def _from_sequence_of_strings(cls,
strings,
*,
dtype: Optional[Dtype] = None,
copy: bool = False) -> IntegerArray:
scalars = to_numeric(strings, errors="raise")
return cls._from_sequence(scalars, dtype=dtype, copy=copy)
def _from_sequence_of_strings(cls,
strings,
*,
dtype=None,
copy: bool = False) -> FloatingArray:
scalars = to_numeric(strings, errors="raise")
return cls._from_sequence(scalars, dtype=dtype, copy=copy)
def _from_sequence_of_strings(
cls: type[T], strings, *, dtype: Dtype | None = None, copy: bool = False
) -> T:
from pandas.core.tools.numeric import to_numeric
scalars = to_numeric(strings, errors="raise")
return cls._from_sequence(scalars, dtype=dtype, copy=copy)
def melt_stub(df, stub, i, j, value_vars, sep):
newdf = melt(df, id_vars=i, value_vars=value_vars,
value_name=stub.rstrip(sep), var_name=j)
newdf[j] = Categorical(newdf[j])
newdf[j] = newdf[j].str.replace(re.escape(stub + sep), "")
# GH17627 Cast numerics suffixes to int/float
newdf[j] = to_numeric(newdf[j], errors='ignore')
return newdf.set_index(i + [j])
def melt_stub(df, stub, i, j, value_vars, sep):
newdf = melt(df, id_vars=i, value_vars=value_vars,
value_name=stub.rstrip(sep), var_name=j)
newdf[j] = Categorical(newdf[j])
newdf[j] = newdf[j].str.replace(re.escape(stub + sep), "")
# GH17627 Cast numerics suffixes to int/float
newdf[j] = to_numeric(newdf[j], errors='ignore')
return newdf.set_index(i + [j])
def _from_sequence_of_strings(cls,
strings,
*,
dtype: Dtype | None = None,
copy=False):
"""
Construct a new ExtensionArray from a sequence of strings.
"""
pa_type = to_pyarrow_type(dtype)
if pa.types.is_timestamp(pa_type):
from pandas.core.tools.datetimes import to_datetime
scalars = to_datetime(strings, errors="raise")
elif pa.types.is_date(pa_type):
from pandas.core.tools.datetimes import to_datetime
scalars = to_datetime(strings, errors="raise").date
elif pa.types.is_duration(pa_type):
from pandas.core.tools.timedeltas import to_timedelta
scalars = to_timedelta(strings, errors="raise")
elif pa.types.is_time(pa_type):
from pandas.core.tools.times import to_time
# "coerce" to allow "null times" (None) to not raise
scalars = to_time(strings, errors="coerce")
elif pa.types.is_boolean(pa_type):
from pandas.core.arrays import BooleanArray
scalars = BooleanArray._from_sequence_of_strings(
strings).to_numpy()
elif (pa.types.is_integer(pa_type) or pa.types.is_floating(pa_type)
or pa.types.is_decimal(pa_type)):
from pandas.core.tools.numeric import to_numeric
scalars = to_numeric(strings, errors="raise")
else:
# Let pyarrow try to infer or raise
scalars = strings
return cls._from_sequence(scalars, dtype=pa_type, copy=copy)
def _from_sequence_of_strings(cls, strings, dtype=None, copy=False):
scalars = to_numeric(strings, errors="raise")
return cls._from_sequence(scalars, dtype, copy)
def _from_sequence_of_strings(
cls, strings, dtype=None, copy: bool = False
) -> "IntegerArray":
scalars = to_numeric(strings, errors="raise")
return cls._from_sequence(scalars, dtype, copy)
def _from_sequence_of_strings(cls, strings, dtype=None, copy=False):
scalars = to_numeric(strings, errors="raise")
return cls._from_sequence(scalars, dtype, copy)