This is the file I am trying to open
https://drive.google.com/file/d/1K2kDBTNXS2ikx9xKmi2Fy0Wsc5u_Lls0/view
It is described here
https://github.com/armancohan/long-summarization
After I added the file to my google drive, this is the code I am trying to use to open it.
from google.colab import drive
drive.mount('/content/gdrive')
import zipfile
zip_ref = zipfile.ZipFile('/content/gdrive/My Drive/arxiv-release.zip', 'r')
zip_ref.extractall('arxiv-release')
zip_ref.close()
This is the error that is raised
---------------------------------------------------------------------------
BadZipFile Traceback (most recent call last)
<ipython-input-9-9965160388a1> in <module>()
1
----> 2 zip_ref.extractall('arxiv-release')
3 zip_ref.close()
5 frames
/usr/lib/python3.6/zipfile.py in extractall(self, path, members, pwd)
1522
1523 for zipinfo in members:
-> 1524 self._extract_member(zipinfo, path, pwd)
1525
1526 #classmethod
/usr/lib/python3.6/zipfile.py in _extract_member(self, member, targetpath, pwd)
1577 with self.open(member, pwd=pwd) as source, \
1578 open(targetpath, "wb") as target:
-> 1579 shutil.copyfileobj(source, target)
1580
1581 return targetpath
/usr/lib/python3.6/shutil.py in copyfileobj(fsrc, fdst, length)
77 """copy data from file-like object fsrc to file-like object fdst"""
78 while 1:
---> 79 buf = fsrc.read(length)
80 if not buf:
81 break
/usr/lib/python3.6/zipfile.py in read(self, n)
870 self._offset = 0
871 while n > 0 and not self._eof:
--> 872 data = self._read1(n)
873 if n < len(data):
874 self._readbuffer = data
/usr/lib/python3.6/zipfile.py in _read1(self, n)
960 if self._left <= 0:
961 self._eof = True
--> 962 self._update_crc(data)
963 return data
964
/usr/lib/python3.6/zipfile.py in _update_crc(self, newdata)
888 # Check the CRC if we're at the end of the file
889 if self._eof and self._running_crc != self._expected_crc:
--> 890 raise BadZipFile("Bad CRC-32 for file %r" % self.name)
891
892 def read1(self, n):
BadZipFile: Bad CRC-32 for file 'arxiv-release/train.txt'
Related
Trying to load a model from past run in mlflow, in jupyterlab, never finishes. After waiting for hours, interrupting the run throws the below state.
---------------------------------------------------------------------------
KeyboardInterrupt Traceback (most recent call last)
Input In [21], in <cell line: 2>()
1 logged_model = 'runs:/7f6932baef144fa69847ba11ef66f8e6/model/'
----> 2 loaded_model = mlflow.tensorflow.load_model(logged_model)
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/mlflow/tensorflow/__init__.py:397, in load_model(model_uri, dst_path)
360 def load_model(model_uri, dst_path=None):
361 """
362 Load an MLflow model that contains the TensorFlow flavor from the specified path.
363
(...)
395 for _, output_signature in signature_definition.outputs.items()]
396 """
--> 397 local_model_path = _download_artifact_from_uri(artifact_uri=model_uri, output_path=dst_path)
398 flavor_conf = _get_flavor_configuration(local_model_path, FLAVOR_NAME)
399 _add_code_from_conf_to_system_path(local_model_path, flavor_conf)
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/mlflow/tracking/artifact_utils.py:95, in _download_artifact_from_uri(artifact_uri, output_path)
92 parsed_uri = parsed_uri._replace(path=posixpath.dirname(parsed_uri.path))
93 root_uri = prefix + urllib.parse.urlunparse(parsed_uri)
---> 95 return get_artifact_repository(artifact_uri=root_uri).download_artifacts(
96 artifact_path=artifact_path, dst_path=output_path
97 )
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/mlflow/store/artifact/runs_artifact_repo.py:125, in RunsArtifactRepository.download_artifacts(self, artifact_path, dst_path)
110 def download_artifacts(self, artifact_path, dst_path=None):
111 """
112 Download an artifact file or directory to a local directory if applicable, and return a
113 local path for it.
(...)
