def factorize(values, sort=False, order=None, na_sentinel=-1):
"""
Encode input values as an enumerated type or categorical variable
Parameters
----------
values : ndarray (1-d)
Sequence
sort : boolean, default False
Sort by values
order :
na_sentinel: int, default -1
Value to mark "not found"
Returns
-------
"""
from pandas.tseries.period import PeriodIndex
vals = np.asarray(values)
is_datetime = com.is_datetime64_dtype(vals)
(hash_klass, vec_klass), vals = _get_data_algo(vals, _hashtables)
table = hash_klass(len(vals))
uniques = vec_klass()
labels = table.get_labels(vals, uniques, 0, na_sentinel)
labels = com._ensure_platform_int(labels)
uniques = uniques.to_array()
if sort and len(uniques) > 0:
try:
sorter = uniques.argsort()
except:
# unorderable in py3 if mixed str/int
t = hash_klass(len(uniques))
t.map_locations(com._ensure_object(uniques))
# order ints before strings
ordered = np.concatenate([
np.sort(np.array([ e for i, e in enumerate(uniques) if f(e) ],dtype=object)) for f in [ lambda x: not isinstance(x,string_types),
lambda x: isinstance(x,string_types) ]
])
sorter = com._ensure_platform_int(t.lookup(com._ensure_object(ordered)))
reverse_indexer = np.empty(len(sorter), dtype=np.int_)
reverse_indexer.put(sorter, np.arange(len(sorter)))
mask = labels < 0
labels = reverse_indexer.take(labels)
np.putmask(labels, mask, -1)
uniques = uniques.take(sorter)
if is_datetime:
uniques = uniques.astype('M8[ns]')
if isinstance(values, PeriodIndex):
uniques = PeriodIndex(ordinal=uniques, freq=values.freq)
return labels, uniques
def na_op(x, y):
try:
result = op(x, y)
except TypeError:
if isinstance(y, list):
y = lib.list_to_object_array(y)
if isinstance(y, (np.ndarray, pd.Series)):
if (is_bool_dtype(x.dtype) and is_bool_dtype(y.dtype)):
result = op(x, y) # when would this be hit?
else:
x = com._ensure_object(x)
y = com._ensure_object(y)
result = lib.vec_binop(x, y, op)
else:
try:
# let null fall thru
if not isnull(y):
y = bool(y)
result = lib.scalar_binop(x, y, op)
except:
raise TypeError("cannot compare a dtyped [{0}] array with "
"a scalar of type [{1}]".format(
x.dtype, type(y).__name__))
return result
def _get_data_algo(values, func_map):
mask = None
if com.is_float_dtype(values):
f = func_map['float64']
values = com._ensure_float64(values)
elif com.needs_i8_conversion(values):
# if we have NaT, punt to object dtype
mask = com.isnull(values)
if mask.ravel().any():
f = func_map['generic']
values = com._ensure_object(values)
values[mask] = np.nan
else:
f = func_map['int64']
values = values.view('i8')
elif com.is_integer_dtype(values):
f = func_map['int64']
values = com._ensure_int64(values)
else:
f = func_map['generic']
values = com._ensure_object(values)
return f, values
def _factorize_keys(lk, rk, sort=True):
if com._is_int_or_datetime_dtype(lk) and com._is_int_or_datetime_dtype(rk):
klass = lib.Int64Factorizer
lk = com._ensure_int64(lk)
rk = com._ensure_int64(rk)
else:
klass = lib.Factorizer
lk = com._ensure_object(lk)
rk = com._ensure_object(rk)
rizer = klass(max(len(lk), len(rk)))
llab = rizer.factorize(lk)
rlab = rizer.factorize(rk)
count = rizer.get_count()
if sort:
uniques = rizer.uniques.to_array()
llab, rlab = _sort_labels(uniques, llab, rlab)
# NA group
lmask = llab == -1; lany = lmask.any()
rmask = rlab == -1; rany = rmask.any()
if lany or rany:
if lany:
np.putmask(llab, lmask, count)
if rany:
np.putmask(rlab, rmask, count)
count += 1
return llab, rlab, count
def _from_arraylike(cls, data, freq, tz):
if not isinstance(data, (np.ndarray, PeriodIndex, DatetimeIndex, Int64Index)):
if np.isscalar(data) or isinstance(data, Period):
raise ValueError('PeriodIndex() must be called with a '
'collection of some kind, %s was passed'
% repr(data))
# other iterable of some kind
if not isinstance(data, (list, tuple)):
data = list(data)
try:
data = com._ensure_int64(data)
if freq is None:
raise ValueError('freq not specified')
data = np.array([Period(x, freq=freq).ordinal for x in data],
dtype=np.int64)
except (TypeError, ValueError):
data = com._ensure_object(data)
if freq is None and len(data) > 0:
freq = getattr(data[0], 'freq', None)
if freq is None:
raise ValueError('freq not specified and cannot be '
'inferred from first element')
data = _get_ordinals(data, freq)
else:
if isinstance(data, PeriodIndex):
if freq is None or freq == data.freq:
freq = data.freq
data = data.values
else:
base1, _ = _gfc(data.freq)
base2, _ = _gfc(freq)
data = period.period_asfreq_arr(data.values, base1,
base2, 1)
else:
if freq is None and len(data) > 0:
freq = getattr(data[0], 'freq', None)
if freq is None:
raise ValueError('freq not specified and cannot be '
'inferred from first element')
if data.dtype != np.int64:
if np.issubdtype(data.dtype, np.datetime64):
data = dt64arr_to_periodarr(data, freq, tz)
else:
try:
data = com._ensure_int64(data)
except (TypeError, ValueError):
data = com._ensure_object(data)
data = _get_ordinals(data, freq)
return data, freq
def _get_codes_for_values(values, levels):
from pandas.core.algorithms import _get_data_algo, _hashtables
if values.dtype != levels.dtype:
values = com._ensure_object(values)
levels = com._ensure_object(levels)
(hash_klass, vec_klass), vals = _get_data_algo(values, _hashtables)
t = hash_klass(len(levels))
t.map_locations(levels)
return com._ensure_platform_int(t.lookup(values))
def _get_codes_for_values(values, categories):
""""
utility routine to turn values into codes given the specified categories
"""
from pandas.core.algorithms import _get_data_algo, _hashtables
if values.dtype != categories.dtype:
values = com._ensure_object(values)
categories = com._ensure_object(categories)
(hash_klass, vec_klass), vals = _get_data_algo(values, _hashtables)
t = hash_klass(len(categories))
t.map_locations(com._values_from_object(categories))
return com._ensure_platform_int(t.lookup(values))
def duplicated(self, keep="first"):
keys = com._values_from_object(com._ensure_object(self.values))
duplicated = lib.duplicated(keys, keep=keep)
try:
return self._constructor(duplicated, index=self.index).__finalize__(self)
except AttributeError:
return np.array(duplicated, dtype=bool)
def duplicated(self, take_last=False):
keys = com._ensure_object(self.values)
duplicated = lib.duplicated(keys, take_last=take_last)
try:
return self._constructor(duplicated, index=self.index).__finalize__(self)
except AttributeError:
return np.array(duplicated, dtype=bool)
def _convert_listlike(arg, box):
if isinstance(arg, (list,tuple)):
arg = np.array(arg, dtype='O')
