the default is True
Valid values: False,True
"""
def use_numexpr_cb(key):
from pandas.core.computation import expressions
expressions.set_use_numexpr(cf.get_option(key))
with cf.config_prefix("compute"):
cf.register_option(
"use_bottleneck",
True,
use_bottleneck_doc,
validator=is_bool,
cb=use_bottleneck_cb,
)
cf.register_option("use_numexpr",
True,
use_numexpr_doc,
validator=is_bool,
cb=use_numexpr_cb)
#
# options from the "display" namespace
pc_precision_doc = """
: int
Floating point output precision (number of significant digits). This is
only a suggestion
: bool
Use the numexpr library to accelerate computation if it is installed,
the default is True
Valid values: False,True
"""
def use_numexpr_cb(key):
from pandas.core.computation import expressions
expressions.set_use_numexpr(cf.get_option(key))
with cf.config_prefix('compute'):
cf.register_option('use_bottleneck',
True,
use_bottleneck_doc,
validator=is_bool,
cb=use_bottleneck_cb)
cf.register_option('use_numexpr',
True,
use_numexpr_doc,
validator=is_bool,
cb=use_numexpr_cb)
#
# options from the "display" namespace
pc_precision_doc = """
: int
Floating point output precision (number of significant digits). This is
only a suggestion
"""
the default is False
Valid values: False,True
"""
def use_numba_cb(key):
from pandas.core.util import numba_
numba_.set_use_numba(cf.get_option(key))
with cf.config_prefix("compute"):
cf.register_option(
"use_bottleneck",
True,
use_bottleneck_doc,
validator=is_bool,
cb=use_bottleneck_cb,
)
cf.register_option("use_numexpr",
True,
use_numexpr_doc,
validator=is_bool,
cb=use_numexpr_cb)
cf.register_option("use_numba",
False,
use_numba_doc,
validator=is_bool,
cb=use_numba_cb)
#
# options from the "display" namespace
"""
config for datetime formatting
"""
from __future__ import annotations
from pandas._config import config as cf
pc_date_dayfirst_doc = """
: boolean
When True, prints and parses dates with the day first, eg 20/01/2005
"""
pc_date_yearfirst_doc = """
: boolean
When True, prints and parses dates with the year first, eg 2005/01/20
"""
with cf.config_prefix("display"):
# Needed upstream of `_libs` because these are used in tslibs.parsing
cf.register_option("date_dayfirst",
False,
pc_date_dayfirst_doc,
validator=cf.is_bool)
cf.register_option("date_yearfirst",
False,
pc_date_yearfirst_doc,
validator=cf.is_bool)
"""
config for datetime formatting
"""
from pandas._config import config as cf
pc_date_dayfirst_doc = """
: boolean
When True, prints and parses dates with the day first, eg 20/01/2005
"""
pc_date_yearfirst_doc = """
: boolean
When True, prints and parses dates with the year first, eg 2005/01/20
"""
with cf.config_prefix('display'):
# Needed upstream of `_libs` because these are used in tslibs.parsing
cf.register_option('date_dayfirst', False, pc_date_dayfirst_doc,
validator=cf.is_bool)
cf.register_option('date_yearfirst', False, pc_date_yearfirst_doc,
validator=cf.is_bool)
except locale.Error:
# can be raised by locale.setlocale(), which is
# called by getpreferredencoding
# (on some systems, see stdlib locale docs)
pass
# when all else fails. this will usually be "ascii"
if not encoding or "ascii" in encoding.lower():
encoding = sys.getdefaultencoding()
# GH#3360, save the reported defencoding at import time
# MPL backends may change it. Make available for debugging.
if not _initial_defencoding:
_initial_defencoding = sys.getdefaultencoding()
return encoding
pc_encoding_doc = """
: str/unicode
Defaults to the detected encoding of the console.
Specifies the encoding to be used for strings returned by to_string,
these are generally strings meant to be displayed on the console.
"""
with cf.config_prefix("display"):
cf.register_option("encoding",
detect_console_encoding(),
pc_encoding_doc,
validator=cf.is_text)
# try again for something better
if not encoding or 'ascii' in encoding.lower():
try:
encoding = locale.getpreferredencoding()
except Exception:
pass
# when all else fails. this will usually be "ascii"
if not encoding or 'ascii' in encoding.lower():
encoding = sys.getdefaultencoding()
# GH#3360, save the reported defencoding at import time
# MPL backends may change it. Make available for debugging.
if not _initial_defencoding:
_initial_defencoding = sys.getdefaultencoding()
return encoding
pc_encoding_doc = """
: str/unicode
Defaults to the detected encoding of the console.
Specifies the encoding to be used for strings returned by to_string,
these are generally strings meant to be displayed on the console.
"""
with cf.config_prefix('display'):
cf.register_option('encoding', detect_console_encoding(), pc_encoding_doc,
validator=cf.is_text)
use_numexpr_doc = """
: bool
Use the numexpr library to accelerate computation if it is installed,
the default is True
Valid values: False,True
"""
def use_numexpr_cb(key):
from pandas.core.computation import expressions
expressions.set_use_numexpr(cf.get_option(key))
with cf.config_prefix('compute'):
cf.register_option('use_bottleneck', True, use_bottleneck_doc,
validator=is_bool, cb=use_bottleneck_cb)
cf.register_option('use_numexpr', True, use_numexpr_doc,
validator=is_bool, cb=use_numexpr_cb)
#
# options from the "display" namespace
pc_precision_doc = """
: int
Floating point output precision (number of significant digits). This is
only a suggestion
"""
pc_colspace_doc = """
: int
Default space for DataFrame columns.
"""
def register(self, key, default_value, doc=""):
if key in registered_options:
del registered_options[key]
# Lift from https://github.com/pandas-dev/pandas/blob/aa1089f5568927bd660a6b5d824b20d456703929/pandas/_config/config.py#L423
register_option(key, default_value, doc)
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
This is a temporary mechanism to wrap around pandas option machinery.
We'll need a permanent solution later on for two main reasons:
1. Users can accidentally clear options via pandas api
2. We need better type handling to help bridge jvm-python communication (GH134)
"""
import os
import tempfile
import pandas as pd
from pandas._config.config import (
get_option,
register_option,
reset_option,
set_option,
)
options = pd.options
CONF_RIKAI_CACHEURI = "rikai.cache_uri"
DEFAULT_RIKAI_CACHEURI = os.path.join(tempfile.gettempdir(), "rikai")
os.makedirs(DEFAULT_RIKAI_CACHEURI, exist_ok=True)
register_option(CONF_RIKAI_CACHEURI, DEFAULT_RIKAI_CACHEURI)
CONF_PARQUET_BLOCK_SIZE = "parquet.block.size"
DEFAULT_ROW_GROUP_SIZE_BYTES = 32 * 1024 * 1024
register_option(CONF_PARQUET_BLOCK_SIZE, DEFAULT_ROW_GROUP_SIZE_BYTES)
