Created
September 27, 2018 22:10
-
-
Save wesm/56c66524b1237a08a528c6eb8d01e44b to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
File "/home/wesm/miniconda/envs/arrow-dev/bin/ipython", line 11, in <module> | |
sys.exit(start_ipython()) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/__init__.py", line 125, in start_ipython | |
return launch_new_instance(argv=argv, **kwargs) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance | |
app.start() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/ipapp.py", line 356, in start | |
self.shell.mainloop() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 485, in mainloop | |
self.interact() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 476, in interact | |
self.run_cell(code, store_history=True) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2662, in run_cell | |
raw_cell, store_history, silent, shell_futures) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2785, in _run_cell | |
interactivity=interactivity, compiler=compiler, result=result) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2909, in run_ast_nodes | |
if self.run_code(code, result): | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2963, in run_code | |
exec(code_obj, self.user_global_ns, self.user_ns) | |
File "<ipython-input-66-37b4667983c2>", line 1, in <module> | |
read_fastparquet() | |
File "<ipython-input-65-9dec9f99efd8>", line 42, in read_fastparquet | |
pf = ParquetFile(SpyReader(f), open_with=spy_open) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 100, in __init__ | |
self._parse_header(fn, verify) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 122, in _parse_header | |
f.seek(0) | |
File "<ipython-input-65-9dec9f99efd8>", line 31, in seek | |
print(''.join(traceback.format_stack())) | |
Seek(0, whence=0) | |
File "/home/wesm/miniconda/envs/arrow-dev/bin/ipython", line 11, in <module> | |
sys.exit(start_ipython()) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/__init__.py", line 125, in start_ipython | |
return launch_new_instance(argv=argv, **kwargs) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance | |
app.start() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/ipapp.py", line 356, in start | |
self.shell.mainloop() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 485, in mainloop | |
self.interact() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 476, in interact | |
self.run_cell(code, store_history=True) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2662, in run_cell | |
raw_cell, store_history, silent, shell_futures) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2785, in _run_cell | |
interactivity=interactivity, compiler=compiler, result=result) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2909, in run_ast_nodes | |
if self.run_code(code, result): | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2963, in run_code | |
exec(code_obj, self.user_global_ns, self.user_ns) | |
File "<ipython-input-66-37b4667983c2>", line 1, in <module> | |
read_fastparquet() | |
File "<ipython-input-65-9dec9f99efd8>", line 42, in read_fastparquet | |
pf = ParquetFile(SpyReader(f), open_with=spy_open) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 100, in __init__ | |
self._parse_header(fn, verify) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 125, in _parse_header | |
f.seek(-8, 2) | |
File "<ipython-input-65-9dec9f99efd8>", line 31, in seek | |
print(''.join(traceback.format_stack())) | |
Seek(-8, whence=2) | |
Tried to read 4, got 4 | |
File "/home/wesm/miniconda/envs/arrow-dev/bin/ipython", line 11, in <module> | |
sys.exit(start_ipython()) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/__init__.py", line 125, in start_ipython | |
return launch_new_instance(argv=argv, **kwargs) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance | |
app.start() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/ipapp.py", line 356, in start | |
self.shell.mainloop() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 485, in mainloop | |
self.interact() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 476, in interact | |
self.run_cell(code, store_history=True) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2662, in run_cell | |
raw_cell, store_history, silent, shell_futures) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2785, in _run_cell | |
interactivity=interactivity, compiler=compiler, result=result) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2909, in run_ast_nodes | |
if self.run_code(code, result): | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2963, in run_code | |
exec(code_obj, self.user_global_ns, self.user_ns) | |
File "<ipython-input-66-37b4667983c2>", line 1, in <module> | |
read_fastparquet() | |
File "<ipython-input-65-9dec9f99efd8>", line 42, in read_fastparquet | |
pf = ParquetFile(SpyReader(f), open_with=spy_open) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 100, in __init__ | |
self._parse_header(fn, verify) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 132, in _parse_header | |
f.seek(-(head_size+8), 2) | |
File "<ipython-input-65-9dec9f99efd8>", line 31, in seek | |
print(''.join(traceback.format_stack())) | |
Seek(-826, whence=2) | |
Tried to read 65536, got 826 | |
File "/home/wesm/miniconda/envs/arrow-dev/bin/ipython", line 11, in <module> | |
sys.exit(start_ipython()) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/__init__.py", line 125, in start_ipython | |
return launch_new_instance(argv=argv, **kwargs) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance | |
