Return to Question

Upd 1/28/2020: Tried two more options with no luck so far. Still looking for help.

A. Passing the raw outputs of train_test_split:

#oversampling minority class using smote
os = SMOTE(random_state = 0)
os_smote_X,os_smote_Y = os.fit_sample(smote_train_X,smote_train_Y)

--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in 1 #oversampling minority class using smote 2 os = SMOTE(random_state = 0) ----> 3 os_smote_X,os_smote_Y = os.fit_resample(smote_train_X,smote_train_Y) 4 os_smote_X = pd.DataFrame(data = os_smote_X,columns=cols) 5 os_smote_Y = pd.DataFrame(data = os_smote_Y,columns=target_col)

/opt/conda/lib/python3.6/site-packages/imblearn/base.py in fit_resample(self, X, y) 73 """ 74 check_classification_targets(y) ---> 75 X, y, binarize_y = self.check_X_y(X, y) 76 77 self.sampling_strategy = check_sampling_strategy(

/opt/conda/lib/python3.6/site-packages/imblearn/base.py in _check_X_y(self, X, y, accept_sparse) 148 if hasattr(y, "loc"): 149 # store information to build a series --> 150 self._y_name = y.name 151 self._y_dtype = y.dtype 152 else:

/opt/conda/lib/python3.6/site-packages/pandas/core/generic.py in getattr(self, name) 5177 if self._info_axis._can_hold_identifiers_and_holds_name(name): 5178
return self[name] -> 5179 return object.getattribute(self, name) 5180 5181 def setattr(self, name, value):

AttributeError: 'DataFrame' object has no attribute 'name'

B. Converting smote_train_X to matrix before passing it alongside smote_train_Y being converted to Series:

smote_train_X_matrix = smote_train_X.as_matrix()
smote_train_Y_series = smote_train_Y.iloc[:,0]

#oversampling minority class using smote
os = SMOTE(random_state = 0)
os_smote_X,os_smote_Y = os.fit_resample(smote_train_X_matrix,smote_train_Y_series)

Note that the resulting matrix and series show a shape of (4633, 46) and (4633,) respectively.

--------------------------------------------------------------------------- ValueError Traceback (most recent call last) /opt/conda/lib/python3.6/site-packages/pandas/core/internals/managers.py in create_block_manager_from_blocks(blocks, axes) 1677
blocks = [ -> 1678 make_block(values=blocks[0], placement=slice(0, len(axes[0]))) 1679 ]

/opt/conda/lib/python3.6/site-packages/pandas/core/internals/blocks.py in make_block(values, placement, klass, ndim, dtype, fastpath) 3283

-> 3284 return klass(values, ndim=ndim, placement=placement) 3285

/opt/conda/lib/python3.6/site-packages/pandas/core/internals/blocks.py in init(self, values, placement, ndim) 127 "Wrong number of items passed {val}, placement implies " --> 128 "{mgr}".format(val=len(self.values), mgr=len(self.mgr_locs)) 129 )

ValueError: Wrong number of items passed 46, placement implies 44

During handling of the above exception, another exception occurred:

ValueError Traceback (most recent call last) in 2 os = SMOTE(random_state = 0) 3 os_smote_X,os_smote_Y = os.fit_resample(smote_train_X_matrix,smote_train_Y_series) ----> 4 os_smote_X = pd.DataFrame(data = os_smote_X,columns=cols) 5 os_smote_Y = pd.DataFrame(data = os_smote_Y,columns=target_col) 6 ###

/opt/conda/lib/python3.6/site-packages/pandas/core/frame.py in init(self, data, index, columns, dtype, copy) 438 mgr = init_dict({data.name: data}, index, columns, dtype=dtype) 439 else: --> 440 mgr = init_ndarray(data, index, columns, dtype=dtype, copy=copy) 441 442 # For data is list-like, or Iterable (will consume into list)

/opt/conda/lib/python3.6/site-packages/pandas/core/internals/construction.py in init_ndarray(values, index, columns, dtype, copy) 211 block_values = [values] 212 --> 213 return create_block_manager_from_blocks(block_values, [columns, index]) 214 215

/opt/conda/lib/python3.6/site-packages/pandas/core/internals/managers.py in create_block_manager_from_blocks(blocks, axes) 1686
blocks = [getattr(b, "values", b) for b in blocks] 1687
tot_items = sum(b.shape[0] for b in blocks) -> 1688 construction_error(tot_items, blocks[0].shape[1:], axes, e) 1689 1690

/opt/conda/lib/python3.6/site-packages/pandas/core/internals/managers.py in construction_error(tot_items, block_shape, axes, e) 1717
raise ValueError("Empty data passed with indices specified.") 1718 raise ValueError( -> 1719 "Shape of passed values is {0}, indices imply {1}".format(passed, implied) 1720 ) 1721