if com.is_datetime64_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg, tz='utc' if utc else None)
except ValueError as e:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, None, tz=tz)
return arg
arg = com._ensure_object(arg)
try:
if format is not None:
result = tslib.array_strptime(arg, format)
else:
result = tslib.array_to_datetime(arg, raise_=errors == 'raise',
utc=utc, dayfirst=dayfirst,
coerce=coerce, unit=unit)
if com.is_datetime64_dtype(result) and box:
result = DatetimeIndex(result, tz='utc' if utc else None)
return result
except ValueError as e:
try:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, None, tz=tz)
except (ValueError, TypeError):
raise e
def _convert_listlike(arg, box, unit):
if isinstance(arg, (list,tuple)) or ((hasattr(arg,'__iter__') and not hasattr(arg,'dtype'))):
arg = np.array(list(arg), dtype='O')
if is_timedelta64_dtype(arg):
value = arg.astype('timedelta64[ns]')
elif is_integer_dtype(arg):
# these are shortcutable
value = arg.astype('timedelta64[{0}]'.format(unit)).astype('timedelta64[ns]')
else:
try:
value = tslib.array_to_timedelta64(_ensure_object(arg), unit=unit, coerce=coerce)
except:
# try to process strings fast; may need to fallback
try:
value = np.array([ _get_string_converter(r, unit=unit)() for r in arg ],dtype='m8[ns]')
except:
value = np.array([ _coerce_scalar_to_timedelta_type(r, unit=unit, coerce=coerce) for r in arg ])
value = value.astype('timedelta64[ns]', copy=False)
if box:
from pandas import TimedeltaIndex
value = TimedeltaIndex(value,unit='ns')
return value
def mode(values):
"""Returns the mode or mode(s) of the passed Series or ndarray (sorted)"""
# must sort because hash order isn't necessarily defined.
from pandas.core.series import Series
if isinstance(values, Series):
constructor = values._constructor
values = values.values
else:
values = np.asanyarray(values)
constructor = Series
dtype = values.dtype
if com.is_integer_dtype(values.dtype):
values = com._ensure_int64(values)
result = constructor(sorted(htable.mode_int64(values)), dtype=dtype)
elif issubclass(values.dtype.type, (np.datetime64, np.timedelta64)):
dtype = values.dtype
values = values.view(np.int64)
result = constructor(sorted(htable.mode_int64(values)), dtype=dtype)
else:
mask = com.isnull(values)
values = com._ensure_object(values)
res = htable.mode_object(values, mask)
try:
res = sorted(res)
except TypeError as e:
warn("Unable to sort modes: %s" % e)
result = constructor(res, dtype=dtype)
return result
def _sqlalchemy_type(self, col):
from sqlalchemy.types import (BigInteger, Float, Text, Boolean,
DateTime, Date, Time, Interval)
if com.is_datetime64_dtype(col):
try:
tz = col.tzinfo
return DateTime(timezone=True)
except:
return DateTime
if com.is_timedelta64_dtype(col):
warnings.warn("the 'timedelta' type is not supported, and will be "
"written as integer values (ns frequency) to the "
"database.", UserWarning)
return BigInteger
elif com.is_float_dtype(col):
return Float
elif com.is_integer_dtype(col):
# TODO: Refine integer size.
return BigInteger
elif com.is_bool_dtype(col):
return Boolean
inferred = lib.infer_dtype(com._ensure_object(col))
if inferred == 'date':
return Date
if inferred == 'time':
return Time
return Text
def _sql_type_name(self, col):
pytype = col.dtype.type
pytype_name = "text"
if issubclass(pytype, np.floating):
pytype_name = "float"
elif com.is_timedelta64_dtype(pytype):
warnings.warn("the 'timedelta' type is not supported, and will be "
"written as integer values (ns frequency) to the "
"database.", UserWarning)
pytype_name = "int"
elif issubclass(pytype, np.integer):
pytype_name = "int"
elif issubclass(pytype, np.datetime64) or pytype is datetime:
# Caution: np.datetime64 is also a subclass of np.number.
pytype_name = "datetime"
elif issubclass(pytype, np.bool_):
pytype_name = "bool"
elif issubclass(pytype, np.object):
pytype = lib.infer_dtype(com._ensure_object(col))
if pytype == "date":
pytype_name = "date"
elif pytype == "time":
pytype_name = "time"
return _SQL_TYPES[pytype_name][self.pd_sql.flavor]
def to_datetime(arg, errors='ignore', dayfirst=False, utc=None, box=True):
"""
Convert argument to datetime
Parameters
----------
arg : string, datetime, array of strings (with possible NAs)
errors : {'ignore', 'raise'}, default 'ignore'
Errors are ignored by default (values left untouched)
utc : boolean, default None
Return UTC DatetimeIndex if True (converting any tz-aware
datetime.datetime objects as well)
Returns
-------
ret : datetime if parsing succeeded
"""
from pandas.core.series import Series
from pandas.tseries.index import DatetimeIndex
if arg is None:
return arg
elif isinstance(arg, datetime):
return arg
elif isinstance(arg, Series):
values = lib.array_to_datetime(com._ensure_object(arg.values),
raise_=errors == 'raise',
utc=utc,
dayfirst=dayfirst)
return Series(values, index=arg.index, name=arg.name)
elif isinstance(arg, (np.ndarray, list)):
if isinstance(arg, list):
arg = np.array(arg, dtype='O')
result = lib.array_to_datetime(com._ensure_object(arg),
raise_=errors == 'raise',
utc=utc,
dayfirst=dayfirst)
if com.is_datetime64_dtype(result) and box:
result = DatetimeIndex(result, tz='utc' if utc else None)
return result
try:
if not arg:
return arg
return parse(arg, dayfirst=dayfirst)
except Exception:
if errors == 'raise':
raise
return arg
def duplicated(self, take_last=False):
keys = com._ensure_object(self.values)
duplicated = lib.duplicated(keys, take_last=take_last)
try:
return self._constructor(duplicated,
index=self.index).__finalize__(self)
except AttributeError:
from pandas.core.index import Index
return Index(duplicated)
def _convert_listlike(arg, format):
if isinstance(arg, (list, tuple)):
arg = np.array(arg, dtype='O')
elif getattr(arg, 'ndim', 1) > 1:
raise TypeError('arg must be a string, datetime, list, tuple, '
'1-d array, or Series')
arg = com._ensure_object(arg)
if infer_time_format and format is None:
format = _guess_time_format_for_array(arg)
times = []
if format is not None:
for element in arg:
try:
times.append(datetime.strptime(element, format).time())
except (ValueError, TypeError):
if errors == 'raise':
raise ValueError("Cannot convert %s to a time with "
"given format %s" % (element, format))
elif errors == 'ignore':
return arg
else:
times.append(None)
else:
formats = _time_formats[:]
format_found = False
for element in arg:
time_object = None
for time_format in formats:
try:
time_object = datetime.strptime(element,
time_format).time()
if not format_found:
# Put the found format in front
fmt = formats.pop(formats.index(time_format))
