Flask Issue about responsible-ai-toolbox

[imatiach-msft]

@dogfood6 could you please post the errors you are seeing when importing RAIInsights or RAIDashboard?
what version of flask are you running? If you create a new compute instance in AzureML Notebook it should have all compatible & verified dependencies that work together with the latest azure-sdk packages.

[dogfood6]

Here is exactly what happens because when i import raiwidgets it doesnt work.

SDKv2 Python 3.10

---

SystemError Traceback (most recent call last)
Cell In[6], line 20
18 import datetime
19 import pickle # to save objects
---> 20 import raiwidgets

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/raiwidgets/init.py:7
4 """Package for the fairness, explanation, and error analysis widgets."""
6 from .version import version
----> 7 from .error_analysis_dashboard import ErrorAnalysisDashboard
8 from .explanation_dashboard import ExplanationDashboard
9 from .fairness_dashboard import FairnessDashboard

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/raiwidgets/error_analysis_dashboard.py:10
8 from .constants import ModelTask
9 from .dashboard import Dashboard
---> 10 from .error_analysis_dashboard_input import ErrorAnalysisDashboardInput
12 DEFAULT_MAX_DEPTH = 3
13 DEFAULT_NUM_LEAVES = 31

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/raiwidgets/error_analysis_dashboard_input.py:11
7 import pandas as pd
9 from erroranalysis._internal.constants import (Metrics, display_name_to_metric,
10 metric_to_display_name)
---> 11 from erroranalysis._internal.error_analyzer import (ModelAnalyzer,
12 PredictionsAnalyzer)
13 from erroranalysis._internal.utils import is_spark
14 from raiutils.data_processing import convert_to_list, serialize_json_safe

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/erroranalysis/_internal/error_analyzer/init.py:5
1 # Copyright (c) Microsoft Corporation
2 # Licensed under the MIT License.
4 """Init file, used for backwards compatibility."""
----> 5 from erroranalysis.analyzer import ModelAnalyzer, PredictionsAnalyzer
7 all = ['PredictionsAnalyzer', 'ModelAnalyzer']

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/erroranalysis/analyzer/init.py:5
1 # Copyright (c) Microsoft Corporation
2 # Licensed under the MIT License.
4 """Module for defining the analyzers."""
----> 5 from .error_analyzer import ModelAnalyzer, PredictionsAnalyzer
7 all = ["PredictionsAnalyzer", "ModelAnalyzer"]

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/erroranalysis/analyzer/error_analyzer.py:29
27 from erroranalysis._internal.utils import generate_random_unique_indexes
28 from erroranalysis._internal.version_checker import check_pandas_version
---> 29 from erroranalysis.error_correlation_methods import (
30 compute_ebm_global_importance, compute_gbm_global_importance)
31 from erroranalysis.report import ErrorReport
33 BIN_THRESHOLD = MatrixParams.BIN_THRESHOLD

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/erroranalysis/error_correlation_methods/init.py:7
4 """Module for defining error correlation methods."""
6 from .ebm import compute_ebm_global_importance
----> 7 from .gbm import compute_gbm_global_importance
9 all = ["compute_ebm_global_importance", "compute_gbm_global_importance"]

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/erroranalysis/error_correlation_methods/gbm.py:7
4 """Defines the error correlation computation using LightGBM with TreeShap."""
6 import numpy as np
----> 7 import shap
8 from lightgbm import LGBMClassifier, LGBMRegressor
10 from erroranalysis._internal.constants import ModelTask

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/shap/init.py:12
9 if (sys.version_info < (3, 0)):
10 warnings.warn("As of version 0.29.0 shap only supports Python 3 (not 2)!")
---> 12 from ._explanation import Explanation, Cohorts
14 # explainers
15 from .explainers._explainer import Explainer

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/shap/_explanation.py:12
10 from slicer import Slicer, Alias, Obj
11 # from ._order import Order
---> 12 from .utils._general import OpChain
13 from .utils._exceptions import DimensionError
15 # slicer confuses pylint...
16 # pylint: disable=no-member

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/shap/utils/init.py:1
----> 1 from ._clustering import hclust_ordering, partition_tree, partition_tree_shuffle, delta_minimization_order, hclust
2 from ._general import approximate_interactions, potential_interactions, sample, safe_isinstance, assert_import, record_import_error
3 from ._general import shapley_coefficients, convert_name, format_value, ordinal_str, OpChain, suppress_stderr