ValueError: Shape of passed values is (8410, 46), indices imply (8410, 44)

I'm trying to resample my dataset after splitting it into train and test partitions using SMOTE. Here's my code:

smote_X = df[cols]
smote_Y = df[target_col]

#Split train and test data
smote_train_X,smote_test_X,smote_train_Y,smote_test_Y = train_test_split(smote_X,smote_Y,test_size = .25,random_state = 111)

smote_train_Y_series = smote_train_Y.iloc[:,0]

#oversampling minority class using smote
os = SMOTE(random_state = 0)
os_smote_X,os_smote_Y = os.fit_sample(smote_train_X_matrix,smote_train_Y_series)

I added line #5 to convert the DataFrame coming out of train_test_split to Series as the newer version of SMOTE fit_sample (docs) wants this data type but it now throws the following error.

Any ideas how to fix it?

-------------------------------------------------------------------------- KeyError Traceback (most recent call last) in 16 #oversampling minority class using smote 17 os = SMOTE(random_state = 0) ---> 18 os_smote_X,os_smote_Y = os.fit_sample(smote_train_X_matrix,smote_train_Y_series) 19 os_smote_X = pd.DataFrame(data = os_smote_X,columns=cols) 20 os_smote_Y = pd.DataFrame(data = os_smote_Y,columns=target_col)

/opt/conda/lib/python3.6/site-packages/imblearn/base.py in fit_resample(self, X, y) 86 if self.X_columns is not None: 87 X = pd.DataFrame(output[0], columns=self.X_columns) ---> 88 X = X_.astype(self.X_dtypes) 89 else: 90 X = output[0]

/opt/conda/lib/python3.6/site-packages/pandas/core/generic.py in astype(self, dtype, copy, errors, **kwargs) 5863
results.append( 5864 col.astype( -> 5865 dtype=dtype[col_name], copy=copy, errors=errors, **kwargs 5866 ) 5867
)

/opt/conda/lib/python3.6/site-packages/pandas/core/generic.py in astype(self, dtype, copy, errors, **kwargs) 5846 if len(dtype) > 1 or self.name not in dtype: 5847
raise KeyError( -> 5848 "Only the Series name can be used for " 5849 "the key in Series dtype mappings." 5850 )

KeyError: 'Only the Series name can be used for the key in Series dtype mappings.'

I'm trying to resample my dataset after splitting it into train and test partitions using SMOTE. Here's my code:

smote_X = df[cols]
smote_Y = df[target_col]

#Split train and test data
smote_train_X,smote_test_X,smote_train_Y,smote_test_Y = train_test_split(smote_X,smote_Y,test_size = .25,random_state = 111)

smote_train_Y_series = smote_train_Y.iloc[:,0]

#oversampling minority class using smote
os = SMOTE(random_state = 0)
os_smote_X,os_smote_Y = os.fit_sample(smote_train_X,smote_train_Y_series)

I added line #5 to convert the DataFrame coming out of train_test_split to Series as the newer version of SMOTE fit_sample (docs) wants this data type but it now throws the following error.

Any ideas how to fix it?

-------------------------------------------------------------------------- KeyError Traceback (most recent call last) in 16 #oversampling minority class using smote 17 os = SMOTE(random_state = 0) ---> 18 os_smote_X,os_smote_Y = os.fit_sample(smote_train_X,smote_train_Y_series) 19 os_smote_X = pd.DataFrame(data = os_smote_X,columns=cols) 20 os_smote_Y = pd.DataFrame(data = os_smote_Y,columns=target_col)

/opt/conda/lib/python3.6/site-packages/imblearn/base.py in fit_resample(self, X, y) 86 if self.X_columns is not None: 87 X = pd.DataFrame(output[0], columns=self.X_columns) ---> 88 X = X_.astype(self.X_dtypes) 89 else: 90 X = output[0]

/opt/conda/lib/python3.6/site-packages/pandas/core/generic.py in astype(self, dtype, copy, errors, **kwargs) 5863
results.append( 5864 col.astype( -> 5865 dtype=dtype[col_name], copy=copy, errors=errors, **kwargs 5866 ) 5867
)

/opt/conda/lib/python3.6/site-packages/pandas/core/generic.py in astype(self, dtype, copy, errors, **kwargs) 5846 if len(dtype) > 1 or self.name not in dtype: 5847
raise KeyError( -> 5848 "Only the Series name can be used for " 5849 "the key in Series dtype mappings." 5850 )

KeyError: 'Only the Series name can be used for the key in Series dtype mappings.'