def __enter__(self):
"""initialization for with statement"""
try:
spss.StartDataStep()
except:
spss.Submit("EXECUTE")
spss.StartDataStep()
return self
def __init__(self):
try:
spss.StartDataStep()
except:
spss.Submit("EXECUTE.")
spss.StartDataStep()
self.ds = spss.Dataset()
self.varlist = self.ds.varlist
self.mrsets = {}
# the api always returns the set name in upper case
for name, theset in self.ds.multiResponseSet.data.items():
self.mrsets[name.upper()] = theset
def __init__(self):
##self.vardict = spssaux.VariableDict()
spss.StartDataStep()
self.ds = spss.Dataset()
self.varlist = self.ds.varlist
self.mrsets = {}
# the api always returns the set name in upper case
for name, theset in self.ds.multiResponseSet.data.iteritems():
self.mrsets[name.upper()] = theset
def getvalues(num, denom, id, dsname):
"""return vectors of num. denom, and id values from constants in syntax or variable values"""
if isname(num[0]) or isname(denom[0]) or isname(id):
spss.StartDataStep()
ds = spss.Dataset(dsname)
else:
ds = None
id = [id]
try:
vallist = []
if ds:
vl = [v.name.lower()
for v in ds.varlist] # variables in the dataset
for v in num, denom, id:
try:
vallist.append([float(val) for val in v])
except: #variable name argument or None
if v[0] is None: # can only happen with id variable
vallist.append([None]) # null label in case no id variable
else:
if len(v) > 1:
raise ValueError(
"Error: Only one variable may be named on each of NUM, DENOM, and ID, and a variable may not be combined with a value: "
+ " ".join(v))
try:
vindex = vl.index(v[0].lower())
vallist.append([val[vindex] for val in ds.cases])
except:
raise ValueError(
"Error: An undefined variable name was specified in NUM, DENOM, or ID: "
+ " ".join(v))
finally:
spss.EndDataStep()
# check and fix value list lengths
maxlen = max([len(vl) for vl in vallist])
for i in range(len(vallist)):
if len(vallist[i]) == 1:
vallist[i] = maxlen * vallist[i]
if len(vallist[i]) != maxlen:
raise ValueError(
"Error: NUM, DENOM and optional ID do not all have the same number of items"
)
return vallist
def metadata(datain, path):
f = open(path + ".met", "w") # open the metadata file
f.write("standard;\n")
f.write("variables\n") # write the variable metadata
if not re.match(r"\.sav$", datain, flags=re.IGNORECASE): # get datain
datain += ".sav" # add .sav
spss.Submit("get file='{0}'.".format(datain))
spss.StartDataStep()
ds = spss.Dataset()
type = -1
frames = 0
for var in ds.varlist:
line = " name={0}".format(var.name) # name
if var.label:
line += ' label="{0}"'.format(var.label.replace('"', '"')) # label
if var.type != type:
if var.type == 0: # type and width
line += " type=float width=8"
else:
line += " type=char width={0}".format(var.type)
type = var.type
if var.valueLabels: # codeframe
line += ' codeframe="{0}"'.format(var.name)
frames = 1
line += ";\n"
f.write(line)
if frames: # write the codeframe metadata
f.write("codeframes\n")
for var in ds.varlist:
if var.valueLabels:
f.write(" name={0}\n".format(var.name))
for val, lab in var.valueLabels.data.iteritems():
f.write(' {0} = "{1}"\n'.format(val, lab))
f.write(" ;\n")
ds.close()
spss.EndDataStep()
f.close()
return 0
def dopropor(num=None,
denom=None,
id=None,
dsname="*",
alpha=.05,
adjust='bonferroni'):
if num is None or denom is None:
raise ValueError("Error: NUM and DENOM keywords are required")
if spss.PyInvokeSpss.IsUTF8mode():
unistr = str
else:
unistr = str
currentds = spss.ActiveDataset()
if currentds == "*":
currentds = "S" + str(random.uniform(0, 1))
spss.Submit("DATASET NAME %s" % currentds)
dsnamed = True
else:
dsnamed = False
