def ReadVariables():
"""Reads Stata dictionary files for NSFG data.
returns: DataFrame that maps variables names to descriptions
"""
vars1 = thinkstats2.ReadStataDct('2002FemPreg.dct').variables
vars2 = thinkstats2.ReadStataDct('2002FemResp.dct').variables
all_vars = vars1.append(vars2)
all_vars.index = all_vars.name
return all_vars
def read_resp_file(dct_file="2002FemResp.dct", dat_file="2002FemResp.dat.gz"):
# Using similar code as the ReadFemPreg from the textbook. Page 5 of the PDF version.
dct = thinkstats2.ReadStataDct(dct_file)
df = dct.ReadFixedWidth(dat_file, compression='gzip')
# Leaving out CleanFemPreg(df) as this doesn't seem to actually do anything.
# The solution also just has 'pass' which indicates this function is incomplete/does not do anything.
return df
def read_2002_fem_resp(stata_file='2002FemResp.dct',
data_file='2002FemResp.dat.gz'):
fixed_width_object = thinkstats2.ReadStataDct(stata_file)
actual_data = fixed_width_object.ReadFixedWidth(data_file,
compression='gzip',
nrows=None)
return actual_data
def ReadFemResp(dct_file='2002FemResp.dct',
dat_file='2002FemResp.dat.gz',
nrows=None):
dct = thinkstats2.ReadStataDct(dct_file)
df = dct.ReadFixedWidth(dat_file, compression='gzip', nrows=nrows)
CleanFemResp(df)
return df
def readFemaleResponses(dictionaryFile='./data/2002FemResp.dct',
dataFile='./data/2002FemResp.dat.gz',
nrows=None):
dictionary = thinkstats2.ReadStataDct(dictionaryFile)
femResp = dictionary.ReadFixedWidth(dataFile,
compression='gzip',
nrows=nrows)
return femResp
def ReadFemResp(
dct_file='/Users/hedyeherfani/Desktop/ThinkStats2-master/code/2002FemResp.dct',
dat_file='/Users/hedyeherfani/Desktop/ThinkStats2-master/code/2002FemResp.dat.gz',
nrows=None):
dct = thinkstats2.ReadStataDct(dct_file)
df = dct.ReadFixedWidth(dat_file, compression='gzip', nrows=nrows)
nsfg.CleanFemResp(df)
return df
def ReadFemResp(dct_file='2002FemResp.dct',
dat_file='2002FemResp.dat.gz',
nrows=None):
#reads dct_file
dct = thinkstats2.ReadStataDct(dct_file)
#creates a data frame
df = dct.ReadFixedWidth(dat_file, compression='gzip', nrows=nrows)
# returns the data frame
return df
def readfunc():
dct_file = '2002FemResp.dct'
dat_file = '2002FemResp.dat.gz'
dct = thinkstats2.ReadStataDct(dct_file)
dataframe = dct.ReadFixedWidth(dat_file, compression='gzip', nrows=None)
print(dataframe['pregnum'].value_counts().sort_index())
print(len(dataframe))
def ReadMale2002(dct_file='2002Male.dct',
dat_file='2002Male.dat.gz'):
"""Reads male data from NSFG Cycle 6.
returns: DataFrame
"""
dct = thinkstats2.ReadStataDct(dct_file, encoding='iso-8859-1')
male = dct.ReadFixedWidth(dat_file, compression='gzip')
CleanResp(male)
return male
def ReadGss(dirname):
"""Reads GSS files from the given directory.
dirname: string
returns: DataFrame
"""
dct = thinkstats2.ReadStataDct(dirname + '/GSS.dct')
gss = dct.ReadFixedWidth(dirname + '/GSS.dat')
return gss
def ReadFemPreg(dct_file='data/2011_2013_FemPregSetup.dct',
dat_file='data/2011_2013_FemPregData.dat.gz'):
"""Reads the NSFG pregnancy data.