formats.insert(0, fmt)
format_found = True
break
except (ValueError, TypeError):
continue
if time_object is not None:
times.append(time_object)
elif errors == 'raise':
raise ValueError("Cannot convert arg {arg} to "
"a time".format(arg=arg))
elif errors == 'ignore':
return arg
else:
times.append(None)
return times
def to_datetime(arg, errors='ignore', dayfirst=False):
"""
Convert argument to datetime
Parameters
----------
arg : string, datetime, array of strings (with possible NAs)
errors : {'ignore', 'raise'}, default 'ignore'
Errors are ignored by default (values left untouched)
Returns
-------
ret : datetime if parsing succeeded
"""
from pandas.core.series import Series
from pandas.tseries.index import DatetimeIndex
if arg is None:
return arg
elif isinstance(arg, datetime):
return arg
elif isinstance(arg, Series):
values = lib.string_to_datetime(com._ensure_object(arg.values),
raise_=errors == 'raise',
dayfirst=dayfirst)
return Series(values, index=arg.index, name=arg.name)
elif isinstance(arg, (np.ndarray, list)):
if isinstance(arg, list):
arg = np.array(arg, dtype='O')
result = lib.string_to_datetime(com._ensure_object(arg),
raise_=errors == 'raise',
dayfirst=dayfirst)
if com.is_datetime64_dtype(result):
result = DatetimeIndex(result)
return result
try:
if not arg:
return arg
return _dtparser.parse(arg, dayfirst=dayfirst)
except Exception:
if errors == 'raise':
raise
return arg
def _get_data_algo(values, func_map):
if com.is_float_dtype(values):
f = func_map['float64']
values = com._ensure_float64(values)
elif com.is_integer_dtype(values):
f = func_map['int64']
values = com._ensure_int64(values)
else:
f = func_map['generic']
values = com._ensure_object(values)
return f, values
def _get_hash_table_and_cast(values):
if com.is_float_dtype(values):
klass = lib.Float64HashTable
values = com._ensure_float64(values)
elif com.is_integer_dtype(values):
klass = lib.Int64HashTable
values = com._ensure_int64(values)
else:
klass = lib.PyObjectHashTable
values = com._ensure_object(values)
return klass, values
def to_numeric(arg, errors='raise'):
"""
Convert argument to a numeric type.
Parameters
----------
arg : list, tuple, 1-d array, or Series
errors : {'ignore', 'raise', 'coerce'}, default 'raise'
- If 'raise', then invalid parsing will raise an exception
- If 'coerce', then invalid parsing will be set as NaN
- If 'ignore', then invalid parsing will return the input
Returns
-------
ret : numeric if parsing succeeded.
Return type depends on input. Series if Series, otherwise ndarray
Examples
--------
Take separate series and convert to numeric, coercing when told to
>>> import pandas as pd
>>> s = pd.Series(['1.0', '2', -3])
>>> pd.to_numeric(s)
>>> s = pd.Series(['apple', '1.0', '2', -3])
>>> pd.to_numeric(s, errors='ignore')
>>> pd.to_numeric(s, errors='coerce')
"""
index = name = None
if isinstance(arg, pd.Series):
index, name = arg.index, arg.name
elif isinstance(arg, (list, tuple)):
arg = np.array(arg, dtype='O')
elif getattr(arg, 'ndim', 1) > 1:
raise TypeError('arg must be a list, tuple, 1-d array, or Series')
conv = arg
arg = com._ensure_object(arg)
coerce_numeric = False if errors in ('ignore', 'raise') else True
try:
conv = lib.maybe_convert_numeric(arg,
set(),
coerce_numeric=coerce_numeric)
except:
if errors == 'raise':
raise
if index is not None:
return pd.Series(conv, index=index, name=name)
else:
return conv
def _value_counts_arraylike(values, dropna=True):
is_datetimetz = com.is_datetimetz(values)
is_period = (isinstance(values, gt.ABCPeriodIndex) or
com.is_period_arraylike(values))
orig = values
from pandas.core.series import Series
values = Series(values).values
dtype = values.dtype
if com.is_datetime_or_timedelta_dtype(dtype) or is_period:
from pandas.tseries.index import DatetimeIndex
from pandas.tseries.period import PeriodIndex
if is_period:
values = PeriodIndex(values)
freq = values.freq
values = values.view(np.int64)
keys, counts = htable.value_count_scalar64(values, dropna)
if dropna:
msk = keys != iNaT
keys, counts = keys[msk], counts[msk]
# convert the keys back to the dtype we came in
keys = keys.astype(dtype)
# dtype handling
if is_datetimetz:
if isinstance(orig, gt.ABCDatetimeIndex):
tz = orig.tz
else:
tz = orig.dt.tz
keys = DatetimeIndex._simple_new(keys, tz=tz)
if is_period:
keys = PeriodIndex._simple_new(keys, freq=freq)
elif com.is_integer_dtype(dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
elif com.is_float_dtype(dtype):
values = com._ensure_float64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
else:
values = com._ensure_object(values)
mask = com.isnull(values)
keys, counts = htable.value_count_object(values, mask)
if not dropna and mask.any():
keys = np.insert(keys, 0, np.NaN)
counts = np.insert(counts, 0, mask.sum())
return keys, counts
def _get_data_algo(values, func_map):
if com.is_float_dtype(values):
f = func_map["float64"]
values = com._ensure_float64(values)
elif com.is_datetime64_dtype(values):
f = func_map["int64"]
values = values.view("i8")
elif com.is_integer_dtype(values):
f = func_map["int64"]
values = com._ensure_int64(values)
else:
f = func_map["generic"]
values = com._ensure_object(values)
return f, values
def _factorize_keys(lk, rk, sort=True):
if com.is_integer_dtype(lk) and com.is_integer_dtype(rk):
klass = lib.Int64Factorizer
lk = com._ensure_int64(lk)
rk = com._ensure_int64(rk)
else:
klass = lib.Factorizer
lk = com._ensure_object(lk)
rk = com._ensure_object(rk)
rizer = klass(max(len(lk), len(rk)))
llab, _ = rizer.factorize(lk)
rlab, _ = rizer.factorize(rk)
count = rizer.get_count()
if sort:
llab, rlab = _sort_labels(rizer.uniques, llab, rlab)
# TODO: na handling
return llab, rlab, count
def value_counts(values, sort=True, ascending=False, normalize=False):
"""
Compute a histogram of the counts of non-null values
Parameters
----------
values : ndarray (1-d)
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
normalize: boolean, default False
If True then compute a relative histogram
Returns
-------
value_counts : Series
"""
from pandas.core.series import Series
values = np.asarray(values)
if com.is_integer_dtype(values.dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_int64(values)
elif issubclass(values.dtype.type, (np.datetime64,np.timedelta64)):
dtype = values.dtype
values = values.view(np.int64)
keys, counts = htable.value_count_int64(values)
# convert the keys back to the dtype we came in
keys = Series(keys,dtype=dtype)
else:
mask = com.isnull(values)
values = com._ensure_object(values)
