def testIndividualStats(self):
# tests calculation of statistics one at a time, to make sure statistic calculations are not
# dependent on each other
tests = [{'stat': QgsStringStatisticalSummary.Count, 'expected': 9},
{'stat': QgsStringStatisticalSummary.CountDistinct, 'expected': 6},
{'stat': QgsStringStatisticalSummary.CountMissing, 'expected': 2},
{'stat': QgsStringStatisticalSummary.Min, 'expected': 'aaaa'},
{'stat': QgsStringStatisticalSummary.Max, 'expected': 'eeee'},
{'stat': QgsStringStatisticalSummary.MinimumLength, 'expected': 0},
{'stat': QgsStringStatisticalSummary.MaximumLength, 'expected': 8},
]
s = QgsStringStatisticalSummary()
for t in tests:
# test constructor
s2 = QgsStringStatisticalSummary(t['stat'])
self.assertEqual(s2.statistics(), t['stat'])
s.setStatistics(t['stat'])
self.assertEqual(s.statistics(), t['stat'])
s.calculate(['cc', 'aaaa', 'bbbbbbbb', 'aaaa', 'eeee', '', 'eeee', '', 'dddd'])
self.assertEqual(s.statistic(t['stat']), t['expected'])
# display name
self.assertTrue(len(QgsStringStatisticalSummary.displayName(t['stat'])) > 0)
def testVariantStats(self):
s = QgsStringStatisticalSummary()
self.assertEqual(s.statistics(), QgsStringStatisticalSummary.All)
s.calculateFromVariants(['cc', 5, 'bbbb', 'aaaa', 'eeee', 6, 9, '9', ''])
self.assertEqual(s.count(), 6)
self.assertEqual(set(s.distinctValues()), set(['cc', 'aaaa', 'bbbb', 'eeee', '', '9']))
self.assertEqual(s.countMissing(), 1)
self.assertEqual(s.min(), '9')
self.assertEqual(s.max(), 'eeee')
def testVariantStats(self):
s = QgsStringStatisticalSummary()
self.assertEqual(s.statistics(), QgsStringStatisticalSummary.All)
s.calculateFromVariants(["cc", 5, "bbbb", "aaaa", "eeee", 6, 9, "9", ""])
self.assertEqual(s.count(), 6)
self.assertEqual(set(s.distinctValues()), set(["cc", "aaaa", "bbbb", "eeee", "", "9"]))
self.assertEqual(s.countMissing(), 1)
self.assertEqual(s.min(), "9")
self.assertEqual(s.max(), "eeee")
def testStats(self):
# we test twice, once with values added as a list and once using values
# added one-at-a-time
s = QgsStringStatisticalSummary()
self.assertEqual(s.statistics(), QgsStringStatisticalSummary.All)
strings = ['cc', 'aaaa', 'bbbbbbbb', 'aaaa', 'eeee', '', 'eeee', '', 'dddd']
s.calculate(strings)
s2 = QgsStringStatisticalSummary()
for string in strings:
s2.addString(string)
s2.finalize()
self.assertEqual(s.count(), 9)
self.assertEqual(s2.count(), 9)
self.assertEqual(s.countDistinct(), 6)
self.assertEqual(s2.countDistinct(), 6)
self.assertEqual(set(s.distinctValues()), set(['cc', 'aaaa', 'bbbbbbbb', 'eeee', 'dddd', '']))
self.assertEqual(s2.distinctValues(), s.distinctValues())
self.assertEqual(s.countMissing(), 2)
self.assertEqual(s2.countMissing(), 2)
self.assertEqual(s.min(), 'aaaa')
self.assertEqual(s2.min(), 'aaaa')
self.assertEqual(s.max(), 'eeee')
self.assertEqual(s2.max(), 'eeee')
self.assertEqual(s.minLength(), 0)
self.assertEqual(s2.minLength(), 0)
self.assertEqual(s.maxLength(), 8)
self.assertEqual(s2.maxLength(), 8)
self.assertEqual(s.meanLength(), 3.33333333333333333333333)
self.assertEqual(s2.meanLength(), 3.33333333333333333333333)
#extra check for minLength without empty strings
s.calculate(['1111111', '111', '11111'])
self.assertEqual(s.minLength(), 3)
def calcStringStats(self, features, feedback, field, count):
total = 100.0 / count if count else 1
stat = QgsStringStatisticalSummary()
for current, ft in enumerate(features):
if feedback.isCanceled():
break
stat.addValue(ft[field.name()])
