calling table_to_df from MS Fabric needing pytables workaround.

Hello i am trying to call the function table_to_df:

import json
import pandas as pd
import numpy as np
from stats_can import StatsCan
sc = StatsCan()

def get_statcan_dict(url_cube):

    with requests.Session() as c:
        var1 = c.get(url_cube)

    dict1 = json.loads(var1.text)
    return dict1
#
def get_statcan_metadata(js_dict,product_id_path):
    # donloaded metadata into a list
    list1 = []
    for i in js_dict:
        list1.append(pd.DataFrame.from_dict(i, orient='index').T)

    # concat that list and then create the dataframe
    df1 = pd.concat(list1)

    # create the download url
    df1['url'] = df1['productId'].apply(lambda x: f'{product_id_path}/{x}-eng.zip')
    return df1

url_cube = "https://www150.statcan.gc.ca/t1/wds/rest/getAllCubesList"
product_id_path = "https://www150.statcan.gc.ca/n1/tbl/csv"

stcan_dict = get_statcan_dict(url_cube)
df = get_statcan_metadata(stcan_dict,product_id_path)
data=sc.table_to_df('10100001')

but i am getting the following error: ImportError Traceback (most recent call last) File ~/cluster-env/clonedenv/lib/python3.10/site-packages/pandas/compat/_optional.py:142, in import_optional_dependency(name, extra, errors, min_version) 141 try: --> 142 module = importlib.import_module(name) 143 except ImportError:

File ~/cluster-env/clonedenv/lib/python3.10/importlib/init.py:126, in import_module(name, package) 125 level += 1 --> 126 return _bootstrap._gcd_import(name[level:], package, level)

File :1050, in _gcd_import(name, package, level)

File :1027, in _find_andload(name, import)

File :1006, in _find_and_loadunlocked(name, import)

File :688, in _load_unlocked(spec)

File :883, in exec_module(self, module)

File :241, in _call_with_frames_removed(f, *args, **kwds)

File ~/cluster-env/clonedenv/lib/python3.10/site-packages/tables/init.py:51 50 # Necessary imports to get versions stored on the cython extension ---> 51 from .utilsextension import get_hdf5_version as _get_hdf5_version 53 from ._version import version

File ~/cluster-env/clonedenv/lib/python3.10/site-packages/tables/utilsextension.pyx:25, in init tables.utilsextension()

File ~/cluster-env/clonedenv/lib/python3.10/site-packages/tables/description.py:9 7 import numpy as np ----> 9 from . import atom 10 from .path import check_name_validity

File ~/cluster-env/clonedenv/lib/python3.10/site-packages/tables/atom.py:5 4 import inspect ----> 5 from typing_extensions import Any, Callable, dataclass_transform, Dict, NoReturn, Union 6 import warnings

ImportError: cannot import name 'Callable' from 'typing_extensions' (/home/trusted-service-user/cluster-env/clonedenv/lib/python3.10/site-packages/typing_extensions.py)

During handling of the above exception, another exception occurred:

ImportError Traceback (most recent call last) Cell In[19], line 1 ----> 1 data=sc.table_to_df('10100001')

File ~/cluster-env/clonedenv/lib/python3.10/site-packages/stats_can/api_class.py:66, in StatsCan.table_to_df(self, table) 48 def table_to_df(self, table): 49 """Read a table to a dataframe. 50 51 Parameters (...) 64 call StatsCan.update_tables(), optionally passing just the table number of interest 65 """ ---> 66 return sc.table_to_df(table=table, path=self.data_folder, h5file="stats_can.h5")

File ~/cluster-env/clonedenv/lib/python3.10/site-packages/stats_can/sc.py:613, in table_to_df(table, path, h5file) 608 warn( 609 "This function will be deprecated in the v3 release. Please see the docs for details.", 610 FutureWarning, 611 ) 612 if h5file: --> 613 df = table_from_h5(table=table, h5file=h5file, path=path) 614 else: 615 df = zip_table_to_dataframe(table=table, path=path)

File ~/cluster-env/clonedenv/lib/python3.10/site-packages/stats_can/sc.py:334, in table_from_h5(table, h5file, path) 332 h5 = path / h5file 333 try: --> 334 with pd.HDFStore(h5, "r") as store: 335 df = pd.read_hdf(store, key=table) 336 except (KeyError, OSError):

File ~/cluster-env/clonedenv/lib/python3.10/site-packages/pandas/io/pytables.py:560, in HDFStore.init(self, path, mode, complevel, complib, fletcher32, **kwargs) 557 if "format" in kwargs: 558 raise ValueError("format is not a defined argument for HDFStore") --> 560 tables = import_optional_dependency("tables") 562 if complib is not None and complib not in tables.filters.all_complibs: 563 raise ValueError( 564 f"complib only supports {tables.filters.all_complibs} compression." 565 )

File ~/cluster-env/clonedenv/lib/python3.10/site-packages/pandas/compat/_optional.py:145, in import_optional_dependency(name, extra, errors, min_version) 143 except ImportError: 144 if errors == "raise": --> 145 raise ImportError(msg) 146 return None 148 # Handle submodules: if we have submodule, grab parent module from sys.modules

ImportError: Missing optional dependency 'pytables'. Use pip or conda to install pytables. pytables has some requirements that i am unable to fulfil in MS Fabric. any workaround or solutions.

ianepreston / stats_can

calling table_to_df from MS Fabric needing pytables workaround. #579