keys, counts = htable.value_count_object(values, mask)
result = Series(counts, index=keys)
if sort:
result.sort()
if not ascending:
result = result[::-1]
if normalize:
result = result / float(values.size)
return result
def _convert_f(arg):
arg = com._ensure_object(arg)
try:
result = lib.array_to_datetime(arg, raise_=errors == 'raise',
utc=utc, dayfirst=dayfirst)
if com.is_datetime64_dtype(result) and box:
result = DatetimeIndex(result, tz='utc' if utc else None)
return result
except ValueError, e:
try:
values, tz = lib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, None, tz=tz)
except (ValueError, TypeError):
raise e
def _get_data_algo(values, func_map):
mask = None
if com.is_float_dtype(values):
f = func_map["float64"]
values = com._ensure_float64(values)
elif com.is_datetime64_dtype(values):
# if we have NaT, punt to object dtype
mask = com.isnull(values)
if mask.ravel().any():
f = func_map["generic"]
values = com._ensure_object(values)
values[mask] = np.nan
else:
f = func_map["int64"]
values = values.view("i8")
elif com.is_integer_dtype(values):
f = func_map["int64"]
values = com._ensure_int64(values)
else:
f = func_map["generic"]
values = com._ensure_object(values)
return f, values
def _convert_listlike(arg, box):
if isinstance(arg, (list,tuple)):
arg = np.array(arg, dtype='O')
if com.is_datetime64_ns_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg, tz='utc' if utc else None)
except ValueError:
pass
return arg
arg = com._ensure_object(arg)
try:
if format is not None:
result = None
# shortcut formatting here
if format == '%Y%m%d':
try:
result = _attempt_YYYYMMDD(arg)
except:
raise ValueError("cannot convert the input to '%Y%m%d' date format")
# fallback
if result is None:
try:
result = tslib.array_strptime(arg, format, coerce=coerce)
except (tslib.OutOfBoundsDatetime):
if errors == 'raise':
raise
result = arg
else:
result = tslib.array_to_datetime(arg, raise_=errors == 'raise',
utc=utc, dayfirst=dayfirst,
coerce=coerce, unit=unit)
if com.is_datetime64_dtype(result) and box:
result = DatetimeIndex(result, tz='utc' if utc else None)
return result
except ValueError as e:
try:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, None, tz=tz)
except (ValueError, TypeError):
raise e
def _get_data_algo(values, func_map):
if com.is_float_dtype(values):
f = func_map['float64']
values = com._ensure_float64(values)
elif com.needs_i8_conversion(values):
f = func_map['int64']
values = values.view('i8')
elif com.is_integer_dtype(values):
f = func_map['int64']
values = com._ensure_int64(values)
else:
f = func_map['generic']
values = com._ensure_object(values)
return f, values
def unique1d(values):
"""
Hash table-based unique
"""
if np.issubdtype(values.dtype, np.floating):
table = _hash.Float64HashTable(len(values))
uniques = np.array(table.unique(com._ensure_float64(values)), dtype=np.float64)
elif np.issubdtype(values.dtype, np.datetime64):
table = _hash.Int64HashTable(len(values))
uniques = table.unique(com._ensure_int64(values))
uniques = uniques.view("M8[ns]")
elif np.issubdtype(values.dtype, np.integer):
table = _hash.Int64HashTable(len(values))
uniques = table.unique(com._ensure_int64(values))
else:
table = _hash.PyObjectHashTable(len(values))
uniques = table.unique(com._ensure_object(values))
return uniques
def unique1d(values):
"""
Hash table-based unique
"""
if np.issubdtype(values.dtype, np.floating):
table = _hash.Float64HashTable(len(values))
uniques = np.array(table.unique(_ensure_float64(values)),
dtype=np.float64)
elif np.issubdtype(values.dtype, np.datetime64):
table = _hash.Int64HashTable(len(values))
uniques = table.unique(_ensure_int64(values))
uniques = uniques.view('M8[ns]')
elif np.issubdtype(values.dtype, np.timedelta64):
table = _hash.Int64HashTable(len(values))
uniques = table.unique(_ensure_int64(values))
uniques = uniques.view('m8[ns]')
elif np.issubdtype(values.dtype, np.integer):
table = _hash.Int64HashTable(len(values))
uniques = table.unique(_ensure_int64(values))
else:
table = _hash.PyObjectHashTable(len(values))
uniques = table.unique(_ensure_object(values))
return uniques
def _convert_listlike(arg, box, unit):
if isinstance(arg, (list, tuple)) or ((hasattr(arg, '__iter__')
and not hasattr(arg, 'dtype'))):
arg = np.array(list(arg), dtype='O')
if is_timedelta64_dtype(arg):
value = arg.astype('timedelta64[ns]')
elif is_integer_dtype(arg):
# these are shortcutable
value = arg.astype(
'timedelta64[{0}]'.format(unit)).astype('timedelta64[ns]')
else:
try:
value = tslib.array_to_timedelta64(_ensure_object(arg),
unit=unit,
coerce=coerce)
except:
# try to process strings fast; may need to fallback
try:
value = np.array(
[_get_string_converter(r, unit=unit)() for r in arg],
dtype='m8[ns]')
except:
value = np.array([
_coerce_scalar_to_timedelta_type(r,
unit=unit,
coerce=coerce)
for r in arg
])
if box:
from pandas import TimedeltaIndex
value = TimedeltaIndex(value, unit='ns')
return value
def value_counts(values, sort=True, ascending=False):
"""
Compute a histogram of the counts of non-null values
Parameters
----------
values : ndarray (1-d)
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
Returns
-------
value_counts : Series
"""
from pandas.core.series import Series
values = np.asarray(values)
if com.is_integer_dtype(values.dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_int64(values)
else:
mask = com.isnull(values)
values = com._ensure_object(values)
keys, counts = htable.value_count_object(values, mask)
result = Series(counts, index=keys)
if sort:
result.sort()
if not ascending:
result = result[::-1]
return result
def _convert_listlike(arg, box):
if isinstance(arg, (list, tuple)):
arg = np.array(arg, dtype='O')
if com.is_datetime64_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg, tz='utc' if utc else None)
except ValueError as e:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, None, tz=tz)
return arg
arg = com._ensure_object(arg)
try:
if format is not None:
result = tslib.array_strptime(arg, format)
else:
result = tslib.array_to_datetime(arg,
raise_=errors == 'raise',
utc=utc,
dayfirst=dayfirst,
coerce=coerce,
unit=unit)
if com.is_datetime64_dtype(result) and box:
result = DatetimeIndex(result, tz='utc' if utc else None)
return result
except ValueError as e:
try:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, None, tz=tz)
except (ValueError, TypeError):
raise e
def value_counts(values,
sort=True,
ascending=False,
normalize=False,
bins=None,
dropna=True):
"""
Compute a histogram of the counts of non-null values.
