Keras Neural Network Error: Setting an Array Element with a Sequence

Question

I'm loading dummy data into a neural network, but I'm receiving an error I can't seem to debug:

Here is my data, visualized:

 df:
Label          Mar
0    | [[.332, .326], [.058, .138]]
0    | [[.234, .246], [.234, .395]]
1    | [[.084, .23], [.745, .923]], 

I'm trying to use the 'Mar' column to predict the 'Label' column (I know this data makes no sense, its just similar to my real data). Here is my neural network code:

model = Sequential()
model.add(Dense(3, input_dim=(1), activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
X = df['Mar']
Y = pd.get_dummies(df['Label'])
model.fit(X, Y, epochs=150, batch_size=10)

Here is the code to create my sample data:

Sample = [{'Label': 0, 'Mar': [[.332, .326], [.058, .138]]},
 {'Label': 0, 'Mar': [[.234, .246], [.013, .592]]},
 {'Label': 1,  'Mar': [[.084, .23], [.745, .923]]}]

df = pd.DataFrame(Sample)

When I get to the final row of this code, I get this error:

Epoch 1/150
-----------------------------------------------------------------------
ValueError                            Traceback (most recent call last)
<ipython-input-271-3d2506918d89> in <module>()
----> 1 model.fit(X, Y, epochs=150, batch_size=10)

/usr/local/lib/python2.7/site-packages/keras/models.pyc in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs)
    854                               class_weight=class_weight,
    855                               sample_weight=sample_weight,
--> 856                               initial_epoch=initial_epoch)
    857 
    858     def evaluate(self, x, y, batch_size=32, verbose=1,

/usr/local/lib/python2.7/site-packages/keras/engine/training.pyc in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs)
   1496                               val_f=val_f, val_ins=val_ins, shuffle=shuffle,
   1497                               callback_metrics=callback_metrics,
-> 1498                               initial_epoch=initial_epoch)
   1499 
   1500     def evaluate(self, x, y, batch_size=32, verbose=1, sample_weight=None):

/usr/local/lib/python2.7/site-packages/keras/engine/training.pyc in _fit_loop(self, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch)
   1150                 batch_logs['size'] = len(batch_ids)
   1151                 callbacks.on_batch_begin(batch_index, batch_logs)
-> 1152                 outs = f(ins_batch)
   1153                 if not isinstance(outs, list):
   1154                     outs = [outs]

/usr/local/lib/python2.7/site-packages/keras/backend/tensorflow_backend.pyc in __call__(self, inputs)
   2227         session = get_session()
   2228         updated = session.run(self.outputs + [self.updates_op],
-> 2229                               feed_dict=feed_dict)
   2230         return updated[:len(self.outputs)]
   2231 

/usr/local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in run(self, fetches, feed_dict, options, run_metadata)
    776     try:
    777       result = self._run(None, fetches, feed_dict, options_ptr,
--> 778                          run_metadata_ptr)
    779       if run_metadata:
    780         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

/usr/local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _run(self, handle, fetches, feed_dict, options, run_metadata)
    952             np_val = subfeed_val.to_numpy_array()
    953           else:
--> 954             np_val = np.asarray(subfeed_val, dtype=subfeed_dtype)
    955 
    956           if (not is_tensor_handle_feed and

/usr/local/lib/python2.7/site-packages/numpy/core/numeric.pyc in asarray(a, dtype, order)
    529 
    530     """
--> 531     return array(a, dtype, copy=False, order=order)
    532 
    533 

ValueError: setting an array element with a sequence.

I now suspect it has something to do with my input columns being list, not np arrays? However, I've tried making them into arrays first and I'm still getting the same error. Would really love and appreciate help!!

Edit I've tried one hot encoding the label field, as I found somewhere online that that may help. It hasn't helped at this point

Answer 1

A couple of issues here,

1. The input is the wrong shape
2. The input is a mixture of arrays and lists.

One possible solution would be to use keras.layers.Flatten to reshape your data, and pd.Series.tolist() to uniformize the data type of the input array:

model = Sequential()
model.add(Flatten(input_shape=(2,2)))
model.add(Dense(3, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
X = df['Mar'].tolist()
Y = df['Label']
model.fit(X, Y, epochs=150, batch_size=10)