feedback.setProgress(int(current * total))
stat.finalize()
results = {self.COUNT: stat.count(),
self.UNIQUE: stat.countDistinct(),
self.EMPTY: stat.countMissing(),
self.FILLED: stat.count() - stat.countMissing(),
self.MIN: stat.min(),
self.MAX: stat.max(),
self.MIN_LENGTH: stat.minLength(),
self.MAX_LENGTH: stat.maxLength(),
self.MEAN_LENGTH: stat.meanLength()}
data = []
data.append(self.tr('Count: {}').format(count))
data.append(self.tr('Unique values: {}').format(stat.countDistinct()))
data.append(self.tr('NULL (missing) values: {}').format(stat.countMissing()))
data.append(self.tr('Minimum value: {}').format(stat.min()))
data.append(self.tr('Maximum value: {}').format(stat.max()))
data.append(self.tr('Minimum length: {}').format(stat.minLength()))
data.append(self.tr('Maximum length: {}').format(stat.maxLength()))
data.append(self.tr('Mean length: {}').format(stat.meanLength()))
return data, results
def calcStringStats(self, values, sink, feedback):
stat = QgsStringStatisticalSummary()
total = 50.0 / len(values) if values else 0
current = 0
for cat, v in values.items():
if feedback.isCanceled():
break
feedback.setProgress(int(current * total) + 50)
stat.calculate(v)
f = QgsFeature()
f.setAttributes(list(cat) + [stat.count(),
stat.countDistinct(),
stat.countMissing(),
stat.count() - stat.countMissing(),
stat.min(),
stat.max(),
stat.minLength(),
stat.maxLength(),
stat.meanLength()
])
sink.addFeature(f, QgsFeatureSink.FastInsert)
current += 1
def calcStringStats(self, features, progress, field):
count = len(features)
total = 100.0 / float(count)
stat = QgsStringStatisticalSummary()
for current, ft in enumerate(features):
stat.addValue(ft[field.name()])
progress.setPercentage(int(current * total))
stat.finalize()
self.setOutputValue(self.COUNT, stat.count())
self.setOutputValue(self.UNIQUE, stat.countDistinct())
self.setOutputValue(self.EMPTY, stat.countMissing())
self.setOutputValue(self.FILLED, stat.count() - stat.countMissing())
self.setOutputValue(self.MIN, stat.min())
self.setOutputValue(self.MAX, stat.max())
self.setOutputValue(self.MIN_LENGTH, stat.minLength())
self.setOutputValue(self.MAX_LENGTH, stat.maxLength())
self.setOutputValue(self.MEAN_LENGTH, stat.meanLength())
data = []
data.append(self.tr('Count: {}').format(count))
data.append(self.tr('Unique values: {}').format(stat.countDistinct()))
data.append(self.tr('NULL (missing) values: {}').format(stat.countMissing()))
data.append(self.tr('Minimum value: {}').format(stat.min()))
data.append(self.tr('Maximum value: {}').format(stat.max()))
data.append(self.tr('Minimum length: {}').format(stat.minLength()))
data.append(self.tr('Maximum length: {}').format(stat.maxLength()))
data.append(self.tr('Mean length: {}').format(stat.meanLength()))
return data
def testStats(self):
s = QgsStringStatisticalSummary()
self.assertEqual(s.statistics(), QgsStringStatisticalSummary.All)
s.calculate(['cc', 'aaaa', 'bbbbbbbb', 'aaaa', 'eeee', '', 'eeee', '', 'dddd'])
self.assertEqual(s.count(), 9)
self.assertEqual(s.countDistinct(), 6)
self.assertEqual(set(s.distinctValues()), set(['cc', 'aaaa', 'bbbbbbbb', 'eeee', 'dddd', '']))
self.assertEqual(s.countMissing(), 2)
self.assertEqual(s.min(), 'aaaa')
self.assertEqual(s.max(), 'eeee')
self.assertEqual(s.minLength(), 0)
self.assertEqual(s.maxLength(), 8)
#extra check for minLength without empty strings
s.calculate(['1111111', '111', '11111'])
self.assertEqual(s.minLength(), 3)
def calcStringStats(self, features, feedback, field):