Parameters
----------
values : ndarray (1-d)
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
normalize: boolean, default False
If True then compute a relative histogram
bins : integer, optional
Rather than count values, group them into half-open bins,
convenience for pd.cut, only works with numeric data
dropna : boolean, default True
Don't include counts of NaN
Returns
-------
value_counts : Series
"""
from pandas.core.series import Series
from pandas.tools.tile import cut
from pandas import Index, PeriodIndex, DatetimeIndex
name = getattr(values, 'name', None)
values = Series(values).values
if bins is not None:
try:
cat, bins = cut(values, bins, retbins=True)
except TypeError:
raise TypeError("bins argument only works with numeric data.")
values = cat.codes
if com.is_categorical_dtype(values.dtype):
result = values.value_counts(dropna)
else:
dtype = values.dtype
is_period = com.is_period_arraylike(values)
is_datetimetz = com.is_datetimetz(values)
if com.is_datetime_or_timedelta_dtype(
dtype) or is_period or is_datetimetz:
if is_period:
values = PeriodIndex(values)
elif is_datetimetz:
tz = getattr(values, 'tz', None)
values = DatetimeIndex(values).tz_localize(None)
values = values.view(np.int64)
keys, counts = htable.value_count_scalar64(values, dropna)
if dropna:
from pandas.tslib import iNaT
msk = keys != iNaT
keys, counts = keys[msk], counts[msk]
# localize to the original tz if necessary
if is_datetimetz:
keys = DatetimeIndex(keys).tz_localize(tz)
# convert the keys back to the dtype we came in
else:
keys = keys.astype(dtype)
elif com.is_integer_dtype(dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
elif com.is_float_dtype(dtype):
values = com._ensure_float64(values)
keys, counts = htable.value_count_scalar64(values, dropna)
else:
values = com._ensure_object(values)
mask = com.isnull(values)
keys, counts = htable.value_count_object(values, mask)
if not dropna and mask.any():
keys = np.insert(keys, 0, np.NaN)
counts = np.insert(counts, 0, mask.sum())
if not isinstance(keys, Index):
keys = Index(keys)
result = Series(counts, index=keys, name=name)
if bins is not None:
# TODO: This next line should be more efficient
result = result.reindex(np.arange(len(cat.categories)),
fill_value=0)
result.index = bins[:-1]
if sort:
result = result.sort_values(ascending=ascending)
if normalize:
result = result / float(values.size)
return result
def factorize(values, sort=False, order=None, na_sentinel=-1, size_hint=None):
"""
Encode input values as an enumerated type or categorical variable
Parameters
----------
values : ndarray (1-d)
Sequence
sort : boolean, default False
Sort by values
order : deprecated
na_sentinel : int, default -1
Value to mark "not found"
size_hint : hint to the hashtable sizer
Returns
-------
labels : the indexer to the original array
uniques : ndarray (1-d) or Index
the unique values. Index is returned when passed values is Index or Series
note: an array of Periods will ignore sort as it returns an always sorted PeriodIndex
"""
if order is not None:
msg = "order is deprecated. See https://github.com/pydata/pandas/issues/6926"
warn(msg, FutureWarning, stacklevel=2)
from pandas.core.index import Index
from pandas.core.series import Series
vals = np.asarray(values)
is_datetime = com.is_datetime64_dtype(vals)
is_timedelta = com.is_timedelta64_dtype(vals)
(hash_klass, vec_klass), vals = _get_data_algo(vals, _hashtables)
table = hash_klass(size_hint or len(vals))
uniques = vec_klass()
labels = table.get_labels(vals, uniques, 0, na_sentinel)
labels = com._ensure_platform_int(labels)
uniques = uniques.to_array()
if sort and len(uniques) > 0:
try:
sorter = uniques.argsort()
except:
# unorderable in py3 if mixed str/int
t = hash_klass(len(uniques))
t.map_locations(com._ensure_object(uniques))
# order ints before strings
ordered = np.concatenate([
np.sort(
np.array([e for i, e in enumerate(uniques) if f(e)],
dtype=object)) for f in [
lambda x: not isinstance(x, string_types),
lambda x: isinstance(x, string_types)
]
])
sorter = com._ensure_platform_int(
t.lookup(com._ensure_object(ordered)))
reverse_indexer = np.empty(len(sorter), dtype=np.int_)
reverse_indexer.put(sorter, np.arange(len(sorter)))
mask = labels < 0
labels = reverse_indexer.take(labels)
np.putmask(labels, mask, -1)
uniques = uniques.take(sorter)
if is_datetime:
uniques = uniques.astype('M8[ns]')
elif is_timedelta:
uniques = uniques.astype('m8[ns]')
if isinstance(values, Index):
uniques = values._shallow_copy(uniques, name=None)
elif isinstance(values, Series):
uniques = Index(uniques)
return labels, uniques
def to_datetime(arg, errors='ignore', dayfirst=False, utc=None, box=True,
format=None, coerce=False, unit='ns'):
"""
Convert argument to datetime
Parameters
----------
arg : string, datetime, array of strings (with possible NAs)
errors : {'ignore', 'raise'}, default 'ignore'
Errors are ignored by default (values left untouched)
dayfirst : boolean, default False
If True parses dates with the day first, eg 20/01/2005
Warning: dayfirst=True is not strict, but will prefer to parse
with day first (this is a known bug).
