def _map(f, arr, na_mask=False, na_value=np.nan, dtype=object):
from pandas.core.series import Series
if not len(arr):
return np.ndarray(0, dtype=dtype)
if isinstance(arr, Series):
arr = arr.values
if not isinstance(arr, np.ndarray):
arr = np.asarray(arr, dtype=object)
if na_mask:
mask = isnull(arr)
try:
result = lib.map_infer_mask(arr, f, mask.view(np.uint8))
except (TypeError, AttributeError):
def g(x):
try:
return f(x)
except (TypeError, AttributeError):
return na_value
return _map(g, arr, dtype=dtype)
if na_value is not np.nan:
np.putmask(result, mask, na_value)
if result.dtype == object:
result = lib.maybe_convert_objects(result)
return result
else:
return lib.map_infer(arr, f)
def _format_strings(self):
if self.float_format is None:
float_format = print_config.float_format
if float_format is None:
fmt_str = '%% .%dg' % print_config.precision
float_format = lambda x: fmt_str % x
else:
float_format = self.float_format
formatter = com.pprint_thing if self.formatter is None else self.formatter
def _format(x):
if self.na_rep is not None and lib.checknull(x):
if x is None:
return 'None'
return self.na_rep
else:
# object dtype
return '%s' % formatter(x)
vals = self.values
is_float = lib.map_infer(vals, com.is_float) & notnull(vals)
leading_space = is_float.any()
fmt_values = []
for i, v in enumerate(vals):
if not is_float[i] and leading_space:
fmt_values.append(' %s' % _format(v))
elif is_float[i]:
fmt_values.append(float_format(v))
else:
fmt_values.append(' %s' % _format(v))
return fmt_values
def _map(f, arr, na_mask=False, na_value=np.nan):
if isinstance(arr, Series):
arr = arr.values
if not isinstance(arr, np.ndarray):
arr = np.asarray(arr, dtype=object)
if na_mask:
mask = isnull(arr)
try:
result = lib.map_infer_mask(arr, f, mask.view(np.uint8))
except (TypeError, AttributeError):
def g(x):
try:
return f(x)
except (TypeError, AttributeError):
return na_value
return _map(g, arr)
if na_value is not np.nan:
np.putmask(result, mask, na_value)
if result.dtype == object:
result = lib.maybe_convert_objects(result)
return result
else:
return lib.map_infer(arr, f)
def str_get_dummies(arr, sep='|'):
"""
Split each string in the Series by sep and return a frame of
dummy/indicator variables.
Parameters
----------
sep : string, default "|"
String to split on.
Returns
-------
dummies : DataFrame
Examples
--------
>>> Series(['a|b', 'a', 'a|c']).str.get_dummies()
a b c
0 1 1 0
1 1 0 0
2 1 0 1
>>> Series(['a|b', np.nan, 'a|c']).str.get_dummies()
a b c
0 1 1 0
1 0 0 0
2 1 0 1
See Also
--------
pandas.get_dummies
"""
from pandas.core.frame import DataFrame
from pandas.core.index import Index
# GH9980, Index.str does not support get_dummies() as it returns a frame
if isinstance(arr, Index):
raise TypeError(
"get_dummies is not supported for string methods on Index")
# TODO remove this hack?
arr = arr.fillna('')
try:
arr = sep + arr + sep
except TypeError:
arr = sep + arr.astype(str) + sep
tags = set()
for ts in arr.str.split(sep):
tags.update(ts)
tags = sorted(tags - set([""]))
dummies = np.empty((len(arr), len(tags)), dtype=np.int64)
for i, t in enumerate(tags):
pat = sep + t + sep
dummies[:, i] = lib.map_infer(arr.values, lambda x: pat in x)
return DataFrame(dummies, arr.index, tags)
def str_get_dummies(arr, sep='|'):
"""
Split each string in the Series by sep and return a frame of
dummy/indicator variables.
Parameters
----------
sep : string, default "|"
String to split on.