app.start() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/ipapp.py", line 356, in start | |
self.shell.mainloop() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 485, in mainloop | |
self.interact() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 476, in interact | |
self.run_cell(code, store_history=True) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2662, in run_cell | |
raw_cell, store_history, silent, shell_futures) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2785, in _run_cell | |
interactivity=interactivity, compiler=compiler, result=result) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2909, in run_ast_nodes | |
if self.run_code(code, result): | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2963, in run_code | |
exec(code_obj, self.user_global_ns, self.user_ns) | |
File "<ipython-input-66-37b4667983c2>", line 1, in <module> | |
read_fastparquet() | |
File "<ipython-input-65-9dec9f99efd8>", line 42, in read_fastparquet | |
pf = ParquetFile(SpyReader(f), open_with=spy_open) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 100, in __init__ | |
self._parse_header(fn, verify) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 134, in _parse_header | |
fmd = read_thrift(f, parquet_thrift.FileMetaData) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/thrift_structures.py", line 32, in read_thrift | |
file_obj.seek(starting_pos + blocks * bufsize + buffer_pos) | |
File "<ipython-input-65-9dec9f99efd8>", line 31, in seek | |
print(''.join(traceback.format_stack())) | |
Seek(459930, whence=0) | |
File "/home/wesm/miniconda/envs/arrow-dev/bin/ipython", line 11, in <module> | |
sys.exit(start_ipython()) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/__init__.py", line 125, in start_ipython | |
return launch_new_instance(argv=argv, **kwargs) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance | |
app.start() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/ipapp.py", line 356, in start | |
self.shell.mainloop() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 485, in mainloop | |
self.interact() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 476, in interact | |
self.run_cell(code, store_history=True) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2662, in run_cell | |
raw_cell, store_history, silent, shell_futures) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2785, in _run_cell | |
interactivity=interactivity, compiler=compiler, result=result) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2909, in run_ast_nodes | |
if self.run_code(code, result): | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2963, in run_code | |
exec(code_obj, self.user_global_ns, self.user_ns) | |
File "<ipython-input-66-37b4667983c2>", line 1, in <module> | |
read_fastparquet() | |
File "<ipython-input-65-9dec9f99efd8>", line 43, in read_fastparquet | |
return pf.to_pandas(['A']) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 426, in to_pandas | |
index=index, assign=parts) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 258, in read_row_group | |
scheme=self.file_scheme) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 344, in read_row_group | |
cats, selfmade, assign=assign) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 321, in read_row_group_arrays | |
catdef=out.get(name+'-catdef', None)) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 194, in read_col | |
infile.seek(off) | |
File "<ipython-input-65-9dec9f99efd8>", line 31, in seek | |
print(''.join(traceback.format_stack())) | |
Seek(4, whence=0) | |
Tried to read 65536, got 65536 | |
Tried to read 65536, got 65536 | |
File "/home/wesm/miniconda/envs/arrow-dev/bin/ipython", line 11, in <module> | |
sys.exit(start_ipython()) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/__init__.py", line 125, in start_ipython | |
return launch_new_instance(argv=argv, **kwargs) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance | |
app.start() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/ipapp.py", line 356, in start | |
self.shell.mainloop() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 485, in mainloop | |
self.interact() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 476, in interact | |
self.run_cell(code, store_history=True) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2662, in run_cell | |
raw_cell, store_history, silent, shell_futures) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2785, in _run_cell | |
interactivity=interactivity, compiler=compiler, result=result) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2909, in run_ast_nodes | |
if self.run_code(code, result): | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2963, in run_code | |
exec(code_obj, self.user_global_ns, self.user_ns) | |
File "<ipython-input-66-37b4667983c2>", line 1, in <module> | |
read_fastparquet() | |
File "<ipython-input-65-9dec9f99efd8>", line 43, in read_fastparquet | |
return pf.to_pandas(['A']) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 426, in to_pandas | |
index=index, assign=parts) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 258, in read_row_group | |
scheme=self.file_scheme) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 344, in read_row_group | |
cats, selfmade, assign=assign) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 321, in read_row_group_arrays | |
catdef=out.get(name+'-catdef', None)) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 195, in read_col | |