utc : boolean, default None
Return UTC DatetimeIndex if True (converting any tz-aware
datetime.datetime objects as well)
box : boolean, default True
If True returns a DatetimeIndex, if False returns ndarray of values
format : string, default None
strftime to parse time, eg "%d/%m/%Y"
coerce : force errors to NaT (False by default)
unit : unit of the arg (D,s,ms,us,ns) denote the unit in epoch
(e.g. a unix timestamp), which is an integer/float number
Returns
-------
ret : datetime if parsing succeeded
"""
from pandas import Timestamp
from pandas.core.series import Series
from pandas.tseries.index import DatetimeIndex
def _convert_listlike(arg, box):
if isinstance(arg, (list,tuple)):
arg = np.array(arg, dtype='O')
if com.is_datetime64_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg, tz='utc' if utc else None)
except ValueError, e:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, None, tz=tz)
return arg
arg = com._ensure_object(arg)
try:
if format is not None:
result = tslib.array_strptime(arg, format)
else:
result = tslib.array_to_datetime(arg, raise_=errors == 'raise',
utc=utc, dayfirst=dayfirst,
coerce=coerce, unit=unit)
if com.is_datetime64_dtype(result) and box:
result = DatetimeIndex(result, tz='utc' if utc else None)
return result
except ValueError, e:
try:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, None, tz=tz)
except (ValueError, TypeError):
raise e
def _convert_listlike(arg, box, format):
if isinstance(arg, (list, tuple)):
arg = np.array(arg, dtype='O')
if com.is_datetime64_ns_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg, tz='utc' if utc else None)
except ValueError:
pass
return arg
arg = com._ensure_object(arg)
if infer_datetime_format and format is None:
format = _guess_datetime_format_for_array(arg, dayfirst=dayfirst)
if format is not None:
# There is a special fast-path for iso8601 formatted
# datetime strings, so in those cases don't use the inferred
# format because this path makes process slower in this
# special case
format_is_iso8601 = ('%Y-%m-%dT%H:%M:%S.%f'.startswith(format)
or
'%Y-%m-%d %H:%M:%S.%f'.startswith(format))
if format_is_iso8601:
format = None
try:
result = None
if format is not None:
# shortcut formatting here
if format == '%Y%m%d':
try:
result = _attempt_YYYYMMDD(arg, coerce=coerce)
except:
raise ValueError(
"cannot convert the input to '%Y%m%d' date format")
# fallback
if result is None:
try:
result = tslib.array_strptime(arg,
format,
exact=exact,
coerce=coerce)
except (tslib.OutOfBoundsDatetime):
if errors == 'raise':
raise
result = arg
except ValueError:
# Only raise this error if the user provided the
# datetime format, and not when it was inferred
if not infer_datetime_format:
raise
if result is None and (format is None or infer_datetime_format):
result = tslib.array_to_datetime(arg,
raise_=errors == 'raise',
utc=utc,
dayfirst=dayfirst,
coerce=coerce,
unit=unit)
if com.is_datetime64_dtype(result) and box:
result = DatetimeIndex(result, tz='utc' if utc else None)
return result
except ValueError as e:
try:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, None, tz=tz)
except (ValueError, TypeError):
raise e
def value_counts(values,
sort=True,
ascending=False,
normalize=False,
bins=None,
dropna=True):
"""
Compute a histogram of the counts of non-null values.
Parameters
----------
values : ndarray (1-d)
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
normalize: boolean, default False
If True then compute a relative histogram
bins : integer, optional
Rather than count values, group them into half-open bins,
convenience for pd.cut, only works with numeric data
dropna : boolean, default True
Don't include counts of NaN
Returns
-------
value_counts : Series
"""
from pandas.core.series import Series
from pandas.tools.tile import cut
from pandas.tseries.period import PeriodIndex
is_period = com.is_period_arraylike(values)
values = Series(values).values
is_category = com.is_categorical_dtype(values.dtype)
if bins is not None:
try:
cat, bins = cut(values, bins, retbins=True)
except TypeError:
raise TypeError("bins argument only works with numeric data.")
values = cat.codes
elif is_category:
bins = values.categories
cat = values
values = cat.codes
dtype = values.dtype
if issubclass(values.dtype.type,
(np.datetime64, np.timedelta64)) or is_period:
if is_period:
values = PeriodIndex(values)
values = values.view(np.int64)
keys, counts = htable.value_count_int64(values)
if dropna:
from pandas.tslib import iNaT
msk = keys != iNaT
keys, counts = keys[msk], counts[msk]
# convert the keys back to the dtype we came in
keys = keys.astype(dtype)
elif com.is_integer_dtype(dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_int64(values)
else:
values = com._ensure_object(values)
mask = com.isnull(values)
keys, counts = htable.value_count_object(values, mask)
if not dropna:
keys = np.insert(keys, 0, np.NaN)
counts = np.insert(counts, 0, mask.sum())
result = Series(counts, index=com._values_from_object(keys))
if bins is not None:
# TODO: This next line should be more efficient
result = result.reindex(np.arange(len(cat.categories)), fill_value=0)
if not is_category:
result.index = bins[:-1]
else:
result.index = cat.categories
if sort:
result.sort()
if not ascending:
result = result[::-1]
if normalize:
result = result / float(values.size)
return result
def _convert_listlike(arg, box, format, name=None):
if isinstance(arg, (list, tuple)):
arg = np.array(arg, dtype='O')
# these are shortcutable
if com.is_datetime64_ns_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg,
tz='utc' if utc else None,
name=name)
except ValueError:
pass
return arg
elif com.is_datetime64tz_dtype(arg):
if not isinstance(arg, DatetimeIndex):
return DatetimeIndex(arg, tz='utc' if utc else None)
if utc:
arg = arg.tz_convert(None).tz_localize('UTC')
return arg
elif unit is not None:
if format is not None:
raise ValueError("cannot specify both format and unit")
arg = getattr(arg, 'values', arg)
result = tslib.array_with_unit_to_datetime(arg,
unit,
errors=errors)
if box:
if errors == 'ignore':
from pandas import Index
return Index(result)
return DatetimeIndex(result,
tz='utc' if utc else None,
name=name)
return result
elif getattr(arg, 'ndim', 1) > 1:
raise TypeError('arg must be a string, datetime, list, tuple, '
'1-d array, or Series')
arg = com._ensure_object(arg)
require_iso8601 = False
if infer_datetime_format and format is None:
format = _guess_datetime_format_for_array(arg, dayfirst=dayfirst)
if format is not None:
# There is a special fast-path for iso8601 formatted
# datetime strings, so in those cases don't use the inferred
# format because this path makes process slower in this
# special case
format_is_iso8601 = _format_is_iso(format)
if format_is_iso8601:
require_iso8601 = not infer_datetime_format
format = None
try:
result = None
if format is not None:
# shortcut formatting here
if format == '%Y%m%d':
try:
result = _attempt_YYYYMMDD(arg, errors=errors)
except:
raise ValueError("cannot convert the input to "
"'%Y%m%d' date format")
# fallback
if result is None:
try:
result = tslib.array_strptime(arg,
format,
exact=exact,
errors=errors)
except tslib.OutOfBoundsDatetime:
if errors == 'raise':
raise
result = arg
except ValueError:
# if format was inferred, try falling back
# to array_to_datetime - terminate here
# for specified formats
if not infer_datetime_format:
if errors == 'raise':
raise
result = arg
if result is None and (format is None or infer_datetime_format):
result = tslib.array_to_datetime(
arg,
errors=errors,
utc=utc,
dayfirst=dayfirst,
yearfirst=yearfirst,
freq=freq,
require_iso8601=require_iso8601)
if com.is_datetime64_dtype(result) and box:
result = DatetimeIndex(result,
tz='utc' if utc else None,
name=name)
return result
except ValueError as e:
try:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, name=name, tz=tz)
except (ValueError, TypeError):
raise e
def to_numeric(arg, errors='raise', downcast=None):
"""
Convert argument to a numeric type.
