alex-ber / alpine-anaconda3 Goto Github PK

import pandas as pd 
from nltk.corpus import stopwords
print(stopwords.words('english'))

Failed with:

Traceback (most recent call last):
File "/opt/anaconda3/lib/python3.8/site-packages/nltk/corpus/util.py", line 86, in __load
root = nltk.data.find('{}/{}'.format(self.subdir, zip_name))
File "/opt/anaconda3/lib/python3.8/site-packages/nltk/data.py", line 701, in find
raise LookupError(resource_not_found)
LookupError:

Resource stopwords not found.
Please use the NLTK Downloader to obtain the resource:
import nltk

nltk.download('stopwords')

For more information see: https://www.nltk.org/data.html
Attempted to load corpora/stopwords.zip/stopwords/
Searched in:
- '/root/nltk_data'
- '/opt/anaconda3/nltk_data'
- '/opt/anaconda3/share/nltk_data'
- '/opt/anaconda3/lib/nltk_data'
- '/usr/share/nltk_data'
- '/usr/local/share/nltk_data'
- '/usr/lib/nltk_data'
- '/usr/local/lib/nltk_data'

During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/opt/anaconda3/lib/python3.8/site-packages/IPython/core/interactiveshell.py", line 3417, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 1, in
runfile('/opt/project/emrpythonconnect/check2.py', wdir='/opt/project/emrpythonconnect')
File "/opt/.pycharm_helpers/pydev/_pydev_bundle/pydev_umd.py", line 197, in runfile
pydev_imports.execfile(filename, global_vars, local_vars) # execute the script
File "/opt/.pycharm_helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/opt/project/emrpythonconnect/check2.py", line 11, in
print(stopwords.words('english'))
File "/opt/anaconda3/lib/python3.8/site-packages/nltk/corpus/util.py", line 123, in getattr
self.__load()
File "/opt/anaconda3/lib/python3.8/site-packages/nltk/corpus/util.py", line 88, in __load
raise e
File "/opt/anaconda3/lib/python3.8/site-packages/nltk/corpus/util.py", line 83, in __load
root = nltk.data.find('{}/{}'.format(self.subdir, self.__name))
File "/opt/anaconda3/lib/python3.8/site-packages/nltk/data.py", line 701, in find
raise LookupError(resource_not_found)
LookupError:

Resource stopwords not found.
Please use the NLTK Downloader to obtain the resource:
import nltk

nltk.download('stopwords')

For more information see: https://www.nltk.org/data.html
Attempted to load corpora/stopwords
Searched in:
- '/root/nltk_data'
- '/opt/anaconda3/nltk_data'
- '/opt/anaconda3/share/nltk_data'
- '/opt/anaconda3/lib/nltk_data'
- '/usr/share/nltk_data'
- '/usr/local/share/nltk_data'
- '/usr/lib/nltk_data'
- '/usr/local/lib/nltk_data'

As work-arround one need to type

docker run -it --entrypoint bash alexberkovich/alpine-python3:0.3.2

or

docker run -it --entrypoint bash alexberkovich/alpine-anaconda3:0.3.2

The entrypoint should be sh/bash.

pip install numpy==1.20.3 success

pip install scipy==1.5.4

`
Collecting scipy==1.5.4
Downloading scipy-1.5.4.tar.gz (25.2 MB)
|████████████████████████████████| 25.2 MB 5.7 MB/s
Installing build dependencies ... \ done
Getting requirements to build wheel ... done
Preparing wheel metadata ... error
ERROR: Command errored out with exit status 1:
command: /usr/bin/python /usr/lib/python3.8/site-packages/pip/_vendor/pep517/_in_process.py prepare_metadata_for_build_wheel /tmp/tmpvkfinqgv
cwd: /tmp/pip-install-ut7y17vq/scipy_018ac8e531bf44fa856ffc58cd6060a6
Complete output (234 lines):
setup.py:460: UserWarning: Unrecognized setuptools command ('dist_info --egg-base /tmp/pip-modern-metadata-7ysq6nl2'), proceeding with generating Cython sources and expanding templates
warnings.warn("Unrecognized setuptools command ('{}'), proceeding with "
Running from SciPy source directory.
lapack_opt_info:
lapack_mkl_info:
customize UnixCCompiler
libraries mkl_rt not found in ['/usr/local/lib', '/usr/lib', '/usr/lib/']
NOT AVAILABLE

openblas_lapack_info:
customize UnixCCompiler
customize UnixCCompiler
  libraries openblas not found in ['/usr/local/lib', '/usr/lib', '/usr/lib/']
  NOT AVAILABLE

