C2 W2 Assignment preprocessing_fn

Course Q&A Machine Learning Engineering for Production(MLOps) Machine Learning Data Lifecycle in Production
1

I get an error that do not trace to the preprocessing_fn that I implemented
and I can’t figure out what is the error referring to by “TypeError: ‘<’ not supported between instances of ‘tuple’ and ‘str’”

# Test your preprocessing_fn

import traffic_transform
from testing_values import feature_description, raw_data

# NOTE: These next two lines are for reloading your traffic_transform module in case you need to 
# update your initial solution and re-run this cell. Please do not remove them especially if you
# have revised your solution. Else, your changes will not be detected.
import importlib
importlib.reload(traffic_transform)

raw_data_metadata = dataset_metadata.DatasetMetadata(schema_utils.schema_from_feature_spec(feature_description))

with tft_beam.Context(temp_dir=tempfile.mkdtemp()):
    transformed_dataset, _ = (
        (raw_data, raw_data_metadata) | tft_beam.AnalyzeAndTransformDataset(traffic_transform.preprocessing_fn))

transformed_data, transformed_metadata = transformed_dataset

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-23-e2a9c8e67836> in <module>
     14 with tft_beam.Context(temp_dir=tempfile.mkdtemp()):
     15     transformed_dataset, _ = (
---> 16         (raw_data, raw_data_metadata) | tft_beam.AnalyzeAndTransformDataset(traffic_transform.preprocessing_fn))
     17 
     18 transformed_data, transformed_metadata = transformed_dataset

/opt/conda/lib/python3.8/site-packages/apache_beam/transforms/ptransform.py in __ror__(self, left, label)
    613     pvalueish = _SetInputPValues().visit(pvalueish, replacements)
    614     self.pipeline = p
--> 615     result = p.apply(self, pvalueish, label)
    616     if deferred:
    617       return result

/opt/conda/lib/python3.8/site-packages/apache_beam/pipeline.py in apply(self, transform, pvalueish, label)
    696         transform.type_check_inputs(pvalueish)
    697 
--> 698       pvalueish_result = self.runner.apply(transform, pvalueish, self._options)
    699 
    700       if type_options is not None and type_options.pipeline_type_check:

/opt/conda/lib/python3.8/site-packages/apache_beam/runners/runner.py in apply(self, transform, input, options)
    183       m = getattr(self, 'apply_%s' % cls.__name__, None)
    184       if m:
--> 185         return m(transform, input, options)
    186     raise NotImplementedError(
    187         'Execution of [%s] not implemented in runner %s.' % (transform, self))

/opt/conda/lib/python3.8/site-packages/apache_beam/runners/runner.py in apply_PTransform(self, transform, input, options)
    213   def apply_PTransform(self, transform, input, options):
    214     # The base case of apply is to call the transform's expand.
--> 215     return transform.expand(input)
    216 
    217   def run_transform(self,

/opt/conda/lib/python3.8/site-packages/tensorflow_transform/beam/impl.py in expand(self, dataset)
   1269     # e.g. caching the values of expensive computations done in AnalyzeDataset.
   1270     transform_fn = (
-> 1271         dataset | 'AnalyzeDataset' >> AnalyzeDataset(self._preprocessing_fn))
   1272 
   1273     if Context.get_use_deep_copy_optimization():

/opt/conda/lib/python3.8/site-packages/apache_beam/transforms/ptransform.py in __ror__(self, pvalueish, _unused)
   1089 
   1090   def __ror__(self, pvalueish, _unused=None):
-> 1091     return self.transform.__ror__(pvalueish, self.label)
   1092 
   1093   def expand(self, pvalue):

/opt/conda/lib/python3.8/site-packages/apache_beam/transforms/ptransform.py in __ror__(self, left, label)
    613     pvalueish = _SetInputPValues().visit(pvalueish, replacements)
    614     self.pipeline = p
--> 615     result = p.apply(self, pvalueish, label)
    616     if deferred:
    617       return result

/opt/conda/lib/python3.8/site-packages/apache_beam/pipeline.py in apply(self, transform, pvalueish, label)
    650       try:
    651         old_label, transform.label = transform.label, label
--> 652         return self.apply(transform, pvalueish)
    653       finally:
    654         transform.label = old_label

/opt/conda/lib/python3.8/site-packages/apache_beam/pipeline.py in apply(self, transform, pvalueish, label)
    696         transform.type_check_inputs(pvalueish)
    697 
--> 698       pvalueish_result = self.runner.apply(transform, pvalueish, self._options)
    699 
    700       if type_options is not None and type_options.pipeline_type_check:

/opt/conda/lib/python3.8/site-packages/apache_beam/runners/runner.py in apply(self, transform, input, options)
    183       m = getattr(self, 'apply_%s' % cls.__name__, None)
    184       if m:
--> 185         return m(transform, input, options)
    186     raise NotImplementedError(
    187         'Execution of [%s] not implemented in runner %s.' % (transform, self))

/opt/conda/lib/python3.8/site-packages/apache_beam/runners/runner.py in apply_PTransform(self, transform, input, options)
    213   def apply_PTransform(self, transform, input, options):
    214     # The base case of apply is to call the transform's expand.
--> 215     return transform.expand(input)
    216 
    217   def run_transform(self,

