traceback

gistfile1.txt

root@rosie-staging:~/rosie# docker run --rm -v /tmp/serenata-data:/tmp/serenata-data rosie
2017-01-30 13:34:50 Creating the CSV file
2017-01-30 13:34:50 Reading the XML file
2017-01-30 13:34:52 Writing record #3,200 to the CSV
2017-01-30 13:34:52 Done!
2017-01-30 13:34:52 Creating the CSV file
2017-01-30 13:34:52 Reading the XML file
2017-01-30 13:37:36 Writing record #342,225 to the CSV
2017-01-30 13:37:36 Done!
2017-01-30 13:37:36 Creating the CSV file
2017-01-30 13:37:36 Reading the XML file
2017-01-30 13:57:05 Writing record #2,404,847 to the CSV/rosie/dataset.py:52: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  dataset['cnpj'] = dataset['cnpj'].str.replace(r'\D', '')
2017-01-30 13:57:05 Writing record #2,404,938 to the CSV
2017-01-30 13:57:05 Done!
Merging all datasets��
Loading current-year.xz��
Loading last-year.xz��
Loading previous-years.xz��
Dropping rows without document_value or reimbursement_number��
Grouping dataset by applicant_id, document_id and year��
Gathering all reimbursement numbers together��
Summing all net values together��
Summing all reimbursement values together��
Generating the new dataset��
Casting changes to a new DataFrame��
Writing it to file��
Done.
Traceback (most recent call last):
  File "rosie.py", line 36, in <module>
    command()
  File "rosie.py", line 23, in run
    rosie.main(target_directory)
  File "/rosie/__init__.py", line 64, in main
    dataset = Dataset(target_directory).get()
  File "/rosie/dataset.py", line 22, in get
    right_on='cnpj')
  File "/usr/local/lib/python3.5/site-packages/pandas/tools/merge.py", line 62, in merge
    return op.get_result()
  File "/usr/local/lib/python3.5/site-packages/pandas/tools/merge.py", line 564, in get_result
    concat_axis=0, copy=self.copy)
  File "/usr/local/lib/python3.5/site-packages/pandas/core/internals.py", line 4825, in concatenate_block_managers
    placement=placement) for placement, join_units in concat_plan]
  File "/usr/local/lib/python3.5/site-packages/pandas/core/internals.py", line 4825, in <listcomp>
    placement=placement) for placement, join_units in concat_plan]
  File "/usr/local/lib/python3.5/site-packages/pandas/core/internals.py", line 4922, in concatenate_join_units
    for ju in join_units]
  File "/usr/local/lib/python3.5/site-packages/pandas/core/internals.py", line 4922, in <listcomp>
    for ju in join_units]
  File "/usr/local/lib/python3.5/site-packages/pandas/core/internals.py", line 5222, in get_reindexed_values
    fill_value=fill_value)
  File "/usr/local/lib/python3.5/site-packages/pandas/core/algorithms.py", line 1100, in take_nd
    out = np.empty(out_shape, dtype=dtype)
MemoryError