def compute_data_type(self, lst: LuxSQLTable):
"""
Function which the equivalent Pandas data type of each variable within the specified Lux DataFrame's SQL table.
Populates the metadata parameters of the specified Lux DataFrame.
Parameters
----------
lst: lux.LuxSQLTable
lux.LuxSQLTable object whose metadata will be calculated
Returns
-------
None
"""
data_type = {}
sql_dtypes = {}
self.get_cardinality(lst)
if "." in lst.table_name:
table_name = lst.table_name[lst.table_name.index(".") + 1 :]
else:
table_name = lst.table_name
# get the data types of the attributes in the SQL table
for attr in list(lst.columns):
datatype_query = "SELECT DATA_TYPE FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_NAME = '{}' AND COLUMN_NAME = '{}'".format(
table_name, attr
)
datatype = list(pandas.read_sql(datatype_query, lux.config.SQLconnection)["data_type"])[0]
sql_dtypes[attr] = datatype
for attr in list(lst.columns):
if str(attr).lower() in ["month", "year"]:
data_type[attr] = "temporal"
elif sql_dtypes[attr] in [
"character",
"character varying",
"boolean",
"uuid",
"text",
]:
data_type[attr] = "nominal"
elif sql_dtypes[attr] in [
"integer",
"numeric",
"decimal",
"bigint",
"real",
"smallint",
"smallserial",
"serial",
"double precision",
]:
if lst.cardinality[attr] < 13:
data_type[attr] = "nominal"
elif check_if_id_like(lst, attr):
lst._data_type[attr] = "id"
else:
data_type[attr] = "quantitative"
elif "time" in sql_dtypes[attr] or "date" in sql_dtypes[attr]:
data_type[attr] = "temporal"
lst._data_type = data_type
def compute_data_type(self, tbl: LuxSQLTable):
"""
Function which the equivalent Pandas data type of each variable within the specified Lux DataFrame's SQL table.
Populates the metadata parameters of the specified Lux DataFrame.
Parameters
----------
tbl: lux.LuxSQLTable
lux.LuxSQLTable object whose metadata will be calculated
Returns
-------
None
"""
data_type = {}
self.get_cardinality(tbl)
if "." in tbl.table_name:
table_name = tbl.table_name[tbl.table_name.index(".") + 1 :]
else:
table_name = tbl.table_name
# get the data types of the attributes in the SQL table
for attr in list(tbl.columns):
datatype_query = lux.config.query_templates['datatype_query'].format(table_name = table_name, attribute = attr)
datatype = list(pandas.read_sql(datatype_query, lux.config.SQLconnection)["data_type"])[0]
if str(attr).lower() in {"month", "year"} or "time" in datatype or "date" in datatype:
data_type[attr] = "temporal"
elif datatype in {
"character",
"character varying",
"boolean",
"uuid",
"text",
}:
data_type[attr] = "nominal"
elif datatype in {
"integer",
"numeric",
"decimal",
"bigint",
"real",
"smallint",
"smallserial",
"serial",
"double",
"double precision",
}:
if tbl.cardinality[attr] < 13:
data_type[attr] = "nominal"
elif check_if_id_like(tbl, attr):
data_type[attr] = "id"
else:
data_type[attr] = "quantitative"
tbl._data_type = data_type
def compute_dataset_metadata(self, tbl: LuxSQLTable):
"""
Function which computes the metadata required for the Lux recommendation system.
Populates the metadata parameters of the specified Lux DataFrame.
Parameters
----------
tbl: lux.LuxSQLTable
lux.LuxSQLTable object whose metadata will be calculated
Returns
-------
None
"""
if not tbl._setup_done:
self.get_SQL_attributes(tbl)
tbl._data_type = {}
#####NOTE: since we aren't expecting users to do much data processing with the SQL database, should we just keep this
##### in the initialization and do it just once
self.compute_data_type(tbl)
self.compute_stats(tbl)