ph = read_thrift(infile, parquet_thrift.PageHeader) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/thrift_structures.py", line 32, in read_thrift | |
file_obj.seek(starting_pos + blocks * bufsize + buffer_pos) | |
File "<ipython-input-65-9dec9f99efd8>", line 31, in seek | |
print(''.join(traceback.format_stack())) | |
Seek(98300, whence=0) | |
Tried to read 163801, got 163801 | |
File "/home/wesm/miniconda/envs/arrow-dev/bin/ipython", line 11, in <module> | |
sys.exit(start_ipython()) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/__init__.py", line 125, in start_ipython | |
return launch_new_instance(argv=argv, **kwargs) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance | |
app.start() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/ipapp.py", line 356, in start | |
self.shell.mainloop() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 485, in mainloop | |
self.interact() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 476, in interact | |
self.run_cell(code, store_history=True) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2662, in run_cell | |
raw_cell, store_history, silent, shell_futures) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2785, in _run_cell | |
interactivity=interactivity, compiler=compiler, result=result) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2909, in run_ast_nodes | |
if self.run_code(code, result): | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2963, in run_code | |
exec(code_obj, self.user_global_ns, self.user_ns) | |
File "<ipython-input-66-37b4667983c2>", line 1, in <module> | |
read_fastparquet() | |
File "<ipython-input-65-9dec9f99efd8>", line 43, in read_fastparquet | |
return pf.to_pandas(['A']) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 426, in to_pandas | |
index=index, assign=parts) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 258, in read_row_group | |
scheme=self.file_scheme) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 344, in read_row_group | |
cats, selfmade, assign=assign) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 321, in read_row_group_arrays | |
catdef=out.get(name+'-catdef', None)) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 194, in read_col | |
infile.seek(off) | |
File "<ipython-input-65-9dec9f99efd8>", line 31, in seek | |
print(''.join(traceback.format_stack())) | |
Seek(229379, whence=0) | |
Tried to read 65536, got 65536 | |
File "/home/wesm/miniconda/envs/arrow-dev/bin/ipython", line 11, in <module> | |
sys.exit(start_ipython()) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/__init__.py", line 125, in start_ipython | |
return launch_new_instance(argv=argv, **kwargs) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance | |
app.start() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/ipapp.py", line 356, in start | |
self.shell.mainloop() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 485, in mainloop | |
self.interact() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 476, in interact | |
self.run_cell(code, store_history=True) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2662, in run_cell | |
raw_cell, store_history, silent, shell_futures) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2785, in _run_cell | |
interactivity=interactivity, compiler=compiler, result=result) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2909, in run_ast_nodes | |
if self.run_code(code, result): | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2963, in run_code | |
exec(code_obj, self.user_global_ns, self.user_ns) | |
File "<ipython-input-66-37b4667983c2>", line 1, in <module> | |
read_fastparquet() | |
File "<ipython-input-65-9dec9f99efd8>", line 43, in read_fastparquet | |
return pf.to_pandas(['A']) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 426, in to_pandas | |
index=index, assign=parts) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 258, in read_row_group | |
scheme=self.file_scheme) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 344, in read_row_group | |
cats, selfmade, assign=assign) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 321, in read_row_group_arrays | |
catdef=out.get(name+'-catdef', None)) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 195, in read_col | |
ph = read_thrift(infile, parquet_thrift.PageHeader) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/thrift_structures.py", line 32, in read_thrift | |
file_obj.seek(starting_pos + blocks * bufsize + buffer_pos) | |
File "<ipython-input-65-9dec9f99efd8>", line 31, in seek | |
print(''.join(traceback.format_stack())) | |
Seek(229420, whence=0) | |
Tried to read 46, got 46 | |
File "/home/wesm/miniconda/envs/arrow-dev/bin/ipython", line 11, in <module> | |
sys.exit(start_ipython()) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/__init__.py", line 125, in start_ipython | |
return launch_new_instance(argv=argv, **kwargs) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance | |
app.start() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/ipapp.py", line 356, in start | |
self.shell.mainloop() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 485, in mainloop | |
self.interact() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 476, in interact | |
self.run_cell(code, store_history=True) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2662, in run_cell | |
raw_cell, store_history, silent, shell_futures) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2785, in _run_cell | |
