types = {
Unsupported,
Boolean,
Numeric,
Categorical,
DateTime,
}
if config["vars"]["path"]["active"].get(bool):
types.add(Path)
if config["vars"]["file"]["active"].get(bool):
types.add(File)
if config["vars"]["image"]["active"].get(bool):
types.add(Image)
if config["vars"]["url"]["active"].get(bool):
types.add(URL)
with warnings.catch_warnings():
warnings.filterwarnings("ignore", category=UserWarning)
super().__init__(types)
if __name__ == "__main__":
from matplotlib import pyplot as plt
config.set_arg_group("explorative")
ts = ProfilingTypeSet()
ts.plot_graph()
plt.show()
def __init__(
self,
df=None,
minimal=False,
explorative=False,
sensitive=False,
dark_mode=False,
orange_mode=False,
sample=None,
config_file: Union[Path, str] = None,
lazy: bool = True,
**kwargs,
):
"""Generate a ProfileReport based on a pandas DataFrame
Args:
df: the pandas DataFrame
minimal: minimal mode is a default configuration with minimal computation
config_file: a config file (.yml), mutually exclusive with `minimal`
lazy: compute when needed
**kwargs: other arguments, for valid arguments, check the default configuration file.
"""
if config_file is not None and minimal:
raise ValueError(
"Arguments `config_file` and `minimal` are mutually exclusive."
)
if df is None and not lazy:
raise ValueError(
"Can init a not-lazy ProfileReport with no DataFrame")
if config_file:
config.set_file(config_file)
elif minimal:
config.set_file(get_config("config_minimal.yaml"))
elif not config.is_default:
pass
# TODO: logging instead of warning
# warnings.warn(
# "Currently configuration is not the default, if you want to restore "
# "default configuration, please run 'pandas_profiling.clear_config()'"
# )
if explorative:
config.set_arg_group("explorative")
if sensitive:
config.set_arg_group("sensitive")
if dark_mode:
config.set_arg_group("dark_mode")
if orange_mode:
config.set_arg_group("orange_mode")
config.set_kwargs(kwargs)
self.df = None
self._df_hash = -1
self._description_set = None
self._sample = sample
self._title = None
self._report = None
self._html = None
self._widgets = None
self._json = None
if df is not None:
# preprocess df
self.df = self.preprocess(df)
if not lazy:
# Trigger building the report structure
_ = self.report
def __init__(
self,
df: Optional[pd.DataFrame] = None,
minimal: bool = False,
explorative: bool = False,
sensitive: bool = False,
dark_mode: bool = False,
orange_mode: bool = False,
sample: Optional[dict] = None,
config_file: Union[Path, str] = None,
lazy: bool = True,
typeset: Optional[VisionsTypeset] = None,
summarizer: Optional[BaseSummarizer] = None,
**kwargs,
):
"""Generate a ProfileReport based on a pandas DataFrame
Args:
df: the pandas DataFrame
minimal: minimal mode is a default configuration with minimal computation
config_file: a config file (.yml), mutually exclusive with `minimal`
lazy: compute when needed
sample: optional dict(name="Sample title", caption="Caption", data=pd.DataFrame())
typeset: optional user typeset to use for type inference
summarizer: optional user summarizer to generate custom summary output
**kwargs: other arguments, for valid arguments, check the default configuration file.
"""
config.clear() # to reset (previous) config.
if config_file is not None and minimal:
raise ValueError(
"Arguments `config_file` and `minimal` are mutually exclusive."
)
if df is None and not lazy:
raise ValueError("Can init a not-lazy ProfileReport with no DataFrame")
if config_file:
config.set_file(config_file)
elif minimal:
config.set_file(get_config("config_minimal.yaml"))
elif not config.is_default:
pass
# warnings.warn(
# "Currently configuration is not the default, if you want to restore "
# "default configuration, please run 'pandas_profiling.clear_config()'"
# )
if explorative:
config.set_arg_group("explorative")
if sensitive:
config.set_arg_group("sensitive")
if dark_mode:
config.set_arg_group("dark_mode")
if orange_mode:
config.set_arg_group("orange_mode")
config.set_kwargs(kwargs)
self.df = None
self._df_hash = -1
self._description_set = None
self._sample = sample
self._title = None
self._report = None
self._html = None
self._widgets = None
self._json = None
self._typeset = typeset
self._summarizer = summarizer
if df is not None:
# preprocess df
self.df = self.preprocess(df)
if not lazy:
# Trigger building the report structure
_ = self.report