def updateStats(self):
if self.current_layer is not None:
current_attribute = self.dlg.getCurrentAttribute()
if current_attribute >= 0:
attribute = self.layer_attributes[current_attribute]
# check if stats have been calculated before
idx = self.checkValuesAvailable(attribute)
if idx == -1:
self.retrieveAttributeValues(attribute)
idx = len(self.attribute_statistics) - 1
stats = self.attribute_statistics[idx]
# calculate stats of selected objects only
select_stats = dict()
if self.current_layer.selectedFeatureCount() > 0:
self.selection_values, self.selection_ids = lfh.getFieldValues(self.current_layer,
attribute['name'], null=False,
selection=True)
sel_values = [val for val in self.selection_values if val != NULL]
select_stats['Number'] = len(sel_values)
select_stats['Mean'] = uf.truncateNumber(np.mean(sel_values))
select_stats['Std Dev'] = uf.truncateNumber(np.std(sel_values))
select_stats['Variance'] = uf.truncateNumber(np.var(sel_values))
select_stats['Median'] = uf.truncateNumber(np.median(sel_values))
select_stats['Minimum'] = np.min(sel_values)
select_stats['Maximum'] = np.max(sel_values)
select_stats['Range'] = uf.truncateNumber(select_stats['Maximum'] - select_stats['Minimum'])
select_stats['1st Quart'] = uf.truncateNumber(np.percentile(sel_values, 25))
select_stats['3rd Quart'] = uf.truncateNumber(np.percentile(sel_values, 75))
select_stats['IQR'] = uf.truncateNumber(select_stats['3rd Quart'] - select_stats['1st Quart'])
select_stats['Gini'] = uf.roundNumber(uf.calcGini(sel_values))
else:
self.selection_values = []
self.selection_ids = []
# update the dialog
self.dlg.setStats(stats, select_stats)
def test_roundNumber_over_100(self):
self.assertEqual(uf.roundNumber(200.0), 200.0)
self.assertEqual(uf.roundNumber(200.045), 200.0)
self.assertEqual(uf.roundNumber(200.055), 200.1)
self.assertEqual(uf.roundNumber(-200.0), -200.0)
self.assertEqual(uf.roundNumber(-200.045), -200.0)
self.assertEqual(uf.roundNumber(-200.055), -200.1)
def test_roundNumber_1_100(self):
self.assertEqual(uf.roundNumber(2.00), 2.00)
self.assertEqual(uf.roundNumber(2.0045), 2.00)
self.assertEqual(uf.roundNumber(2.0055), 2.01)
self.assertEqual(uf.roundNumber(-2.00), -2.00)
self.assertEqual(uf.roundNumber(-2.0045), -2.00)
self.assertEqual(uf.roundNumber(-2.0055), -2.01)
def test_roundNumber_001_1(self):
self.assertEqual(uf.roundNumber(0.2000), 0.2000)
self.assertEqual(uf.roundNumber(0.200045), 0.2000)
self.assertEqual(uf.roundNumber(0.200055), 0.2001)
self.assertEqual(uf.roundNumber(-0.2000), -0.2000)
self.assertEqual(uf.roundNumber(-0.200045), -0.2000)
self.assertEqual(uf.roundNumber(-0.200055), -0.2001)
def retrieveAttributeValues(self, attribute):
storage = self.current_layer.storageType()
if 'spatialite' in storage.lower():
# todo: retrieve values and ids using SQL query
values, ids = lfh.getFieldValues(self.current_layer, attribute["name"], null=True)
clean_values = [val for val in values if val != NULL]
elif 'postgresql' in storage.lower():
# todo: retrieve values and ids using SQL query
values, ids = lfh.getFieldValues(self.current_layer, attribute["name"], null=True)
clean_values = [val for val in values if val != NULL]
else:
values, ids = lfh.getFieldValues(self.current_layer, attribute["name"], null=True)
# we need to keep the complete values set for the scatterplot, must get rid of NULL values for other stats
clean_values = [val for val in values if val != NULL]
if values and ids:
stats = dict()
stats['Layer'] = self.current_layer.name()
stats['Attribute'] = attribute['name']
stats['Number'] = len(clean_values)
stats['Mean'] = uf.truncateNumber(np.mean(clean_values))
stats['Std Dev'] = uf.truncateNumber(np.std(clean_values))
stats['Variance'] = uf.truncateNumber(np.var(clean_values))
stats['Median'] = uf.truncateNumber(np.median(clean_values))
stats['Minimum'] = np.min(clean_values)
stats['Maximum'] = np.max(clean_values)
stats['Range'] = uf.truncateNumber(stats['Maximum'] - stats['Minimum'])
stats['1st Quart'] = uf.truncateNumber(np.percentile(clean_values, 25))
stats['3rd Quart'] = uf.truncateNumber(np.percentile(clean_values, 75))
stats['IQR'] = uf.truncateNumber(stats['3rd Quart'] - stats['1st Quart'])
stats['Gini'] = uf.roundNumber(uf.calcGini(clean_values))
# store the results
self.attribute_statistics.append(stats)
# store retrieved values for selection stats and charts
attr = dict()
attr['Layer'] = self.current_layer.name()
attr['Attribute'] = attribute['name']
attr['values'] = values
attr['ids'] = ids
attr['nulls'] = (len(values) != len(clean_values))
attr['bins'] = uf.calcBins(clean_values)
self.attribute_values.append(attr)
def calculateBivariateStats(self, xname, xvalues, yname, yvalues):
bistats = dict()
bistats['Layer'] = self.current_layer.name()
bistats['x'] = xname
bistats['y'] = yname
bistats['r'] = uf.roundNumber(np.corrcoef(xvalues, yvalues)[1][0])
fit, residuals, rank, singular_values, rcond = np.polyfit(xvalues, yvalues, 1, None, True, None, False)
bistats['slope'] = fit[0]
bistats['intercept'] = fit[1]
bistats['r2'] = uf.roundNumber((1 - residuals[0] / (len(yvalues) * np.var(yvalues))))
# fixme: pvalue calc not correct
bistats['p'] = 0
if bistats['slope'] > 0:
bistats['line'] = "%s + %s * X" % (uf.roundNumber(bistats['intercept']), uf.roundNumber(bistats['slope']))
else:
bistats['line'] = "%s - %s * X" % (
uf.roundNumber(abs(bistats['intercept'])), uf.roundNumber(bistats['slope']))
self.bivariate_statistics.append(bistats)
def test_roundNumber_wrong_type(self):
self.assertRaises(TypeError, lambda: uf.roundNumber("0.002000"))