ZeroDivision Error executing ProfileReport

[mldhamacher]

Current Behaviour

ZeroDivisionError while executing

report = ProfileReport(df, title='None', correlations=None)

with a spark dataframe.

---------------------------------------------------------------------------
ZeroDivisionError                         Traceback (most recent call last)
<command-4043649982577705> in <cell line: 37>()
     35 
     36 # print(df.schema)# display(df)
---> 37 profile_data(spark, data_df=df, start_date=start_date)
     38 # results = profile_data(spark, data_df=df, start_date=start_date)

<command-4043649982577705> in profile_data(spark, data_df, start_date)
     12 
     13     # json_object = report.to_json()
---> 14     report_html = report.to_html()
     15     displayHTML(report_html)
     16     # jobj = json.loads(json_object)

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/typeguard/__init__.py in wrapper(*args, **kwargs)
   1031         memo = _CallMemo(python_func, _localns, args=args, kwargs=kwargs)
   1032         check_argument_types(memo)
-> 1033         retval = func(*args, **kwargs)
   1034         try:
   1035             check_return_type(retval, memo)

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/profile_report.py in to_html(self)
    468 
    469         """
--> 470         return self.html
    471 
    472     def to_json(self) -> str:

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/typeguard/__init__.py in wrapper(*args, **kwargs)
   1031         memo = _CallMemo(python_func, _localns, args=args, kwargs=kwargs)
   1032         check_argument_types(memo)
-> 1033         retval = func(*args, **kwargs)
   1034         try:
   1035             check_return_type(retval, memo)

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/profile_report.py in html(self)
    275     def html(self) -> str:
    276         if self._html is None:
--> 277             self._html = self._render_html()
    278         return self._html
    279 

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/typeguard/__init__.py in wrapper(*args, **kwargs)
   1031         memo = _CallMemo(python_func, _localns, args=args, kwargs=kwargs)
   1032         check_argument_types(memo)
-> 1033         retval = func(*args, **kwargs)
   1034         try:
   1035             check_return_type(retval, memo)

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/profile_report.py in _render_html(self)
    383         from ydata_profiling.report.presentation.flavours import HTMLReport
    384 
--> 385         report = self.report
    386 
    387         with tqdm(

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/typeguard/__init__.py in wrapper(*args, **kwargs)
   1031         memo = _CallMemo(python_func, _localns, args=args, kwargs=kwargs)
   1032         check_argument_types(memo)
-> 1033         retval = func(*args, **kwargs)
   1034         try:
   1035             check_return_type(retval, memo)

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/profile_report.py in report(self)
    269     def report(self) -> Root:
    270         if self._report is None:
--> 271             self._report = get_report_structure(self.config, self.description_set)
    272         return self._report
    273 

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/typeguard/__init__.py in wrapper(*args, **kwargs)
   1031         memo = _CallMemo(python_func, _localns, args=args, kwargs=kwargs)
   1032         check_argument_types(memo)
-> 1033         retval = func(*args, **kwargs)
   1034         try:
   1035             check_return_type(retval, memo)

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/profile_report.py in description_set(self)
    251     def description_set(self) -> BaseDescription:
    252         if self._description_set is None:
--> 253             self._description_set = describe_df(
    254                 self.config,
    255                 self.df,

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/model/describe.py in describe(config, df, summarizer, typeset, sample)
     72         # Variable-specific
     73         pbar.total += len(df.columns)
---> 74         series_description = get_series_descriptions(
     75             config, df, summarizer, typeset, pbar
     76         )

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/multimethod/__init__.py in __call__(self, *args, **kwargs)
    313         func = self[tuple(func(arg) for func, arg in zip(self.type_checkers, args))]
    314         try:
--> 315             return func(*args, **kwargs)
    316         except TypeError as ex:
    317             raise DispatchError(f"Function {func.__code__}") from ex

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/model/spark/summary_spark.py in spark_get_series_descriptions(config, df, summarizer, typeset, pbar)
     90     args = [(name, df) for name in df.columns]
     91     with multiprocessing.pool.ThreadPool(12) as executor:
---> 92         for i, (column, description) in enumerate(
     93             executor.imap_unordered(multiprocess_1d, args)
     94         ):

/usr/lib/python3.9/multiprocessing/pool.py in next(self, timeout)
    868         if success:
    869             return value
--> 870         raise value
    871 
    872     __next__ = next                    # XXX