Returns
-------
dummies : DataFrame
Examples
--------
>>> Series(['a|b', 'a', 'a|c']).str.get_dummies()
a b c
0 1 1 0
1 1 0 0
2 1 0 1
>>> Series(['a|b', np.nan, 'a|c']).str.get_dummies()
a b c
0 1 1 0
1 0 0 0
2 1 0 1
See Also
--------
pandas.get_dummies
"""
from pandas.core.frame import DataFrame
from pandas.core.index import Index
# GH9980, Index.str does not support get_dummies() as it returns a frame
if isinstance(arr, Index):
raise TypeError("get_dummies is not supported for string methods on "
"Index")
# TODO remove this hack?
arr = arr.fillna('')
try:
arr = sep + arr + sep
except TypeError:
arr = sep + arr.astype(str) + sep
tags = set()
for ts in arr.str.split(sep):
tags.update(ts)
tags = sorted(tags - set([""]))
dummies = np.empty((len(arr), len(tags)), dtype=np.int64)
for i, t in enumerate(tags):
pat = sep + t + sep
dummies[:, i] = lib.map_infer(arr.values, lambda x: pat in x)
return DataFrame(dummies, arr.index, tags)
def _dt_box_array(arr, offset=None, tz=None):
if arr is None:
return arr
if not isinstance(arr, np.ndarray):
return arr
boxfunc = lambda x: Timestamp(x, offset=offset, tz=tz)
return lib.map_infer(arr, boxfunc)
def _dt_box_array(arr, offset=None, tz=None):
if arr is None:
return arr
if not isinstance(arr, np.ndarray):
return arr
boxfunc = lambda x: Timestamp(x, offset=offset, tz=tz)
return lib.map_infer(arr, boxfunc)
def auto_map(arr, f, otherargs, n_results=1, required="all"):
from pandas.core.series import Series
if all(np.isscalar(a) for a in otherargs):
res = lib.map_infer(arr, lambda v: f(v, *otherargs))
return Series(res, index=arr.index, copy=False)
n_otherargs = len(otherargs)
if required == "all":
required = list(range(n_otherargs))
res = map_iter_args(arr, f, azip(*otherargs), n_otherargs, required, n_results)
res = [Series(col, index=arr.index, copy=False) for col in res]
if n_results == 1:
return res[0]
return res
def auto_map(arr, f, otherargs, n_results=1, required='all'):
from pandas.core.series import Series
if all(np.isscalar(a) for a in otherargs):
res = lib.map_infer(arr, lambda v: f(v, *otherargs))
return Series(res, index=arr.index, copy=False)
n_otherargs = len(otherargs)
if required == 'all':
required = list(range(n_otherargs))
res = map_iter_args(arr, f, azip(*otherargs), n_otherargs, required,
n_results)
res = [Series(col, index=arr.index, copy=False) for col in res]
if n_results == 1:
return res[0]
return res
def _format_strings(self, use_unicode=False):
if self.float_format is None:
float_format = print_config.float_format
if float_format is None:
fmt_str = "%% .%dg" % print_config.precision
float_format = lambda x: fmt_str % x
else:
float_format = self.float_format
if use_unicode:
def _strify(x):
return _stringify(x, print_config.encoding)
formatter = _strify if self.formatter is None else self.formatter
else:
formatter = str if self.formatter is None else self.formatter
def _format(x):
if self.na_rep is not None and lib.checknull(x):
if x is None:
return "None"
return self.na_rep
else:
# object dtype
return "%s" % formatter(x)
vals = self.values
is_float = lib.map_infer(vals, com.is_float) & notnull(vals)
leading_space = is_float.any()
fmt_values = []
for i, v in enumerate(vals):
if not is_float[i] and leading_space:
fmt_values.append(" %s" % _format(v))
elif is_float[i]:
fmt_values.append(float_format(v))
else:
fmt_values.append(" %s" % _format(v))
return fmt_values
def str_get_dummies(arr, sep='|'):
"""
Split each string by sep and return a frame of dummy/indicator variables.
Examples
--------
>>> Series(['a|b', 'a', 'a|c']).str.get_dummies()
a b c
0 1 1 0
1 1 0 0
2 1 0 1
>>> pd.Series(['a|b', np.nan, 'a|c']).str.get_dummies()
a b c
0 1 1 0
1 0 0 0
2 1 0 1
See also ``pd.get_dummies``.
"""
from pandas.core.frame import DataFrame
# TODO remove this hack?
arr = arr.fillna('')
try:
arr = sep + arr + sep
except TypeError:
arr = sep + arr.astype(str) + sep
tags = set()
for ts in arr.str.split(sep):
tags.update(ts)
tags = sorted(tags - set([""]))
dummies = np.empty((len(arr), len(tags)), dtype=np.int64)
for i, t in enumerate(tags):
pat = sep + t + sep
dummies[:, i] = lib.map_infer(arr.values, lambda x: pat in x)
return DataFrame(dummies, arr.index, tags)
def str_get_dummies(arr, sep='|'):
"""
Split each string by sep and return a frame of dummy/indicator variables.