count = len(features)
total = 100.0 / float(count)
stat = QgsStringStatisticalSummary()
for current, ft in enumerate(features):
stat.addValue(ft[field.name()])
feedback.setProgress(int(current * total))
stat.finalize()
self.setOutputValue(self.COUNT, stat.count())
self.setOutputValue(self.UNIQUE, stat.countDistinct())
self.setOutputValue(self.EMPTY, stat.countMissing())
self.setOutputValue(self.FILLED, stat.count() - stat.countMissing())
self.setOutputValue(self.MIN, stat.min())
self.setOutputValue(self.MAX, stat.max())
self.setOutputValue(self.MIN_LENGTH, stat.minLength())
self.setOutputValue(self.MAX_LENGTH, stat.maxLength())
self.setOutputValue(self.MEAN_LENGTH, stat.meanLength())
data = []
data.append(self.tr('Count: {}').format(count))
data.append(self.tr('Unique values: {}').format(stat.countDistinct()))
data.append(
self.tr('NULL (missing) values: {}').format(stat.countMissing()))
data.append(self.tr('Minimum value: {}').format(stat.min()))
data.append(self.tr('Maximum value: {}').format(stat.max()))
data.append(self.tr('Minimum length: {}').format(stat.minLength()))
data.append(self.tr('Maximum length: {}').format(stat.maxLength()))
data.append(self.tr('Mean length: {}').format(stat.meanLength()))
return data
def testIndividualStats(self):
# tests calculation of statistics one at a time, to make sure statistic calculations are not
# dependent on each other
tests = [
{"stat": QgsStringStatisticalSummary.Count, "expected": 9},
{"stat": QgsStringStatisticalSummary.CountDistinct, "expected": 6},
{"stat": QgsStringStatisticalSummary.CountMissing, "expected": 2},
{"stat": QgsStringStatisticalSummary.Min, "expected": "aaaa"},
{"stat": QgsStringStatisticalSummary.Max, "expected": "eeee"},
{"stat": QgsStringStatisticalSummary.MinimumLength, "expected": 0},
{"stat": QgsStringStatisticalSummary.MaximumLength, "expected": 8},
{"stat": QgsStringStatisticalSummary.MeanLength, "expected": 3.3333333333333335},
]
s = QgsStringStatisticalSummary()
s3 = QgsStringStatisticalSummary()
for t in tests:
# test constructor
s2 = QgsStringStatisticalSummary(t["stat"])
self.assertEqual(s2.statistics(), t["stat"])
s.setStatistics(t["stat"])
s3.setStatistics(t["stat"])
self.assertEqual(s.statistics(), t["stat"])
strings = ["cc", "aaaa", "bbbbbbbb", "aaaa", "eeee", "", "eeee", "", "dddd"]
s.calculate(strings)
s3.reset()
for string in strings:
s3.addString(string)
s3.finalize()
self.assertEqual(s.statistic(t["stat"]), t["expected"])
self.assertEqual(s3.statistic(t["stat"]), t["expected"])
# display name
self.assertTrue(len(QgsStringStatisticalSummary.displayName(t["stat"])) > 0)
def calcStringStats(self, features, feedback, field, count):
total = 100.0 / count if count else 1
stat = QgsStringStatisticalSummary()
for current, ft in enumerate(features):
if feedback.isCanceled():
break
stat.addValue(ft[field.name()])
feedback.setProgress(int(current * total))
stat.finalize()
results = {self.COUNT: stat.count(),
self.UNIQUE: stat.countDistinct(),
self.EMPTY: stat.countMissing(),
self.FILLED: stat.count() - stat.countMissing(),
self.MIN: stat.min(),
self.MAX: stat.max(),
self.MIN_LENGTH: stat.minLength(),
self.MAX_LENGTH: stat.maxLength(),
self.MEAN_LENGTH: stat.meanLength()}
data = []
data.append(self.tr('Count: {}').format(count))
data.append(self.tr('Unique values: {}').format(stat.countDistinct()))
data.append(self.tr('NULL (missing) values: {}').format(stat.countMissing()))
