當前位置: 首頁>>代碼示例>>Python>>正文


Python stata.StataReader類代碼示例

本文整理匯總了Python中pandas.io.stata.StataReader的典型用法代碼示例。如果您正苦於以下問題:Python StataReader類的具體用法?Python StataReader怎麽用?Python StataReader使用的例子?那麽, 這裏精選的類代碼示例或許可以為您提供幫助。


在下文中一共展示了StataReader類的11個代碼示例,這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚,您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: test_read_dta18

    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')
開發者ID:agijsberts,項目名稱:pandas,代碼行數:27,代碼來源:test_stata.py

示例2: read_stata

	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
開發者ID:shafiquejamal,項目名稱:easyframes,代碼行數:8,代碼來源:easyframes.py

示例3: test_data_method

    def test_data_method(self):
        # Minimal testing of legacy data method
        reader_114 = StataReader(self.dta1_114)
        with warnings.catch_warnings(record=True) as w:
            parsed_114_data = reader_114.data()

        reader_114 = StataReader(self.dta1_114)
        parsed_114_read = reader_114.read()
        tm.assert_frame_equal(parsed_114_data, parsed_114_read)
開發者ID:agijsberts,項目名稱:pandas,代碼行數:9,代碼來源:test_stata.py

示例4: test_read_dta1

    def test_read_dta1(self):
        reader = StataReader(self.dta1)
        parsed = reader.data()
        # Pandas uses np.nan as missing value. Thus, all columns will be of type float, regardless of their name.
        expected = DataFrame([(np.nan, np.nan, np.nan, np.nan, np.nan)],
                             columns=['float_miss', 'double_miss', 'byte_miss', 'int_miss', 'long_miss'])

        for i, col in enumerate(parsed.columns):
            np.testing.assert_almost_equal(
                parsed[col],
                expected[expected.columns[i]]
            )
開發者ID:agconti,項目名稱:pandas,代碼行數:12,代碼來源:test_stata.py

示例5: test_read_dta1

    def test_read_dta1(self):
        reader = StataReader(self.dta1)
        parsed = reader.data()
        # Pandas uses np.nan as missing value.
        # Thus, all columns will be of type float, regardless of their name.
        expected = DataFrame([(np.nan, np.nan, np.nan, np.nan, np.nan)],
                             columns=['float_miss', 'double_miss', 'byte_miss',
                                      'int_miss', 'long_miss'])

        # this is an oddity as really the nan should be float64, but
        # the casting doesn't fail so need to match stata here
        expected['float_miss'] = expected['float_miss'].astype(np.float32)
        tm.assert_frame_equal(parsed, expected)
開發者ID:X1mengYu,項目名稱:pandas,代碼行數:13,代碼來源:test_stata.py

示例6: _retrieve_data

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}
開發者ID:jtorcasso,項目名稱:micro-forecasting,代碼行數:50,代碼來源:pystata.py

示例7: test_read_dta1

    def test_read_dta1(self):
        reader_114 = StataReader(self.dta1_114)
        parsed_114 = reader_114.data()
        reader_117 = StataReader(self.dta1_117)
        parsed_117 = reader_117.data()
        # Pandas uses np.nan as missing value.
        # Thus, all columns will be of type float, regardless of their name.
        expected = DataFrame(
            [(np.nan, np.nan, np.nan, np.nan, np.nan)],
            columns=["float_miss", "double_miss", "byte_miss", "int_miss", "long_miss"],
        )

        # this is an oddity as really the nan should be float64, but
        # the casting doesn't fail so need to match stata here
        expected["float_miss"] = expected["float_miss"].astype(np.float32)

        tm.assert_frame_equal(parsed_114, expected)
        tm.assert_frame_equal(parsed_117, expected)
開發者ID:RanaivosonHerimanitra,項目名稱:pandas,代碼行數:18,代碼來源:test_stata.py

