def test_vis_set_specs():
url = (
"https://github.com/lux-org/lux-datasets/blob/master/data/olympic.csv?raw=true"
)
df = pd.read_csv(url)
vis = Vis(["Height", "SportType=Ball"], df)
vis.set_intent(["Height", "SportType=Ice"])
assert vis.get_attr_by_attr_name("SportType")[0].value == "Ice"
def test_vis():
url = (
"https://github.com/lux-org/lux-datasets/blob/master/data/olympic.csv?raw=true"
)
df = pd.read_csv(url)
vis = Vis(["Height", "SportType=Ball"], df)
assert vis.get_attr_by_attr_name("Height")[0].bin_size != 0
assert vis.get_attr_by_attr_name("Record")[0].aggregation == "count"
def test_vis_set_specs(global_var):
df = pytest.olympic
vis = Vis(["Height", "SportType=Ball"], df)
vis.set_intent(["Height", "SportType=Ice"])
assert vis.get_attr_by_attr_name("SportType")[0].value == "Ice"
df.clear_intent()
def test_vis(global_var):
df = pytest.olympic
vis = Vis(["Height", "SportType=Ball"], df)
assert vis.get_attr_by_attr_name("Height")[0].bin_size != 0
assert vis.get_attr_by_attr_name("Record")[0].aggregation == "count"
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 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
def test_vis():
df = pd.read_csv("lux/data/olympic.csv")
from lux.vis.Vis import Vis
vis = Vis(["Height", "SportType=Ball"], df)
assert vis.get_attr_by_attr_name("Height")[0].bin_size != 0
assert vis.get_attr_by_attr_name("Record")[0].aggregation == 'count'
def test_vis_set_specs():
df = pd.read_csv("lux/data/olympic.csv")
from lux.vis.Vis import Vis
vis = Vis(["Height", "SportType=Ball"], df)
vis.set_intent(["Height", "SportType=Ice"])
assert vis.get_attr_by_attr_name("SportType")[0].value == "Ice"