Examples
--------
>>> Series(['a|b', 'a', 'a|c']).str.get_dummies()
a b c
0 1 1 0
1 1 0 0
2 1 0 1
>>> pd.Series(['a|b', np.nan, 'a|c']).str.get_dummies()
a b c
0 1 1 0
1 0 0 0
2 1 0 1
See also ``pd.get_dummies``.
"""
from pandas.core.frame import DataFrame
# TODO remove this hack?
arr = arr.fillna('')
try:
arr = sep + arr + sep
except TypeError:
arr = sep + arr.astype(str) + sep
tags = set()
for ts in arr.str.split(sep):
tags.update(ts)
tags = sorted(tags - set([""]))
dummies = np.empty((len(arr), len(tags)), dtype=np.int64)
for i, t in enumerate(tags):
pat = sep + t + sep
dummies[:, i] = lib.map_infer(arr.values, lambda x: pat in x)
return DataFrame(dummies, arr.index, tags)
def _format_strings(self):
if self.float_format is None:
float_format = get_option("display.float_format")
if float_format is None:
fmt_str = '%% .%dg' % get_option("display.precision")
float_format = lambda x: fmt_str % x
else:
float_format = self.float_format
formatter = (lambda x: com.pprint_thing(x,escape_chars=('\t','\r','\n'))) \
if self.formatter is None else self.formatter
def _format(x):
if self.na_rep is not None and lib.checknull(x):
if x is None:
return 'None'
return self.na_rep
else:
# object dtype
return '%s' % formatter(x)
vals = self.values
is_float = lib.map_infer(vals, com.is_float) & notnull(vals)
leading_space = is_float.any()
fmt_values = []
for i, v in enumerate(vals):
if not is_float[i] and leading_space:
fmt_values.append(' %s' % _format(v))
elif is_float[i]:
fmt_values.append(float_format(v))
else:
fmt_values.append(' %s' % _format(v))
return fmt_values
def _format_strings(self):
if self.float_format is None:
float_format = get_option("print.float_format")
if float_format is None:
fmt_str = '%% .%dg' % get_option("print.precision")
float_format = lambda x: fmt_str % x
else:
float_format = self.float_format
formatter = (lambda x: com.pprint_thing(x,escape_chars=('\t','\r','\n'))) \
if self.formatter is None else self.formatter
def _format(x):
if self.na_rep is not None and lib.checknull(x):
if x is None:
return 'None'
return self.na_rep
else:
# object dtype
return '%s' % formatter(x)
vals = self.values
is_float = lib.map_infer(vals, com.is_float) & notnull(vals)
leading_space = is_float.any()
fmt_values = []
for i, v in enumerate(vals):
if not is_float[i] and leading_space:
fmt_values.append(' %s' % _format(v))
elif is_float[i]:
fmt_values.append(float_format(v))
else:
fmt_values.append(' %s' % _format(v))
return fmt_values
def _convert_to_indexer(self, obj, axis=0):
"""
Convert indexing key into something we can use to do actual fancy
indexing on an ndarray
Examples
ix[:5] -> slice(0, 5)
ix[[1,2,3]] -> [1,2,3]
ix[['foo', 'bar', 'baz']] -> [i, j, k] (indices of foo, bar, baz)
Going by Zen of Python?
"In the face of ambiguity, refuse the temptation to guess."
raise AmbiguousIndexError with integer labels?
- No, prefer label-based indexing
"""
labels = self.obj._get_axis(axis)
is_int_index = _is_integer_index(labels)
if com.is_integer(obj) and not is_int_index:
return obj
try:
return labels.get_loc(obj)
except (KeyError, TypeError):
pass
if isinstance(obj, slice):
ltype = labels.inferred_type
if ltype == 'floating':
int_slice = _is_int_slice(obj)
else:
# floats that are within tolerance of int used
int_slice = _is_index_slice(obj)
null_slice = obj.start is None and obj.stop is None
# could have integers in the first level of the MultiIndex
position_slice = (int_slice and not ltype == 'integer'
and not isinstance(labels, MultiIndex))
start, stop = obj.start, obj.stop
# last ditch effort: if we are mixed and have integers
try:
if 'mixed' in ltype and int_slice:
if start is not None:
i = labels.get_loc(start)
if stop is not None:
j = labels.get_loc(stop)
position_slice = False
except KeyError:
if ltype == 'mixed-integer-float':
raise
if null_slice or position_slice:
slicer = obj
else:
try:
i, j = labels.slice_locs(start, stop)
slicer = slice(i, j, obj.step)
except Exception:
if _is_index_slice(obj):
if labels.inferred_type == 'integer':
raise
slicer = obj
else:
raise
return slicer
elif _is_list_like(obj):
if com._is_bool_indexer(obj):
objarr = _check_bool_indexer(labels, obj)
return objarr
else:
if isinstance(obj, Index):
objarr = obj.values
else:
objarr = _asarray_tuplesafe(obj)
# If have integer labels, defer to label-based indexing
if _is_integer_dtype(objarr) and not is_int_index:
if labels.inferred_type != 'integer':
objarr = np.where(objarr < 0,
len(labels) + objarr, objarr)
