SoyGema
commented
1 year ago Hello there.
I'm experiencing the same issue here.
So far, I´ve tried to removepart of the string coming from the categorical column to try to make an smaller string, using this function . Unfortunaltely , I am not able to make it work yet.
def remove_substring_from_column(df, column_name, substring, inplace=True):
"""
Removes a specified substring from a particular column in a DataFrame.
Parameters:
- df (pandas.DataFrame): The input DataFrame.
- column_name (str): The name of the column from which the substring should be removed.
- substring (str): The substring to remove.
- inplace (bool, optional): If True, modifies the input DataFrame directly. If False, returns a modified copy.
Defaults to True.
Returns:
- pandas.DataFrame or None: If inplace is False, returns a modified copy of the DataFrame.
If inplace is True, returns None and the input DataFrame is modified in place.
"""
if inplace:
target_df = df
else:
target_df = df.copy()
if column_name in target_df.columns:
print(f"Before removal: {target_df[column_name].head()}")
target_df[column_name] = target_df[column_name].str.replace(substring, '', regex=False)
print(f"After removal: {target_df[column_name].head()}")
if not inplace:
return target_df
print('# ----data removed----#' + str(substring) + ' ' + str(column_name))
return target_df`Maybe decreasing the font size or increasing the Canvas Size might work.
Anyone has any idea of how to tackle this , beyond trying changing the string length or doing a label encoding step ?
🙏🙏 Thanks for the time dedicated to tackle this issue ! 🙏🙏
fabclmnt
jonathanyulan99
sdbeuf
BoPeng
somnambWl
chalozin
hschaeufler
Current Behaviour
The ProfileReport fails to generate, and i dont find if the issue is already solved or a way to bypass it.
I think because of the size of my data, it fails to generate the wordcloud.
The full error output is:
IndexError Traceback (most recent call last) File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\wordcloud\wordcloud.py:458, in WordCloud.generate_from_frequencies(self, frequencies, max_font_size) 457 try: --> 458 fontsize = int(2 sizes[0] sizes[1] 459 / (sizes[0] + sizes[1])) 460 # quick fix for if self.layout contains less than 2 values 461 # on very small images it can be empty
IndexError: list index out of range
During handling of the above exception, another exception occurred:
IndexError Traceback (most recent call last) File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\wordcloud\wordcloud.py:464, in WordCloud.generate_from_frequencies(self, frequencies, max_font_size) 463 try: --> 464 font_size = sizes[0] 465 except IndexError:
IndexError: list index out of range
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last) File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\IPython\core\formatters.py:344, in BaseFormatter.call(self, obj) 342 method = get_real_method(obj, self.print_method) 343 if method is not None: --> 344 return method() 345 return None 346 else:
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\ydata_profiling\profile_report.py:520, in ProfileReport._reprhtml(self) 518 def _reprhtml(self) -> None: 519 """The ipython notebook widgets user interface gets called by the jupyter notebook.""" --> 520 self.to_notebook_iframe()
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\ydata_profiling\profile_report.py:500, in ProfileReport.to_notebook_iframe(self) 498 with warnings.catch_warnings(): 499 warnings.simplefilter("ignore") --> 500 display(get_notebook_iframe(self.config, self))
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\ydata_profiling\report\presentation\flavours\widget\notebook.py:75, in get_notebook_iframe(config, profile) 73 output = get_notebook_iframe_src(config, profile) 74 elif attribute == IframeAttribute.srcdoc: ---> 75 output = get_notebook_iframe_srcdoc(config, profile) 76 else: 77 raise ValueError( 78 f'Iframe Attribute can be "src" or "srcdoc" (current: {attribute}).' 79 )
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\ydata_profiling\report\presentation\flavours\widget\notebook.py:29, in get_notebook_iframe_srcdoc(config, profile) 27 width = config.notebook.iframe.width 28 height = config.notebook.iframe.height ---> 29 src = html.escape(profile.to_html()) 31 iframe = f'' 33 return HTML(iframe)
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\ydata_profiling\profile_report.py:470, in ProfileReport.to_html(self) 462 def to_html(self) -> str: 463 """Generate and return complete template as lengthy string 464 for using with frameworks. 465 (...) 468 469 """ --> 470 return self.html