dct_file: string file name
dat_file: string file name
returns: DataFrame
"""
dct = thinkstats2.ReadStataDct(dct_file, encoding='iso-8859-1')
df = dct.ReadFixedWidth(dat_file, compression='gzip')
CleanFemPreg(df)
return df
def ReadResp(dct_file, dat_file, **options):
"""Reads the NSFG respondent data.
dct_file: string file name
dat_file: string file name
returns: DataFrame
"""
dct = thinkstats2.ReadStataDct(dct_file, encoding='iso-8859-1')
df = dct.ReadFixedWidth(dat_file, compression='gzip', **options)
return df
def ReadFemResp2002(dct_file='2002FemResp.dct',
dat_file='2002FemResp.dat.gz'):
"""Reads respondent data from NSFG Cycle 6.
returns: DataFrame
"""
usecols = ['caseid', 'cmbirth', 'cmintvw', 'finalwgt', 'age_r']
dct = thinkstats2.ReadStataDct(dct_file, encoding='iso-8859-1')
resp = dct.ReadFixedWidth(dat_file, compression='gzip', usecols=usecols)
CleanResp(resp)
return resp
def ReadFemResp(dct_file='2002FemResp.dct', dat_file='2002FemResp.dat.gz'):
"""
This function read female pregnant information
:param dct_file: the format of the file documented in 2002FemPreg.dct
:param dat_file: a gzip-compressed data file in plain text, with fixed width columns
:return: a dataframe
"""
dct = thinkstats2.ReadStataDct(dct_file)
df = dct.ReadFixedWidth(dat_file, compression='gzip')
CleanFemResp(df)
return df
def ReadFemResp(dct_file='2002FemResp.dct',
dat_file='2002FemResp.dat.gz',
nrows=None):
''' (str file name, str file name) -> DataFrame
Reads the NSFG respondents data file and returns a DataFrame.
'''
dct = thinkstats2.ReadStataDct(dct_file)
df = dct.ReadFixedWidth(dat_file, compression='gzip', nrows=nrows)
CleanFemResp(df)
return df
def ReadFemPreg(dct_file, dat_file):
"""Reads the NSFG 2006-2010 pregnancy data.
dct_file: string file name
dat_file: string file name
returns: DataFrame
"""
dct = thinkstats2.ReadStataDct(dct_file, encoding='iso-8859-1')
df = dct.ReadFixedWidth(dat_file, compression='gzip')
CleanFemPreg(df)
return df
def read_fem_resp(datfile='2002FemResp.dat.gz', dctfile='2002FemResp.dct'):
"""
Reads the respondent file filename and returns the DataFrame
:type datfile: str
:type dctfile: str
:rtype: pd.DataFrame
"""
dct = thinkstats2.ReadStataDct(dctfile)
df = dct.ReadFixedWidth(datfile, compression='gzip')
clean_fem_resp(df)
return df
def ReadMale2010(dct_file='2006_2010_MaleSetup.dct',
dat_file='2006_2010_Male.dat.gz'):
"""Reads male data from NSFG Cycle 7.
returns: DataFrame
"""
dct = thinkstats2.ReadStataDct(dct_file, encoding='iso-8859-1')
male = dct.ReadFixedWidth(dat_file, compression='gzip')
male['finalwgt'] = male.wgtq1q16
return male
def ReadFemResp(dct_file, dat_file, nrows=None):
"""Reads the NSFG respondent data.
dct_file: string file name
dat_file: string file name
returns: DataFrame
"""
dct = thinkstats2.ReadStataDct(dct_file)
df = dct.ReadFixedWidth(dat_file, compression='gzip', nrows=nrows)
CleanFemResp(df)
return df
def ReadFemPreg(dct_file='2002FemPreg.dct', dat_file='2002FemPreg.dat.gz'):
"""Reads the NSFG pregnancy data.
dct_file: string file name
dat_file: string file name
returns: DataFrame
"""
dct = thinkstats2.ReadStataDct(dct_file)
df = dct.ReadFixedWidth(dat_file, compression='gzip')
CleanFemPreg(df)
return df
def ReadFemPreg(dct_file='2002FemPreg.dct',
dat_file='2002FemPreg.dat.gz',
nrows=None):
"""Reads the NSFG respondent data.
