")
--> 102 data[data_type] = [(row[x], str(row[y])) for _, row in df.iterrows()]
103 else:
104 # each sample is a tuple ("text", ["label", "label", ...])
~\Anaconda3\lib\site-packages\pandas\core\series.py in getitem(self, key)
866 key = com.apply_if_callable(key, self)
867 try:
--> 868 result = self.index.get_value(self, key)
869
870 if not is_scalar(result):
~\Anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_value(self, series, key)
4387 raise InvalidIndexError(key)
4388 else:
-> 4389 raise e1
4390 except Exception: # pragma: no cover
4391 raise e1
~\Anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_value(self, series, key)
4373 try:
4374 return self._engine.get_value(s, k,
-> 4375 tz=getattr(series.dtype, 'tz', None))
4376 except KeyError as e1:
4377 if len(self) > 0 and (self.holds_integer() or self.is_boolean()):
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_value()
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_value()
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()
KeyError: 'text'
from deeppavlov import train_model, configs
​
I want that data will be feeded without errors. Now Data look like
value label
1600 rows

Answer 1

There are undocumented initialization arguments x='text' and y='labels' — headers for x and y data. The error is there because pandas could not find the text header in your data.
Remember also that you use header=1 and rows numbers start with 0, so the first line in your csv-file is skipped.