data.append(self.tr('Minimum value: {}').format(stat.min()))
data.append(self.tr('Maximum value: {}').format(stat.max()))
data.append(self.tr('Minimum length: {}').format(stat.minLength()))
data.append(self.tr('Maximum length: {}').format(stat.maxLength()))
data.append(self.tr('Mean length: {}').format(stat.meanLength()))
return data, results
def processAlgorithm(self, parameters, context, feedback):
source = self.parameterAsSource(parameters, self.INPUT, context)
if source is None:
raise QgsProcessingException(
self.invalidSourceError(parameters, self.INPUT))
join_source = self.parameterAsSource(parameters, self.JOIN, context)
if join_source is None:
raise QgsProcessingException(
self.invalidSourceError(parameters, self.JOIN))
join_fields = self.parameterAsFields(parameters, self.JOIN_FIELDS,
context)
discard_nomatch = self.parameterAsBool(parameters,
self.DISCARD_NONMATCHING,
context)
summaries = [
self.statistics[i][0] for i in sorted(
self.parameterAsEnums(parameters, self.SUMMARIES, context))
]
if not summaries:
# none selected, so use all
summaries = [s[0] for s in self.statistics]
source_fields = source.fields()
fields_to_join = QgsFields()
join_field_indexes = []
if not join_fields:
# no fields selected, use all
join_fields = [
join_source.fields().at(i).name()
for i in range(len(join_source.fields()))
]
def addFieldKeepType(original, stat):
"""
Adds a field to the output, keeping the same data type as the original
"""
field = QgsField(original)
field.setName(field.name() + '_' + stat)
fields_to_join.append(field)
def addField(original, stat, type):
"""
Adds a field to the output, with a specified type
"""
field = QgsField(original)
field.setName(field.name() + '_' + stat)
field.setType(type)
if type == QVariant.Double:
field.setLength(20)
field.setPrecision(6)
fields_to_join.append(field)
numeric_fields = (('count', QVariant.Int,
'count'), ('unique', QVariant.Int, 'variety'),
('min', QVariant.Double,
'min'), ('max', QVariant.Double,
'max'), ('range', QVariant.Double,
'range'), ('sum', QVariant.Double,
'sum'),
('mean', QVariant.Double,
'mean'), ('median', QVariant.Double, 'median'),
('stddev', QVariant.Double,
'stDev'), ('minority', QVariant.Double, 'minority'),
('majority', QVariant.Double,
'majority'), ('q1', QVariant.Double,
'firstQuartile'),
('q3', QVariant.Double,
'thirdQuartile'), ('iqr', QVariant.Double,
'interQuartileRange'))
datetime_fields = (('count', QVariant.Int, 'count'),
('unique', QVariant.Int, 'countDistinct'),
('empty', QVariant.Int, 'countMissing'),
('filled', QVariant.Int), ('min', None), ('max',
None))
string_fields = (('count', QVariant.Int,
'count'), ('unique', QVariant.Int, 'countDistinct'),
('empty', QVariant.Int, 'countMissing'),
('filled', QVariant.Int), ('min', None, 'min'),
('max', None, 'max'), ('min_length', QVariant.Int,
'minLength'),
('max_length', QVariant.Int, 'maxLength'),
('mean_length', QVariant.Double, 'meanLength'))
field_types = []
for f in join_fields:
idx = join_source.fields().lookupField(f)
if idx >= 0:
join_field_indexes.append(idx)
join_field = join_source.fields().at(idx)
if join_field.isNumeric():
field_types.append('numeric')
field_list = numeric_fields
elif join_field.type() in (QVariant.Date, QVariant.Time,
QVariant.DateTime):
field_types.append('datetime')
field_list = datetime_fields
else:
field_types.append('string')
field_list = string_fields
for f in field_list:
if f[0] in summaries:
if f[1] is not None:
addField(join_field, f[0], f[1])
else:
