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 test_describe_df(column, describe_data, expected_results, summarizer):
config = Settings()
config.vars.num.low_categorical_threshold = 0
typeset = ProfilingTypeSet(config)
describe_data_frame = pd.DataFrame({column: describe_data[column]})
if column == "somedate":
describe_data_frame["somedate"] = pd.to_datetime(
describe_data_frame["somedate"]
)
results = describe(config, describe_data_frame, summarizer, typeset)
assert {
"analysis",
"table",
"variables",
"scatter",
"correlations",
"missing",
"messages",
"package",
"sample",
"duplicates",
} == set(results.keys()), "Not in results"
# Loop over variables
for k, v in expected_results[column].items():
if v == check_is_NaN:
test_condition = k not in results["variables"][column]
elif isinstance(v, float):
test_condition = pytest.approx(v) == results["variables"][column][k]
else:
test_condition = v == results["variables"][column][k]
assert (
test_condition
), f"Value `{results['variables'][column][k]}` for key `{k}` in column `{column}` is not NaN"
if results["variables"][column]["type"] in ["Numeric", "DateTime"]:
assert (
"histogram" in results["variables"][column]
), f"Histogram missing for column {column}"
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))
infers,
)
from pandas_profiling.config import config
from pandas_profiling.model.typeset import (
Boolean,
Categorical,
DateTime,
Numeric,
ProfilingTypeSet,
Unsupported,
)
series = get_series()
typeset = ProfilingTypeSet()
contains_map = {
Numeric: {
"int_series",
"Int64_int_series",
"int_range",
"Int64_int_nan_series",
"int_series_boolean",
"np_uint32",
"pd_uint32",
"float_series",
"float_series2",
"float_series3",
"float_series4",
"inf_series",
def typeset(self):
if self._typeset is None:
self._typeset = ProfilingTypeSet()
return self._typeset
def typeset(self) -> Optional[VisionsTypeset]:
if self._typeset is None:
self._typeset = ProfilingTypeSet(self.config)
return self._typeset
def typeset(config):
return ProfilingTypeSet(config)
def typeset():
return ProfilingTypeSet()
(15, 16),
(17, 18),
],
"date_str": ["2018-01-01", "2017-02-01", "2018-04-07"],
"nullable_int":
pd.Series([1, None], dtype="Int64"),
}
return {key: pd.Series(values, name=key) for key, values in data.items()}
series = get_profiling_series()
config = Settings()
config.vars.num.low_categorical_threshold = 0
my_typeset = ProfilingTypeSet(config)
type_map = {str(k): k for k in my_typeset.types}
Numeric = type_map["Numeric"]
Categorical = type_map["Categorical"]
Boolean = type_map["Boolean"]
DateTime = type_map["DateTime"]
Unsupported = type_map["Unsupported"]
config2 = Settings()
config2.vars.num.low_categorical_threshold = 2
typeset2 = ProfilingTypeSet(config2)
type_map2 = {str(k): k for k in typeset2.types}
Numeric2 = type_map2["Numeric"]
Categorical2 = type_map2["Categorical"]
Boolean2 = type_map2["Boolean"]
from tests.unit.test_utils import patch_arg
if int(pd.__version__.split(".")[0]) < 1:
from visions.dtypes.boolean import BoolDtype # noqa: F401
btype = "Bool"
else:
btype = "boolean"
base_path = os.path.abspath(os.path.dirname(__file__))
series = get_series()
my_config = Settings()
my_config.vars.num.low_categorical_threshold = 0
my_typeset_default = ProfilingTypeSet(my_config)
type_map = {str(k): k for k in my_typeset_default.types}
Numeric = type_map["Numeric"]
Categorical = type_map["Categorical"]
Boolean = type_map["Boolean"]
DateTime = type_map["DateTime"]
Unsupported = type_map["Unsupported"]
contains_map = {
Numeric: {
"int_series",
"Int64_int_series",
"int_range",
"Int64_int_nan_series",
"int_series_boolean",