Python pandas.compat.iterkeys() Examples
The following are 11
code examples of pandas.compat.iterkeys().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
pandas.compat
, or try the search function
.
.
Example #1
| Source File: test_stata.py From recruit with Apache License 2.0 | 5 votes |
|
def test_missing_value_conversion(self, file):
columns = ['int8_', 'int16_', 'int32_', 'float32_', 'float64_']
smv = StataMissingValue(101)
keys = [key for key in iterkeys(smv.MISSING_VALUES)]
keys.sort()
data = []
for i in range(27):
row = [StataMissingValue(keys[i + (j * 27)]) for j in range(5)]
data.append(row)
expected = DataFrame(data, columns=columns)
parsed = read_stata(getattr(self, file), convert_missing=True)
tm.assert_frame_equal(parsed, expected)
Example #2
| Source File: stata.py From recruit with Apache License 2.0 | 5 votes |
|
def _do_convert_categoricals(self, data, value_label_dict, lbllist,
order_categoricals):
"""
Converts categorical columns to Categorical type.
"""
value_labels = list(compat.iterkeys(value_label_dict))
cat_converted_data = []
for col, label in zip(data, lbllist):
if label in value_labels:
# Explicit call with ordered=True
cat_data = Categorical(data[col], ordered=order_categoricals)
categories = []
for category in cat_data.categories:
if category in value_label_dict[label]:
categories.append(value_label_dict[label][category])
else:
categories.append(category) # Partially labeled
try:
cat_data.categories = categories
except ValueError:
vc = Series(categories).value_counts()
repeats = list(vc.index[vc > 1])
repeats = '\n' + '-' * 80 + '\n'.join(repeats)
raise ValueError('Value labels for column {col} are not '
'unique. The repeated labels are:\n'
'{repeats}'
.format(col=col, repeats=repeats))
# TODO: is the next line needed above in the data(...) method?
cat_data = Series(cat_data, index=data.index)
cat_converted_data.append((col, cat_data))
else:
cat_converted_data.append((col, data[col]))
data = DataFrame.from_dict(OrderedDict(cat_converted_data))
return data
Example #3
| Source File: test_stata.py From vnpy_crypto with MIT License | 5 votes |
|
def test_missing_value_conversion(self, file):
columns = ['int8_', 'int16_', 'int32_', 'float32_', 'float64_']
smv = StataMissingValue(101)
keys = [key for key in iterkeys(smv.MISSING_VALUES)]
keys.sort()
data = []
for i in range(27):
row = [StataMissingValue(keys[i + (j * 27)]) for j in range(5)]
data.append(row)
expected = DataFrame(data, columns=columns)
parsed = read_stata(getattr(self, file), convert_missing=True)
tm.assert_frame_equal(parsed, expected)
Example #4
| Source File: stata.py From vnpy_crypto with MIT License | 5 votes |
|
def _do_convert_categoricals(self, data, value_label_dict, lbllist,
order_categoricals):
"""
Converts categorical columns to Categorical type.
"""
value_labels = list(compat.iterkeys(value_label_dict))
cat_converted_data = []
for col, label in zip(data, lbllist):
if label in value_labels:
# Explicit call with ordered=True
cat_data = Categorical(data[col], ordered=order_categoricals)
categories = []
for category in cat_data.categories:
if category in value_label_dict[label]:
categories.append(value_label_dict[label][category])
else:
categories.append(category) # Partially labeled
try:
cat_data.categories = categories
except ValueError:
vc = Series(categories).value_counts()
repeats = list(vc.index[vc > 1])
repeats = '\n' + '-' * 80 + '\n'.join(repeats)
msg = 'Value labels for column {0} are not unique. The ' \
'repeated labels are:\n{1}'.format(col, repeats)
raise ValueError(msg)
# TODO: is the next line needed above in the data(...) method?
cat_data = Series(cat_data, index=data.index)
cat_converted_data.append((col, cat_data))
else:
cat_converted_data.append((col, data[col]))
data = DataFrame.from_dict(OrderedDict(cat_converted_data))
return data
Example #5
| Source File: test_stata.py From predictive-maintenance-using-machine-learning with Apache License 2.0 | 5 votes |
|
def test_missing_value_conversion(self, file):
columns = ['int8_', 'int16_', 'int32_', 'float32_', 'float64_']
smv = StataMissingValue(101)
keys = [key for key in iterkeys(smv.MISSING_VALUES)]
keys.sort()
data = []
for i in range(27):
row = [StataMissingValue(keys[i + (j * 27)]) for j in range(5)]
data.append(row)
expected = DataFrame(data, columns=columns)
parsed = read_stata(getattr(self, file), convert_missing=True)
tm.assert_frame_equal(parsed, expected)
Example #6
| Source File: stata.py From predictive-maintenance-using-machine-learning with Apache License 2.0 | 5 votes |
|
def _do_convert_categoricals(self, data, value_label_dict, lbllist,
order_categoricals):
"""
Converts categorical columns to Categorical type.
