def test_vis_custom_aggregation_as_str():
df = pd.read_csv("lux/data/college.csv")
import numpy as np
vis = Vis(["HighestDegree", lux.Clause("AverageCost", aggregation="max")], df)
assert vis.get_attr_by_data_model("measure")[0].aggregation == "max"
assert vis.get_attr_by_data_model("measure")[0]._aggregation_name == "max"
def test_vis_custom_aggregation_as_numpy_func():
df = pd.read_csv("lux/data/college.csv")
from lux.vis.Vis import Vis
import numpy as np
vis = Vis(["HighestDegree",lux.Clause("AverageCost",aggregation=np.ptp)],df)
assert vis.get_attr_by_data_model("measure")[0].aggregation == np.ptp
assert vis.get_attr_by_data_model("measure")[0]._aggregation_name =='ptp'
def test_vis_custom_aggregation_as_str(global_var):
df = pytest.college_df
import numpy as np
vis = Vis(["HighestDegree", lux.Clause("AverageCost", aggregation="max")], df)
assert vis.get_attr_by_data_model("measure")[0].aggregation == "max"
assert vis.get_attr_by_data_model("measure")[0]._aggregation_name == "max"
def deviation_from_overall(vis: Vis, ldf: LuxDataFrame, filter_specs: list, msr_attribute: str) -> int:
"""
Difference in bar chart/histogram shape from overall chart
Note: this function assumes that the filtered vis.data is operating on the same range as the unfiltered vis.data.
Parameters
----------
vis : Vis
ldf : LuxDataFrame
filter_specs : list
List of filters from the Vis
msr_attribute : str
The attribute name of the measure value of the chart
Returns
-------
int
Score describing how different the vis is from the overall vis
"""
v_filter_size = get_filtered_size(filter_specs, ldf)
v_size = len(vis.data)
v_filter = vis.data[msr_attribute]
total = v_filter.sum()
v_filter = v_filter / total # normalize by total to get ratio
if total == 0:
return 0
# Generate an "Overall" Vis (TODO: This is computed multiple times for every vis, alternative is to directly access df.current_vis but we do not have guaruntee that will always be unfiltered vis (in the non-Filter action scenario))
import copy
unfiltered_vis = copy.copy(vis)
# Remove filters, keep only attribute intent
unfiltered_vis._inferred_intent = utils.get_attrs_specs(vis._inferred_intent)
ldf.executor.execute([unfiltered_vis], ldf)
v = unfiltered_vis.data[msr_attribute]
v = v / v.sum()
assert len(v) == len(v_filter), "Data for filtered and unfiltered vis have unequal length."
sig = v_filter_size / v_size # significance factor
# Euclidean distance as L2 function
rankSig = 1 # category measure value ranking significance factor
# if the vis is a barchart, count how many categories' rank, based on measure value, changes after the filter is applied
if vis.mark == "bar":
dimList = vis.get_attr_by_data_model("dimension")
# use Pandas rank function to calculate rank positions for each category
v_rank = unfiltered_vis.data.rank()
v_filter_rank = vis.data.rank()
# go through and count the number of ranking changes between the filtered and unfiltered data
numCategories = ldf.cardinality[dimList[0].attribute]
for r in range(0, numCategories - 1):
if v_rank[msr_attribute][r] != v_filter_rank[msr_attribute][r]:
rankSig += 1
# normalize ranking significance factor
rankSig = rankSig / numCategories
from scipy.spatial.distance import euclidean
return sig * rankSig * euclidean(v, v_filter)
def test_vis_custom_aggregation_as_numpy_func(global_var):
df = pytest.college_df
from lux.vis.Vis import Vis
import numpy as np
vis = Vis(["HighestDegree", lux.Clause("AverageCost", aggregation=np.ptp)], df)
assert vis.get_attr_by_data_model("measure")[0].aggregation == np.ptp
assert vis.get_attr_by_data_model("measure")[0]._aggregation_name == "ptp"
def determine_encoding(ldf: LuxDataFrame, vis: Vis):
'''
Populates Vis 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 intent
