def executeAggregate(view: View):
'''
Aggregate data points on an axis for bar or line charts
Parameters
----------
view: lux.View
lux.View object that represents a visualization
ldf : lux.luxDataFrame.LuxDataFrame
LuxDataFrame with specified context.
Returns
-------
None
'''
import numpy as np
xAttr = view.getAttrByChannel("x")[0]
yAttr = view.getAttrByChannel("y")[0]
groupbyAttr = ""
measureAttr = ""
if (yAttr.aggregation != ""):
groupbyAttr = xAttr
measureAttr = yAttr
aggFunc = yAttr.aggregation
if (xAttr.aggregation != ""):
groupbyAttr = yAttr
measureAttr = xAttr
aggFunc = xAttr.aggregation
allAttrVals = view.data.uniqueValues[groupbyAttr.attribute]
if (measureAttr != ""):
if (measureAttr.attribute == "Record"):
view.data = view.data.reset_index()
view.data = view.data.groupby(
groupbyAttr.attribute).count().reset_index()
view.data = view.data.rename(columns={"index": "Record"})
view.data = view.data[[groupbyAttr.attribute, "Record"]]
else:
groupbyResult = view.data.groupby(groupbyAttr.attribute)
view.data = groupbyResult.agg(aggFunc).reset_index()
resultVals = list(view.data[groupbyAttr.attribute])
if (len(resultVals) != len(allAttrVals)):
# For filtered aggregation that have missing groupby-attribute values, set these aggregated value as 0, since no datapoints
for vals in allAttrVals:
if (vals not in resultVals):
view.data.loc[len(view.data)] = [vals, 0]
assert len(list(view.data[groupbyAttr.attribute])) == len(
allAttrVals
), f"Aggregated data missing values compared to original range of values of `{groupbyAttr.attribute}`."
view.data = view.data.sort_values(by=groupbyAttr.attribute,
ascending=True)
view.data = view.data.reset_index()
view.data = view.data.drop(columns="index")
def executeFilter(view: View):
assert view.data is not None, "executeFilter assumes input view.data is populated (if not, populate with LuxDataFrame values)"
filters = utils.getFilterSpecs(view.specLst)
if (filters):
# TODO: Need to handle OR logic
for filter in filters:
view.data = PandasExecutor.applyFilter(view.data,
filter.attribute,
filter.filterOp,
filter.value)
def executeAggregate(view:View, ldf:LuxDataFrame):
import pandas as pd
xAttr = view.getAttrByChannel("x")[0]
yAttr = view.getAttrByChannel("y")[0]
groupbyAttr =""
measureAttr =""
if (yAttr.aggregation!=""):
groupbyAttr = xAttr
measureAttr = yAttr
aggFunc = yAttr.aggregation
if (xAttr.aggregation!=""):
groupbyAttr = yAttr
measureAttr = xAttr
aggFunc = xAttr.aggregation
if (measureAttr!=""):
#barchart case, need count data for each group
if (measureAttr.attribute=="Record"):
whereClause, filterVars = SQLExecutor.executeFilter(view)
countQuery = "SELECT {}, COUNT({}) FROM {} {} GROUP BY {}".format(groupbyAttr.attribute, groupbyAttr.attribute, ldf.table_name, whereClause, groupbyAttr.attribute)
view.data = pd.read_sql(countQuery, ldf.SQLconnection)
view.data = view.data.rename(columns={"count":"Record"})
view.data = utils.pandasToLux(view.data)
else:
whereClause, filterVars = SQLExecutor.executeFilter(view)
if aggFunc == "mean":
meanQuery = "SELECT {}, AVG({}) as {} FROM {} {} GROUP BY {}".format(groupbyAttr.attribute, measureAttr.attribute, measureAttr.attribute, ldf.table_name, whereClause, groupbyAttr.attribute)
view.data = pd.read_sql(meanQuery, ldf.SQLconnection)
view.data = utils.pandasToLux(view.data)
if aggFunc == "sum":
meanQuery = "SELECT {}, SUM({}) as {} FROM {} {} GROUP BY {}".format(groupbyAttr.attribute, measureAttr.attribute, measureAttr.attribute, ldf.table_name, whereClause, groupbyAttr.attribute)
view.data = pd.read_sql(meanQuery, ldf.SQLconnection)
view.data = utils.pandasToLux(view.data)
if aggFunc == "max":
meanQuery = "SELECT {}, MAX({}) as {} FROM {} {} GROUP BY {}".format(groupbyAttr.attribute, measureAttr.attribute, measureAttr.attribute, ldf.table_name, whereClause, groupbyAttr.attribute)
view.data = pd.read_sql(meanQuery, ldf.SQLconnection)
view.data = utils.pandasToLux(view.data)
