Python StataReader.read方法代码示例

# 需要导入模块: from pandas.io.stata import StataReader [as 别名]
# 或者: from pandas.io.stata.StataReader import read [as 别名]
    def test_read_dta1(self):
        reader_114 = StataReader(self.dta1_114)
        parsed_114 = reader_114.read()
        reader_117 = StataReader(self.dta1_117)
        parsed_117 = reader_117.read()
        # 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)

# 需要导入模块: from pandas.io.stata import StataReader [as 别名]
# 或者: from pandas.io.stata.StataReader import read [as 别名]
    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)

# 需要导入模块: from pandas.io.stata import StataReader [as 别名]
# 或者: from pandas.io.stata.StataReader import read [as 别名]
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)
pwide.columns = ['{}{}'.format('inc_labor', a) for a in pwide.columns]

# 需要导入模块: from pandas.io.stata import StataReader [as 别名]
# 或者: from pandas.io.stata.StataReader import read [as 别名]
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)])
models = list(models)