numvec, denomvec, idvec = getvalues(num, denom, id, dsname)
# clean data, discard missing
droplist = []
for i in range(len(numvec)):
droplist.append(numvec[i] is not None
and denomvec[i] is not None) #missing data
if (droplist[i] and (numvec[i] > denomvec[i] or denomvec[i] <= 0)):
raise ValueError(
"Error: NUM value greater than DENOM value or zero denominator: %s, %s"
% (numvec[i], denomvec[i]))
for lis in numvec, denomvec, idvec:
lis = [x for f, x in zip(droplist, lis) if f] #prune missing values
if len(numvec) == 0:
raise ValueError("Error: No valid proportions were found to analyze")
alphalow = alpha / 2
alphahigh = 1 - alphalow
dotest = len(numvec) > 1
try:
spss.StartDataStep() #TODO: pending transformations
except:
spss.Submit("EXECUTE")
spss.StartDataStep()
# calculate ci's via SPSS IDFs
ds = spss.Dataset(name=None)
spss.SetActive(ds)
ds.varlist.append("p", 0)
ds.varlist.append("num", 0)
ds.varlist.append("denom", 0)
p0 = numvec[0] / denomvec[0]
sdvec = []
for i in range(len(numvec)):
p1 = numvec[i] / denomvec[i]
sdvec.append(
sqrt(p0 * (1 - p0) / denomvec[0] + p1 * (1 - p1) / denomvec[i]))
#p = (numvec[i] + numvec[0]) / (denomvec[i] + denomvec[0])
#z = (p1 - p0)/sqrt(p * (1 - p)*(1/denomvec[0] + 1/denomvec[i]))
ds.cases.append([p1, numvec[i], denomvec[i]])
spss.EndDataStep()
cmd =r"""COMPUTE PLOWBI = IDF.BETA(%(alphalow)s, num + .5, denom-num + .5).
COMPUTE PHIGHBI = IDF.BETA(%(alphahigh)s, num + .5, denom - num + .5).
DO IF num > 0.
COMPUTE PLOWPOIS = (IDF.CHISQ(%(alphalow)s, 2*num)/2)/denom.
ELSE.
COMPUTE PLOWPOIS = 0.
END IF.
COMPUTE PHIGHPOIS = (IDF.CHISQ(%(alphahigh)s, 2*(num+1))/2) / denom.
COMPUTE ZTAIL = IDF.NORMAL(%(alphahigh)s, 0,1).
EXECUTE."""\
% {"alphalow": alphalow, "alphahigh": alphahigh}
spss.Submit(cmd)
plowbi = []
phighbi = []
plowpois = []
phighpois = []
spss.StartDataStep()
ds = spss.Dataset(name="*")
for case in ds.cases:
i = 3
for v in plowbi, phighbi, plowpois, phighpois:
v.append(case[i])
i += 1
zalpha2 = case[-1]
try:
closeafter = False
spss.SetActive(spss.Dataset(name=currentds))
except:
closeafter = True
ds.close()
spss.EndDataStep()
from spss import CellText
spss.StartProcedure("Proportions")
table = spss.BasePivotTable("Proportion Confidence Intervals",
"Proportions")
titlefootnote = "Alpha = %.3f" % alpha
if 0. in numvec:
titlefootnote += " (One-sided %.3f when p = 0)" % (alpha / 2.)
table.TitleFootnotes(titlefootnote)
rowdim = table.Append(spss.Dimension.Place.row, "Proportions")
coldim = table.Append(spss.Dimension.Place.column, "Statistics")
cols = [
"p", "Binomial\nLower CI", "Binomial\nUpper CI", "Poisson\nLower CI",
"Poisson\nUpper CI", "Difference\nfrom p0",
"Difference from p0\nLower CI", "Difference from p0\nUpper CI"
]
table.SetCategories(coldim, [CellText.String(v) for v in cols])
idvec = [
not v is None and unistr(v) or unistr(i + 1)
for i, v in enumerate(idvec)
]
table.SetCategories(rowdim, [CellText.String(v) for v in idvec])
for i in range(len(numvec)):
p1 = numvec[i] / denomvec[i]
if i > 0:
zdifflow = p1 - p0 - sdvec[i] * zalpha2
zdiffhigh = p1 - p0 + sdvec[i] * zalpha2
else:
zdifflow = zdiffhigh = 0.
table.SetCellsByRow(CellText.String(idvec[i]), [
CellText.Number(v)
for v in (numvec[i] / denomvec[i], plowbi[i], phighbi[i],
plowpois[i], phighpois[i], p1 - p0, zdifflow, zdiffhigh)
])
if i == 0:
table[(CellText.String(idvec[0]),
CellText.String(cols[-3]))] = CellText.String("-")
table[(CellText.String(idvec[0]),
CellText.String(cols[-2]))] = CellText.String("-")
table[(CellText.String(idvec[0]),
CellText.String(cols[-1]))] = CellText.String("-")
spss.EndProcedure()
if closeafter:
spss.Submit(r"""NEW FILE.