示例8: StataReader

from setup_prediction_lag import predict_abc
from load_data import extrap, abcd

from paths import paths

#----------------------------------------------------------------

seed = 1234
aux_draw = 99

#----------------------------------------------------------------


# bring in file with indexes for extrapolation bootstrap
reader = StataReader(paths.psid_bsid)
psid = reader.data(convert_dates=False, convert_categoricals=False)
psid = psid.iloc[:,0:aux_draw] # limit PSID to the number of repetitions you need
nlsy = pd.read_csv(paths.nlsy_bsid)

# set up extrapolation indexes (there are multiple data sets)
extrap_index = pd.concat([psid, nlsy], axis=0, keys=('psid', 'nlsy'), names=('dataset','id'))
extrap_source= ['psid' for j in range(0, psid.shape[0])] + ['nlsy' for k in range(0, nlsy.shape[0])]

#----------------------------------------------------------------

def boot_predict_aux(extrap, adraw):

	# prepare indexes of extrapolation data for bootstrap
	extrap_draw = extrap_index.loc[:, 'draw{}'.format(adraw)]
	extrap_tuples = list(zip(*[extrap_source,extrap_draw]))
開發者ID:jorgelgarcia,項目名稱:abc-treatmenteffects-finalseason,代碼行數:30,代碼來源:bootstrap_prediction.py

示例9: StataReader

if not os.path.exists(paths.data):
	os.mkdir(paths.data)

'''Load and Cache Datasets
   -----------------------

Notes:
- Ensures no overlap in id
- Trims observations with any labor income over $300,000 (U.S., 2014)
'''

#--------------------------------------------------------------------

print "Loading PSID"
reader = StataReader(paths.psid)
psid = reader.read(convert_dates=False, convert_categoricals=False)
psid = psid.dropna(subset=['id']).set_index('id')

# Trimming
inc = psid.filter(regex='^inc_labor[0-9][0-9]')
psid = psid.loc[psid.male == 0]
psid = psid.loc[psid.black == 1]
psid = psid.loc[((inc < inc.quantile(0.90)) | (inc.isnull())).all(axis=1)]

# Interpolating
plong = pd.wide_to_long(psid[inc.columns].reset_index(), 
    ['inc_labor'], i='id', j='age').sort_index()
plong = plong.interpolate(limit=5)
pwide = plong.unstack()
pwide.columns = pwide.columns.droplevel(0)
開發者ID:jorgelgarcia,項目名稱:abc-treatmenteffects-finalseason,代碼行數:30,代碼來源:setup_data.py

示例10: meta_labels

    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
開發者ID:CivicKnowledge,項目名稱:ambry10-bundles,代碼行數:65,代碼來源:old-bundle.py

示例11: StataReader

Desc:   This code selects the IPW variables for specific ABC outcomes.
        We only do this for the pooled sample to increase power. We use
        a linear probiaility model for this. We select the 3 variables
        that minimize the BIC.
"""
import pandas as pd
from pandas.io.stata import StataReader
import numpy as np
import statsmodels.api as sm
from patsy import dmatrices
import itertools
from paths import paths

# import data
reader = StataReader(paths.abccare)
data = reader.read(convert_dates=False, convert_categoricals=False)
data = data.set_index('id')
data = data.sort_index()
data.drop(data.loc[(data.RV==1) & (data.R==0)].index, inplace=True)

# bring in outcomes files, and find the ABC-only/CARE-only ones
outcomes = pd.read_csv(paths.outcomes, index_col='variable')
only_abc = outcomes.loc[outcomes.only_abc == 1].index
only_care = outcomes.loc[outcomes.only_care == 1].index

bank = pd.read_csv(paths.controls)
ipwvars = np.unique(outcomes.loc[~outcomes.ipw_var.isnull(),'ipw_var'].get_values())

# generate the list of all possible models
models = itertools.chain.from_iterable([itertools.combinations(bank.loc[:, 'variable'], 3)])
開發者ID:jorgelgarcia,項目名稱:abc-treatmenteffects-finalseason,代碼行數:30,代碼來源:ipw_selection.py


注:本文中的pandas.io.stata.StataReader類示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台,相關代碼片段篩選自各路編程大神貢獻的開源項目,源碼版權歸原作者所有,傳播和使用請參考對應項目的License;未經允許,請勿轉載。