saradindusengupta/email_spam_filter

ValueError: Wrong number of items passed 3, placement implies 1

Opened this issue · 0 comments

when i try to run this part of the code:
data['tokenized_text']=data.apply(tokenize, axis=0)
data['token_count']=data.apply(token_count, axis=0)
data['lang']='en'
#Prepare training and test data
#We randomize the rows to subset the dataframe
df.reset_index(inplace=True)
df=df.reindex(np.random.permutation(df.index))
len_unseen=10000
df_unseen_test= df.iloc[:len_unseen]
df_model = df.iloc[len_unseen:]

I get this error:


KeyError Traceback (most recent call last)
~/opt/anaconda3/lib/python3.8/site-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
2894 try:
-> 2895 return self._engine.get_loc(casted_key)
2896 except KeyError as err:

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()

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: 'tokenized_text'

The above exception was the direct cause of the following exception:

KeyError Traceback (most recent call last)
~/opt/anaconda3/lib/python3.8/site-packages/pandas/core/generic.py in _set_item(self, key, value)
3573 try:
-> 3574 loc = self._info_axis.get_loc(key)
3575 except KeyError:

~/opt/anaconda3/lib/python3.8/site-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
2896 except KeyError as err:
-> 2897 raise KeyError(key) from err
2898

KeyError: 'tokenized_text'

During handling of the above exception, another exception occurred:

ValueError Traceback (most recent call last)
in
----> 1 data['tokenized_text']=data.apply(tokenize, axis=0)
2 data['token_count']=data.apply(token_count, axis=0)
3 data['lang']='en'
4 #Prepare training and test data
5 # We randomize the rows to subset the dataframe

~/opt/anaconda3/lib/python3.8/site-packages/pandas/core/frame.py in setitem(self, key, value)
3038 else:
3039 # set column
-> 3040 self._set_item(key, value)
3041
3042 def _setitem_slice(self, key: slice, value):

~/opt/anaconda3/lib/python3.8/site-packages/pandas/core/frame.py in _set_item(self, key, value)
3115 self._ensure_valid_index(value)
3116 value = self._sanitize_column(key, value)
-> 3117 NDFrame._set_item(self, key, value)
3118
3119 # check if we are modifying a copy

~/opt/anaconda3/lib/python3.8/site-packages/pandas/core/generic.py in _set_item(self, key, value)
3575 except KeyError:
3576 # This item wasn't present, just insert at end
-> 3577 self._mgr.insert(len(self._info_axis), key, value)
3578 return
3579

~/opt/anaconda3/lib/python3.8/site-packages/pandas/core/internals/managers.py in insert(self, loc, item, value, allow_duplicates)
1187 value = _safe_reshape(value, (1,) + value.shape)
1188
-> 1189 block = make_block(values=value, ndim=self.ndim, placement=slice(loc, loc + 1))
1190
1191 for blkno, count in _fast_count_smallints(self.blknos[loc:]):

~/opt/anaconda3/lib/python3.8/site-packages/pandas/core/internals/blocks.py in make_block(values, placement, klass, ndim, dtype)
2720 values = DatetimeArray._simple_new(values, dtype=dtype)
2721
-> 2722 return klass(values, ndim=ndim, placement=placement)
2723
2724

~/opt/anaconda3/lib/python3.8/site-packages/pandas/core/internals/blocks.py in init(self, values, placement, ndim)
128
129 if self._validate_ndim and self.ndim and len(self.mgr_locs) != len(self.values):
--> 130 raise ValueError(
131 f"Wrong number of items passed {len(self.values)}, "
132 f"placement implies {len(self.mgr_locs)}"

ValueError: Wrong number of items passed 3, placement implies 1

Please help