DATASET NAME %s.""" % "S" + str(random.uniform(0, 1)))
import spss, spssaux
print(spss.__version__)
spss.Submit(
"get file='C:\\Users\\sam\\Desktop\\Data202201119\\20201119_1047.sav'.")
spss.StartDataStep()
myDataset = spss.Dataset()
myVarlist = myDataset.varlist
print(len(myVarlist))
print(myVarlist)
for i in range(len(myVarlist)):
print(str(i) + "--->" + spssaux.GetVariableNamesList()[i])
def genVarsCategoryList(varnames, specialvalues, macroname, missing, order,
weightvar, specialsorder, valuelabelsdict, missingvaluesdict,
customattr, attrname):
"""Generate sorted list(s) of values with possible insertion of extra values
and return list of SPSS macros to be created.
varnames is a sequence of variable names to process.
specialvalues is a sequence of values that should be inserted before the first zero count or at the end if no zeros or None.
If a special value already occurs in a varname, it will be moved.
macroname is a list of macronames of the same length as varnames to generate or None.
missing is 'include' or 'exclude' to determine whether user missing values are included or excluded.
order is 'a' or 'd' to specify the sort direction.
weightvar can be specified as a variable name to be used as a weight in determing the counts to sort by.
It must not occur in varnames.
specialsorder is 'before' or 'after' and indicates the location of the specials section
If other, values that have value labels are appended to the list of values found
in the data.
customattr indicates whether a custom attribute with the order should be generated
attrname is the name of the custom attribute
This function is mainly useful as a helper function for Ctables in building CATEGORIES subcommands.
It may be useful to combine it with OTHERNM and/or MISSING in the category list.
"""
if weightvar:
if weightvar in varnames:
raise ValueError(_("""The weight variable cannot be included as a variable."""))
varnamesAndWeight = varnames + [weightvar]
else:
varnamesAndWeight = varnames
curs = spssdata.Spssdata(indexes=varnamesAndWeight, names=False, omitmissing=missing =='exclude')
nvar = len(varnames)
vvalues=[{} for i in range(nvar)] # for accumulating counts for all variable values
for cn, case in enumerate(curs):
casecpy = copy.copy(case)
if weightvar:
w = casecpy[nvar]
if w is None:
w = 0.0
else:
w = 1.0
for i in range(nvar):
if not casecpy[i] is None: # omit sysmis values and optionally user missing values
curval = casecpy[i]
vvalues[i][curval] = vvalues[i].get(curval,0.) + w # count occurrences, possibly weighted
curs.CClose()
valuelist = []
macrosgenerated = []
customattrlist = []
for i, vname in enumerate(varnames):
# if labeled values were supplied but did not occur in the data,
# add them with a count of zero
if not valuelabelsdict is None:
labeledbutnotfound = valuelabelsdict[vname] - set(vvalues[i].keys())
for val in labeledbutnotfound:
vvalues[i][val] = 0.
if not specialvalues is None: # remove special values from count list
for v in specialvalues:
if v in vvalues[i]:
del(vvalues[i][v])
valuelist.append(sorted([(value, key) for (key, value) in vvalues[i].iteritems()], reverse = order == 'd'))
if not specialvalues is None:
if specialsorder == "after":
valuelist[i].extend([(None, v) for v in specialvalues])
else:
valuelist[i] = [(None, v) for v in specialvalues] + valuelist[i]
if isinstance(valuelist[i][0][1], basestring):
qchar = '"'
else:
qchar = ''
if macroname is not None:
if not macroname[i].startswith("!"):
macroname[i] = "!" + macroname[i]
macrosgenerated.append([macroname[i],
" ".join([qchar + strconv(k).rstrip() + qchar for (value, k) in valuelist[i]])])
if customattr:
customattrlist.append([vname, " ".join([qchar + strconv(k).rstrip() + qchar for (value, k) in valuelist[i]])])
if customattr:
try: # cannot start datastep if there are pending transformations
spss.StartDataStep()
except:
spss.Submit("EXECUTE.")
spss.StartDataStep()
ds = spss.Dataset()
for spec in customattrlist:
ds.varlist[spec[0]].attributes[attrname] = spec[1]
spss.EndDataStep()
return macrosgenerated, customattrlist
