本文整理汇总了Python中pandas.io.stata.StataReader.variable_labels方法的典型用法代码示例。如果您正苦于以下问题：Python StataReader.variable_labels方法的具体用法？Python StataReader.variable_labels怎么用？Python StataReader.variable_labels使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类pandas.io.stata.StataReader的用法示例。
在下文中一共展示了StataReader.variable_labels方法的4个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: test_read_dta18
# 需要导入模块: from pandas.io.stata import StataReader [as 别名]
# 或者: from pandas.io.stata.StataReader import variable_labels [as 别名]
def test_read_dta18(self):
parsed_118 = self.read_dta(self.dta22_118)
parsed_118["Bytes"] = parsed_118["Bytes"].astype('O')
expected = DataFrame.from_records(
[['Cat', 'Bogota', u'Bogotá', 1, 1.0, u'option b Ünicode', 1.0],
['Dog', 'Boston', u'Uzunköprü', np.nan, np.nan, np.nan, np.nan],
['Plane', 'Rome', u'Tromsø', 0, 0.0, 'option a', 0.0],
['Potato', 'Tokyo', u'Elâzığ', -4, 4.0, 4, 4],
['', '', '', 0, 0.3332999, 'option a', 1/3.]
],
columns=['Things', 'Cities', 'Unicode_Cities_Strl', 'Ints', 'Floats', 'Bytes', 'Longs'])
expected["Floats"] = expected["Floats"].astype(np.float32)
for col in parsed_118.columns:
tm.assert_almost_equal(parsed_118[col], expected[col])
rdr = StataReader(self.dta22_118)
vl = rdr.variable_labels()
vl_expected = {u'Unicode_Cities_Strl': u'Here are some strls with Ünicode chars',
u'Longs': u'long data',
u'Things': u'Here are some things',
u'Bytes': u'byte data',
u'Ints': u'int data',
u'Cities': u'Here are some cities',
u'Floats': u'float data'}
tm.assert_dict_equal(vl, vl_expected)
self.assertEqual(rdr.data_label, u'This is a Ünicode data label')示例2: read_stata
# 需要导入模块: from pandas.io.stata import StataReader [as 别名]
# 或者: from pandas.io.stata.StataReader import variable_labels [as 别名]
def read_stata(self, *args, **kwargs):
reader = StataReader(*args, **kwargs)
self.df = reader.data()
self.variable_labels = reader.variable_labels()
self._initialize_variable_labels()
self.value_labels = reader.value_labels()
# self.data_label = reader.data_label()
return self.df示例3: _retrieve_data
# 需要导入模块: from pandas.io.stata import StataReader [as 别名]
# 或者: from pandas.io.stata.StataReader import variable_labels [as 别名]
def _retrieve_data(dtafile):
'''retrieve data dictionary from STATA .dta file'''
datafile = os.path.basename(dtafile).split('.')
if len(datafile) != 2:
raise ValueError('dtafile must look like "file.dta"')
if datafile[1] != 'dta':
raise ValueError('dtafile must have ".dta" extension')
base = datafile[0]
hdf = os.path.join('.data_cache', '{}.h5'.format(base))
lPickle = os.path.join('.data_cache', '{}_labels.pickle'.format(base))
vPickle = os.path.join('.data_cache', '{}_vlabels.pickle'.format(base))
dTime = os.path.join('.data_cache', '{}_dtime.pickle'.format(base))
if all([os.path.isfile(d) for d in [hdf, lPickle, vPickle, dTime]]):
if os.path.getmtime(dtafile) == cPickle.load(open(dTime, 'rb')):
from pandas import read_hdf
data = read_hdf(hdf, 'data')
labels = cPickle.load(open(lPickle, 'rb'))
vlabels = cPickle.load(open(vPickle, 'rb'))
elif not os.path.isdir('.data_cache'):
os.makedirs('.data_cache')
try:
data
except:
from pandas.io.stata import StataReader
from pandas import HDFStore
print "Data is changed or no cached data found"
print "Creating data objects from {}".format(dtafile)
reader = StataReader(dtafile)
data = reader.data(convert_dates=False,convert_categoricals=False)
labels = reader.variable_labels()
vlabels = reader.value_labels()
store = HDFStore(hdf)
store['data'] = data
cPickle.dump(labels, open(lPickle, 'wb'))
cPickle.dump(vlabels, open(vPickle, 'wb'))
cPickle.dump(os.path.getmtime(dtafile), open(dTime, 'wb'))
store.close()
return {'data':data, 'labels':labels, 'vlabels':vlabels}示例4: meta_labels
# 需要导入模块: from pandas.io.stata import StataReader [as 别名]
# 或者: from pandas.io.stata.StataReader import variable_labels [as 别名]
def meta_labels(self):
"""Read the labels for the variables and code values for the variables, using the
Stata reader. """
import re
import os
import struct
import pandas as pd
from pandas.io.stata import StataReader
var_labels = None
val_labels = None
if not os.path.exists(self.filesystem.path('meta','variable_labels.yaml')):
for name, fn in self.sources():
if name.endswith('l'):
self.log("Getting labels for {} from {} (This is really slow)".format(name, fn))
reader = StataReader(fn)
df = reader.data() # Can't get labels before reading data
var_labels = reader.variable_labels()
val_labels = reader.value_labels()
break
self.filesystem.write_yaml(var_labels, 'meta','variable_labels.yaml')
self.filesystem.write_yaml(val_labels, 'meta','value_labels.yaml')
else:
self.log("Skipping extracts; already exist")
# The value codes include both the value codes and the imputation codes. The imputation codes
# are extracted as positive integers, when they really should be negative.
table_values = {}
imputation_values = {}
if not val_labels:
val_labels = self.filesystem.read_yaml('meta','value_labels.yaml')
for k,v in val_labels.items():
table_values[k] = {}
imputation_values[k] = { -10: 'NO IMPUTATION' }
for code, code_val in v.items():
signed_code = struct.unpack('i',struct.pack('I',int(code)))[0] # Convert the unsigned to signed
if signed_code < 0:
imputation_values[k][signed_code] = code_val
else:
table_values[k][code] = code_val
self.filesystem.write_yaml(table_values, 'meta','table_codes.yaml')
self.filesystem.write_yaml(imputation_values, 'meta','imputation_codes.yaml')
self.log("{} table variables".format(len(table_values)))
self.log("{} imputation variables".format(len(imputation_values)))
return True