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/shap/utils/_clustering.py:4
2 import scipy as sp
3 from scipy.spatial.distance import pdist
----> 4 from numba import jit
5 import sklearn
6 import warnings

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/numba/init.py:42
38 from numba.core.decorators import (cfunc, generated_jit, jit, njit, stencil,
39 jit_module)
41 # Re-export vectorize decorators and the thread layer querying function
---> 42 from numba.np.ufunc import (vectorize, guvectorize, threading_layer,
43 get_num_threads, set_num_threads)
45 # Re-export Numpy helpers
46 from numba.np.numpy_support import carray, farray, from_dtype

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/numba/np/ufunc/init.py:3
1 # -- coding: utf-8 --
----> 3 from numba.np.ufunc.decorators import Vectorize, GUVectorize, vectorize, guvectorize
4 from numba.np.ufunc._internal import PyUFunc_None, PyUFunc_Zero, PyUFunc_One
5 from numba.np.ufunc import _internal, array_exprs

File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/numba/np/ufunc/decorators.py:3
1 import inspect
----> 3 from numba.np.ufunc import _internal
4 from numba.np.ufunc.parallel import ParallelUFuncBuilder, ParallelGUFuncBuilder
6 from numba.core.registry import DelayedRegistry

SystemError: initialization of _internal failed without raising an exception

[dogfood6]

Python 3.8 AzureML

this is the code i am running

_###############

Libraries

###############
import pandas as pd # manipulate data
import numpy as np # calculate the mean and standard deviation
import sklearn
from scipy.stats import stats, randint
import random
from sklearn import preprocessing
from sklearn.model_selection import GridSearchCV, cross_val_score, learning_curve # cross validation and tuning
from sklearn.model_selection import train_test_split # split data into training and testing sets
from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error
import xgboost as xgb # XGBoost
from xgboost.sklearn import XGBRegressor
import itertools
import matplotlib.pyplot as plt
import seaborn as sns; sns.set()
import datetime
import pickle # to save objects
import raiwidgets_

WARNING:root:'PYARROW_IGNORE_TIMEZONE' environment variable was not set. It is required to set this environment variable to '1' in both driver and executor sides if you use pyarrow>=2.0.0. pandas-on-Spark will set it for you but it does not work if there is a Spark context already launched.

AttributeError Traceback (most recent call last)
Cell In[2], line 20
18 import datetime
19 import pickle # to save objects
---> 20 import raiwidgets

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/raiwidgets/init.py:7
4 """Package for the fairness, explanation, and error analysis widgets."""
6 from .version import version
----> 7 from .error_analysis_dashboard import ErrorAnalysisDashboard
8 from .explanation_dashboard import ExplanationDashboard
9 from .fairness_dashboard import FairnessDashboard

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/raiwidgets/error_analysis_dashboard.py:10
8 from .constants import ModelTask
9 from .dashboard import Dashboard
---> 10 from .error_analysis_dashboard_input import ErrorAnalysisDashboardInput
12 DEFAULT_MAX_DEPTH = 3
13 DEFAULT_NUM_LEAVES = 31

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/raiwidgets/error_analysis_dashboard_input.py:11
7 import pandas as pd
9 from erroranalysis._internal.constants import (Metrics, display_name_to_metric,
10 metric_to_display_name)
---> 11 from erroranalysis._internal.error_analyzer import (ModelAnalyzer,
12 PredictionsAnalyzer)
13 from erroranalysis._internal.utils import is_spark
14 from raiutils.data_processing import convert_to_list, serialize_json_safe

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/erroranalysis/_internal/error_analyzer/init.py:5
1 # Copyright (c) Microsoft Corporation
2 # Licensed under the MIT License.
4 """Init file, used for backwards compatibility."""
----> 5 from erroranalysis.analyzer import ModelAnalyzer, PredictionsAnalyzer
7 all = ['PredictionsAnalyzer', 'ModelAnalyzer']

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/erroranalysis/analyzer/init.py:5
1 # Copyright (c) Microsoft Corporation
2 # Licensed under the MIT License.
4 """Module for defining the analyzers."""
----> 5 from .error_analyzer import ModelAnalyzer, PredictionsAnalyzer
7 all = ["PredictionsAnalyzer", "ModelAnalyzer"]