openblas_clapack_info:
customize UnixCCompiler
customize UnixCCompiler
  libraries openblas,lapack not found in ['/usr/local/lib', '/usr/lib', '/usr/lib/']
  NOT AVAILABLE

flame_info:
customize UnixCCompiler
  libraries flame not found in ['/usr/local/lib', '/usr/lib', '/usr/lib/']
  NOT AVAILABLE

atlas_3_10_threads_info:
Setting PTATLAS=ATLAS
customize UnixCCompiler
  libraries lapack_atlas not found in /usr/local/lib
customize UnixCCompiler
  libraries tatlas,tatlas not found in /usr/local/lib
customize UnixCCompiler
  libraries lapack_atlas not found in /usr/lib
customize UnixCCompiler
  libraries tatlas,tatlas not found in /usr/lib
customize UnixCCompiler
  libraries lapack_atlas not found in /usr/lib/
customize UnixCCompiler
  libraries tatlas,tatlas not found in /usr/lib/
<class 'numpy.distutils.system_info.atlas_3_10_threads_info'>
  NOT AVAILABLE

atlas_3_10_info:
customize UnixCCompiler
  libraries lapack_atlas not found in /usr/local/lib
customize UnixCCompiler
  libraries satlas,satlas not found in /usr/local/lib
customize UnixCCompiler
  libraries lapack_atlas not found in /usr/lib
customize UnixCCompiler
  libraries satlas,satlas not found in /usr/lib
customize UnixCCompiler
  libraries lapack_atlas not found in /usr/lib/
customize UnixCCompiler
  libraries satlas,satlas not found in /usr/lib/
<class 'numpy.distutils.system_info.atlas_3_10_info'>
  NOT AVAILABLE

atlas_threads_info:
Setting PTATLAS=ATLAS
customize UnixCCompiler
  libraries lapack_atlas not found in /usr/local/lib
customize UnixCCompiler
  libraries ptf77blas,ptcblas,atlas not found in /usr/local/lib
customize UnixCCompiler
  libraries lapack_atlas not found in /usr/lib
customize UnixCCompiler
  libraries ptf77blas,ptcblas,atlas not found in /usr/lib
customize UnixCCompiler
  libraries lapack_atlas not found in /usr/lib/
customize UnixCCompiler
  libraries ptf77blas,ptcblas,atlas not found in /usr/lib/
<class 'numpy.distutils.system_info.atlas_threads_info'>
  NOT AVAILABLE

atlas_info:
customize UnixCCompiler
  libraries lapack_atlas not found in /usr/local/lib
customize UnixCCompiler
  libraries f77blas,cblas,atlas not found in /usr/local/lib
customize UnixCCompiler
  libraries lapack_atlas not found in /usr/lib
customize UnixCCompiler
  libraries f77blas,cblas,atlas not found in /usr/lib
customize UnixCCompiler
  libraries lapack_atlas not found in /usr/lib/
customize UnixCCompiler
  libraries f77blas,cblas,atlas not found in /usr/lib/
<class 'numpy.distutils.system_info.atlas_info'>
  NOT AVAILABLE

accelerate_info:
  NOT AVAILABLE

lapack_info:
customize UnixCCompiler
customize UnixCCompiler
  FOUND:
    libraries = ['lapack', 'lapack']
    library_dirs = ['/usr/lib']
    language = f77

blas_opt_info:
blas_mkl_info:
customize UnixCCompiler
  libraries mkl_rt not found in ['/usr/local/lib', '/usr/lib', '/usr/lib/']
  NOT AVAILABLE

blis_info:
customize UnixCCompiler
  libraries blis not found in ['/usr/local/lib', '/usr/lib', '/usr/lib/']
  NOT AVAILABLE

openblas_info:
customize UnixCCompiler
customize UnixCCompiler
  libraries openblas not found in ['/usr/local/lib', '/usr/lib', '/usr/lib/']
  NOT AVAILABLE

atlas_3_10_blas_threads_info:
Setting PTATLAS=ATLAS
customize UnixCCompiler
  libraries tatlas not found in ['/usr/local/lib', '/usr/lib', '/usr/lib/']
  NOT AVAILABLE

atlas_3_10_blas_info:
customize UnixCCompiler
  libraries satlas not found in ['/usr/local/lib', '/usr/lib', '/usr/lib/']
  NOT AVAILABLE

atlas_blas_threads_info:
Setting PTATLAS=ATLAS
customize UnixCCompiler
  libraries ptf77blas,ptcblas,atlas not found in ['/usr/local/lib', '/usr/lib', '/usr/lib/']
  NOT AVAILABLE

atlas_blas_info:
customize UnixCCompiler
  libraries f77blas,cblas,atlas not found in ['/usr/local/lib', '/usr/lib', '/usr/lib/']
  NOT AVAILABLE