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\ydata_profiling\profile_report.py:277, in ProfileReport.html(self) 274 @property 275 def html(self) -> str: 276 if self._html is None: --> 277 self._html = self._render_html() 278 return self._html
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\ydata_profiling\profile_report.py:385, in ProfileReport._render_html(self) 382 def _render_html(self) -> str: 383 from ydata_profiling.report.presentation.flavours import HTMLReport --> 385 report = self.report 387 with tqdm( 388 total=1, desc="Render HTML", disable=not self.config.progress_bar 389 ) as pbar: 390 html = HTMLReport(copy.deepcopy(report)).render( 391 nav=self.config.html.navbar_show, 392 offline=self.config.html.use_local_assets, (...) 400 version=self.description_set.package["ydata_profiling_version"], 401 )
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\ydata_profiling\profile_report.py:271, in ProfileReport.report(self) 268 @property 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
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\ydata_profiling\report\structure\report.py:387, in get_report_structure(config, summary) 368 section_items: List[Renderable] = [ 369 Container( 370 get_dataset_items(config, summary, alerts), (...) 374 ), 375 ] 377 if len(summary.variables) > 0: 378 section_items.append( 379 Dropdown( 380 name="Variables", 381 anchor_id="variables-dropdown", 382 id="variables-dropdown", 383 is_row=True, 384 classes=["dropdown-toggle"], 385 items=list(summary.variables), 386 item=Container( --> 387 render_variables_section(config, summary), 388 sequence_type="accordion", 389 name="Variables", 390 anchor_id="variables", 391 ), 392 ) 393 ) 395 scatter_items = get_interactions(config, summary.scatter) 396 if len(scatter_items) > 0:
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\ydata_profiling\report\structure\report.py:162, in render_variables_section(config, dataframe_summary) 160 variable_type = summary["type"] 161 render_map_type = render_map.get(variable_type, render_map["Unsupported"]) --> 162 template_variables.update(render_map_type(config, template_variables)) 164 # Ignore these 165 if reject_variables:
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\ydata_profiling\report\structure\variables\render_text.py:81, in render_text(config, summary) 77 top_items.append(table) 79 if words and "word_counts" in summary: 80 mini_wordcloud = Image( ---> 81 plot_word_cloud(config, summary["word_counts"]), 82 image_format=config.plot.image_format, 83 alt="Mini wordcloud", 84 ) 85 top_items.append(mini_wordcloud) 86 template_variables["top"] = Container(top_items, sequence_type="grid")
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\contextlib.py:75, in ContextDecorator.call..inner(*args, kwds)
72 @wraps(func)
73 def inner(*args, *kwds):
74 with self._recreate_cm():
---> 75 return func(args, kwds)
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\ydata_profiling\visualisation\plot.py:126, in plot_word_cloud(config, word_counts) 124 @manage_matplotlib_context() 125 def plot_word_cloud(config: Settings, word_counts: pd.Series) -> str: --> 126 _plot_word_cloud(series=word_counts) 127 return plot_360_n0sc0pe(config)
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\ydata_profiling\visualisation\plot.py:38, in _plot_word_cloud(series, figsize) 36 for i, series_data in enumerate(series): 37 word_dict = series_data.to_dict() ---> 38 wordcloud = WordCloud( 39 background_color="white", random_state=123, width=300, height=200, scale=2 40 ).generate_from_frequencies(word_dict) 42 ax = plot.add_subplot(1, len(series), i + 1) 43 ax.imshow(wordcloud)
File ~\AppData\Roaming\jupyterlab-desktop\jlab_server\lib\site-packages\wordcloud\wordcloud.py:466, in WordCloud.generate_from_frequencies(self, frequencies, max_font_size) 464 font_size = sizes[0] 465 except IndexError: --> 466 raise ValueError( 467 "Couldn't find space to draw. Either the Canvas size" 468 " is too small or too much of the image is masked " 469 "out.") 470 else: 471 font_size = max_font_size
ValueError: Couldn't find space to draw. Either the Canvas size is too small or too much of the image is masked out.
Expected Behaviour
I'm expecting the ProfileReport to generate, but skipping the wordclouds.
Maybe an option to turn the wordclouds off, so the profile generates but skips that.
Data Description
My data is private, about 2 million rows and +200 columns. Can't identify the column (s ???) that is causing the error.
Code that reproduces the bug
pandas-profiling version
v4.6.1
Dependencies
OS
Windows 11
Checklist