def test_summarizer(config):
pps = PandasProfilingSummarizer(typeset=ProfilingTypeSet(config))
_ = format_summary(pps.summarize(config, pd.Series([1, 2, 3, 4, 5]), "Unsupported"))
_ = format_summary(pps.summarize(config, pd.Series([1, 2, 3, 4, 5]), "Numeric"))
_ = format_summary(
pps.summarize(
config,
pd.Series(pd.date_range(start="1/1/2018", end="1/08/2018")),
"DateTime",
)
)
_ = format_summary(
pps.summarize(config, pd.Series(["abc", "abc", "abba"]), "Categorical")
)
_ = format_summary(
pps.summarize(config, pd.Series(["https://www.example.com"]), "URL")
)
_ = format_summary(
pps.summarize(
config,
pd.Series(
[
os.path.abspath(
base_path
+ r"../../../src/pandas_profiling/model/typeset_does_not_exist.py"
)
]
),
"Path",
)
)
_ = format_summary(
pps.summarize(
config,
pd.Series(
[
os.path.abspath(
base_path + r"../../../src/pandas_profiling/model/typeset.py"
)
]
),
"File",
)
)
_ = format_summary(
pps.summarize(
config,
pd.Series(
[os.path.abspath(base_path + r"../../../docsrc/assets/lambda-labs.png")]
),
"Image",
)
)
_ = format_summary(
pps.summarize(config, pd.Series([True, False, True, False, False]), "Boolean")
)
def _render_json(self):
def encode_it(o):
if isinstance(o, dict):
return {encode_it(k): encode_it(v) for k, v in o.items()}
else:
if isinstance(o, (bool, int, float, str)):
return o
elif isinstance(o, list):
return [encode_it(v) for v in o]
elif isinstance(o, set):
return {encode_it(v) for v in o}
elif isinstance(o, (pd.DataFrame, pd.Series)):
return o.to_json()
elif isinstance(o, np.ndarray):
return encode_it(o.tolist())
else:
return str(o)
description = self.description_set
disable_progress_bar = not config["progress_bar"].get(bool)
with tqdm(total=1, desc="Render JSON",
disable=disable_progress_bar) as pbar:
description = format_summary(description)
description = encode_it(description)
data = json.dumps(description, indent=4)
pbar.update()
return data
def _render_json(self) -> str:
def encode_it(o: Any) -> Any:
if isinstance(o, dict):
return {encode_it(k): encode_it(v) for k, v in o.items()}
else:
if isinstance(o, (bool, int, float, str)):
return o
elif isinstance(o, list):
return [encode_it(v) for v in o]
elif isinstance(o, set):
return {encode_it(v) for v in o}
elif isinstance(o, (pd.DataFrame, pd.Series)):
return encode_it(o.to_dict(orient="records"))
elif isinstance(o, np.ndarray):
return encode_it(o.tolist())
elif isinstance(o, Sample):
return encode_it(o.dict())
elif isinstance(o, np.generic):
return o.item()
else:
return str(o)
description = self.description_set
with tqdm(total=1,
desc="Render JSON",
disable=not self.config.progress_bar) as pbar:
description = format_summary(description)
description = encode_it(description)
data = json.dumps(description, indent=4)
pbar.update()
return data
def test_summarizer():
pps = PandasProfilingSummarizer(typeset=ProfilingTypeSet())
_ = format_summary(pps.summarize(pd.Series([1, 2, 3, 4, 5]), Unsupported))
_ = format_summary(pps.summarize(pd.Series([1, 2, 3, 4, 5]), Numeric))
_ = format_summary(
pps.summarize(
pd.Series(pd.date_range(start="1/1/2018", end="1/08/2018")),
DateTime))
_ = format_summary(
pps.summarize(pd.Series(["abc", "abc", "abba"]), Categorical))
_ = format_summary(
pps.summarize(pd.Series(["https://www.example.com"]), URL))
_ = format_summary(
pps.summarize(
pd.Series([
os.path.abspath(
base_path +
r"../../../src/pandas_profiling/model/typeset_does_not_exist.py"
)
]),
Path,
))
_ = format_summary(
pps.summarize(
pd.Series([
os.path.abspath(
base_path +
r"../../../src/pandas_profiling/model/typeset.py")
]),
File,
))
_ = format_summary(
pps.summarize(
pd.Series([
os.path.abspath(base_path +
r"../../../docsrc/assets/lambda-labs.png")
]),
Image,
))
_ = format_summary(
pps.summarize(pd.Series([True, False, True, False, False]), Boolean))