/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/numpy/distutils/system_info.py:690: UserWarning:
    Optimized (vendor) Blas libraries are not found.
    Falls back to netlib Blas library which has worse performance.
    A better performance should be easily gained by switching
    Blas library.
  self.calc_info()
blas_info:
customize UnixCCompiler
  libraries blas not found in ['/usr/local/lib', '/usr/lib', '/usr/lib/']
  NOT AVAILABLE

/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/numpy/distutils/system_info.py:690: UserWarning:
    Blas (http://www.netlib.org/blas/) libraries not found.
    Directories to search for the libraries can be specified in the
    numpy/distutils/site.cfg file (section [blas]) or by setting
    the BLAS environment variable.
  self.calc_info()
blas_src_info:
  NOT AVAILABLE

/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/numpy/distutils/system_info.py:690: UserWarning:
    Blas (http://www.netlib.org/blas/) sources not found.
    Directories to search for the sources can be specified in the
    numpy/distutils/site.cfg file (section [blas_src]) or by setting
    the BLAS_SRC environment variable.
  self.calc_info()
  NOT AVAILABLE

/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/numpy/distutils/system_info.py:1712: UserWarning:
    Blas (http://www.netlib.org/blas/) libraries not found.
    Directories to search for the libraries can be specified in the
    numpy/distutils/site.cfg file (section [blas]) or by setting
    the BLAS environment variable.
  if getattr(self, '_calc_info_{}'.format(lapack))():
/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/numpy/distutils/system_info.py:1712: UserWarning:
    Blas (http://www.netlib.org/blas/) sources not found.
    Directories to search for the sources can be specified in the
    numpy/distutils/site.cfg file (section [blas_src]) or by setting
    the BLAS_SRC environment variable.
  if getattr(self, '_calc_info_{}'.format(lapack))():
  FOUND:
    libraries = ['lapack', 'lapack']
    library_dirs = ['/usr/lib']
    language = f77
    define_macros = [('NO_ATLAS_INFO', 1)]

/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/numpy/distutils/system_info.py:782: UserWarning: Specified path /tmp/pip-build-env-cbc8_kzr/overlay/include/python3.8 is invalid.
  return self.get_paths(self.section, key)
scipy/odr/setup.py:19: UserWarning:
    Blas (http://www.netlib.org/blas/) libraries not found.
    Directories to search for the libraries can be specified in the
    numpy/distutils/site.cfg file (section [blas]) or by setting
    the BLAS environment variable.
  warnings.warn(BlasNotFoundError.__doc__)
Traceback (most recent call last):
  File "/usr/lib/python3.8/site-packages/pip/_vendor/pep517/_in_process.py", line 280, in <module>
    main()
  File "/usr/lib/python3.8/site-packages/pip/_vendor/pep517/_in_process.py", line 263, in main
    json_out['return_val'] = hook(**hook_input['kwargs'])
  File "/usr/lib/python3.8/site-packages/pip/_vendor/pep517/_in_process.py", line 133, in prepare_metadata_for_build_wheel
    return hook(metadata_directory, config_settings)
  File "/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/setuptools/build_meta.py", line 166, in prepare_metadata_for_build_wheel
    self.run_setup()
  File "/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/setuptools/build_meta.py", line 258, in run_setup
    super(_BuildMetaLegacyBackend,
  File "/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/setuptools/build_meta.py", line 150, in run_setup
    exec(compile(code, __file__, 'exec'), locals())
  File "setup.py", line 583, in <module>
    setup_package()
  File "setup.py", line 579, in setup_package
    setup(**metadata)
  File "/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/numpy/distutils/core.py", line 137, in setup
    config = configuration()
  File "setup.py", line 485, in configuration
    config.add_subpackage('scipy')
  File "/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/numpy/distutils/misc_util.py", line 1033, in add_subpackage
    config_list = self.get_subpackage(subpackage_name, subpackage_path,
  File "/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/numpy/distutils/misc_util.py", line 999, in get_subpackage
    config = self._get_configuration_from_setup_py(
  File "/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/numpy/distutils/misc_util.py", line 941, in _get_configuration_from_setup_py
    config = setup_module.configuration(*args)
  File "scipy/setup.py", line 17, in configuration
    config.add_subpackage('odr')
  File "/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/numpy/distutils/misc_util.py", line 1033, in add_subpackage
    config_list = self.get_subpackage(subpackage_name, subpackage_path,
  File "/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/numpy/distutils/misc_util.py", line 999, in get_subpackage
    config = self._get_configuration_from_setup_py(
  File "/tmp/pip-build-env-cbc8_kzr/overlay/lib/python3.8/site-packages/numpy/distutils/misc_util.py", line 941, in _get_configuration_from_setup_py
    config = setup_module.configuration(*args)
  File "scipy/odr/setup.py", line 28, in configuration
    blas_info['define_macros'].extend(numpy_nodepr_api['define_macros'])
KeyError: 'define_macros'
----------------------------------------