return objarr
# this is not the most robust, but...
if (isinstance(labels, MultiIndex)
and not isinstance(objarr[0], tuple)):
level = 0
_, indexer = labels.reindex(objarr, level=level)
check = labels.levels[0].get_indexer(objarr)
else:
level = None
# XXX
if labels.is_unique:
indexer = check = labels.get_indexer(objarr)
else:
mask = np.zeros(len(labels), dtype=bool)
lvalues = labels.values
for x in objarr:
# ugh
to_or = lib.map_infer(lvalues, x.__eq__)
if not to_or.any():
raise KeyError('%s not in index' % str(x))
mask |= to_or
indexer = check = mask.nonzero()[0]
mask = check == -1
if mask.any():
raise KeyError('%s not in index' % objarr[mask])
return indexer
else:
return labels.get_loc(obj)
def _box_values(self, values):
f = lambda x: Period(ordinal=x, freq=self.freq)
return lib.map_infer(values, f)
def _get_ordinals(data, freq):
f = lambda x: Period(x, freq=freq).ordinal
if isinstance(data[0], Period):
return period.extract_ordinals(data, freq)
else:
return lib.map_infer(data, f)
def get_chunk(self, rows=None):
if rows is not None and self.skip_footer:
raise ValueError('skip_footer not supported for iteration')
try:
content = self._get_lines(rows)
except StopIteration:
if self._first_chunk:
content = []
else:
raise
# done with first read, next time raise StopIteration
self._first_chunk = False
if len(content) == 0: # pragma: no cover
if self.index_col is not None:
if np.isscalar(self.index_col):
index = Index([], name=self.index_name)
else:
index = MultiIndex.from_arrays([[]] * len(self.index_col),
names=self.index_name)
else:
index = Index([])
return DataFrame(index=index, columns=self.columns)
zipped_content = list(lib.to_object_array(content).T)
if not self._has_complex_date_col and self.index_col is not None:
index = self._get_simple_index(zipped_content)
index = self._agg_index(index)
else:
index = Index(np.arange(len(content)))
col_len, zip_len = len(self.columns), len(zipped_content)
if col_len != zip_len:
row_num = -1
for (i, l) in enumerate(content):
if len(l) != col_len:
break
footers = 0
if self.skip_footer:
footers = self.skip_footer
row_num = self.pos - (len(content) - i + footers)
msg = ('Expecting %d columns, got %d in row %d' %
(col_len, zip_len, row_num))
raise ValueError(msg)
data = dict((k, v) for k, v in izip(self.columns, zipped_content))
# apply converters
for col, f in self.converters.iteritems():
if isinstance(col, int) and col not in self.columns:
col = self.columns[col]
data[col] = lib.map_infer(data[col], f)
columns = list(self.columns)
if self.parse_dates is not None:
data, columns = self._process_date_conversion(data)
data = _convert_to_ndarrays(data, self.na_values, self.verbose)
df = DataFrame(data=data, columns=columns, index=index)
if self._has_complex_date_col and self.index_col is not None:
if not self._name_processed:
self.index_name = self._get_index_name(list(columns))
self._name_processed = True
data = dict(((k, v) for k, v in df.iteritems()))
index = self._get_complex_date_index(data,
col_names=columns,
parse_dates=False)
index = self._agg_index(index, False)
data = dict(((k, v.values) for k, v in data.iteritems()))
df = DataFrame(data=data, columns=columns, index=index)
if self.squeeze and len(df.columns) == 1:
return df[df.columns[0]]
return df
def _box_values(self, values):
"""
apply box func to passed values
"""
return lib.map_infer(values, self._box_func)
def get_chunk(self, rows=None):
if rows is not None and self.skip_footer:
raise ValueError("skip_footer not supported for iteration")
try:
content = self._get_lines(rows)
