def predict(self,
idadf,
outtable=None,
transaction_id=None,
item_id=None,
type="rules",
limit=1,
sort=None):
"""
Apply the rules and patterns of an association rules model to other
transactions. You can apply all rules or only specific rules according
to specified criteria.
Parameters
----------
idadf : IdaDataFrame
IdaDataFrame to be used as input.
outtable : str, optional
The name of the output table in which the mapping between the input
sequences and the associated rules or patterns is written. If the
parameter corresponds to an existing table in the database, it is
replaced.
transaction_id : str, optional
The column of the input table that identifies the transaction ID.
By default, this is the same tid column that is specified in the
stored procedure to build the model.
item_id : str, optional
The column of the input table that identifies an item of the
transaction. By default, this is the same item column that is
specified in the stored procedure to build the model.
type : str, optional, default : "rules"
The type of information that is written in the output table. The
following values are possible: ‘rules’ and ‘patterns’.
limit : int, optional, >=1, default: 1
The maximum number of rules or patterns that is written in the
output table for each input sequence.
sort : str or list, optional
A list of keywords that indicates the order in which the rules or
patterns are written in the output table. The order of the list is
descending. The items are separated by semicolons. The following
values are possible: ‘support’, ‘confidence’, ‘lift’, and ‘length’.
The ‘confidence’ value can only be specified if the type parameter
is ‘rules’. If the type parameter is ‘rules’, the default is:
support;confidence;length. If the type parameter is ‘patterns’,
the default is: support;lift;length.
Notes
-----
When "type" is set to "rules", it looks like nothing is returned.
"""
if not isinstance(idadf, ibmdbpy.IdaDataFrame):
raise TypeError("Argument should be an IdaDataFrame")
if sort is not None:
sort = ';'.join(sort)
if transaction_id is None:
transaction_id = self.transaction_id
if item_id is None:
item_id = self.item_id
# Check the ID
if transaction_id not in idadf.columns:
raise ValueError("Transaction id column" + transaction_id +
" is not available in IdaDataFrame.")
if self._idadb is None:
raise IdaAssociationRulesError(
"No Association rules model was trained before.")
# The version where we don't replace the outtable if it exists but raise an exception
#if outtable is not None:
# if idadf._idadb.exists_table(outtable):
# raise ValueError("Table "+ outtable +" already exists.")
#else:
# outtable = idadf._idadb._get_valid_modelname('PREDICT_ASSOCRULES_')
if self.outtable is None:
self.outtable = idadf._idadb._get_valid_tablename('NAIVEBAYES_')
else:
self.outtable = ibmdbpy.utils.check_tablename(self.outtable)
if idadf._idadb.exists_table(self.outtable):
idadf._idadb.drop_table(self.outtable)
self.outtable = outtable
self.type = type
self.limit = limit
self.sort = sort
# Create a temporay view
idadf.internal_state._create_view()
tmp_view_name = idadf.internal_state.current_state
if "." in tmp_view_name:
tmp_view_name = tmp_view_name.split('.')[-1]
try:
idadf._idadb._call_stored_procedure("IDAX.PREDICT_ASSOCRULES ",
model=self.modelname,
intable=tmp_view_name,
outtable=outtable,
tid=transaction_id,
item=item_id,
type=type,
limit=limit,
sort=sort)
except:
raise
finally:
idadf.internal_state._delete_view()
idadf._cursor.commit()
self.labels_ = ibmdbpy.IdaDataFrame(idadf._idadb, outtable)
return self.labels_
def _retrieve_AssociationRules_Model(self, modelname, verbose=False):
"""
Retrieve information about the model to print the results. The
Association Rules IDAX function stores its result in 4 tables:
* <MODELNAME>_ASSOCPATTERNS
* <MODELNAME>_ASSOCPATTERNS_STATISTICS
* <MODELNAME>_ASSOCRULES
* <MODELNAME>_ITEMS
Parameters
----------
modelname : str
The name of the model that is retrieved.
verbose : bol, default: False
Verbosity mode.