ERROR: Command errored out with exit status 1: /usr/bin/python /usr/lib/python3.8/site-packages/pip/_vendor/pep517/_in_process.py prepare_metadata_for_build_wheel /tmp/tmpvkfinqgv Check the logs for full command output.
WARNING: You are using pip version 20.3.1; however, version 21.1.2 is available.
You should consider upgrading via the '/usr/bin/python -m pip install --upgrade pip' command.
bash-5.0#
bash-5.0# apk add openblas-dev
fetch http://dl-cdn.alpinelinux.org/alpine/v3.12/main/aarch64/APKINDEX.tar.gz
fetch http://dl-cdn.alpinelinux.org/alpine/v3.12/community/aarch64/APKINDEX.tar.gz
(1/2) Installing openblas (0.3.9-r2)
(2/2) Installing openblas-dev (0.3.9-r2)
Executing glibc-bin-2.32-r0.trigger
/usr/glibc-compat/sbin/ldconfig: /usr/glibc-compat/lib/ld-linux-aarch64.so.1 is not a symbolic link

OK: 614 MiB in 121 packages
bash-5.0# pip install scipy
Collecting scipy
Downloading scipy-1.6.3.tar.gz (27.2 MB)
|████████████████████████████████| 27.2 MB 5.5 MB/s
Installing build dependencies ... done
Getting requirements to build wheel ... done
Preparing wheel metadata ... error
ERROR: Command errored out with exit status 1:
command: /usr/bin/python /usr/lib/python3.8/site-packages/pip/_vendor/pep517/_in_process.py prepare_metadata_for_build_wheel /tmp/tmpi7v8cye1
cwd: /tmp/pip-install-hx4tjyta/scipy_85e0e5970b2d4f13913c09679a317a4f
Complete output (4 lines):
setup.py:462: UserWarning: Unrecognized setuptools command ('dist_info --egg-base /tmp/pip-modern-metadata-undac0lj'), proceeding with generating Cython sources and expanding templates
warnings.warn("Unrecognized setuptools command ('{}'), proceeding with "
Error: 'numpy' must be installed before running the build.

----------------------------------------

ERROR: Command errored out with exit status 1: /usr/bin/python /usr/lib/python3.8/site-packages/pip/_vendor/pep517/_in_process.py prepare_metadata_for_build_wheel /tmp/tmpi7v8cye1 Check the logs for full command output.

`

apk add openblas-dev=0.3.9-r2 should be added to Dockerfile (maybe there are more packages to add...)
https://unix.stackexchange.com/questions/550290/using-blas-in-alpine-linux

`
#!/usr/bin/python3

#taken from https://python.gotrained.com/tf-idf-twitter-sentiment-analysis/

import numpy as np
import pandas as pd
import re
import nltk
nltk.download('stopwords')
from nltk.corpus import stopwords

tweets = pd.read_csv("https://raw.githubusercontent.com/kolaveridi/kaggle-Twitter-US-Airline-Sentiment-/master/Tweets.csv")

print(tweets.head())

print(tweets.shape)

import matplotlib
matplotlib.use('PDF')

import matplotlib.pyplot as plt
import seaborn as sns

sns.countplot(x='airline_sentiment', data=tweets)
plt.savefig("/opt/project/emrpythonconnect/figure_1")

sns.countplot(x='airline', data=tweets)
plt.savefig("/opt/project/emrpythonconnect/figure_2")

sns.countplot(x='airline', hue="airline_sentiment", data=tweets)
plt.savefig("/opt/project/emrpythonconnect/figure_3")

X = tweets.iloc[:, 10].values
y = tweets.iloc[:, 1].values

processed_tweets = []

for tweet in range(0, len(X)):
# Remove all the special characters
processed_tweet = re.sub(r'\W', ' ', str(X[tweet]))

