Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

bug fix and leverage update #405

Merged
merged 2 commits into from
May 2, 2024
Merged

bug fix and leverage update #405

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2165f4b
bug fix and leverage update
Tarun-Sreepada May 2, 2024
2a34f92
Merge branch 'main' into main
udayRage May 2, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 6 additions & 4 deletions PAMI/AssociationRules/basic/confidence.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,9 +179,12 @@ def _readPatterns(self):
# print("Using column: ", col, "for support")
for i in range(len(pattern)):
# if pattern[i] != tuple(): exit()
if pattern[i] != tuple():
raise ValueError("Pattern should be a tuple. PAMI is going through a major revision. Please raise an issue in the github repository regarding this error and provide information regarding input and algorithm.\
In the meanwhile try saving the patterns to a file using (alg).save() and use the file as input. If that doesn't work, please raise an issue in the github repository.")
if type(pattern[i]) != tuple:
raise ValueError("Pattern should be a tuple. PAMI is going through a major revision.\
Please raise an issue in the github repository regarding this error and provide information regarding input and algorithm.\
In the meanwhile try saving the patterns to a file using (alg).save() and use the file as input. \
If that doesn't work, please raise an issue in the github repository.\
Got pattern: ", pattern[i], "at index: ", i, "in the dataframe, type: ", type(pattern[i]))
s = tuple(sorted(pattern[i]))
self._frequentPatterns[s] = support[i]
if isinstance(self._iFile, str):
Expand All @@ -192,7 +195,6 @@ def _readPatterns(self):
line = line.split(':')
s = line[0].split(self._sep)
s = tuple(sorted(s))

self._frequentPatterns[s] = int(line[1])
else:
try:
Expand Down
28 changes: 15 additions & 13 deletions PAMI/AssociationRules/basic/leverage.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
#
# import PAMI.AssociationRules.basic import ARWithleverage as alg
#
# obj = alg.ARWithleverage(iFile, minConf)
# obj = alg.ARWithleverage(iFile, minLev)
#
# obj.mine()
#
Expand Down Expand Up @@ -70,7 +70,7 @@ class leverage:

:**Parameters**: - **iFile** (*str*) -- *Name of the Input file to mine complete set of association rules*
- **oFile** (*str*) -- *Name of the Output file to write association rules*
- **minConf** (*float*) -- *Minimum leverage to mine all the satisfying association rules. The user can specify the minConf in float between the range of 0 to 1.*
- **minLev** (*float*) -- *Minimum leverage to mine all the satisfying association rules. The user can specify the minLev in float between the range of 0 to 1.*
- **sep** (*str*) -- *This variable is used to distinguish items from one another in a transaction. The default seperator is tab space. However, the users can override their default separator.*

:**Attributes**: - **startTime** (*float*) -- *To record the start time of the mining process.*
Expand All @@ -89,13 +89,13 @@ class leverage:

Format:

(.venv) $ python3 ARWithleverage.py <inputFile> <outputFile> <minConf> <sep>
(.venv) $ python3 ARWithleverage.py <inputFile> <outputFile> <minLev> <sep>

Example Usage:

(.venv) $ python3 ARWithleverage.py sampleDB.txt patterns.txt 0.5 ' '

.. note:: minConf can be specified in a value between 0 and 1.
.. note:: minLev can be specified in a value between 0 and 1.


**Calling from a python program**
Expand All @@ -104,7 +104,7 @@ class leverage:

import PAMI.AssociationRules.basic import ARWithleverage as alg

obj = alg.ARWithleverage(iFile, minConf)
obj = alg.ARWithleverage(iFile, minLev)

obj.mine()

Expand Down Expand Up @@ -146,19 +146,20 @@ class leverage:
_memoryRSS = float()
_frequentPatterns = {}

def __init__(self, iFile, minConf, sep):
def __init__(self, iFile, minLev, sep, maxTS):
"""
:param iFile: input file name or path
:type iFile: str
:param minConf: minimum leverage
:type minConf: float
:param minLev: minimum leverage
:type minLev: float
:param sep: Delimiter of input file
:type sep: str
"""
self._iFile = iFile
self._minLev = minConf
self._minLev = minLev
self._finalPatterns = {}
self._sep = sep
self._maxTS = maxTS

def _readPatterns(self):
"""
Expand All @@ -179,7 +180,7 @@ def _readPatterns(self):
# print("Using column: ", col, "for support")
for i in range(len(pattern)):
# if pattern[i] != tuple(): exit()
if pattern[i] != tuple():
if type(pattern[i]) != tuple:
raise ValueError("Pattern should be a tuple. PAMI is going through a major revision. Please raise an issue in the github repository regarding this error and provide information regarding input and algorithm.\
In the meanwhile try saving the patterns to a file using (alg).save() and use the file as input. If that doesn't work, please raise an issue in the github repository.")
s = tuple(sorted(pattern[i]))
Expand All @@ -203,7 +204,7 @@ def _readPatterns(self):
s = line[0].split(self._sep)
s = [x.strip() for x in s]
s = tuple(sorted(s))
self._frequentPatterns[s] = int(line[1])
self._frequentPatterns[s] = int(line[1]) / self._maxTS
except IOError:
print("File Not Found")
quit()
Expand Down Expand Up @@ -234,8 +235,9 @@ def mine(self):
for c in combinations(keys[i], r=idx):
antecedent = c
# consequent = keys[i] - antecedent
# conf = key / self._frequentPatterns[antecedent]
lev = key - (self._frequentPatterns[antecedent] * self._frequentPatterns[keys[i]])
consequent = tuple(sorted([x for x in keys[i] if x not in antecedent]))
# Lev = key / self._frequentPatterns[antecedent]
lev = key - self._frequentPatterns[antecedent] * self._frequentPatterns[consequent]
if lev >= self._minLev:
self._finalPatterns[antecedent + tuple(['->']) + keys[i]] = lev

Expand Down
2 changes: 1 addition & 1 deletion PAMI/AssociationRules/basic/lift.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,7 +179,7 @@ def _readPatterns(self):
# print("Using column: ", col, "for support")
for i in range(len(pattern)):
# if pattern[i] != tuple(): exit()
if pattern[i] != tuple():
if type(pattern[i]) != tuple:
raise ValueError("Pattern should be a tuple. PAMI is going through a major revision. Please raise an issue in the github repository regarding this error and provide information regarding input and algorithm.\
In the meanwhile try saving the patterns to a file using (alg).save() and use the file as input. If that doesn't work, please raise an issue in the github repository.")
s = tuple(sorted(pattern[i]))
Expand Down