vis : lux.vis.Vis
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 clause in vis._inferred_intent:
if (clause.value == ""):
if (clause.data_model == "dimension"):
ndim += 1
elif (clause.data_model == "measure"
and clause.attribute != "Record"):
nmsr += 1
else: # preserve to add back to _inferred_intent later
filters.append(clause)
# Helper function (TODO: Move this into utils)
def line_or_bar(ldf, dimension: Clause, measure: Clause):
dim_type = dimension.data_type
# If no aggregation function is specified, then default as average
if (measure.aggregation == ""):
measure.set_aggregation("mean")
if (dim_type == "temporal" or dim_type == "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
#count_col = Clause( attribute="count()", data_model="measure")
count_col = Clause(attribute="Record",
aggregation="count",
data_model="measure",
data_type="quantitative")
auto_channel = {}
if (ndim == 0 and nmsr == 1):
# Histogram with Count
measure = vis.get_attr_by_data_model("measure",
exclude_record=True)[0]
if (len(vis.get_attr_by_attr_name("Record")) < 0):
vis._inferred_intent.append(count_col)
# If no bin specified, then default as 10
if (measure.bin_size == 0):
measure.bin_size = 10
auto_channel = {"x": measure, "y": count_col}
vis.mark = "histogram"
elif (ndim == 1 and (nmsr == 0 or nmsr == 1)):
# Line or Bar Chart
if (nmsr == 0):
vis._inferred_intent.append(count_col)
dimension = vis.get_attr_by_data_model("dimension")[0]
measure = vis.get_attr_by_data_model("measure")[0]
vis.mark, auto_channel = line_or_bar(ldf, dimension, measure)
elif (ndim == 2 and (nmsr == 0 or nmsr == 1)):
# Line or Bar chart broken down by the dimension
dimensions = vis.get_attr_by_data_model("dimension")
d1 = dimensions[0]
d2 = dimensions[1]
if (ldf.cardinality[d1.attribute] < ldf.cardinality[d2.attribute]):
# d1.channel = "color"
vis.remove_column_from_spec(d1.attribute)
dimension = d2
color_attr = d1
else:
if (d1.attribute == d2.attribute):
vis._inferred_intent.pop(
0
) # if same attribute then remove_column_from_spec will remove both dims, we only want to remove one
else:
vis.remove_column_from_spec(d2.attribute)
dimension = d1
color_attr = d2
# Colored Bar/Line chart with Count as default measure
if (nmsr == 0):
vis._inferred_intent.append(count_col)
measure = vis.get_attr_by_data_model("measure")[0]
vis.mark, auto_channel = line_or_bar(ldf, dimension, measure)
auto_channel["color"] = color_attr
elif (ndim == 0 and nmsr == 2):
# Scatterplot
vis.mark = "scatter"
vis._inferred_intent[0].set_aggregation(None)
vis._inferred_intent[1].set_aggregation(None)
auto_channel = {
"x": vis._inferred_intent[0],
"y": vis._inferred_intent[1]
}
elif (ndim == 1 and nmsr == 2):
# Scatterplot broken down by the dimension
measure = vis.get_attr_by_data_model("measure")
m1 = measure[0]
m2 = measure[1]
vis._inferred_intent[0].set_aggregation(None)
vis._inferred_intent[1].set_aggregation(None)
color_attr = vis.get_attr_by_data_model("dimension")[0]
vis.remove_column_from_spec(color_attr)
vis.mark = "scatter"
auto_channel = {"x": m1, "y": m2, "color": color_attr}
elif (ndim == 0 and nmsr == 3):
# Scatterplot with color
vis.mark = "scatter"
auto_channel = {
"x": vis._inferred_intent[0],
"y": vis._inferred_intent[1],
"color": vis._inferred_intent[2]
}
relevant_attributes = [
auto_channel[channel].attribute for channel in auto_channel
]
relevant_min_max = dict((attr, ldf.min_max[attr])
for attr in relevant_attributes
if attr != "Record" and attr in ldf.min_max)
vis.min_max = relevant_min_max
if (auto_channel != {}):
vis = Compiler.enforce_specified_channel(vis, auto_channel)
vis._inferred_intent.extend(
filters) # add back the preserved filters
def interestingness(vis:Vis ,ldf:LuxDataFrame) -> int:
"""
Compute the interestingness score of the vis.
