Tutorial 8 Medins issue

[Bergylta]

Input

pp.process_zoo_classifications()

Output

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[86], line 1
----> 1 pp.process_zoo_classifications()

File /usr/src/app/kso/kso_utils/kso_utils/project.py:746, in ProjectProcessor.process_zoo_classifications(self, test)
    742     workflow_checks = self.workflow_widget.checks
    744 # Retrieve a subset of the subjects from the workflows of interest and
    745 # populate the sql subjects table
--> 746 selected_zoo_workflows = zoo_utils.sample_subjects_from_workflows(
    747     project=self.project,
    748     server_connection=self.server_connection,
    749     db_connection=self.db_connection,
    750     workflow_widget_checks=workflow_checks,
    751     workflows_df=self.zoo_info["workflows"],
    752     subjects_df=self.zoo_info["subjects"],
    753 )
    755 # Make sure all the classifications have existing subjects,
    756 # Flatten the classifications provided the cit. scientists
    757 self.processed_zoo_classifications = zoo_utils.process_zoo_classifications(
    758     project=self.project,
    759     db_connection=self.db_connection,
   (...)
    763     selected_zoo_workflows=selected_zoo_workflows,
    764 )

File /usr/src/app/kso/kso_utils/kso_utils/zooniverse_utils.py:1294, in sample_subjects_from_workflows(project, server_connection, db_connection, workflow_widget_checks, workflows_df, subjects_df)
   1290 drop_table(conn=db_connection, table_name="subjects")
   1292 if len(subjects_series) > 0:
   1293     # Fill or re-fill subjects table
-> 1294     populate_subjects(project, server_connection, db_connection, subjects_series)
   1295 else:
   1296     logging.error("No subjects to populate database from the workflows selected.")

File /usr/src/app/kso/kso_utils/kso_utils/zooniverse_utils.py:1169, in populate_subjects(project, server_connection, db_connection, subjects)
   1166         species_df = species_df.rename(columns={"id": "frame_exp_sp_id"})
   1168         # Reference the expected species on the uploaded subjects
-> 1169         subjects = pd.merge(
   1170             subjects,
   1171             species_df,
   1172             how="left",
   1173             on="frame_exp_sp_id",
   1174         )
   1176 else:
   1177     right_types = ["frame", "clip"]

File /usr/local/lib/python3.8/dist-packages/pandas/core/reshape/merge.py:107, in merge(left, right, how, on, left_on, right_on, left_index, right_index, sort, suffixes, copy, indicator, validate)
     90 @Substitution("\nleft : DataFrame or named Series")
     91 @Appender(_merge_doc, indents=0)
     92 def merge(
   (...)
    105     validate: str | None = None,
    106 ) -> DataFrame:
--> 107     op = _MergeOperation(
    108         left,
    109         right,
    110         how=how,
    111         on=on,
    112         left_on=left_on,
    113         right_on=right_on,
    114         left_index=left_index,
    115         right_index=right_index,
    116         sort=sort,
    117         suffixes=suffixes,
    118         copy=copy,
    119         indicator=indicator,
    120         validate=validate,
    121     )
    122     return op.get_result()

File /usr/local/lib/python3.8/dist-packages/pandas/core/reshape/merge.py:704, in _MergeOperation.__init__(self, left, right, how, on, left_on, right_on, axis, left_index, right_index, sort, suffixes, copy, indicator, validate)
    696 (
    697     self.left_join_keys,
    698     self.right_join_keys,
    699     self.join_names,
    700 ) = self._get_merge_keys()
    702 # validate the merge keys dtypes. We may need to coerce
    703 # to avoid incompatible dtypes
--> 704 self._maybe_coerce_merge_keys()
    706 # If argument passed to validate,
    707 # check if columns specified as unique
    708 # are in fact unique.
    709 if validate is not None:

File /usr/local/lib/python3.8/dist-packages/pandas/core/reshape/merge.py:1257, in _MergeOperation._maybe_coerce_merge_keys(self)
   1251     # unless we are merging non-string-like with string-like
   1252     elif (
   1253         inferred_left in string_types and inferred_right not in string_types
   1254     ) or (
   1255         inferred_right in string_types and inferred_left not in string_types
   1256     ):
-> 1257         raise ValueError(msg)
   1259 # datetimelikes must match exactly
   1260 elif needs_i8_conversion(lk.dtype) and not needs_i8_conversion(rk.dtype):

ValueError: You are trying to merge on object and int64 colu
mns. If you wish to proceed you should use pd.concat