Parameters
----------
arg : list, tuple, 1-d array, or Series
errors : {'ignore', 'raise', 'coerce'}, default 'raise'
- If 'raise', then invalid parsing will raise an exception
- If 'coerce', then invalid parsing will be set as NaN
- If 'ignore', then invalid parsing will return the input
downcast : {'integer', 'signed', 'unsigned', 'float'} , default None
If not None, and if the data has been successfully cast to a
numerical dtype (or if the data was numeric to begin with),
downcast that resulting data to the smallest numerical dtype
possible according to the following rules:
- 'integer' or 'signed': smallest signed int dtype (min.: np.int8)
- 'unsigned': smallest unsigned int dtype (min.: np.uint8)
- 'float': smallest float dtype (min.: np.float32)
As this behaviour is separate from the core conversion to
numeric values, any errors raised during the downcasting
will be surfaced regardless of the value of the 'errors' input.
In addition, downcasting will only occur if the size
of the resulting data's dtype is strictly larger than
the dtype it is to be cast to, so if none of the dtypes
checked satisfy that specification, no downcasting will be
performed on the data.
.. versionadded:: 0.19.0
Returns
-------
ret : numeric if parsing succeeded.
Return type depends on input. Series if Series, otherwise ndarray
Examples
--------
Take separate series and convert to numeric, coercing when told to
>>> import pandas as pd
>>> s = pd.Series(['1.0', '2', -3])
>>> pd.to_numeric(s)
0 1.0
1 2.0
2 -3.0
dtype: float64
>>> pd.to_numeric(s, downcast='float')
0 1.0
1 2.0
2 -3.0
dtype: float32
>>> pd.to_numeric(s, downcast='signed')
0 1
1 2
2 -3
dtype: int8
>>> s = pd.Series(['apple', '1.0', '2', -3])
>>> pd.to_numeric(s, errors='ignore')
0 apple
1 1.0
2 2
3 -3
dtype: object
>>> pd.to_numeric(s, errors='coerce')
0 NaN
1 1.0
2 2.0
3 -3.0
dtype: float64
"""
if downcast not in (None, 'integer', 'signed', 'unsigned', 'float'):
raise ValueError('invalid downcasting method provided')
is_series = False
is_index = False
is_scalar = False
if isinstance(arg, pd.Series):
is_series = True
values = arg.values
elif isinstance(arg, pd.Index):
is_index = True
values = arg.asi8
if values is None:
values = arg.values
elif isinstance(arg, (list, tuple)):
values = np.array(arg, dtype='O')
elif np.isscalar(arg):
if com.is_number(arg):
return arg
is_scalar = True
values = np.array([arg], dtype='O')
elif getattr(arg, 'ndim', 1) > 1:
raise TypeError('arg must be a list, tuple, 1-d array, or Series')
else:
values = arg
try:
if com.is_numeric_dtype(values):
pass
elif com.is_datetime_or_timedelta_dtype(values):
values = values.astype(np.int64)
else:
values = com._ensure_object(values)
coerce_numeric = False if errors in ('ignore', 'raise') else True
values = lib.maybe_convert_numeric(values,
set(),
coerce_numeric=coerce_numeric)
except Exception:
if errors == 'raise':
raise
# attempt downcast only if the data has been successfully converted
# to a numerical dtype and if a downcast method has been specified
if downcast is not None and com.is_numeric_dtype(values):
typecodes = None
if downcast in ('integer', 'signed'):
typecodes = np.typecodes['Integer']
elif downcast == 'unsigned' and np.min(values) > 0:
typecodes = np.typecodes['UnsignedInteger']
elif downcast == 'float':
typecodes = np.typecodes['Float']
# pandas support goes only to np.float32,
# as float dtypes smaller than that are
# extremely rare and not well supported
float_32_char = np.dtype(np.float32).char
float_32_ind = typecodes.index(float_32_char)
typecodes = typecodes[float_32_ind:]
if typecodes is not None:
# from smallest to largest
for dtype in typecodes:
if np.dtype(dtype).itemsize < values.dtype.itemsize:
values = com._possibly_downcast_to_dtype(values, dtype)
# successful conversion
if values.dtype == dtype:
break
if is_series:
return pd.Series(values, index=arg.index, name=arg.name)
elif is_index:
# because we want to coerce to numeric if possible,
# do not use _shallow_copy_with_infer
return Index(values, name=arg.name)
elif is_scalar:
return values[0]
else:
return values
def _convert_listlike(arg, box, format, name=None):
if isinstance(arg, (list, tuple)):
arg = np.array(arg, dtype='O')
# these are shortcutable
if com.is_datetime64_ns_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg,
tz='utc' if utc else None,
name=name)
except ValueError:
pass
return arg
elif format is None and com.is_integer_dtype(arg) and unit == 'ns':
result = arg.astype('datetime64[ns]')
if box:
return DatetimeIndex(result,
tz='utc' if utc else None,
name=name)
return result
arg = com._ensure_object(arg)
require_iso8601 = False
if infer_datetime_format and format is None:
format = _guess_datetime_format_for_array(arg, dayfirst=dayfirst)
if format is not None:
# There is a special fast-path for iso8601 formatted
# datetime strings, so in those cases don't use the inferred
# format because this path makes process slower in this
# special case
format_is_iso8601 = (('%Y-%m-%dT%H:%M:%S.%f'.startswith(format)
or '%Y-%m-%d %H:%M:%S.%f'.startswith(format))
and format != '%Y')
if format_is_iso8601:
require_iso8601 = not infer_datetime_format
format = None
try:
result = None
if format is not None:
# shortcut formatting here
if format == '%Y%m%d':
try:
result = _attempt_YYYYMMDD(arg, errors=errors)
except:
raise ValueError(
"cannot convert the input to '%Y%m%d' date format")
# fallback
if result is None:
try:
result = tslib.array_strptime(arg,
format,
exact=exact,
errors=errors)
except (tslib.OutOfBoundsDatetime):
if errors == 'raise':
raise
result = arg
except ValueError:
# if format was inferred, try falling back
# to array_to_datetime - terminate here
# for specified formats
if not infer_datetime_format:
if errors == 'raise':
raise
result = arg
if result is None and (format is None or infer_datetime_format):
result = tslib.array_to_datetime(
arg,
errors=errors,
utc=utc,
dayfirst=dayfirst,
yearfirst=yearfirst,
freq=freq,
unit=unit,
require_iso8601=require_iso8601)
if com.is_datetime64_dtype(result) and box:
result = DatetimeIndex(result,
tz='utc' if utc else None,
name=name)
return result
except ValueError as e:
try:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, name=name, tz=tz)
except (ValueError, TypeError):
raise e
def value_counts(values,
sort=True,
ascending=False,
normalize=False,
bins=None):
"""
Compute a histogram of the counts of non-null values
Parameters
----------
values : ndarray (1-d)
sort : boolean, default True
Sort by values
ascending : boolean, default False
Sort in ascending order
normalize: boolean, default False
If True then compute a relative histogram
bins : integer, optional
Rather than count values, group them into half-open bins,
convenience for pd.cut, only works with numeric data
Returns
-------
value_counts : Series
"""
from pandas.core.series import Series
from pandas.tools.tile import cut
values = Series(values).values
if bins is not None:
try:
cat, bins = cut(values, bins, retbins=True)
except TypeError:
raise TypeError("bins argument only works with numeric data.")