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/erroranalysis/analyzer/error_analyzer.py:22
20 from erroranalysis._internal.metrics import metric_to_func
21 from erroranalysis._internal.process_categoricals import process_categoricals
---> 22 from erroranalysis._internal.surrogate_error_tree import
23 compute_error_tree as _compute_error_tree
24 from erroranalysis._internal.surrogate_error_tree import
25 compute_error_tree_on_dataset as _compute_error_tree_on_dataset
26 from erroranalysis._internal.utils import generate_random_unique_indexes

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/erroranalysis/_internal/surrogate_error_tree.py:9
7 import numpy as np
8 import pandas as pd
----> 9 from lightgbm import Booster, LGBMClassifier, LGBMRegressor
10 from sklearn.metrics import (mean_absolute_error, mean_squared_error,
11 median_absolute_error, r2_score)
13 from erroranalysis._internal.cohort_filter import filter_from_cohort

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/lightgbm/init.py:8
2 """LightGBM, Light Gradient Boosting Machine.
3
4 Contributors: https://github.com/microsoft/LightGBM/graphs/contributors.
5 """
6 import os
----> 8 from .basic import Booster, Dataset, register_logger
9 from .callback import early_stopping, print_evaluation, record_evaluation, reset_parameter
10 from .engine import CVBooster, cv, train

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/lightgbm/basic.py:17
14 import numpy as np
15 import scipy.sparse
---> 17 from .compat import PANDAS_INSTALLED, concat, dt_DataTable, is_dtype_sparse, pd_DataFrame, pd_Series
18 from .libpath import find_lib_path
21 class _DummyLogger:

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/lightgbm/compat.py:115
113 from dask import delayed
114 from dask.array import Array as dask_Array
--> 115 from dask.dataframe import DataFrame as dask_DataFrame
116 from dask.dataframe import Series as dask_Series
117 from dask.distributed import Client, default_client, wait

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/dask/dataframe/init.py:3
1 try:
2 from ..base import compute
----> 3 from . import backends, dispatch, rolling
4 from .core import (
5 DataFrame,
6 Index,
(...)
12 to_timedelta,
13 )
14 from .groupby import Aggregation

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/dask/dataframe/backends.py:17
15 from ..utils import is_arraylike, typename
16 from ._compat import PANDAS_GT_100
---> 17 from .core import DataFrame, Index, Scalar, Series, _Frame
18 from .dispatch import (
19 categorical_dtype_dispatch,
20 concat,
(...)
30 union_categoricals_dispatch,
31 )
32 from .extensions import make_array_nonempty, make_scalar

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/dask/dataframe/core.py:56
36 from ..utils import (
37 IndexCallable,
38 M,
(...)
53 typename,
54 )
55 from . import methods
---> 56 from .accessor import DatetimeAccessor, StringAccessor
57 from .categorical import CategoricalAccessor, categorize
58 from .dispatch import (
59 get_parallel_type,
60 group_split_dispatch,
61 hash_object_dispatch,
62 meta_nonempty,
63 )

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/dask/dataframe/accessor.py:109
98 """Accessor object for datetimelike properties of the Series values.
99
100 Examples
(...)
103 >>> s.dt.microsecond # doctest: +SKIP
104 """
106 _accessor_name = "dt"
--> 109 class StringAccessor(Accessor):
110 """Accessor object for string properties of the Series values.
111
112 Examples
(...)
115 >>> s.str.lower() # doctest: +SKIP
116 """
118 _accessor_name = "str"

File /anaconda/envs/azureml_py38/lib/python3.8/site-packages/dask/dataframe/accessor.py:121, in StringAccessor()
118 _accessor_name = "str"
119 _not_implemented = {"get_dummies"}
--> 121 @derived_from(pd.core.strings.StringMethods)
122 def split(self, pat=None, n=-1, expand=False):
123 if expand:
124 if n == -1:

AttributeError: module 'pandas.core.strings' has no attribute 'StringMethods'

[dogfood6]

FINALLY GOT IT FIXED SORRY FOR BOTHERING

[imatiach-msft]

@dogfood6 great to hear that it is resolved - if you are still having issues, please let us know. I would be happy to get on a Teams call (or your preferred meeting software). I can send you the Teams meeting invite next time if you run into any issues and we can schedule a debugging session.