123 :return: Absolute path of the local filesystem location containing the desired artifacts.
124 """
--> 125 return self.repo.download_artifacts(artifact_path, dst_path)
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/mlflow/store/artifact/artifact_repo.py:242, in ArtifactRepository.download_artifacts(self, artifact_path, dst_path)
240 # Check if the artifacts points to a directory
241 if self._is_directory(artifact_path):
--> 242 dst_local_path, inflight_downloads = async_download_artifact_dir(
243 src_artifact_dir_path=artifact_path, dst_local_dir_path=dst_path
244 )
245 else:
246 inflight_downloads = async_download_artifact(
247 src_artifact_path=artifact_path, dst_local_dir_path=dst_path
248 )
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/mlflow/store/artifact/artifact_repo.py:208, in ArtifactRepository.download_artifacts.<locals>.async_download_artifact_dir(src_artifact_dir_path, dst_local_dir_path)
206 for file_info in dir_content:
207 if file_info.is_dir:
--> 208 inflight_downloads += async_download_artifact_dir(
209 src_artifact_dir_path=file_info.path,
210 dst_local_dir_path=dst_local_dir_path,
211 )[2]
212 else:
213 inflight_downloads += async_download_artifact(
214 src_artifact_path=file_info.path,
215 dst_local_dir_path=dst_local_dir_path,
216 )
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/mlflow/store/artifact/artifact_repo.py:199, in ArtifactRepository.download_artifacts.<locals>.async_download_artifact_dir(src_artifact_dir_path, dst_local_dir_path)
195 local_dir = os.path.join(dst_local_dir_path, src_artifact_dir_path)
196 inflight_downloads = []
197 dir_content = [ # prevent infinite loop, sometimes the dir is recursively included
198 file_info
--> 199 for file_info in self.list_artifacts(src_artifact_dir_path)
200 if file_info.path != "." and file_info.path != src_artifact_dir_path
201 ]
202 if not dir_content: # empty dir
203 if not os.path.exists(local_dir):
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/mlflow/store/artifact/sftp_artifact_repo.py:94, in SFTPArtifactRepository.list_artifacts(self, path)
92 artifact_dir = self.path
93 list_dir = posixpath.join(artifact_dir, path) if path else artifact_dir
---> 94 if not self.sftp.isdir(list_dir):
95 return []
96 artifact_files = self.sftp.listdir(list_dir)
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/pysftp/__init__.py:652, in Connection.isdir(self, remotepath)
650 self._sftp_connect()
651 try:
--> 652 result = S_ISDIR(self._sftp.stat(remotepath).st_mode)
653 except IOError: # no such file
654 result = False
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/paramiko/sftp_client.py:493, in SFTPClient.stat(self, path)
491 path = self._adjust_cwd(path)
492 self._log(DEBUG, "stat({!r})".format(path))
--> 493 t, msg = self._request(CMD_STAT, path)
494 if t != CMD_ATTRS:
495 raise SFTPError("Expected attributes")
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/paramiko/sftp_client.py:822, in SFTPClient._request(self, t, *arg)
820 def _request(self, t, *arg):
821 num = self._async_request(type(None), t, *arg)
--> 822 return self._read_response(num)
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/paramiko/sftp_client.py:852, in SFTPClient._read_response(self, waitfor)
850 while True:
851 try:
--> 852 t, data = self._read_packet()
853 except EOFError as e:
854 raise SSHException("Server connection dropped: {}".format(e))
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/paramiko/sftp.py:201, in BaseSFTP._read_packet(self)
200 def _read_packet(self):
--> 201 x = self._read_all(4)
202 # most sftp servers won't accept packets larger than about 32k, so
203 # anything with the high byte set (> 16MB) is just garbage.
204 if byte_ord(x[0]):
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/paramiko/sftp.py:185, in BaseSFTP._read_all(self, n)
183 break
184 else:
--> 185 x = self.sock.recv(n)
187 if len(x) == 0:
188 raise EOFError()
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/paramiko/channel.py:699, in Channel.recv(self, nbytes)
686 """
687 Receive data from the channel. The return value is a string
688 representing the data received. The maximum amount of data to be
(...)
696 if no data is ready before the timeout set by `settimeout`.
