def _apply_schema(self, pdf: pd.DataFrame,
schema: Optional[Schema]) -> Tuple[pd.DataFrame, Schema]:
PD_UTILS.ensure_compatible(pdf)
if pdf.columns.dtype == "object": # pdf has named schema
pschema = _input_schema(pdf)
if schema is None or pschema == schema:
return pdf, pschema.assert_not_empty()
pdf = pdf[schema.assert_not_empty().names]
else: # pdf has no named schema
schema = _input_schema(schema).assert_not_empty()
assert_or_throw(
pdf.shape[1] == len(schema),
ValueError(
f"Pandas datafame column count doesn't match {schema}"),
)
pdf.columns = schema.names
return PD_UTILS.enforce_type(pdf, schema.pa_schema,
null_safe=True), schema
def __init__( # noqa: C901
self,
df: Any = None,
schema: Any = None,
metadata: Any = None,
pandas_df_wrapper: bool = False,
):
try:
apply_schema = True
if df is None:
schema = _input_schema(schema).assert_not_empty()
df = []
if isinstance(df, PandasDataFrame):
# TODO: This is useless if in this way and wrong
pdf = df.native
schema = None
elif isinstance(df, (pd.DataFrame, pd.Series)):
if isinstance(df, pd.Series):
df = df.to_frame()
pdf = df
schema = None if schema is None else _input_schema(schema)
if pandas_df_wrapper and schema is not None:
apply_schema = False
elif isinstance(df, Iterable):
schema = _input_schema(schema).assert_not_empty()
pdf = pd.DataFrame(df, columns=schema.names)
pdf = PD_UTILS.enforce_type(pdf,
schema.pa_schema,
null_safe=True)
if PD_UTILS.empty(pdf):
for k, v in schema.items():
pdf[k] = pdf[k].astype(v.type.to_pandas_dtype())
apply_schema = False
else:
raise ValueError(f"{df} is incompatible with PandasDataFrame")
if apply_schema:
pdf, schema = self._apply_schema(pdf, schema)
super().__init__(schema, metadata)
self._native = pdf
except Exception as e:
raise FugueDataFrameInitError from e
def as_pandas(self) -> pd.DataFrame:
"""Convert to pandas DataFrame"""
pdf = pd.DataFrame(self.as_array(), columns=self.schema.names)
return PD_UTILS.enforce_type(pdf, self.schema.pa_schema, null_safe=True)
def __init__(self, data, schema, enforce=False):
s = expression_to_schema(schema)
df = pd.DataFrame(data, columns=s.names)
self.native = PD_UTILS.enforce_type(df, s, enforce)
self.schema = s