The interestingness metric is dependent on the vis type.
Parameters
----------
vis : Vis
ldf : LuxDataFrame
Returns
-------
int
Interestingness Score
"""
if vis.data is None or len(vis.data)==0:
raise Exception("Vis.data needs to be populated before interestingness can be computed. Run Executor.execute(vis,ldf).")
n_dim = 0
n_msr = 0
filter_specs = utils.get_filter_specs(vis._inferred_intent)
vis_attrs_specs = utils.get_attrs_specs(vis._inferred_intent)
record_attrs = list(filter(lambda x: x.attribute=="Record" and x.data_model=="measure", vis_attrs_specs))
n_record = len(record_attrs)
for clause in vis_attrs_specs:
if (clause.attribute!="Record"):
if (clause.data_model == 'dimension'):
n_dim += 1
if (clause.data_model == 'measure'):
n_msr += 1
n_filter = len(filter_specs)
attr_specs = [clause for clause in vis_attrs_specs if clause.attribute != "Record"]
dimension_lst = vis.get_attr_by_data_model("dimension")
measure_lst = vis.get_attr_by_data_model("measure")
v_size = len(vis.data)
# Line/Bar Chart
#print("r:", n_record, "m:", n_msr, "d:",n_dim)
if (n_dim == 1 and (n_msr==0 or n_msr==1)):
if (v_size<2): return -1
if (n_filter == 0):
return unevenness(vis, ldf, measure_lst, dimension_lst)
elif(n_filter==1):
return deviation_from_overall(vis, ldf, filter_specs, measure_lst[0].attribute)
# Histogram
elif (n_dim == 0 and n_msr == 1):
if (v_size<2): return -1
if (n_filter == 0):
v = vis.data["Number of Records"]
return skewness(v)
elif (n_filter == 1):
return deviation_from_overall(vis, ldf, filter_specs, "Number of Records")
# Scatter Plot
elif (n_dim == 0 and n_msr == 2):
if (v_size<2): return -1
if (n_filter==1):
v_filter_size = get_filtered_size(filter_specs, vis.data)
sig = v_filter_size/v_size
else:
sig = 1
return sig * monotonicity(vis,attr_specs)
# Scatterplot colored by Dimension
elif (n_dim == 1 and n_msr == 2):
if (v_size<5): return -1
color_attr = vis.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
# colored line and barchart cases
elif ((vis.mark == "line" or vis.mark == "bar") and n_dim == 2):
return 0.2
# Default
else:
return -1
def interestingness(vis: Vis, ldf: LuxDataFrame) -> int:
"""
Compute the interestingness score of the vis.
The interestingness metric is dependent on the vis type.
Parameters
----------
vis : Vis
ldf : LuxDataFrame
Returns
-------
int
Interestingness Score
"""
if vis.data is None or len(vis.data) == 0:
return -1
# raise Exception("Vis.data needs to be populated before interestingness can be computed. Run Executor.execute(vis,ldf).")
