def determineEncoding(ldf: LuxDataFrame, view: View):
'''
Populates View with the appropriate mark type and channel information based on ShowMe logic
Currently support up to 3 dimensions or measures
Parameters
----------
ldf : lux.luxDataFrame.LuxDataFrame
LuxDataFrame with underspecified context
view : lux.view.View
Returns
-------
None
Notes
-----
Implementing automatic encoding from Tableau's VizQL
Mackinlay, J. D., Hanrahan, P., & Stolte, C. (2007).
Show Me: Automatic presentation for visual analysis.
IEEE Transactions on Visualization and Computer Graphics, 13(6), 1137–1144.
https://doi.org/10.1109/TVCG.2007.70594
'''
# Count number of measures and dimensions
Ndim = 0
Nmsr = 0
filters = []
for spec in view.specLst:
if (spec.value == ""):
if (spec.dataModel == "dimension"):
Ndim += 1
elif (spec.dataModel == "measure"
and spec.attribute != "Record"):
Nmsr += 1
else: # preserve to add back to specLst later
filters.append(spec)
# Helper function (TODO: Move this into utils)
def lineOrBar(ldf, dimension, measure):
dimType = dimension.dataType
# If no aggregation function is specified, then default as average
if (measure.aggregation == ""):
measure.aggregation = "mean"
if (dimType == "temporal" or dimType == "oridinal"):
return "line", {"x": dimension, "y": measure}
else: # unordered categorical
# if cardinality large than 5 then sort bars
if ldf.cardinality[dimension.attribute] > 5:
dimension.sort = "ascending"
return "bar", {"x": measure, "y": dimension}
# ShowMe logic + additional heuristics
#countCol = Spec( attribute="count()", dataModel="measure")
countCol = Spec(attribute="Record",
aggregation="count",
dataModel="measure",
dataType="quantitative")
# xAttr = view.getAttrByChannel("x") # not used as of now
# yAttr = view.getAttrByChannel("y")
# zAttr = view.getAttrByChannel("z")
autoChannel = {}
if (Ndim == 0 and Nmsr == 1):
# Histogram with Count
measure = view.getAttrByDataModel("measure", excludeRecord=True)[0]
if (len(view.getAttrByAttrName("Record")) < 0):
view.specLst.append(countCol)
# If no bin specified, then default as 10
if (measure.binSize == 0):
measure.binSize = 10
autoChannel = {"x": measure, "y": countCol}
view.xMinMax = ldf.xMinMax
view.mark = "histogram"
elif (Ndim == 1 and (Nmsr == 0 or Nmsr == 1)):
# Line or Bar Chart
if (Nmsr == 0):
view.specLst.append(countCol)
dimension = view.getAttrByDataModel("dimension")[0]
measure = view.getAttrByDataModel("measure")[0]
view.mark, autoChannel = lineOrBar(ldf, dimension, measure)
elif (Ndim == 2 and (Nmsr == 0 or Nmsr == 1)):
# Line or Bar chart broken down by the dimension
dimensions = view.getAttrByDataModel("dimension")
d1 = dimensions[0]
d2 = dimensions[1]
if (ldf.cardinality[d1.attribute] < ldf.cardinality[d2.attribute]):
# d1.channel = "color"
view.removeColumnFromSpec(d1.attribute)
dimension = d2
colorAttr = d1
else:
if (d1.attribute == d2.attribute):
view.specLst.pop(
0
) # if same attribute then removeColumnFromSpec will remove both dims, we only want to remove one
else:
view.removeColumnFromSpec(d2.attribute)
dimension = d1
colorAttr = d2
# Colored Bar/Line chart with Count as default measure
if (Nmsr == 0):
view.specLst.append(countCol)
measure = view.getAttrByDataModel("measure")[0]
view.mark, autoChannel = lineOrBar(ldf, dimension, measure)
autoChannel["color"] = colorAttr
elif (Ndim == 0 and Nmsr == 2):
# Scatterplot
view.xMinMax = ldf.xMinMax
view.yMinMax = ldf.yMinMax
view.mark = "scatter"
autoChannel = {"x": view.specLst[0], "y": view.specLst[1]}
elif (Ndim == 1 and Nmsr == 2):
# Scatterplot broken down by the dimension
measure = view.getAttrByDataModel("measure")
m1 = measure[0]
m2 = measure[1]
colorAttr = view.getAttrByDataModel("dimension")[0]
view.removeColumnFromSpec(colorAttr)
view.xMinMax = ldf.xMinMax
view.yMinMax = ldf.yMinMax
view.mark = "scatter"
autoChannel = {"x": m1, "y": m2, "color": colorAttr}
elif (Ndim == 0 and Nmsr == 3):
# Scatterplot with color
view.xMinMax = ldf.xMinMax
view.yMinMax = ldf.yMinMax
view.mark = "scatter"
autoChannel = {
"x": view.specLst[0],
"y": view.specLst[1],
"color": view.specLst[2]
}
if (autoChannel != {}):
view = Compiler.enforceSpecifiedChannel(view, autoChannel)
view.specLst.extend(filters) # add back the preserved filters
def interestingness(view:View ,ldf:LuxDataFrame) -> int:
"""
Compute the interestingness score of the view.
The interestingness metric is dependent on the view type.
Parameters
----------
view : View
ldf : LuxDataFrame
Returns
-------
int
Interestingness Score
"""
if view.data is None:
raise Exception("View.data needs to be populated before interestingness can be computed. Run Executor.execute(view,ldf).")
n_dim = 0
n_msr = 0
filterSpecs = utils.getFilterSpecs(view.specLst)
viewAttrsSpecs = utils.getAttrsSpecs(view.specLst)
for spec in viewAttrsSpecs:
if (spec.attribute!="Record"):
if (spec.dataModel == 'dimension'):
n_dim += 1
if (spec.dataModel == 'measure'):
n_msr += 1
n_filter = len(filterSpecs)
attr_specs = [spec for spec in viewAttrsSpecs if spec.attribute != "Record"]
dimensionLst = view.getAttrByDataModel("dimension")
measureLst = view.getAttrByDataModel("measure")
# Bar Chart
if (n_dim == 1 and (n_msr == 0 or n_msr==1)):
if (n_filter == 0):
return unevenness(view, ldf, measureLst, dimensionLst)
elif(n_filter==1):
return deviationFromOverall(view,ldf,filterSpecs,measureLst[0].attribute)
# Histogram
elif (n_dim == 0 and n_msr == 1):
if (n_filter == 0):
v = view.data["Count of Records"]
return skewness(v)
elif (n_filter == 1):
return deviationFromOverall(view,ldf,filterSpecs,"Count of Records")
# Scatter Plot
elif (n_dim == 0 and n_msr == 2):
if (n_filter==1):
v_filter_size = getFilteredSize(filterSpecs,view.data)
v_size = len(view.data)
sig = v_filter_size/v_size
else:
sig = 1
return sig * monotonicity(view,attr_specs)
# Scatterplot colored by Dimension
elif (n_dim == 1 and n_msr == 2):
colorAttr = view.getAttrByChannel("color")[0].attribute
C = ldf.cardinality[colorAttr]
if (C<40):
return 1/C
else:
return -1
# Scatterplot colored by dimension
elif (n_dim== 1 and n_msr == 2):
return 0.2
# Scatterplot colored by measure
elif (n_msr == 3):
return 0.1
# Default
else:
return -1