697 """
698 try:
--> 699 out = self.in_buffer.read(nbytes, self.timeout)
700 except PipeTimeout:
701 raise socket.timeout()
File ~/.conda/envs/tensorflow/lib/python3.8/site-packages/paramiko/buffered_pipe.py:160, in BufferedPipe.read(self, nbytes, timeout)
158 while (len(self._buffer) == 0) and not self._closed:
159 then = time.time()
--> 160 self._cv.wait(timeout)
161 if timeout is not None:
162 timeout -= time.time() - then
File ~/.conda/envs/tensorflow/lib/python3.8/threading.py:302, in Condition.wait(self, timeout)
300 try: # restore state no matter what (e.g., KeyboardInterrupt)
301 if timeout is None:
--> 302 waiter.acquire()
303 gotit = True
304 else:
KeyboardInterrupt:
The mlflow tracking server is working properly for all the other operations. I am able to log params, metrics and artifacts. But I am not able to load a model or retrive any of the artifacts.
Update:
Looks like a bug as per https://github.com/mlflow/mlflow/issues/5656.
Please upgrade mlflow, their is some issue with version 1.26.0
pip install mlflow==1.27.0
Assuming you are also using above version
I am trying to extract the text from the following PDF.
First, I used the PyPDF2 library. I used the following code:
from PyPDF2 import PdfFileReader
pdf = PdfFileReader('March_5_8000/1.pdf',strict=False)
information = pdf.getDocumentInfo()
This throws the following error:
/opt/conda/envs/fastai/lib/python3.6/site-packages/PyPDF2/pdf.py in getObject(self, indirectReference)
1597 if debug: print((" Uncompressed Object", indirectReference.idnum, indirectReference.generation, ":", start))
1598 self.stream.seek(start, 0)
-> 1599 idnum, generation = self.readObjectHeader(self.stream)
1600 if idnum != indirectReference.idnum and self.xrefIndex:
1601 # Xref table probably had bad indexes due to not being zero-indexed
/opt/conda/envs/fastai/lib/python3.6/site-packages/PyPDF2/pdf.py in readObjectHeader(self, stream)
1665 warnings.warn("Superfluous whitespace found in object header %s %s" % \
1666 (idnum, generation), utils.PdfReadWarning)
-> 1667 return int(idnum), int(generation)
1668
1669 def cacheGetIndirectObject(self, generation, idnum):
ValueError: invalid literal for int() with base 10: b'obj'
I also tried using the pdfrw library, but that returned the same error:
Code:
from pdfrw import PdfReader
x = PdfReader('March_5_8000/980.pdf')
x.keys()
ERROR:
PdfParseError Traceback (most recent call last)
<ipython-input-6-6d3575671b6c> in <module>
1 from pdfrw import PdfReader
----> 2 x = PdfReader('March_5_8000/980.pdf')
3 x.keys()
/opt/conda/envs/fastai/lib/python3.6/site-packages/pdfrw/pdfreader.py in __init__(self, fname, fdata, decompress, decrypt, password, disable_gc, verbose)
617 while 1:
618 source.obj_offsets = {}
--> 619 trailer, is_stream = self.parsexref(source)
620 prev = trailer.Prev
621 if prev is None:
/opt/conda/envs/fastai/lib/python3.6/site-packages/pdfrw/pdfreader.py in parsexref(self, source)
463 return self.readdict(source), False
464 else:
--> 465 source.exception('Expected "xref" keyword or xref stream object')
466
467 def readpages(self, node):
/opt/conda/envs/fastai/lib/python3.6/site-packages/pdfrw/tokens.py in exception(self, *arg)
227
228 def exception(self, *arg):
--> 229 raise PdfParseError(self.msg(*arg))
PdfParseError: Expected "xref" keyword or xref stream object (line=2238, col=39, token='obj')
How can I solve this?
Hey I have a very short question. I need to load data for my machine learning course, but it does not work for me and I have no idea why. Im using Jupyter with Python 3.
My Code:
from sklearn.datasets import fetch_covtype
forest = fetch_covtype()
For my friend it works fine with the same conditions. I already tried to update sklearn with pip install -U scikit-learn, but it did not solve the problem. I hope somebody can help me.