addFieldKeepType(join_field, f[0])
out_fields = QgsProcessingUtils.combineFields(source_fields,
fields_to_join)
(sink, dest_id) = self.parameterAsSink(parameters, self.OUTPUT,
context, out_fields,
source.wkbType(),
source.sourceCrs())
if sink is None:
raise QgsProcessingException(
self.invalidSinkError(parameters, self.OUTPUT))
# do the join
predicates = [
self.predicates[i][0]
for i in self.parameterAsEnums(parameters, self.PREDICATE, context)
]
features = source.getFeatures()
total = 100.0 / source.featureCount() if source.featureCount() else 0
# bounding box transform
bbox_transform = QgsCoordinateTransform(source.sourceCrs(),
join_source.sourceCrs(),
context.project())
for current, f in enumerate(features):
if feedback.isCanceled():
break
if not f.hasGeometry():
if not discard_nomatch:
# ensure consistent count of attributes - otherwise non matching
# features will have incorrect attribute length
# and provider may reject them
attrs = f.attributes()
if len(attrs) < len(out_fields):
attrs += [NULL] * (len(out_fields) - len(attrs))
f.setAttributes(attrs)
sink.addFeature(f, QgsFeatureSink.FastInsert)
continue
bbox = bbox_transform.transformBoundingBox(
f.geometry().boundingBox())
engine = None
values = []
request = QgsFeatureRequest().setFilterRect(
bbox).setSubsetOfAttributes(
join_field_indexes).setDestinationCrs(
source.sourceCrs(), context.transformContext())
for test_feat in join_source.getFeatures(request):
if feedback.isCanceled():
break
join_attributes = []
for a in join_field_indexes:
join_attributes.append(test_feat.attributes()[a])
if engine is None:
engine = QgsGeometry.createGeometryEngine(
f.geometry().constGet())
engine.prepareGeometry()
for predicate in predicates:
if getattr(engine,
predicate)(test_feat.geometry().constGet()):
values.append(join_attributes)
break
feedback.setProgress(int(current * total))
if len(values) == 0:
if discard_nomatch:
continue
else:
# ensure consistent count of attributes - otherwise non matching
# features will have incorrect attribute length
# and provider may reject them
attrs = f.attributes()
if len(attrs) < len(out_fields):
attrs += [NULL] * (len(out_fields) - len(attrs))
f.setAttributes(attrs)
sink.addFeature(f, QgsFeatureSink.FastInsert)
else:
attrs = f.attributes()
for i in range(len(join_field_indexes)):
attribute_values = [v[i] for v in values]
field_type = field_types[i]
if field_type == 'numeric':
stat = QgsStatisticalSummary()
for v in attribute_values:
stat.addVariant(v)
stat.finalize()
for s in numeric_fields:
if s[0] in summaries:
attrs.append(getattr(stat, s[2])())
elif field_type == 'datetime':
stat = QgsDateTimeStatisticalSummary()
stat.calculate(attribute_values)
for s in datetime_fields:
if s[0] in summaries:
if s[0] == 'filled':
attrs.append(stat.count() -
stat.countMissing())
elif s[0] == 'min':
attrs.append(
stat.statistic(
QgsDateTimeStatisticalSummary.Min))
elif s[0] == 'max':
attrs.append(
stat.statistic(
QgsDateTimeStatisticalSummary.Max))
else:
attrs.append(getattr(stat, s[2])())
else:
stat = QgsStringStatisticalSummary()
for v in attribute_values:
if v == NULL:
stat.addString('')
else:
stat.addString(str(v))
stat.finalize()
for s in string_fields:
if s[0] in summaries:
if s[0] == 'filled':
attrs.append(stat.count() -
stat.countMissing())
else:
attrs.append(getattr(stat, s[2])())
f.setAttributes(attrs)
sink.addFeature(f, QgsFeatureSink.FastInsert)
return {self.OUTPUT: dest_id}
def calcStringStats(self, values, sink, feedback):
