def test_dateformatter():
ldf = pd.read_csv("lux/data/car.csv")
# change pandas dtype for the column "Year" to datetype
ldf["Year"] = pd.to_datetime(ldf["Year"], format="%Y")
timestamp = np.datetime64("2019-08-26")
ldf.maintain_metadata()
assert date_utils.date_formatter(timestamp, ldf) == "2019"
ldf["Year"][0] = np.datetime64("1970-03-01") # make month non unique
assert date_utils.date_formatter(timestamp, ldf) == "2019-8"
ldf["Year"][0] = np.datetime64("1970-03-03") # make day non unique
assert date_utils.date_formatter(timestamp, ldf) == "2019-8-26"
def test_dateformatter():
ldf = pd.read_csv("lux/data/car.csv")
ldf["Year"] = pd.to_datetime(
ldf["Year"],
format='%Y') # change pandas dtype for the column "Year" to datetype
timestamp = np.datetime64('2019-08-26')
assert (date_utils.date_formatter(timestamp, ldf) == '2019')
ldf["Year"][0] = np.datetime64('1970-03-01') # make month non unique
assert (date_utils.date_formatter(timestamp, ldf) == '2019-8')
ldf["Year"][0] = np.datetime64('1970-03-03') # make day non unique
assert (date_utils.date_formatter(timestamp, ldf) == '2019-8-26')
def populate_data_type_model(ldf, vlist):
"""
Given a underspecified Clause, populate the data_type and data_model information accordingly
Parameters
----------
ldf : lux.core.frame
LuxDataFrame with underspecified intent
vis_collection : list[lux.vis.Vis]
List of lux.Vis objects that will have their underspecified Clause details filled out.
"""
# TODO: copy might not be neccesary
from lux.utils.date_utils import is_datetime_string
data_model_lookup = lux.config.executor.compute_data_model_lookup(
ldf.data_type)
for vis in vlist:
for clause in vis._inferred_intent:
if clause.description == "?":
clause.description = ""
# TODO: Note that "and not is_datetime_string(clause.attribute))" is a temporary hack and breaks the `test_row_column_group` example
# and not is_datetime_string(clause.attribute):
if clause.attribute != "" and clause.attribute != "Record":
if clause.data_type == "":
clause.data_type = ldf.data_type[clause.attribute]
if clause.data_type == "id":
clause.data_type = "nominal"
if clause.data_type == "geographical":
clause.data_type = "nominal"
if clause.data_model == "":
clause.data_model = data_model_lookup[clause.attribute]
if clause.value != "":
# If user provided title for Vis, then don't override.
if vis.title == "":
if isinstance(clause.value, np.datetime64):
chart_title = date_utils.date_formatter(
clause.value, ldf)
else:
chart_title = clause.value
vis.title = f"{clause.attribute} {clause.filter_op} {chart_title}"
vis._ndim = 0
vis._nmsr = 0
for clause in vis._inferred_intent:
if clause.value == "":
if clause.data_model == "dimension":
vis._ndim += 1
elif clause.data_model == "measure" and clause.attribute != "Record":
vis._nmsr += 1
def populate_data_type_model(ldf, vis_collection) -> VisList:
"""
Given a underspecified Clause, populate the data_type and data_model information accordingly
Parameters
----------
ldf : lux.core.frame
LuxDataFrame with underspecified intent
vis_collection : list[lux.vis.Vis]
List of lux.Vis objects that will have their underspecified Clause details filled out.
Returns
-------
vlist: VisList
vis list with compiled lux.Vis objects.
"""
# TODO: copy might not be neccesary
from lux.utils.date_utils import is_datetime_string
import copy
vlist = copy.deepcopy(vis_collection) # Preserve the original dobj
for vis in vlist:
for clause in vis._inferred_intent:
if clause.description == "?":
clause.description = ""
# TODO: Note that "and not is_datetime_string(clause.attribute))" is a temporary hack and breaks the `test_row_column_group` example
if (clause.attribute != "" and clause.attribute != "Record"
): # and not is_datetime_string(clause.attribute):
if clause.data_type == "":
clause.data_type = ldf.data_type_lookup[
clause.attribute]
if clause.data_type == "id":
clause.data_type = "nominal"
if clause.data_model == "":
clause.data_model = ldf.data_model_lookup[
clause.attribute]
if clause.value != "":
if (
vis.title == ""
): # If user provided title for Vis, then don't override.
if isinstance(clause.value, np.datetime64):
chart_title = date_utils.date_formatter(
clause.value, ldf)
else:
chart_title = clause.value
vis.title = (
f"{clause.attribute} {clause.filter_op} {chart_title}"
)
return vlist
def populate_data_type_model(ldf, vis_collection) -> VisList:
"""
Given a underspecified Clause, populate the data_type and data_model information accordingly
Parameters
----------
ldf : lux.luxDataFrame.LuxDataFrame
LuxDataFrame with underspecified intent
vis_collection : list[lux.vis.Vis]
List of lux.Vis objects that will have their underspecified Clause details filled out.
Returns
-------
vc: VisList
vis list with compiled lux.Vis objects.
"""
# TODO: copy might not be neccesary
import copy
vc = copy.deepcopy(vis_collection) # Preserve the original dobj
for vis in vc:
for clause in vis._inferred_intent:
if (clause.description == "?"):
clause.description = ""
if (clause.attribute != "" and clause.attribute != "Record"):
# if (clause.data_type == ""):
clause.data_type = ldf.data_type_lookup[clause.attribute]
# if (clause.data_model == ""):
clause.data_model = ldf.data_model_lookup[clause.attribute]
if (clause.value != ""):
if (
vis.title == ""
): #If user provided title for Vis, then don't override.
if (isinstance(clause.value, np.datetime64)):
chart_title = date_utils.date_formatter(
clause.value, ldf)
else:
chart_title = clause.value
vis.title = f"{clause.attribute} {clause.filter_op} {chart_title}"
return vc