It creates the following error:
UnboundLocalError Traceback (most recent call last)
/opt/conda/lib/python3.7/site-packages/sklearn/datasets/covtype.py in fetch_covtype(data_home, download_if_missing, random_state, shuffle, return_X_y)
126 try:
--> 127 X, y
128 except NameError:
UnboundLocalError: local variable 'X' referenced before assignment
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-9-fb303a92b6ca> in <module>
----> 1 forest =fetch_covtype()
/opt/conda/lib/python3.7/site-packages/sklearn/datasets/covtype.py in fetch_covtype(data_home, download_if_missing, random_state, shuffle, return_X_y)
127 X, y
128 except NameError:
--> 129 X, y = _refresh_cache([samples_path, targets_path], 9)
130 # TODO: Revert to the following two lines in v0.23
131 # X = joblib.load(samples_path)
/opt/conda/lib/python3.7/site-packages/sklearn/datasets/base.py in _refresh_cache(files, compress)
928 msg = "sklearn.externals.joblib is deprecated in 0.21"
929 with warnings.catch_warnings(record=True) as warns:
--> 930 data = tuple([joblib.load(f) for f in files])
931
932 refresh_needed = any([str(x.message).startswith(msg) for x in warns])
/opt/conda/lib/python3.7/site-packages/sklearn/datasets/base.py in <listcomp>(.0)
928 msg = "sklearn.externals.joblib is deprecated in 0.21"
929 with warnings.catch_warnings(record=True) as warns:
--> 930 data = tuple([joblib.load(f) for f in files])
931
932 refresh_needed = any([str(x.message).startswith(msg) for x in warns])
/opt/conda/lib/python3.7/site-packages/joblib/numpy_pickle.py in load(filename, mmap_mode)
603 return load_compatibility(fobj)
604
--> 605 obj = _unpickle(fobj, filename, mmap_mode)
606
607 return obj
/opt/conda/lib/python3.7/site-packages/joblib/numpy_pickle.py in _unpickle(fobj, filename, mmap_mode)
527 obj = None
528 try:
--> 529 obj = unpickler.load()
530 if unpickler.compat_mode:
531 warnings.warn("The file '%s' has been generated with a "
/opt/conda/lib/python3.7/pickle.py in load(self)
1083 raise EOFError
1084 assert isinstance(key, bytes_types)
-> 1085 dispatch[key[0]](self)
1086 except _Stop as stopinst:
1087 return stopinst.value
/opt/conda/lib/python3.7/site-packages/joblib/numpy_pickle.py in load_build(self)
353 if isinstance(array_wrapper, NDArrayWrapper):
354 self.compat_mode = True
--> 355 self.stack.append(array_wrapper.read(self))
356
357 # Be careful to register our new method.
/opt/conda/lib/python3.7/site-packages/joblib/numpy_pickle.py in read(self, unpickler)
196 array = self.read_mmap(unpickler)
197 else:
--> 198 array = self.read_array(unpickler)
199
200 # Manage array subclass case
/opt/conda/lib/python3.7/site-packages/joblib/numpy_pickle.py in read_array(self, unpickler)
147 read_size = int(read_count * self.dtype.itemsize)
148 data = _read_bytes(unpickler.file_handle,
--> 149 read_size, "array data")
150 array[i:i + read_count] = \
151 unpickler.np.frombuffer(data, dtype=self.dtype,
/opt/conda/lib/python3.7/site-packages/joblib/numpy_pickle_utils.py in _read_bytes(fp, size, error_template)
241 if len(data) != size:
242 msg = "EOF: reading %s, expected %d bytes got %d"
--> 243 raise ValueError(msg % (error_template, size, len(data)))
244 else:
245 return data
ValueError: EOF: reading array data, expected 262144 bytes got 209661
I loaded a csv file using the following code
from pyspark import SparkContext
from pyspark.sql import *
sc = SparkContext(master='local[1]')
df = sq.read.csv(file_path,header='true',inferSchema='true')
But, when i tried to convert this spark dataframe i have to a pandas dataframe using the following code
pdf = df.toPandas()
i got the following error
OSError Traceback (most recent call last)