stat = QgsStringStatisticalSummary()
total = 50.0 / len(values) if values else 0
current = 0
for cat, v in values.items():
if feedback.isCanceled():
break
feedback.setProgress(int(current * total) + 50)
stat.calculate(v)
f = QgsFeature()
f.setAttributes(
list(cat) + [
stat.count(),
stat.countDistinct(),
stat.countMissing(),
stat.count() - stat.countMissing(),
stat.min(),
stat.max(),
stat.minLength(),
stat.maxLength(),
stat.meanLength()
])
sink.addFeature(f, QgsFeatureSink.FastInsert)
current += 1
def testIndividualStats(self):
# tests calculation of statistics one at a time, to make sure statistic calculations are not
# dependent on each other
tests = [
{
'stat': QgsStringStatisticalSummary.Count,
'expected': 9
},
{
'stat': QgsStringStatisticalSummary.CountDistinct,
'expected': 6
},
{
'stat': QgsStringStatisticalSummary.CountMissing,
'expected': 2
},
{
'stat': QgsStringStatisticalSummary.Min,
'expected': 'aaaa'
},
{
'stat': QgsStringStatisticalSummary.Max,
'expected': 'eeee'
},
{
'stat': QgsStringStatisticalSummary.MinimumLength,
'expected': 0
},
{
'stat': QgsStringStatisticalSummary.MaximumLength,
'expected': 8
},
{
'stat': QgsStringStatisticalSummary.MeanLength,
'expected': 3.3333333333333335
},
]
s = QgsStringStatisticalSummary()
s3 = QgsStringStatisticalSummary()
for t in tests:
# test constructor
s2 = QgsStringStatisticalSummary(t['stat'])
self.assertEqual(s2.statistics(), t['stat'])
s.setStatistics(t['stat'])
s3.setStatistics(t['stat'])
self.assertEqual(s.statistics(), t['stat'])
strings = [
'cc', 'aaaa', 'bbbbbbbb', 'aaaa', 'eeee', '', 'eeee', '',
'dddd'
]
s.calculate(strings)
s3.reset()
for string in strings:
s3.addString(string)
s3.finalize()
self.assertEqual(s.statistic(t['stat']), t['expected'])
self.assertEqual(s3.statistic(t['stat']), t['expected'])
# display name
self.assertTrue(
len(QgsStringStatisticalSummary.displayName(t['stat'])) > 0)
def testStats(self):
# we test twice, once with values added as a list and once using values
# added one-at-a-time
s = QgsStringStatisticalSummary()
self.assertEqual(s.statistics(), QgsStringStatisticalSummary.All)
strings = [
'cc', 'aaaa', 'bbbbbbbb', 'aaaa', 'eeee', '', 'eeee', '', 'dddd'
]
s.calculate(strings)
s2 = QgsStringStatisticalSummary()
for string in strings:
s2.addString(string)
s2.finalize()
self.assertEqual(s.count(), 9)
self.assertEqual(s2.count(), 9)
self.assertEqual(s.countDistinct(), 6)
self.assertEqual(s2.countDistinct(), 6)
self.assertEqual(set(s.distinctValues()),
set(['cc', 'aaaa', 'bbbbbbbb', 'eeee', 'dddd', '']))
self.assertEqual(s2.distinctValues(), s.distinctValues())
self.assertEqual(s.countMissing(), 2)
self.assertEqual(s2.countMissing(), 2)
self.assertEqual(s.min(), 'aaaa')
self.assertEqual(s2.min(), 'aaaa')
self.assertEqual(s.max(), 'eeee')
self.assertEqual(s2.max(), 'eeee')
self.assertEqual(s.minLength(), 0)
self.assertEqual(s2.minLength(), 0)
self.assertEqual(s.maxLength(), 8)
self.assertEqual(s2.maxLength(), 8)
self.assertEqual(s.meanLength(), 3.33333333333333333333333)
self.assertEqual(s2.meanLength(), 3.33333333333333333333333)
#extra check for minLength without empty strings
s.calculate(['1111111', '111', '11111'])
self.assertEqual(s.minLength(), 3)
def processAlgorithm(self, feedback):
layer = dataobjects.getObjectFromUri(
self.getParameterValue(self.INPUT_LAYER))
fieldName = self.getParameterValue(self.FIELD_NAME)
outputFile = self.getOutputValue(self.OUTPUT_HTML_FILE)
request = QgsFeatureRequest().setFlags(QgsFeatureRequest.NoGeometry).setSubsetOfAttributes([fieldName],
