def description_set(self) -> Dict[str, Any]:
if self._description_set is None:
self._description_set = describe_df(
self.config,
self.df,
self.summarizer,
self.typeset,
self._sample,
)
return self._description_set
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
)
from dash.dependencies import Input, Output
import dash_utils as du
import seaborn as sns
import os
import plotly.graph_objs as go
from pandas_profiling.model.describe import describe as describe_df
base_path = os.path.abspath(os.path.dirname(__file__))
# -- data
# df = pd.read_csv('./data/diamonds.csv', sep=',', index_col=0)
df = sns.load_dataset('diamonds')
# using pandas profiling to create the description
desc = describe_df(df)
variables = desc['variables']
variables = {
k: v
for k, v in variables.items()
if str(v['type'] != 'Variabe.TYPE_UNSUPPORTED')
}
cats = {
col: {
'CAT':
variables[col]['type'],
'n_unique':
variables[col]['distinct_count']
if str(variables[col]['type']) == "Variable.TYPE_CAT" else 0
}
for col in variables.keys()
def description_set(self):
if self._description_set is None:
self._description_set = describe_df(self.title, self.df,
self._sample)
return self._description_set
def description_set(self):
if self._description_set is None:
_ = self.df_hash
self._description_set = describe_df(self.title, self.df)
return self._description_set
