Need warning for cross validation

There is a scenario where if you specify your samples for training and testing and they get filtered out, you may get this error. This basically says that your testing samples were filtered out. A better message is needed

```
(from tensorflow.python.ops.random_ops) is deprecated and will be removed in a future version.
...skipping...
accuracy/Log (defined at /lib/python3.6/site-packages/mmvec/multimodal.py:159)

Input Source operations connected to node accuracy/multinomial/Multinomial:
accuracy/Log (defined at /lib/python3.6/site-packages/mmvec/multimodal.py:159)

Original stack trace for 'accuracy/multinomial/Multinomial':
File "/bin/mmvec", line 225, in
mmvec()
File "/lib/python3.6/site-packages/click/core.py", line 764, in __call__
return self.main(*args, **kwargs)
File "/lib/python3.6/site-packages/click/core.py", line 717, in main
rv = self.invoke(ctx)
File "/lib/python3.6/site-packages/click/core.py", line 1137, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
File "/lib/python3.6/site-packages/click/core.py", line 956, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/lib/python3.6/site-packages/click/core.py", line 555, in invoke
return callback(*args, **kwargs)
File "/bin/mmvec", line 168, in paired_omics
test_microbes_coo, test_metabolites_df.values)
File "/lib/python3.6/site-packages/mmvec/multimodal.py", line 160, in __call__
self.cv_size)
File "/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 324, in new_func
return func(*args, **kwargs)
File "/lib/python3.6/site-packages/tensorflow/python/ops/random_ops.py", line 357, in multinomial
return multinomial_categorical_impl(logits, num_samples, output_dtype, seed)
File "/lib/python3.6/site-packages/tensorflow/python/ops/random_ops.py", line 393, in multinomial_categorical_impl
logits, num_samples, seed=seed1, seed2=seed2, output_dtype=dtype)
File "/lib/python3.6/site-packages/tensorflow/python/ops/gen_random_ops.py", line 85, in multinomial
seed2=seed2, output_dtype=output_dtype, name=name)
File "/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3616, in create_op
op_def=op_def)
File "/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2005, in __init__
self._traceback = tf_stack.extract_stack()
```

Start at mmvec/multimodal.py around line 159 and trace the cross-validation path from the /bin/mmvec paired_omics entry point. Reproduce the case where specified training or testing samples are filtered out, then verify that it produces a clear warning identifying the affected testing samples instead of the TensorFlow traceback.

Written by the indexing model from the issue text.