interactivity=interactivity, compiler=compiler, result=result) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2909, in run_ast_nodes | |
if self.run_code(code, result): | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2963, in run_code | |
exec(code_obj, self.user_global_ns, self.user_ns) | |
File "<ipython-input-66-37b4667983c2>", line 1, in <module> | |
read_fastparquet() | |
File "<ipython-input-65-9dec9f99efd8>", line 43, in read_fastparquet | |
return pf.to_pandas(['A']) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 426, in to_pandas | |
index=index, assign=parts) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 258, in read_row_group | |
scheme=self.file_scheme) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 344, in read_row_group | |
cats, selfmade, assign=assign) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 321, in read_row_group_arrays | |
catdef=out.get(name+'-catdef', None)) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 194, in read_col | |
infile.seek(off) | |
File "<ipython-input-65-9dec9f99efd8>", line 31, in seek | |
print(''.join(traceback.format_stack())) | |
Seek(229557, whence=0) | |
Tried to read 65536, got 65536 | |
Tried to read 65536, got 65536 | |
File "/home/wesm/miniconda/envs/arrow-dev/bin/ipython", line 11, in <module> | |
sys.exit(start_ipython()) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/__init__.py", line 125, in start_ipython | |
return launch_new_instance(argv=argv, **kwargs) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance | |
app.start() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/ipapp.py", line 356, in start | |
self.shell.mainloop() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 485, in mainloop | |
self.interact() | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/terminal/interactiveshell.py", line 476, in interact | |
self.run_cell(code, store_history=True) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2662, in run_cell | |
raw_cell, store_history, silent, shell_futures) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2785, in _run_cell | |
interactivity=interactivity, compiler=compiler, result=result) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2909, in run_ast_nodes | |
if self.run_code(code, result): | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2963, in run_code | |
exec(code_obj, self.user_global_ns, self.user_ns) | |
File "<ipython-input-66-37b4667983c2>", line 1, in <module> | |
read_fastparquet() | |
File "<ipython-input-65-9dec9f99efd8>", line 43, in read_fastparquet | |
return pf.to_pandas(['A']) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 426, in to_pandas | |
index=index, assign=parts) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/api.py", line 258, in read_row_group | |
scheme=self.file_scheme) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 344, in read_row_group | |
cats, selfmade, assign=assign) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 321, in read_row_group_arrays | |
catdef=out.get(name+'-catdef', None)) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/core.py", line 195, in read_col | |
ph = read_thrift(infile, parquet_thrift.PageHeader) | |
File "/home/wesm/miniconda/envs/arrow-dev/lib/python3.6/site-packages/fastparquet/thrift_structures.py", line 32, in read_thrift | |
file_obj.seek(starting_pos + blocks * bufsize + buffer_pos) | |
File "<ipython-input-65-9dec9f99efd8>", line 31, in seek | |
print(''.join(traceback.format_stack())) | |
Seek(327853, whence=0) | |
Tried to read 163801, got 132085 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import pandas as pd | |
import pyarrow | |
import pyarrow.parquet as arrow_pq | |
from fastparquet import ParquetFile | |
# data to generate | |
ROW_LENGTH = 40000 # decreasing below 32750ish eliminates exception | |
N_ROWS = 10 | |
# file write params | |
ROW_GROUP_SIZE = 5 # Lower numbers eliminate exception, but strange data is read (e.g. Nones) | |
FILENAME = 'test.parquet' | |
def write_arrow(length): | |
df = pd.DataFrame({'A': ['A' * length for _ in range(N_ROWS)]}) | |
if os.path.isfile(FILENAME): | |
os.remove(FILENAME) | |
arrow_table = pyarrow.Table.from_pandas(df) | |
arrow_pq.write_table(arrow_table, | |
FILENAME, | |
use_dictionary=False, | |
compression='NONE', | |
row_group_size=ROW_GROUP_SIZE) | |
def read_arrow(): | |
print("arrow:") | |
table2 = arrow_pq.read_table(FILENAME) | |
return table2.to_pandas() | |
for i in range(30000, 40000): | |
print(i) | |
write_arrow(i) | |
df1 = read_arrow() | |
df2 = read_fastparquet() | |
pd.util.testing.assert_frame_equal(df1, df2) | |
import io | |
import traceback | |
class SpyReader(object): | |
def __init__(self, f): | |
self.f = f | |
def __del__(self): | |
return self.f.close() | |
def __enter__(self): | |
return self | |
def __exit__(self, exc_type, exc_value, tb): | |
self.close() | |
def close(self): | |
return self.f.close() | |
def tell(self): | |
return self.f.tell() | |
def read(self, nbytes): | |
result = self.f.read(nbytes) | |
print('Tried to read {0}, got {1}'.format(nbytes, len(result))) | |
return result | |
def seek(self, position, whence=0): | |
print(''.join(traceback.format_stack())) | |
print('Seek({0}, whence={1})'.format(position, whence)) | |
return self.f.seek(position, whence) | |
def spy_open(filename, mode='rb'): | |
return SpyReader(open(filename, mode)) | |
def read_fastparquet(): | |
with open(FILENAME, 'rb') as f: | |
pf = ParquetFile(SpyReader(f), open_with=spy_open) | |
return pf.to_pandas(['A']) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment