def set_variables(self, **vars):
"""Change configuration variables (invalidates caches where necessary)
Args:
**vars: configuration parameters to change
Examples:
>>> ProfileReport(df).set_variables(title="NewTitle", html={"minify_html": False})
"""
changed = set(vars.keys())
if len({"progress_bar", "pool_size"} & changed) > 0:
# Cache can persist
pass
if len({"notebook"} & changed) > 0:
self._widgets = None
if len({"html", "title"} & changed) > 0:
self._html = None
if not {"progress_bar", "pool_size", "notebook", "html", "title"
} >= changed:
# In all other cases, empty cache
self._description_set = None
self._title = None
self._report = None
self._html = None
self._widgets = None
self._json = None
if len(vars) == 1:
config[list(vars.keys())[0]] = list(vars.values())[0]
else:
config.set_kwargs(vars)
def __init__(
self,
df=None,
minimal=False,
explorative=False,
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_resource("configs/config_minimal.yaml"))
elif explorative:
config.set_file(get_resource("configs/config_explorative.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()'"
# )
config.set_kwargs(kwargs)
self.df = None
self._df_hash = -1
self._description_set = None
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, config_file: Path = None, **kwargs):
if config_file:
config.config.set_file(str(config_file))
config.set_kwargs(kwargs)
# Treat index as any other column
if (not pd.Index(np.arange(0, len(df))).equals(df.index)
or df.index.dtype != np.int64):
df = df.reset_index()
# Rename reserved column names
df = rename_index(df)
# Remove spaces and colons from column names
df = clean_column_names(df)
# Sort column names
sort = config["sort"].get(str)
if sys.version_info[1] <= 5 and sort != "None":
warnings.warn("Sorting is supported from Python 3.6+")
if sort in ["asc", "ascending"]:
df = df.reindex(sorted(df.columns, key=lambda s: s.casefold()),
axis=1)
elif sort in ["desc", "descending"]:
df = df.reindex(reversed(
sorted(df.columns, key=lambda s: s.casefold())),
axis=1)
elif sort != "None":
raise ValueError(
'"sort" should be "ascending", "descending" or None.')
# Store column order
config["column_order"] = df.columns.tolist()
# Get dataset statistics
description_set = describe_df(df)
# Get sample
sample = {}
n_head = config["samples"]["head"].get(int)
if n_head > 0:
sample["head"] = df.head(n=n_head)
n_tail = config["samples"]["tail"].get(int)
if n_tail > 0:
sample["tail"] = df.tail(n=n_tail)
# Render HTML
self.html = to_html(sample, description_set)
self.minify_html = config["minify_html"].get(bool)
self.use_local_assets = config["use_local_assets"].get(bool)
self.title = config["title"].get(str)
self.description_set = description_set
self.sample = sample
def __init__(self, df, minimal=False, config_file: Path = None, **kwargs):
if sys.version_info <= (3, 5):
warnings.warn(
"This is the last release to support Python 3.5, please upgrade.",
category=DeprecationWarning,
)
if config_file is not None and minimal:
raise ValueError(
"Arguments `config_file` and `minimal` are mutually exclusive."
)
if minimal:
config_file = get_config_minimal()
if config_file:
config.set_file(str(config_file))
config.set_kwargs(kwargs)
self.date_start = datetime.utcnow()
# Treat index as any other column
if (not pd.Index(np.arange(0, len(df))).equals(df.index)
or df.index.dtype != np.int64):
df = df.reset_index()
# Rename reserved column names
df = rename_index(df)
# Ensure that columns are strings
df.columns = df.columns.astype("str")
# Get dataset statistics
description_set = describe_df(df)
# Build report structure
self.sample = self.get_sample(df)
self.title = config["title"].get(str)
self.description_set = description_set
self.date_end = datetime.utcnow()
disable_progress_bar = not config["progress_bar"].get(bool)
with tqdm(total=1,
desc="build report structure",
disable=disable_progress_bar) as pbar:
self.report = get_report_structure(self.date_start, self.date_end,
self.sample, description_set)
pbar.update()
def __init__(self, df, minimal=False, config_file: Path = None, **kwargs):
if config_file is not None and minimal:
raise ValueError(
"Arguments `config_file` and `minimal` are mutually exclusive."
)
if minimal:
config_file = get_config_minimal()
if config_file:
config.config.set_file(str(config_file))
config.set_kwargs(kwargs)
self.date_start = datetime.utcnow()
# Treat index as any other column
if (
not pd.Index(np.arange(0, len(df))).equals(df.index)
or df.index.dtype != np.int64
):
df = df.reset_index()
# Rename reserved column names
df = rename_index(df)
# Ensure that columns are strings
df.columns = df.columns.astype("str")
# Sort names according to config (asc, desc, no sort)
df = self.sort_column_names(df)
config["column_order"] = df.columns.tolist()
# Get dataset statistics
description_set = describe_df(df)
# Build report structure
self.sample = self.get_sample(df)
self.title = config["title"].get(str)
self.description_set = description_set
self.date_end = datetime.utcnow()
self.report = get_report_structure(
self.date_start, self.date_end, self.sample, description_set
)
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,
**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())
**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
# 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 = None
self._summarizer = None
if df is not None:
# preprocess df
self.df = self.preprocess(df)
if not lazy:
# Trigger building the report structure
_ = self.report