<ipython-input-27-cf3578af3a8d> in <module>()
----> 1 a = df.toPandas()
D:\softwares\anaconda\lib\site-packages\pyspark\sql\dataframe.py in toPandas(self)
1964 raise RuntimeError("%s\n%s" % (_exception_message(e), msg))
1965 else:
-> 1966 pdf = pd.DataFrame.from_records(self.collect(), columns=self.columns)
1967
1968 dtype = {}
D:\softwares\anaconda\lib\site-packages\pyspark\sql\dataframe.py in collect(self)
465 with SCCallSiteSync(self._sc) as css:
466 port = self._jdf.collectToPython()
--> 467 return list(_load_from_socket(port, BatchedSerializer(PickleSerializer())))
468
469 #ignore_unicode_prefix
D:\softwares\anaconda\lib\site-packages\pyspark\serializers.py in load_stream(self, stream)
143 while True:
144 try:
--> 145 yield self._read_with_length(stream)
146 except EOFError:
147 return
D:\softwares\anaconda\lib\site-packages\pyspark\serializers.py in _read_with_length(self, stream)
168 if len(obj) < length:
169 raise EOFError
--> 170 return self.loads(obj)
171
172 def dumps(self, obj):
D:\softwares\anaconda\lib\site-packages\pyspark\serializers.py in loads(self, obj, encoding)
557 if sys.version >= '3':
558 def loads(self, obj, encoding="bytes"):
--> 559 return pickle.loads(obj, encoding=encoding)
560 else:
561 def loads(self, obj, encoding=None):
D:\softwares\anaconda\lib\site-packages\pyspark\sql\types.py in <lambda>(*a)
1426 # This is used to unpickle a Row from JVM
1427 def _create_row_inbound_converter(dataType):
-> 1428 return lambda *a: dataType.fromInternal(a)
1429
1430
D:\softwares\anaconda\lib\site-packages\pyspark\sql\types.py in fromInternal(self, obj)
628 # Only calling fromInternal function for fields that need conversion
629 values = [f.fromInternal(v) if c else v
--> 630 for f, v, c in zip(self.fields, obj, self._needConversion)]
631 else:
632 values = obj
D:\softwares\anaconda\lib\site-packages\pyspark\sql\types.py in <listcomp>(.0)
628 # Only calling fromInternal function for fields that need conversion
629 values = [f.fromInternal(v) if c else v
--> 630 for f, v, c in zip(self.fields, obj, self._needConversion)]
631 else:
632 values = obj
D:\softwares\anaconda\lib\site-packages\pyspark\sql\types.py in fromInternal(self, obj)
440
441 def fromInternal(self, obj):
--> 442 return self.dataType.fromInternal(obj)
443
444 def typeName(self):
D:\softwares\anaconda\lib\site-packages\pyspark\sql\types.py in fromInternal(self, ts)
198 if ts is not None:
199 # using int to avoid precision loss in float
--> 200 return datetime.datetime.fromtimestamp(ts // 1000000).replace(microsecond=ts % 1000000)
201
202
OSError: [Errno 22] Invalid argument
Can anyone help me on how to solve this error?
My code:
from gensim.models import Word2Vec
from gensim.models import KeyedVectors
import pickle
with open('word2vec_model', 'rb') as handle:
model = pickle.load(handle)
The error that happens:
ValueError
Traceback (most recent call last)
<ipython-input-2-aa1ad84b16ed> in <module>()
18 #if you do NOT have RAM >= 12GB, use the code below.
19 with open('word2vec_model', 'rb') as handle:
---> 20 model = pickle.load(handle)
C:\Users\home pc\Anaconda2\lib\pickle.pyc in load(file)
1382
1383 def load(file):
-> 1384 return Unpickler(file).load()
1385
1386 def loads(str):
C:\Users\home pc\Anaconda2\lib\pickle.pyc in load(self)
862 while 1:
863 key = read(1)
--> 864 dispatch[key](self)
865 except _Stop, stopinst:
866 return stopinst.value
C:\Users\home pc\Anaconda2\lib\pickle.pyc in load_proto(self)
890 proto = ord(self.read(1))
891 if not 0 <= proto <= 2:
--> 892 raise ValueError, "unsupported pickle protocol: %d" % proto
893 dispatch[PROTO] = load_proto
894
ValueError: unsupported pickle protocol: 4