n_dim = 0
n_msr = 0
filter_specs = utils.get_filter_specs(vis._inferred_intent)
vis_attrs_specs = utils.get_attrs_specs(vis._inferred_intent)
record_attrs = list(
filter(
lambda x: x.attribute == "Record" and x.data_model == "measure",
vis_attrs_specs,
))
n_record = len(record_attrs)
for clause in vis_attrs_specs:
if clause.attribute != "Record":
if clause.data_model == "dimension":
n_dim += 1
if clause.data_model == "measure":
n_msr += 1
n_filter = len(filter_specs)
attr_specs = [
clause for clause in vis_attrs_specs if clause.attribute != "Record"
]
dimension_lst = vis.get_attr_by_data_model("dimension")
measure_lst = vis.get_attr_by_data_model("measure")
v_size = len(vis.data)
# Line/Bar Chart
# print("r:", n_record, "m:", n_msr, "d:",n_dim)
if n_dim == 1 and (n_msr == 0 or n_msr == 1):
if v_size < 2:
return -1
if n_filter == 0:
return unevenness(vis, ldf, measure_lst, dimension_lst)
elif n_filter == 1:
return deviation_from_overall(vis, ldf, filter_specs,
measure_lst[0].attribute)
# Histogram
elif n_dim == 0 and n_msr == 1:
if v_size < 2:
return -1
if n_filter == 0 and "Number of Records" in vis.data:
if "Number of Records" in vis.data:
v = vis.data["Number of Records"]
return skewness(v)
elif n_filter == 1 and "Number of Records" in vis.data:
return deviation_from_overall(vis, ldf, filter_specs,
"Number of Records")
return -1
# Scatter Plot
elif n_dim == 0 and n_msr == 2:
if v_size < 10:
return -1
if vis.mark == "heatmap":
return weighted_correlation(vis.data["xBinStart"],
vis.data["yBinStart"],
vis.data["count"])
if n_filter == 1:
v_filter_size = get_filtered_size(filter_specs, vis.data)
sig = v_filter_size / v_size
else:
sig = 1
return sig * monotonicity(vis, attr_specs)
# Scatterplot colored by Dimension
elif n_dim == 1 and n_msr == 2:
if v_size < 10:
return -1
color_attr = vis.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
# colored line and barchart cases
elif vis.mark == "line" and n_dim == 2:
return 0.15
# for colored bar chart, scoring based on Chi-square test for independence score.
# gives higher scores to colored bar charts with fewer total categories as these charts are easier to read and thus more useful for users
elif vis.mark == "bar" and n_dim == 2:
from scipy.stats import chi2_contingency
measure_column = vis.get_attr_by_data_model("measure")[0].attribute
dimension_columns = vis.get_attr_by_data_model("dimension")
groupby_column = dimension_columns[0].attribute
color_column = dimension_columns[1].attribute
contingency_table = []
groupby_cardinality = ldf.cardinality[groupby_column]
groupby_unique_vals = ldf.unique_values[groupby_column]
for c in range(0, groupby_cardinality):
contingency_table.append(
vis.data[vis.data[groupby_column] ==
groupby_unique_vals[c]][measure_column])
score = 0.12
# ValueError results if an entire column of the contingency table is 0, can happen if an applied filter results in
# a category having no counts
try:
color_cardinality = ldf.cardinality[color_column]
# scale down score based on number of categories
chi2_score = chi2_contingency(contingency_table)[0] * 0.9**(
color_cardinality + groupby_cardinality)
score = min(0.10, chi2_score)
except ValueError:
pass
return score
# Default
else:
return -1
def interestingness(vis: Vis, ldf: LuxDataFrame) -> int:
"""
Compute the interestingness score of the vis.
The interestingness metric is dependent on the vis type.
Parameters
----------
vis : Vis
ldf : LuxDataFrame
Returns
-------
int
Interestingness Score
"""
if vis.data is None or len(vis.data) == 0:
return -1
# raise Exception("Vis.data needs to be populated before interestingness can be computed. Run Executor.execute(vis,ldf).")
