def random_categorical(ldf):
intent = [lux.Clause("?", data_type="nominal")]
vlist = VisList(intent, ldf)
for vis in vlist:
vis.score = 10
vlist.sort()
vlist = vlist.showK()
return {
"action": "bars",
"description": "Random list of Bar charts",
"collection": vlist,
}
def correlation(ldf: LuxDataFrame, ignore_transpose: bool = True):
"""
Generates bivariate visualizations that represent all pairwise relationships in the data.
Parameters
----------
ldf : LuxDataFrame
LuxDataFrame with underspecified intent.
ignore_transpose: bool
Boolean flag to ignore pairs of attributes whose transpose are already computed (i.e., {X,Y} will be ignored if {Y,X} is already computed)
Returns
-------
recommendations : Dict[str,obj]
object with a collection of visualizations that result from the Correlation action.
"""
import numpy as np
filter_specs = utils.get_filter_specs(ldf._intent)
intent = [
lux.Clause("?", data_model="measure"),
lux.Clause("?", data_model="measure"),
]
intent.extend(filter_specs)
vlist = VisList(intent, ldf)
recommendation = {
"action":
"Correlation",
"description":
"Show relationships between two <p class='highlight-descriptor'>quantitative</p> attributes.",
}
ignore_rec_flag = False
# Doesn't make sense to compute correlation if less than 4 data values
if len(ldf) < 5:
ignore_rec_flag = True
# Then use the data populated in the vis list to compute score
for vis in vlist:
measures = vis.get_attr_by_data_model("measure")
if len(measures) < 2:
raise ValueError(
f"Can not compute correlation between {[x.attribute for x in ldf.columns]} since less than 2 measure values present."
)
msr1 = measures[0].attribute
msr2 = measures[1].attribute
if ignore_transpose:
check_transpose = check_transpose_not_computed(vlist, msr1, msr2)
else:
check_transpose = True
if check_transpose:
vis.score = interestingness(vis, ldf)
else:
vis.score = -1
if ignore_rec_flag:
recommendation["collection"] = []
return recommendation
vlist.sort()
vlist = vlist.showK()
recommendation["collection"] = vlist
return recommendation
def univariate(ldf, data_type_constraint="quantitative"):
'''
Generates bar chart distributions of different attributes in the dataframe.
Parameters
----------
ldf : lux.core.frame
LuxDataFrame with underspecified intent.
data_type_constraint: str
Controls the type of distribution chart that will be rendered.
Returns
-------
recommendations : Dict[str,obj]
object with a collection of visualizations that result from the Distribution action.
'''
import numpy as np
filter_specs = utils.get_filter_specs(ldf._intent)
ignore_rec_flag = False
if (data_type_constraint == "quantitative"):
intent = [
lux.Clause("?",
data_type="quantitative",
exclude="Number of Records")
]
intent.extend(filter_specs)
recommendation = {
"action":
"Distribution",
"description":
"Show univariate histograms of <p class='highlight-descriptor'>quantitative</p> attributes."
}
if (
len(ldf) < 5
): # Doesn't make sense to generate a histogram if there is less than 5 datapoints (pre-aggregated)
ignore_rec_flag = True
elif (data_type_constraint == "nominal"):
intent = [lux.Clause("?", data_type="nominal")]
intent.extend(filter_specs)
recommendation = {
"action":
"Occurrence",
"description":
"Show frequency of occurrence for <p class='highlight-descriptor'>categorical</p> attributes."
}
elif (data_type_constraint == "temporal"):
intent = [lux.Clause("?", data_type="temporal")]
intent.extend(filter_specs)
recommendation = {
"action":
"Temporal",
"description":
"Show trends over <p class='highlight-descriptor'>time-related</p> attributes."
}
if (
len(ldf) < 3
): # Doesn't make sense to generate a line chart if there is less than 3 datapoints (pre-aggregated)
ignore_rec_flag = True
if (ignore_rec_flag):
recommendation["collection"] = []
return recommendation
vlist = VisList(intent, ldf)
for vis in vlist:
vis.score = interestingness(vis, ldf)
# vlist = vlist.topK(15) # Basic visualizations should not be capped
vlist.sort()
recommendation["collection"] = vlist
return recommendation
def univariate(ldf, *args):
"""
Generates bar chart distributions of different attributes in the dataframe.
Parameters
----------
ldf : lux.core.frame
LuxDataFrame with underspecified intent.
data_type_constraint: str
Controls the type of distribution chart that will be rendered.
Returns
-------
recommendations : Dict[str,obj]
object with a collection of visualizations that result from the Distribution action.