/opt/conda/lib/python3.8/site-packages/tensorflow_transform/beam/impl.py in expand(self, dataset)
   1201   def expand(self, dataset):
   1202     input_values, input_metadata = dataset
-> 1203     result, cache = super().expand((input_values, None, None, input_metadata))
   1204     assert not cache
   1205     return result

/opt/conda/lib/python3.8/site-packages/tensorflow_transform/beam/impl.py in expand(self, dataset)
   1002     # need to be serialized to SavedModel.
   1003     graph, structured_inputs, structured_outputs = (
-> 1004         impl_helper.trace_preprocessing_function(self._preprocessing_fn, specs,
   1005                                                  self._use_tf_compat_v1,
   1006                                                  base_temp_dir))

/opt/conda/lib/python3.8/site-packages/tensorflow_transform/impl_helper.py in trace_preprocessing_function(preprocessing_fn, input_specs, use_tf_compat_v1, base_temp_dir)
    714     return _trace_preprocessing_fn_v1(preprocessing_fn, input_specs)
    715   else:
--> 716     return _trace_preprocessing_fn_v2(preprocessing_fn, input_specs,
    717                                       base_temp_dir)
    718 

/opt/conda/lib/python3.8/site-packages/tensorflow_transform/impl_helper.py in _trace_preprocessing_fn_v2(preprocessing_fn, specs, base_temp_dir)
    680       evaluated_replacements=None)
    681   with annotators.object_tracker_scope(annotators.ObjectTracker()):
--> 682     concrete_fn = get_traced_transform_fn(
    683         preprocessing_fn, specs, tf_graph_context).get_concrete_function()
    684   return (concrete_fn.graph,

/opt/conda/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in get_concrete_function(self, *args, **kwargs)
   1231   def get_concrete_function(self, *args, **kwargs):
   1232     # Implements GenericFunction.get_concrete_function.
-> 1233     concrete = self._get_concrete_function_garbage_collected(*args, **kwargs)
   1234     concrete._garbage_collector.release()  # pylint: disable=protected-access
   1235     return concrete

/opt/conda/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _get_concrete_function_garbage_collected(self, *args, **kwargs)
   1211       if self._stateful_fn is None:
   1212         initializers = []
-> 1213         self._initialize(args, kwargs, add_initializers_to=initializers)
   1214         self._initialize_uninitialized_variables(initializers)
   1215 

/opt/conda/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
    757     self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph)
    758     self._concrete_stateful_fn = (
--> 759         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
    760             *args, **kwds))
    761 

/opt/conda/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   3064       args, kwargs = None, None
   3065     with self._lock:
-> 3066       graph_function, _ = self._maybe_define_function(args, kwargs)
   3067     return graph_function
   3068 

/opt/conda/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
   3461 
   3462           self._function_cache.missed.add(call_context_key)
-> 3463           graph_function = self._create_graph_function(args, kwargs)
   3464           self._function_cache.primary[cache_key] = graph_function
   3465 

/opt/conda/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3296     arg_names = base_arg_names + missing_arg_names
   3297     graph_function = ConcreteFunction(
-> 3298         func_graph_module.func_graph_from_py_func(
   3299             self._name,
   3300             self._python_function,

/opt/conda/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes, acd_record_initial_resource_uses)
   1009       # invariant: `func_outputs` contains only Tensors, CompositeTensors,
   1010       # TensorArrays and `None`s.
-> 1011       func_outputs = nest.map_structure(convert, func_outputs,
   1012                                         expand_composites=True)
   1013 

/opt/conda/lib/python3.8/site-packages/tensorflow/python/util/nest.py in map_structure(func, *structure, **kwargs)
    864 
    865   flat_structure = (flatten(s, expand_composites) for s in structure)
--> 866   entries = zip(*flat_structure)
    867 
    868   return pack_sequence_as(

/opt/conda/lib/python3.8/site-packages/tensorflow/python/util/nest.py in <genexpr>(.0)
    863                           expand_composites=expand_composites)
    864 
--> 865   flat_structure = (flatten(s, expand_composites) for s in structure)
    866   entries = zip(*flat_structure)
    867 

/opt/conda/lib/python3.8/site-packages/tensorflow/python/util/nest.py in flatten(structure, expand_composites)
    415     return [None]
    416   expand_composites = bool(expand_composites)
--> 417   return _pywrap_utils.Flatten(structure, expand_composites)
    418 
    419 

TypeError: '<' not supported between instances of 'tuple' and 'str'
1 Like
2

Check if you have used < or % in ( ) or [ ]

3

I haven’t use it anywhere if you even look at the error tracing it’s not even tracing to the preprocessing function that I implemented

4

I am tagging MLops mentor @balaji.ambresh as I don’t have access to this assignment. Balaji can you please have a look here.

5

@Mohamed_Ahmed_Sayed Odds are good that one of your expressions is ending with an extra comma when it shouldn’t. This makes the comparison happen between a string and a tuple. If you’re unable to find this, please click my name and message your notebook as an attachment.