"""
value_labels = list(compat.iterkeys(value_label_dict))
cat_converted_data = []
for col, label in zip(data, lbllist):
if label in value_labels:
# Explicit call with ordered=True
cat_data = Categorical(data[col], ordered=order_categoricals)
categories = []
for category in cat_data.categories:
if category in value_label_dict[label]:
categories.append(value_label_dict[label][category])
else:
categories.append(category) # Partially labeled
try:
cat_data.categories = categories
except ValueError:
vc = Series(categories).value_counts()
repeats = list(vc.index[vc > 1])
repeats = '\n' + '-' * 80 + '\n'.join(repeats)
raise ValueError('Value labels for column {col} are not '
'unique. The repeated labels are:\n'
'{repeats}'
.format(col=col, repeats=repeats))
# TODO: is the next line needed above in the data(...) method?
cat_data = Series(cat_data, index=data.index)
cat_converted_data.append((col, cat_data))
else:
cat_converted_data.append((col, data[col]))
data = DataFrame.from_dict(OrderedDict(cat_converted_data))
return data
Example #7
| Source File: holiday.py From japandas with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def to_pickle(dates, path):
rules = []
keys = sorted(compat.iterkeys(dates))
for dt in keys:
name = dates[dt]
h = holiday.Holiday(
name, dt.year, month=dt.month, day=dt.day)
rules.append(h)
with open(path, mode='wb') as w:
compat.cPickle.dump(rules, w, protocol=2)
print('pickled {0} data'.format(len(dates)))
Example #8
| Source File: stata.py From Splunking-Crime with GNU Affero General Public License v3.0 | 5 votes |
|
def _do_convert_categoricals(self, data, value_label_dict, lbllist,
order_categoricals):
"""
Converts categorical columns to Categorical type.
"""
value_labels = list(compat.iterkeys(value_label_dict))
cat_converted_data = []
for col, label in zip(data, lbllist):
if label in value_labels:
# Explicit call with ordered=True
cat_data = Categorical(data[col], ordered=order_categoricals)
categories = []
for category in cat_data.categories:
if category in value_label_dict[label]:
categories.append(value_label_dict[label][category])
else:
categories.append(category) # Partially labeled
try:
cat_data.categories = categories
except ValueError:
vc = Series(categories).value_counts()
repeats = list(vc.index[vc > 1])
repeats = '\n' + '-' * 80 + '\n'.join(repeats)
msg = 'Value labels for column {0} are not unique. The ' \
'repeated labels are:\n{1}'.format(col, repeats)
raise ValueError(msg)
# TODO: is the next line needed above in the data(...) method?
cat_data = Series(cat_data, index=data.index)
cat_converted_data.append((col, cat_data))
else:
cat_converted_data.append((col, data[col]))
data = DataFrame.from_items(cat_converted_data)
return data
Example #9
| Source File: test_stata.py From elasticintel with GNU General Public License v3.0 | 5 votes |
|
def test_missing_value_conversion(self, file):
columns = ['int8_', 'int16_', 'int32_', 'float32_', 'float64_']
smv = StataMissingValue(101)
keys = [key for key in iterkeys(smv.MISSING_VALUES)]
keys.sort()
data = []
for i in range(27):
row = [StataMissingValue(keys[i + (j * 27)]) for j in range(5)]
data.append(row)
expected = DataFrame(data, columns=columns)
parsed = read_stata(getattr(self, file), convert_missing=True)
tm.assert_frame_equal(parsed, expected)
Example #10
| Source File: stata.py From elasticintel with GNU General Public License v3.0 | 5 votes |
|
def _do_convert_categoricals(self, data, value_label_dict, lbllist,
order_categoricals):
"""
Converts categorical columns to Categorical type.
"""
value_labels = list(compat.iterkeys(value_label_dict))
cat_converted_data = []
for col, label in zip(data, lbllist):
if label in value_labels:
# Explicit call with ordered=True
cat_data = Categorical(data[col], ordered=order_categoricals)
categories = []
for category in cat_data.categories:
if category in value_label_dict[label]:
categories.append(value_label_dict[label][category])
else:
categories.append(category) # Partially labeled
try:
cat_data.categories = categories
except ValueError:
vc = Series(categories).value_counts()
repeats = list(vc.index[vc > 1])
repeats = '\n' + '-' * 80 + '\n'.join(repeats)
msg = 'Value labels for column {0} are not unique. The ' \
'repeated labels are:\n{1}'.format(col, repeats)
raise ValueError(msg)
# TODO: is the next line needed above in the data(...) method?
cat_data = Series(cat_data, index=data.index)
cat_converted_data.append((col, cat_data))
else:
cat_converted_data.append((col, data[col]))
data = DataFrame.from_items(cat_converted_data)
return data
Example #11
| Source File: test_stata.py From twitter-stock-recommendation with MIT License | 5 votes |
|
def test_missing_value_conversion(self, file):
columns = ['int8_', 'int16_', 'int32_', 'float32_', 'float64_']
smv = StataMissingValue(101)
keys = [key for key in iterkeys(smv.MISSING_VALUES)]
keys.sort()
data = []
for i in range(27):
row = [StataMissingValue(keys[i + (j * 27)]) for j in range(5)]
data.append(row)
expected = DataFrame(data, columns=columns)
parsed = read_stata(getattr(self, file), convert_missing=True)
tm.assert_frame_equal(parsed, expected)