"""
import numpy as np
if len(args) == 0:
data_type_constraint = "quantitative"
else:
data_type_constraint = args[0][0]
filter_specs = utils.get_filter_specs(ldf._intent)
ignore_rec_flag = False
if data_type_constraint == "quantitative":
possible_attributes = [
c for c in ldf.columns if ldf.data_type[c] == "quantitative"
and ldf.cardinality[c] > 5 and c != "Number of Records"
]
intent = [lux.Clause(possible_attributes)]
intent.extend(filter_specs)
examples = ""
if len(possible_attributes) >= 1:
examples = f" (e.g., {possible_attributes[0]})"
recommendation = {
"action":
"Distribution",
"description":
"Show univariate histograms of <p class='highlight-descriptor'>quantitative</p> attributes.",
"long_description":
f"Distribution displays univariate histogram distributions of all quantitative attributes{examples}. Visualizations are ranked from most to least skewed.",
}
# Doesn't make sense to generate a histogram if there is less than 5 datapoints (pre-aggregated)
if ldf.length < 5:
ignore_rec_flag = True
elif data_type_constraint == "nominal":
possible_attributes = [
c for c in ldf.columns if ldf.data_type[c] == "nominal"
and ldf.cardinality[c] > 5 and c != "Number of Records"
]
examples = ""
if len(possible_attributes) >= 1:
examples = f" (e.g., {possible_attributes[0]})"
intent = [lux.Clause("?", data_type="nominal")]
intent.extend(filter_specs)
recommendation = {
"action":
"Occurrence",
"description":
"Show frequency of occurrence for <p class='highlight-descriptor'>categorical</p> attributes.",
"long_description":
f"Occurence displays bar charts of counts for all categorical attributes{examples}. Visualizations are ranked from most to least uneven across the bars. ",
}
elif data_type_constraint == "geographical":
possible_attributes = [
c for c in ldf.columns if ldf.data_type[c] == "geographical"
and ldf.cardinality[c] > 5 and c != "Number of Records"
]
examples = ""
if len(possible_attributes) >= 1:
examples = f" (e.g., {possible_attributes[0]})"
intent = [
lux.Clause("?", data_type="geographical"),
lux.Clause("?", data_model="measure")
]
intent.extend(filter_specs)
recommendation = {
"action":
"Geographical",
"description":
"Show choropleth maps of <p class='highlight-descriptor'>geographic</p> attributes",
"long_description":
f"Occurence displays choropleths of averages for some geographic attribute{examples}. Visualizations are ranked by diversity of the geographic attribute.",
}
elif data_type_constraint == "temporal":
intent = [lux.Clause("?", data_type="temporal")]
intent.extend(filter_specs)
recommendation = {
"action":
"Temporal",
"description":
"Show trends over <p class='highlight-descriptor'>time-related</p> attributes.",
"long_description":
"Temporal displays line charts for all attributes related to datetimes in the dataframe.",
}
# Doesn't make sense to generate a line chart if there is less than 3 datapoints (pre-aggregated)
if ldf.length < 3:
ignore_rec_flag = True
if ignore_rec_flag:
recommendation["collection"] = []
return recommendation
vlist = VisList(intent, ldf)
for vis in vlist:
vis.score = interestingness(vis, ldf)
vlist.sort()
recommendation["collection"] = vlist
return recommendation
def univariate(ldf, *args):
"""
Generates bar chart distributions of different attributes in the dataframe.
Parameters
----------
ldf : lux.core.frame
LuxDataFrame with underspecified intent.
data_type_constraint: str
Controls the type of distribution chart that will be rendered.
Returns
-------
recommendations : Dict[str,obj]
object with a collection of visualizations that result from the Distribution action.
"""
import numpy as np
if len(args) == 0:
data_type_constraint = "quantitative"
else:
data_type_constraint = args[0][0]
filter_specs = utils.get_filter_specs(ldf._intent)
ignore_rec_flag = False
if data_type_constraint == "quantitative":
possible_attributes = [
c for c in ldf.columns if ldf.data_type[c] == "quantitative"
and ldf.cardinality[c] > 5 and c != "Number of Records"
]
intent = [lux.Clause(possible_attributes)]
intent.extend(filter_specs)
recommendation = {
"action":
"Distribution",
"description":
"Show univariate histograms of <p class='highlight-descriptor'>quantitative</p> attributes.",
}
# Doesn't make sense to generate a histogram if there is less than 5 datapoints (pre-aggregated)
if len(ldf) < 5:
ignore_rec_flag = True
elif data_type_constraint == "nominal":
intent = [lux.Clause("?", data_type="nominal")]
intent.extend(filter_specs)
recommendation = {
"action":
"Occurrence",
"description":
"Show frequency of occurrence for <p class='highlight-descriptor'>categorical</p> attributes.",
}
elif data_type_constraint == "temporal":
intent = [lux.Clause("?", data_type="temporal")]
intent.extend(filter_specs)
recommendation = {
"action":
"Temporal",
"description":
"Show trends over <p class='highlight-descriptor'>time-related</p> attributes.",
}
# Doesn't make sense to generate a line chart if there is less than 3 datapoints (pre-aggregated)
if len(ldf) < 3:
ignore_rec_flag = True
if ignore_rec_flag:
recommendation["collection"] = []
return recommendation
vlist = VisList(intent, ldf)
for vis in vlist:
vis.score = interestingness(vis, ldf)
vlist.sort()
recommendation["collection"] = vlist
return recommendation