except StopIteration:
if self._first_chunk:
content = []
else:
raise
# done with first read, next time raise StopIteration
self._first_chunk = False
columns = list(self.orig_columns)
if len(content) == 0: # pragma: no cover
if self.index_col is not None:
if np.isscalar(self.index_col):
index = Index([], name=self.index_name)
columns.pop(self.index_col)
else:
index = MultiIndex.from_arrays([[]] * len(self.index_col), names=self.index_name)
for n in self.index_col:
columns.pop(n)
else:
index = Index([])
return DataFrame(index=index, columns=columns)
alldata = self._rows_to_cols(content)
data = self._exclude_implicit_index(alldata)
# apply converters
for col, f in self.converters.iteritems():
if isinstance(col, int) and col not in self.orig_columns:
col = self.orig_columns[col]
data[col] = lib.map_infer(data[col], f)
data = _convert_to_ndarrays(data, self.na_values, self.verbose)
if self.parse_dates is not None:
data, columns = self._process_date_conversion(data)
if self.index_col is None:
numrows = len(content)
index = Index(np.arange(numrows))
elif not self._has_complex_date_col:
index = self._get_simple_index(alldata, columns)
index = self._agg_index(index)
elif self._has_complex_date_col:
if not self._name_processed:
self.index_name = self._explicit_index_names(list(columns))
self._name_processed = True
index = self._get_complex_date_index(data, columns)
index = self._agg_index(index, False)
df = DataFrame(data=data, columns=columns, index=index)
if self.squeeze and len(df.columns) == 1:
return df[df.columns[0]]
return df
def _convert_to_indexer(self, obj, axis=0):
"""
Convert indexing key into something we can use to do actual fancy
indexing on an ndarray
Examples
ix[:5] -> slice(0, 5)
ix[[1,2,3]] -> [1,2,3]
ix[['foo', 'bar', 'baz']] -> [i, j, k] (indices of foo, bar, baz)
Going by Zen of Python?
"In the face of ambiguity, refuse the temptation to guess."
raise AmbiguousIndexError with integer labels?
- No, prefer label-based indexing
"""
labels = self.obj._get_axis(axis)
is_int_index = _is_integer_index(labels)
if com.is_integer(obj) and not is_int_index:
return obj
try:
return labels.get_loc(obj)
except (KeyError, TypeError):
pass
if isinstance(obj, slice):
ltype = labels.inferred_type
if ltype == 'floating':
int_slice = _is_int_slice(obj)
else:
# floats that are within tolerance of int used
int_slice = _is_index_slice(obj)
null_slice = obj.start is None and obj.stop is None
# could have integers in the first level of the MultiIndex
position_slice = (int_slice
and not ltype == 'integer'
and not isinstance(labels, MultiIndex))
start, stop = obj.start, obj.stop
# last ditch effort: if we are mixed and have integers
try:
if 'mixed' in ltype and int_slice:
if start is not None:
i = labels.get_loc(start)
if stop is not None:
j = labels.get_loc(stop)
position_slice = False
except KeyError:
if ltype == 'mixed-integer-float':
raise
if null_slice or position_slice:
slicer = obj
else:
try:
i, j = labels.slice_locs(start, stop)
slicer = slice(i, j, obj.step)
except Exception:
if _is_index_slice(obj):
if labels.inferred_type == 'integer':
raise
slicer = obj
else:
raise
return slicer
elif _is_list_like(obj):
if com._is_bool_indexer(obj):
objarr = _check_bool_indexer(labels, obj)
return objarr
else:
if isinstance(obj, Index):
objarr = obj.values
else:
objarr = _asarray_tuplesafe(obj)
# If have integer labels, defer to label-based indexing
if _is_integer_dtype(objarr) and not is_int_index:
if labels.inferred_type != 'integer':
objarr = np.where(objarr < 0,
len(labels) + objarr, objarr)
