def execute_aggregate(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
x_attr = view.get_attr_by_channel("x")[0]
y_attr = view.get_attr_by_channel("y")[0]
groupby_attr = ""
measure_attr = ""
if (y_attr.aggregation != ""):
groupby_attr = x_attr
measure_attr = y_attr
agg_func = y_attr.aggregation
if (x_attr.aggregation != ""):
groupby_attr = y_attr
measure_attr = x_attr
agg_func = x_attr.aggregation
all_attr_vals = view.data.unique_values[groupby_attr.attribute]
if (measure_attr != ""):
if (measure_attr.attribute == "Record"):
view.data = view.data.reset_index()
view.data = view.data.groupby(
groupby_attr.attribute).count().reset_index()
view.data = view.data.rename(columns={"index": "Record"})
view.data = view.data[[groupby_attr.attribute, "Record"]]
else:
groupby_result = view.data.groupby(groupby_attr.attribute)
view.data = groupby_result.agg(agg_func).reset_index()
result_vals = list(view.data[groupby_attr.attribute])
if (len(result_vals) != len(all_attr_vals)):
# For filtered aggregation that have missing groupby-attribute values, set these aggregated value as 0, since no datapoints
for vals in all_attr_vals:
if (vals not in result_vals):
view.data.loc[len(view.data)] = [vals, 0]
assert len(list(view.data[groupby_attr.attribute])) == len(
all_attr_vals
), f"Aggregated data missing values compared to original range of values of `{groupby_attr.attribute}`."
view.data = view.data.sort_values(by=groupby_attr.attribute,
ascending=True)
view.data = view.data.reset_index()
view.data = view.data.drop(columns="index")
def execute_aggregate(view: View, ldf: LuxDataFrame):
import pandas as pd
x_attr = view.get_attr_by_channel("x")[0]
y_attr = view.get_attr_by_channel("y")[0]
groupby_attr = ""
measure_attr = ""
if (y_attr.aggregation != ""):
groupby_attr = x_attr
measure_attr = y_attr
agg_func = y_attr.aggregation
if (x_attr.aggregation != ""):
groupby_attr = y_attr
measure_attr = x_attr
agg_func = x_attr.aggregation
if (measure_attr != ""):
#barchart case, need count data for each group
if (measure_attr.attribute == "Record"):
where_clause, filterVars = SQLExecutor.execute_filter(view)
count_query = "SELECT {}, COUNT({}) FROM {} {} GROUP BY {}".format(
groupby_attr.attribute, groupby_attr.attribute,
ldf.table_name, where_clause, groupby_attr.attribute)
view.data = pd.read_sql(count_query, ldf.SQLconnection)
view.data = view.data.rename(columns={"count": "Record"})
view.data = utils.pandas_to_lux(view.data)
else:
where_clause, filterVars = SQLExecutor.execute_filter(view)
if agg_func == "mean":
mean_query = "SELECT {}, AVG({}) as {} FROM {} {} GROUP BY {}".format(
groupby_attr.attribute, measure_attr.attribute,
measure_attr.attribute, ldf.table_name, where_clause,
groupby_attr.attribute)
view.data = pd.read_sql(mean_query, ldf.SQLconnection)
view.data = utils.pandas_to_lux(view.data)
if agg_func == "sum":
mean_query = "SELECT {}, SUM({}) as {} FROM {} {} GROUP BY {}".format(
groupby_attr.attribute, measure_attr.attribute,
measure_attr.attribute, ldf.table_name, where_clause,
groupby_attr.attribute)
view.data = pd.read_sql(mean_query, ldf.SQLconnection)
view.data = utils.pandas_to_lux(view.data)
if agg_func == "max":
mean_query = "SELECT {}, MAX({}) as {} FROM {} {} GROUP BY {}".format(
groupby_attr.attribute, measure_attr.attribute,
measure_attr.attribute, ldf.table_name, where_clause,
groupby_attr.attribute)
view.data = pd.read_sql(mean_query, ldf.SQLconnection)
view.data = utils.pandas_to_lux(view.data)
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
filter_specs = utils.get_filter_specs(view.spec_lst)
view_attrs_specs = utils.get_attrs_specs(view.spec_lst)
for spec in view_attrs_specs:
if (spec.attribute != "Record"):
if (spec.data_model == 'dimension'):
n_dim += 1
if (spec.data_model == 'measure'):
n_msr += 1
n_filter = len(filter_specs)
attr_specs = [
spec for spec in view_attrs_specs if spec.attribute != "Record"
]
dimension_lst = view.get_attr_by_data_model("dimension")
measure_lst = view.get_attr_by_data_model("measure")
# Bar Chart
if (n_dim == 1 and (n_msr == 0 or n_msr == 1)):
if (n_filter == 0):
return unevenness(view, ldf, measure_lst, dimension_lst)
elif (n_filter == 1):
return deviation_from_overall(view, ldf, filter_specs,
measure_lst[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 deviation_from_overall(view, ldf, filter_specs,
"Count of Records")
# Scatter Plot
elif (n_dim == 0 and n_msr == 2):
if (n_filter == 1):
v_filter_size = get_filtered_size(filter_specs, 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):
color_attr = view.get_attr_by_channel("color")[0].attribute
C = ldf.cardinality[color_attr]
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