dct_file: string file name
dat_file: string file name
returns: DataFrame
"""
dct = thinkstats2.ReadStataDct(dct_file)
df = dct.ReadFixedWidth(dat_file, compression='gzip', nrows=nrows)
return df
def ReadFemPreg(dct_file='/Users/hedyeherfani/Desktop/ThinkStats2-master/code/2002FemPreg.dct',
dat_file='/Users/hedyeherfani/Desktop/ThinkStats2-master/code/2002FemPreg.dat.gz'):
"""Reads the NSFG pregnancy data.
dct_file: string file name
dat_file: string file name
returns: DataFrame
"""
dct = thinkstats2.ReadStataDct(dct_file)
df = dct.ReadFixedWidth(dat_file, compression='gzip')
CleanFemPreg(df)
return df
def ReadFemResp(file1, file2, nrows=None):
""" This function takes the dct and dat files (NSFG respondent data),
reads them and returns a dataframe of the data.
:param file1: (str) dct filename
:param file2: (str) dat filename
:param nrows: option
:return: df - dataframe of NSFG respondent data
"""
dct = thinkstats2.ReadStataDct(file1)
df = dct.ReadFixedWidth(file2, compression="gzip", nrows=nrows)
return df
def readNplotNUMKDHH(dctfile='2002FemResp.dct',
datfile='2002FemResp.dat.gz',
compression='gzip'):
""" read data to fram and plot NUMKDHH PMF"""
dct = thinkstats2.ReadStataDct(dctfile)
df = dct.ReadFixedWidth(datfile, compression=compression)
pmf = thinkstats2.Pmf(df.numkdhh)
thinkplot.Pmf(pmf, label='numkdhh')
pmf2 = BiasedPmf(pmf)
thinkplot.Pmf(pmf2, label='biased')
thinkplot.show()
def ReadFemResp(dct_file='2002FemResp.dct',
dat_file='2002FemResp.dat.gz',
nrows=None):
""" Read the FemRecp data file.
dct_file: string file name
dat_file: string file name
returns: DataFrame
"""
dct = thinkstats2.ReadStataDct(dct_file)
df = dct.ReadFixedWidth(dat_file, compression='gzip', nrows=nrows)
CleanFemResp(df)
return df
def ReadFemResp(dct_file='/Users/hedyeherfani/Desktop/ThinkStats2-master/code/2002FemResp.dct',
dat_file='/Users/hedyeherfani/Desktop/ThinkStats2-master/code/2002FemResp.dat.gz',
nrows=None):
"""Reads the NSFG respondent data.
dct_file: string file name
dat_file: string file name
returns: DataFrame
"""
dct = thinkstats2.ReadStataDct(dct_file)
df = dct.ReadFixedWidth(dat_file, compression='gzip', nrows=nrows)
CleanFemResp(df)
return df
def ReadFemResp(dct_file='2002FemResp.dct',
dat_file='2002FemResp.dat.gz',
**options):
"""Reads the NSFG respondent data.
dct_file: string file name
dat_file: string file name
returns: DataFrame
"""
dct = thinkstats2.ReadStataDct(dct_file)
df = dct.ReadFixedWidth(dat_file, compression='gzip', **options)
CleanData(df)
return df
def ReadFemResp(dct_file='2002FemResp.dct', dat_file='2002FemResp.dat.gz'):
dct = thinkstats2.ReadStataDct(dct_file)
df = dct.ReadFixedWidth(dat_file, compression='gzip')
return df
def testReadStataDct(self):
dct = thinkstats2.ReadStataDct('2002FemPreg.dct')
self.assertEqual(len(dct.variables), 243)
self.assertEqual(len(dct.colspecs), 243)
self.assertEqual(len(dct.names), 243)
self.assertEqual(dct.colspecs[-1][1], -1)
def readResp(dct_file='2002FemResp.dct', dat_file='2002FemResp.dat.gz'):
resp_dict = thinkstats2.ReadStataDct(dct_file)
resp_df = resp_dict.ReadFixedWidth(dat_file, compression='gzip')
return resp_df