return objarr
# this is not the most robust, but...
if (isinstance(labels, MultiIndex) and
not isinstance(objarr[0], tuple)):
level = 0
_, indexer = labels.reindex(objarr, level=level)
check = labels.levels[0].get_indexer(objarr)
else:
level = None
# XXX
if labels.is_unique:
indexer = check = labels.get_indexer(objarr)
else:
mask = np.zeros(len(labels), dtype=bool)
lvalues = labels.values
for x in objarr:
# ugh
to_or = lib.map_infer(lvalues, x.__eq__)
if not to_or.any():
raise KeyError('%s not in index' % str(x))
mask |= to_or
indexer = check = mask.nonzero()[0]
mask = check == -1
if mask.any():
raise KeyError('%s not in index' % objarr[mask])
return indexer
else:
return labels.get_loc(obj)
def _map(f, arr):
if not isinstance(arr, np.ndarray):
arr = np.asarray(arr, dtype=object)
return lib.map_infer(arr, f)
def _box_values(self, values):
"""
apply box func to passed values
"""
import pandas.lib as lib
return lib.map_infer(values, self._box_func)
def _have_unicode(self):
mask = lib.map_infer(self.values, lambda x: isinstance(x, unicode))
return mask.any()
def _box_values(self, values):
f = lambda x: Period(ordinal=x, freq=self.freq)
return lib.map_infer(values, f)
def _box_values(self, values):
return lib.map_infer(values, lib.Timestamp)
def _box_values(self, values):
return lib.map_infer(values, lib.Timestamp)
def _get_object_index(self):
boxfunc = lambda x: Timestamp(x, offset=self.offset, tz=self.tz)
boxed_values = lib.map_infer(self.asi8, boxfunc)
return Index(boxed_values, dtype=object)
def _have_unicode(self):
mask = lib.map_infer(self.values, lambda x: isinstance(x, unicode))
return mask.any()
def _map(f, arr):
if not isinstance(arr, np.ndarray):
arr = np.asarray(arr, dtype=object)
return lib.map_infer(arr, f)
def _box_values(self, values):
"""
apply box func to passed values
"""
import pandas.lib as lib
return lib.map_infer(values, self._box_func)
def _box_values(self, values):
"""
apply box func to passed values
"""
return lib.map_infer(values, self._box_func)
def _get_object_index(self):
boxfunc = lambda x: Timestamp(x, offset=self.offset, tz=self.tz)
boxed_values = lib.map_infer(self.asi8, boxfunc)
return Index(boxed_values, dtype=object)
def _get_ordinals(data, freq):
f = lambda x: Period(x, freq=freq).ordinal
if isinstance(data[0], Period):
return period.extract_ordinals(data, freq)
else:
return lib.map_infer(data, f)
def get_chunk(self, rows=None):
if rows is not None and self.skip_footer:
raise ValueError('skip_footer not supported for iteration')
try:
content = self._get_lines(rows)
except StopIteration:
if self._first_chunk:
content = []
else:
raise
# done with first read, next time raise StopIteration
self._first_chunk = False
if len(content) == 0: # pragma: no cover
if self.index_col is not None:
if np.isscalar(self.index_col):
index = Index([], name=self.index_name)
else:
index = MultiIndex.from_arrays([[]] * len(self.index_col),
names=self.index_name)
else:
index = Index([])
return DataFrame(index=index, columns=self.columns)
zipped_content = list(lib.to_object_array(content).T)
if not self._has_complex_date_col and self.index_col is not None:
index = self._get_simple_index(zipped_content)
index = self._agg_index(index)
else:
index = Index(np.arange(len(content)))
col_len, zip_len = len(self.columns), len(zipped_content)
if col_len != zip_len:
row_num = -1
for (i, l) in enumerate(content):
if len(l) != col_len:
break
footers = 0
if self.skip_footer:
footers = self.skip_footer
row_num = self.pos - (len(content) - i + footers)
msg = ('Expecting %d columns, got %d in row %d' %
(col_len, zip_len, row_num))
raise ValueError(msg)
data = dict((k, v) for k, v in izip(self.columns, zipped_content))
# apply converters
for col, f in self.converters.iteritems():
if isinstance(col, int) and col not in self.columns:
col = self.columns[col]
data[col] = lib.map_infer(data[col], f)
columns = list(self.columns)
if self.parse_dates is not None:
data, columns = self._process_date_conversion(data)
data = _convert_to_ndarrays(data, self.na_values, self.verbose)
df = DataFrame(data=data, columns=columns, index=index)
if self._has_complex_date_col and self.index_col is not None:
if not self._name_processed:
self.index_name = self._get_index_name(list(columns))
self._name_processed = True
data = dict(((k, v) for k, v in df.iteritems()))
index = self._get_complex_date_index(data, col_names=columns,
parse_dates=False)
index = self._agg_index(index, False)
data = dict(((k, v.values) for k, v in data.iteritems()))
df = DataFrame(data=data, columns=columns, index=index)
if self.squeeze and len(df.columns) == 1:
return df[df.columns[0]]
return df