try:
filter_specs = utils.get_filter_specs(vis._inferred_intent)
vis_attrs_specs = utils.get_attrs_specs(vis._inferred_intent)
n_dim = vis._ndim
n_msr = vis._nmsr
n_filter = len(filter_specs)
attr_specs = [clause for clause in vis_attrs_specs if clause.attribute != "Record"]
dimension_lst = vis.get_attr_by_data_model("dimension")
measure_lst = vis.get_attr_by_data_model("measure")
v_size = len(vis.data)
if (
n_dim == 1
and (n_msr == 0 or n_msr == 1)
and ldf.current_vis is not None
and vis.get_attr_by_channel("y")[0].data_type == "quantitative"
and len(ldf.current_vis) == 1
and ldf.current_vis[0].mark == "line"
and len(get_filter_specs(ldf.intent)) > 0
):
query_vc = VisList(ldf.current_vis, ldf)
query_vis = query_vc[0]
preprocess(query_vis)
preprocess(vis)
return 1 - euclidean_dist(query_vis, vis)
# Line/Bar Chart
# print("r:", n_record, "m:", n_msr, "d:",n_dim)
if n_dim == 1 and (n_msr == 0 or n_msr == 1):
if v_size < 2:
return -1
if n_filter == 0:
return unevenness(vis, ldf, measure_lst, dimension_lst)
elif n_filter == 1:
return deviation_from_overall(vis, ldf, filter_specs, measure_lst[0].attribute)
# Histogram
elif n_dim == 0 and n_msr == 1:
if v_size < 2:
return -1
if n_filter == 0 and "Number of Records" in vis.data:
if "Number of Records" in vis.data:
v = vis.data["Number of Records"]
return skewness(v)
elif n_filter == 1 and "Number of Records" in vis.data:
return deviation_from_overall(vis, ldf, filter_specs, "Number of Records")
return -1
# Scatter Plot
elif n_dim == 0 and n_msr == 2:
if v_size < 10:
return -1
if vis.mark == "heatmap":
return weighted_correlation(
vis.data["xBinStart"], vis.data["yBinStart"], vis.data["count"]
)
if n_filter == 1:
v_filter_size = get_filtered_size(filter_specs, vis.data)
sig = v_filter_size / v_size
else:
sig = 1
return sig * monotonicity(vis, attr_specs)
# Scatterplot colored by Dimension
elif n_dim == 1 and n_msr == 2:
if v_size < 10:
return -1
color_attr = vis.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
# colored line and barchart cases
elif vis.mark == "line" and n_dim == 2:
return 0.15
# for colored bar chart, scoring based on Chi-square test for independence score.
# gives higher scores to colored bar charts with fewer total categories as these charts are easier to read and thus more useful for users
elif vis.mark == "bar" and n_dim == 2:
from scipy.stats import chi2_contingency
measure_column = vis.get_attr_by_data_model("measure")[0].attribute
dimension_columns = vis.get_attr_by_data_model("dimension")
groupby_column = dimension_columns[0].attribute
color_column = dimension_columns[1].attribute
contingency_tbl = pd.crosstab(
vis.data[groupby_column],
vis.data[color_column],
values=vis.data[measure_column],
aggfunc=sum,
)
try:
color_cardinality = ldf.cardinality[color_column]
groupby_cardinality = ldf.cardinality[groupby_column]
# scale down score based on number of categories
chi2_score = chi2_contingency(contingency_tbl)[0] * 0.9 ** (
color_cardinality + groupby_cardinality
)
score = min(0.10, chi2_score)
except (ValueError, KeyError):
# ValueError results if an entire column of the contingency table is 0, can happen if an applied filter results in a category having no counts
score = -1
return score
# Default
else:
return -1
except:
if lux.config.interestingness_fallback:
# Supress interestingness related issues
warnings.warn(f"An error occurred when computing interestingness for: {vis}")
return -1
else:
raise
def determine_encoding(ldf: LuxDataFrame, vis: Vis):
"""
Populates Vis with the appropriate mark type and channel information based on ShowMe logic
Currently support up to 3 dimensions or measures
Parameters
----------
ldf : lux.core.frame
LuxDataFrame with underspecified intent
vis : lux.vis.Vis
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 = vis._ndim
nmsr = vis._nmsr
# preserve to add back to _inferred_intent later
filters = utils.get_filter_specs(vis._inferred_intent)
# Helper function (TODO: Move this into utils)
def line_or_bar_or_geo(ldf, dimension: Clause, measure: Clause):