values = cat.labels
if com.is_integer_dtype(values.dtype):
values = com._ensure_int64(values)
keys, counts = htable.value_count_int64(values)
elif issubclass(values.dtype.type, (np.datetime64, np.timedelta64)):
dtype = values.dtype
values = values.view(np.int64)
keys, counts = htable.value_count_int64(values)
# convert the keys back to the dtype we came in
keys = Series(keys, dtype=dtype)
else:
mask = com.isnull(values)
values = com._ensure_object(values)
keys, counts = htable.value_count_object(values, mask)
result = Series(counts, index=com._values_from_object(keys))
if bins is not None:
# TODO: This next line should be more efficient
result = result.reindex(np.arange(len(cat.levels)), fill_value=0)
result.index = bins[:-1]
if sort:
result.sort()
if not ascending:
result = result[::-1]
if normalize:
result = result / float(values.size)
return result
def factorize(values, sort=False, order=None, na_sentinel=-1):
"""
Encode input values as an enumerated type or categorical variable
Parameters
----------
values : ndarray (1-d)
Sequence
sort : boolean, default False
Sort by values
order :
na_sentinel: int, default -1
Value to mark "not found"
Returns
-------
labels : the indexer to the original array
uniques : the unique values
note: an array of Periods will ignore sort as it returns an always sorted PeriodIndex
"""
from pandas.tseries.period import PeriodIndex
vals = np.asarray(values)
is_datetime = com.is_datetime64_dtype(vals)
(hash_klass, vec_klass), vals = _get_data_algo(vals, _hashtables)
table = hash_klass(len(vals))
uniques = vec_klass()
labels = table.get_labels(vals, uniques, 0, na_sentinel)
labels = com._ensure_platform_int(labels)
uniques = uniques.to_array()
if sort and len(uniques) > 0:
try:
sorter = uniques.argsort()
except:
# unorderable in py3 if mixed str/int
t = hash_klass(len(uniques))
t.map_locations(com._ensure_object(uniques))
# order ints before strings
ordered = np.concatenate([
np.sort(
np.array([e for i, e in enumerate(uniques) if f(e)],
dtype=object)) for f in [
lambda x: not isinstance(x, string_types),
lambda x: isinstance(x, string_types)
]
])
sorter = com._ensure_platform_int(
t.lookup(com._ensure_object(ordered)))
reverse_indexer = np.empty(len(sorter), dtype=np.int_)
reverse_indexer.put(sorter, np.arange(len(sorter)))
mask = labels < 0
labels = reverse_indexer.take(labels)
np.putmask(labels, mask, -1)
uniques = uniques.take(sorter)
if is_datetime:
uniques = uniques.astype('M8[ns]')
if isinstance(values, PeriodIndex):
uniques = PeriodIndex(ordinal=uniques, freq=values.freq)
return labels, uniques
def to_numeric(arg, errors='raise'):
"""
Convert argument to a numeric type.
Parameters
----------
arg : list, tuple, 1-d array, or Series
errors : {'ignore', 'raise', 'coerce'}, default 'raise'
- If 'raise', then invalid parsing will raise an exception
- If 'coerce', then invalid parsing will be set as NaN
- If 'ignore', then invalid parsing will return the input
Returns
-------
ret : numeric if parsing succeeded.
Return type depends on input. Series if Series, otherwise ndarray
Examples
--------
Take separate series and convert to numeric, coercing when told to
>>> import pandas as pd
>>> s = pd.Series(['1.0', '2', -3])
>>> pd.to_numeric(s)
>>> s = pd.Series(['apple', '1.0', '2', -3])
>>> pd.to_numeric(s, errors='ignore')
>>> pd.to_numeric(s, errors='coerce')
"""
is_series = False
is_index = False
is_scalar = False
if isinstance(arg, pd.Series):
is_series = True
values = arg.values
elif isinstance(arg, pd.Index):
is_index = True
values = arg.asi8
if values is None:
values = arg.values
elif isinstance(arg, (list, tuple)):
values = np.array(arg, dtype='O')
elif np.isscalar(arg):
if com.is_number(arg):
return arg
is_scalar = True
values = np.array([arg], dtype='O')
elif getattr(arg, 'ndim', 1) > 1:
raise TypeError('arg must be a list, tuple, 1-d array, or Series')
else:
values = arg
if com.is_numeric_dtype(values):
pass
elif com.is_datetime_or_timedelta_dtype(values):
values = values.astype(np.int64)
else:
values = com._ensure_object(values)
coerce_numeric = False if errors in ('ignore', 'raise') else True
try:
values = lib.maybe_convert_numeric(values,
set(),
coerce_numeric=coerce_numeric)
except:
if errors == 'raise':
raise
if is_series:
return pd.Series(values, index=arg.index, name=arg.name)
elif is_index:
# because we want to coerce to numeric if possible,
# do not use _shallow_copy_with_infer
return Index(values, name=arg.name)
elif is_scalar:
return values[0]
else:
return values