/usr/lib/python3.9/multiprocessing/pool.py in worker(inqueue, outqueue, initializer, initargs, maxtasks, wrap_exception)
    123         job, i, func, args, kwds = task
    124         try:
--> 125             result = (True, func(*args, **kwds))
    126         except Exception as e:
    127             if wrap_exception and func is not _helper_reraises_exception:

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/model/spark/summary_spark.py in multiprocess_1d(args)
     86         """
     87         column, df = args
---> 88         return column, describe_1d(config, df.select(column), summarizer, typeset)
     89 
     90     args = [(name, df) for name in df.columns]

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/multimethod/__init__.py in __call__(self, *args, **kwargs)
    313         func = self[tuple(func(arg) for func, arg in zip(self.type_checkers, args))]
    314         try:
--> 315             return func(*args, **kwargs)
    316         except TypeError as ex:
    317             raise DispatchError(f"Function {func.__code__}") from ex

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/model/spark/summary_spark.py in spark_describe_1d(config, series, summarizer, typeset)
     62         }[dtype]
     63 
---> 64     return summarizer.summarize(config, series, dtype=vtype)
     65 
     66 

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/model/summarizer.py in summarize(self, config, series, dtype)
     40             object:
     41         """
---> 42         _, _, summary = self.handle(str(dtype), config, series, {"type": str(dtype)})
     43         return summary
     44 

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/model/handler.py in handle(self, dtype, *args, **kwargs)
     60         funcs = self.mapping.get(dtype, [])
     61         op = compose(funcs)
---> 62         return op(*args)
     63 
     64 

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/model/handler.py in func2(*x)
     19                 return f(*x)
     20             else:
---> 21                 return f(*res)
     22 
     23         return func2

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/model/handler.py in func2(*x)
     19                 return f(*x)
     20             else:
---> 21                 return f(*res)
     22 
     23         return func2

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/model/handler.py in func2(*x)
     15     def func(f: Callable, g: Callable) -> Callable:
     16         def func2(*x) -> Any:
---> 17             res = g(*x)
     18             if type(res) == bool:
     19                 return f(*x)

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/multimethod/__init__.py in __call__(self, *args, **kwargs)
    313         func = self[tuple(func(arg) for func, arg in zip(self.type_checkers, args))]
    314         try:
--> 315             return func(*args, **kwargs)
    316         except TypeError as ex:
    317             raise DispatchError(f"Function {func.__code__}") from ex

/local_disk0/.ephemeral_nfs/cluster_libraries/python/lib/python3.9/site-packages/ydata_profiling/model/spark/describe_supported_spark.py in describe_supported_spark(config, series, summary)
     29     summary["is_unique"] = n_unique == count
     30     summary["n_unique"] = n_unique
---> 31     summary["p_unique"] = n_unique / count
     32 
     33     return config, series, summary

ZeroDivisionError: division by zero

Expected Behaviour

Get a data profiling report in json or html

Data Description

Code that reproduces the bug

from ydata_profiling import ProfileReport

df = spark.read.format('delta').load(f"abfss://***@***.dfs.core.windows.net/***")
df = df.withColumn("FakeNum", lit(0.0)) # Suggestions by other users to workaround the error.

# Suggestion by other users to set correlation to None.
report = ProfileReport(data_df, title='None', correlations=None)

# Both methods below throw the same error.
json_object = report.to_json()
report_html = report.to_html()

pandas-profiling version

v4.5.0

Dependencies

arrow==1.2.3
json5==0.9.14
jsonpatch==1.33
jsonpointer==2.4
jsonschema==4.19.0
jsonschema-specifications==2023.7.1
makefun==1.15.1
MarkupSafe==2.0.1
matplotlib==3.4.3
matplotlib-inline==0.1.2
numpy==1.22.4
pandas==1.3.4
pandocfilters==1.4.3
ydata-profiling==4.5.0
zipp==3.16.2

OS

Databricks

Checklist

• There is not yet another bug report for this issue in the issue tracker
• The problem is reproducible from this bug report. This guide can help to craft a minimal bug report.
• The issue has not been resolved by the entries listed under Common Issues.

[mldhamacher]

This issues seems to be related to this one here: #1350

[fabclmnt]

Hi @mldhamacher ,

thank you for reporting. For sake of ease of management, can I ask you to comment your issues under #1305 as this is an already reported behaviour?

Cheers.