Notes
-----
Needs better formatting instead of printing the tables
"""
modelname = ibmdbpy.utils.check_tablename(modelname)
if self._idadb is None:
raise IdaAssociationRulesError(
"No Association rules model was trained before.")
assocpatterns = self._idadb.ida_query('SELECT * FROM "' +
self._idadb.current_schema +
'"."' + modelname +
'_ASSOCPATTERNS"')
assocpatterns.columns = [x.upper() for x in assocpatterns.columns]
assocpatterns_stats = self._idadb.ida_query(
'SELECT * FROM "' + self._idadb.current_schema + '"."' +
modelname + '_ASSOCPATTERNS_STATISTICS"')
assocpatterns_stats.columns = [
x.upper() for x in assocpatterns_stats.columns
]
assocrules = self._idadb.ida_query('SELECT * FROM "' +
self._idadb.current_schema + '"."' +
modelname + '_ASSOCRULES"')
assocrules.columns = [x.upper() for x in assocrules.columns]
items = self._idadb.ida_query('SELECT * FROM "' +
self._idadb.current_schema + '"."' +
modelname + '_ITEMS"')
items.columns = [x.upper() for x in items.columns]
if verbose is True:
print("assocpatterns")
print(assocpatterns)
print("assocpatterns_stats")
print(assocpatterns_stats)
print("assocrules")
print(assocrules)
print("items")
print(items)
return
def _retrieve_AssociationRules_Model(self, modelname, verbose=False):
"""
Retrieve information about the model to print the results. The
Association Rules IDAX function stores its result in 4 tables:
* <MODELNAME>_ASSOCPATTERNS
* <MODELNAME>_ASSOCPATTERNS_STATISTICS
* <MODELNAME>_ASSOCRULES
* <MODELNAME>_ITEMS
Parameters
----------
modelname : str
The name of the model that is retrieved.
verbose : bool, default: False
Verbosity mode.
Notes
-----
Needs better formatting instead of printing the tables
"""
modelname = ibmdbpy.utils.check_tablename(modelname)
if self._idadb is None:
raise IdaAssociationRulesError(
"No Association rules model was trained before.")
# Note: The name of the columns in hardcoded, this is done so as a
# workaround for some bug in a specific ODBC linux driver.
# In case the implementation of the IDA method changes, this may break
# But still would not be difficult to fix
assocpatterns = self._idadb.ida_query('SELECT * FROM "' +
self._idadb.current_schema +
'"."' + modelname +
'_ASSOCPATTERNS"')
assocpatterns.columns = ["ITEMSETID", "ITEMID"]
assocpatterns.columns = [x.upper() for x in assocpatterns.columns]
assocpatterns_stats = self._idadb.ida_query(
'SELECT * FROM "' + self._idadb.current_schema + '"."' +
modelname + '_ASSOCPATTERNS_STATISTICS"')
assocpatterns_stats.columns = [
"ITEMSETID", "LENGTH", "COUNT", "SUPPORT", "LIFT", "PRUNED"
]
assocpatterns_stats.columns = [
x.upper() for x in assocpatterns_stats.columns
]
assocrules = self._idadb.ida_query('SELECT * FROM "' +
self._idadb.current_schema + '"."' +
modelname + '_ASSOCRULES"')
assocrules.columns = [
"RULEID", "ITEMSETID", "BODYID", "HEADID", "CONFIDENCE", "PRUNED"
]
assocrules.columns = [x.upper() for x in assocrules.columns]
items = self._idadb.ida_query('SELECT * FROM "' +
self._idadb.current_schema + '"."' +
modelname + '_ITEMS"')
items.columns = ["ITEMID", "ITEM", "ITEMNAME", "COUNT", "SUPPORT"]
items.columns = [x.upper() for x in items.columns]
if verbose is True:
print("assocpatterns")
print(assocpatterns)
print(" ")
print("assocpatterns_stats")
print(assocpatterns_stats)
print(" ")
print("assocrules")
print(assocrules)
print(" ")
print("items")
print(items)
print(" ")
return