# remove all single characters
processed_tweet = re.sub(r'\s+[a-zA-Z]\s+', ' ', processed_tweet)

# Remove single characters from the start
processed_tweet = re.sub(r'\^[a-zA-Z]\s+', ' ', processed_tweet)

# Substituting multiple spaces with single space
processed_tweet= re.sub(r'\s+', ' ', processed_tweet, flags=re.I)

# Removing prefixed 'b'
processed_tweet = re.sub(r'^b\s+', '', processed_tweet)

# Converting to Lowercase
processed_tweet = processed_tweet.lower()

processed_tweets.append(processed_tweet)

from sklearn.feature_extraction.text import TfidfVectorizer
tfidfconverter = TfidfVectorizer(max_features=2000, min_df=5, max_df=0.7, stop_words=stopwords.words('english'))
X = tfidfconverter.fit_transform(processed_tweets).toarray()
`

Traceback (most recent call last):
File "/opt/anaconda3/lib/python3.8/site-packages/IPython/core/interactiveshell.py", line 3417, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 1, in
runfile('/opt/project/emrpythonconnect/check2.py', wdir='/opt/project/emrpythonconnect')
File "/opt/.pycharm_helpers/pydev/_pydev_bundle/pydev_umd.py", line 197, in runfile
pydev_imports.execfile(filename, global_vars, local_vars) # execute the script
File "/opt/.pycharm_helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/opt/project/emrpythonconnect/check2.py", line 8, in
import nltk
File "/opt/anaconda3/lib/python3.8/site-packages/nltk/init.py", line 143, in
from nltk.chunk import *
File "/opt/anaconda3/lib/python3.8/site-packages/nltk/chunk/init.py", line 157, in
from nltk.chunk.api import ChunkParserI
File "/opt/anaconda3/lib/python3.8/site-packages/nltk/chunk/api.py", line 13, in
from nltk.parse import ParserI
File "/opt/anaconda3/lib/python3.8/site-packages/nltk/parse/init.py", line 100, in
from nltk.parse.transitionparser import TransitionParser
File "/opt/anaconda3/lib/python3.8/site-packages/nltk/parse/transitionparser.py", line 22, in
from sklearn.datasets import load_svmlight_file
File "/opt/anaconda3/lib/python3.8/site-packages/sklearn/init.py", line 64, in
from .base import clone
File "/opt/anaconda3/lib/python3.8/site-packages/sklearn/base.py", line 14, in
from .utils.fixes import signature
File "/opt/anaconda3/lib/python3.8/site-packages/sklearn/utils/init.py", line 14, in
from . import _joblib
File "/opt/anaconda3/lib/python3.8/site-packages/sklearn/utils/_joblib.py", line 22, in
from ..externals import joblib
File "/opt/anaconda3/lib/python3.8/site-packages/sklearn/externals/joblib/init.py", line 119, in
from .parallel import Parallel
File "/opt/anaconda3/lib/python3.8/site-packages/sklearn/externals/joblib/parallel.py", line 28, in
from ._parallel_backends import (FallbackToBackend, MultiprocessingBackend,
File "/opt/anaconda3/lib/python3.8/site-packages/sklearn/externals/joblib/_parallel_backends.py", line 22, in
from .executor import get_memmapping_executor
File "/opt/anaconda3/lib/python3.8/site-packages/sklearn/externals/joblib/executor.py", line 14, in
from .externals.loky.reusable_executor import get_reusable_executor
File "/opt/anaconda3/lib/python3.8/site-packages/sklearn/externals/joblib/externals/loky/init.py", line 12, in
from .backend.reduction import set_loky_pickler
File "/opt/anaconda3/lib/python3.8/site-packages/sklearn/externals/joblib/externals/loky/backend/reduction.py", line 125, in
from sklearn.externals.joblib.externals import cloudpickle # noqa: F401
File "/opt/anaconda3/lib/python3.8/site-packages/sklearn/externals/joblib/externals/cloudpickle/init.py", line 3, in
from .cloudpickle import *
File "/opt/anaconda3/lib/python3.8/site-packages/sklearn/externals/joblib/externals/cloudpickle/cloudpickle.py", line 167, in
_cell_set_template_code = _make_cell_set_template_code()
File "/opt/anaconda3/lib/python3.8/site-packages/sklearn/externals/joblib/externals/cloudpickle/cloudpickle.py", line 148, in _make_cell_set_template_code
return types.CodeType(
TypeError: an integer is required (got type bytes)