dim_type = dimension.data_type
# If no aggregation function is specified, then default as average
if measure.aggregation == "":
measure.set_aggregation("mean")
if dim_type == "temporal" or dim_type == "oridinal":
if isinstance(dimension.attribute, pd.Timestamp):
# If timestamp, use the _repr_ (e.g., TimeStamp('2020-04-05 00.000')--> '2020-04-05')
attr = str(dimension.attribute._date_repr)
else:
attr = dimension.attribute
if ldf.cardinality[attr] == 1:
return "bar", {"x": measure, "y": dimension}
else:
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"
if utils.like_geo(dimension.get_attr()):
return "geographical", {"x": dimension, "y": measure}
return "bar", {"x": measure, "y": dimension}
# ShowMe logic + additional heuristics
# count_col = Clause( attribute="count()", data_model="measure")
count_col = Clause(
attribute="Record",
aggregation="count",
data_model="measure",
data_type="quantitative",
)
auto_channel = {}
if ndim == 0 and nmsr == 1:
# Histogram with Count
measure = vis.get_attr_by_data_model("measure",
exclude_record=True)[0]
if len(vis.get_attr_by_attr_name("Record")) < 0:
vis._inferred_intent.append(count_col)
# If no bin specified, then default as 10
if measure.bin_size == 0:
measure.bin_size = 10
auto_channel = {"x": measure, "y": count_col}
vis._mark = "histogram"
elif ndim == 1 and (nmsr == 0 or nmsr == 1):
# Line or Bar Chart
if nmsr == 0:
vis._inferred_intent.append(count_col)
dimension = vis.get_attr_by_data_model("dimension")[0]
measure = vis.get_attr_by_data_model("measure")[0]
vis._mark, auto_channel = line_or_bar_or_geo(
ldf, dimension, measure)
elif ndim == 2 and (nmsr == 0 or nmsr == 1):
# Line or Bar chart broken down by the dimension
dimensions = vis.get_attr_by_data_model("dimension")
d1 = dimensions[0]
d2 = dimensions[1]
if ldf.cardinality[d1.attribute] < ldf.cardinality[d2.attribute]:
# d1.channel = "color"
vis.remove_column_from_spec(d1.attribute)
dimension = d2
color_attr = d1
else:
# if same attribute then remove_column_from_spec will remove both dims, we only want to remove one
if d1.attribute == d2.attribute:
vis._inferred_intent.pop(0)
else:
vis.remove_column_from_spec(d2.attribute)
dimension = d1
color_attr = d2
# Colored Bar/Line chart with Count as default measure
if not ldf.pre_aggregated:
if nmsr == 0 and not ldf.pre_aggregated:
vis._inferred_intent.append(count_col)
measure = vis.get_attr_by_data_model("measure")[0]
vis._mark, auto_channel = line_or_bar_or_geo(
ldf, dimension, measure)
auto_channel["color"] = color_attr
elif ndim == 0 and nmsr == 2:
# Scatterplot
vis._mark = "scatter"
vis._inferred_intent[0].set_aggregation(None)
vis._inferred_intent[1].set_aggregation(None)
auto_channel = {
"x": vis._inferred_intent[0],
"y": vis._inferred_intent[1]
}
elif ndim == 1 and nmsr == 2:
# Scatterplot broken down by the dimension
measure = vis.get_attr_by_data_model("measure")
m1 = measure[0]
m2 = measure[1]
vis._inferred_intent[0].set_aggregation(None)
vis._inferred_intent[1].set_aggregation(None)
color_attr = vis.get_attr_by_data_model("dimension")[0]
vis.remove_column_from_spec(color_attr)
vis._mark = "scatter"
auto_channel = {"x": m1, "y": m2, "color": color_attr}
elif ndim == 0 and nmsr == 3:
# Scatterplot with color
vis._mark = "scatter"
auto_channel = {
"x": vis._inferred_intent[0],
"y": vis._inferred_intent[1],
"color": vis._inferred_intent[2],
}
relevant_attributes = [
auto_channel[channel].attribute for channel in auto_channel
]
relevant_min_max = dict((attr, ldf._min_max[attr])
for attr in relevant_attributes
if attr != "Record" and attr in ldf._min_max)
# Replace scatterplot with heatmap
HBIN_START = 5000
if vis.mark == "scatter" and lux.config.heatmap and len(
ldf) > HBIN_START:
vis._postbin = True
ldf._message.add_unique(
f"Large scatterplots detected: Lux is automatically binning scatterplots to heatmaps.",
priority=98,
)
vis._mark = "heatmap"
vis._min_max = relevant_min_max
if auto_channel != {}:
vis = Compiler.enforce_specified_channel(vis, auto_channel)
vis._inferred_intent.extend(
filters) # add back the preserved filters