layer.fields())
stat = QgsStringStatisticalSummary()
features = vector.features(layer, request)
count = len(features)
total = 100.0 / float(count)
for current, ft in enumerate(features):
stat.addValue(ft[fieldName])
feedback.setProgress(int(current * total))
stat.finalize()
data = []
data.append(self.tr('Analyzed layer: {}').format(layer.name()))
data.append(self.tr('Analyzed field: {}').format(fieldName))
data.append(self.tr('Minimum length: {}').format(stat.minLength()))
data.append(self.tr('Maximum length: {}').format(stat.maxLength()))
data.append(self.tr('Mean length: {}').format(stat.meanLength()))
data.append(self.tr('Filled values: {}').format(stat.count() - stat.countMissing()))
data.append(self.tr('NULL (missing) values: {}').format(stat.countMissing()))
data.append(self.tr('Count: {}').format(stat.count()))
data.append(self.tr('Unique: {}').format(stat.countDistinct()))
data.append(self.tr('Minimum string value: {}').format(stat.min()))
data.append(self.tr('Maximum string value: {}').format(stat.max()))
self.createHTML(outputFile, data)
self.setOutputValue(self.MIN_LEN, stat.minLength())
self.setOutputValue(self.MAX_LEN, stat.maxLength())
self.setOutputValue(self.MEAN_LEN, stat.meanLength())
self.setOutputValue(self.FILLED, stat.count() - stat.countMissing())
self.setOutputValue(self.EMPTY, stat.countMissing())
self.setOutputValue(self.COUNT, stat.count())
self.setOutputValue(self.UNIQUE, stat.countDistinct())
self.setOutputValue(self.MIN_VALUE, stat.min())
self.setOutputValue(self.MAX_VALUE, stat.max())
def processAlgorithm(self, feedback):
layer = dataobjects.getLayerFromString(
self.getParameterValue(self.INPUT_LAYER))
fieldName = self.getParameterValue(self.FIELD_NAME)
outputFile = self.getOutputValue(self.OUTPUT_HTML_FILE)
request = QgsFeatureRequest().setFlags(
QgsFeatureRequest.NoGeometry).setSubsetOfAttributes([fieldName],
layer.fields())
stat = QgsStringStatisticalSummary()
features = vector.features(layer, request)
count = len(features)
total = 100.0 / float(count)
for current, ft in enumerate(features):
stat.addValue(ft[fieldName])
feedback.setProgress(int(current * total))
stat.finalize()
data = []
data.append(self.tr('Analyzed layer: {}').format(layer.name()))
data.append(self.tr('Analyzed field: {}').format(fieldName))
data.append(self.tr('Minimum length: {}').format(stat.minLength()))
data.append(self.tr('Maximum length: {}').format(stat.maxLength()))
data.append(self.tr('Mean length: {}').format(stat.meanLength()))
data.append(
self.tr('Filled values: {}').format(stat.count() -
stat.countMissing()))
data.append(
self.tr('NULL (missing) values: {}').format(stat.countMissing()))
data.append(self.tr('Count: {}').format(stat.count()))
data.append(self.tr('Unique: {}').format(stat.countDistinct()))
data.append(self.tr('Minimum string value: {}').format(stat.min()))
data.append(self.tr('Maximum string value: {}').format(stat.max()))
self.createHTML(outputFile, data)
self.setOutputValue(self.MIN_LEN, stat.minLength())
self.setOutputValue(self.MAX_LEN, stat.maxLength())
self.setOutputValue(self.MEAN_LEN, stat.meanLength())
self.setOutputValue(self.FILLED, stat.count() - stat.countMissing())
self.setOutputValue(self.EMPTY, stat.countMissing())
self.setOutputValue(self.COUNT, stat.count())
self.setOutputValue(self.UNIQUE, stat.countDistinct())
self.setOutputValue(self.MIN_VALUE, stat.min())
self.setOutputValue(self.MAX_VALUE, stat.max())
