From c6f86bdb722aac53bb39b0d78d2b538b6f07a692 Mon Sep 17 00:00:00 2001
From: Camil Staps
Date: Sat, 12 Dec 2015 16:47:44 +0000
Subject: Assignment 5

---
 Assignment 5/packages/apriori        | Bin 0 -> 348990 bytes
 Assignment 5/packages/run_apriori.py | 102 +++++++++++++++++++++++++++++++++++
 2 files changed, 102 insertions(+)
 create mode 100755 Assignment 5/packages/apriori
 create mode 100644 Assignment 5/packages/run_apriori.py

(limited to 'Assignment 5/packages')

diff --git a/Assignment 5/packages/apriori b/Assignment 5/packages/apriori
new file mode 100755
index 0000000..97c006e
Binary files /dev/null and b/Assignment 5/packages/apriori differ
diff --git a/Assignment 5/packages/run_apriori.py b/Assignment 5/packages/run_apriori.py
new file mode 100644
index 0000000..d2affac
--- /dev/null
+++ b/Assignment 5/packages/run_apriori.py	
@@ -0,0 +1,102 @@
+import numpy as np
+from subprocess import call
+import re
+import os
+
+'''
+ run_apriory.py 
+ version: 0.2
+ last change: 26/11/2014, by Wout Megchelenbrink
+ fixed lots of issues
+'''
+
+'''
+ Adapted by Camil Staps 2015/12/12
+ 
+  * Make it a function
+  * Allow for calling it from another directory
+'''
+
+def run_apriori(filename, minSup, minConf, maxRule):
+    from sys import exit, platform as _platform
+    
+    # Run Apriori Algorithm
+    print('Mining for frequent itemsets by the Apriori algorithm')
+    
+    if _platform == 'linux' or _platform == 'linux2':
+        cmd = '"' + os.path.dirname(os.path.realpath(__file__)) + '/apriori"'
+    elif _platform == 'darwin':
+        cmd = '"' + os.path.dirname(os.path.realpath(__file__)) + '/aprioriMAC"'
+    elif _platform == 'win32':
+        cmd = '"' + os.path.dirname(os.path.realpath(__file__)) + '/apriori.exe"'
+        
+    status1 = call(cmd + " -s{0} -v\"[Sup. %3S]\" {1} apriori_temp1.txt".format(minSup, filename), shell=True)
+    
+    if status1!=0:
+        print('An error occured while calling apriori, a likely cause is that minSup was set to high such that no frequent itemsets were generated or spaces are included in the path to the apriori files.')
+        exit()
+    if minConf>0:
+        print('Mining for associations by the Apriori algorithm')
+        
+        status2 = call(cmd + ' -tr -f"," -o -n{0} -c{1} -s{2} -v"[Conf. %3C,Sup. %3S]" {3} apriori_temp2.txt'.format(maxRule, minConf, minSup, filename), shell=True)
+            
+        if status2!=0:
+            print('An error occured while calling apriori')
+            exit()
+    print('Apriori analysis done, extracting results')
+    
+    
+    # Extract information from stored files apriori_temp1.txt and apriori_temp2.txt
+    f = open('apriori_temp1.txt','r')
+    lines = f.readlines()
+    f.close()
+    # Extract Frequent Itemsets
+    FrequentItemsets = ['']*len(lines)
+    sup = np.zeros((len(lines),1))
+    
+    for i,line in enumerate(lines):
+        FrequentItemsets[i] = line[0:-1]
+        tmpSupport = re.findall(' \d*[.]\d*', line)
+        if len(tmpSupport) == 0:
+            tmpSupport = re.findall(' \d*', line)
+        
+        sup[i] = tmpSupport[0]
+    os.remove('apriori_temp1.txt')
+        
+    # Read the file
+    f = open('apriori_temp2.txt','r')
+    lines = f.readlines()
+    f.close()
+    # Extract Association rules
+    AssocRules = ['']*len(lines)
+    conf = np.zeros((len(lines),1))
+    for i,line in enumerate(lines):
+        AssocRules[i] = line[0:-1]
+        
+        tmpConf = re.findall(' \d*[.]\d*,', line)    
+        if len(tmpConf) == 0:
+            tmpConf = re.findall(' \d*,', line)    
+        
+        conf[i] = tmpConf[0][1:-1]
+    os.remove('apriori_temp2.txt')    
+    
+    # sort (FrequentItemsets by support value, AssocRules by confidence value)
+    AssocRulesSorted = [AssocRules[item] for item in np.argsort(conf,axis=0).ravel()]
+    AssocRulesSorted.reverse()
+    FrequentItemsetsSorted = [FrequentItemsets[item] for item in np.argsort(sup,axis=0).ravel()]
+    FrequentItemsetsSorted.reverse()
+    
+    return FrequentItemsetsSorted, AssocRulesSorted
+    
+def apriori_print(FrequentItemsetsSorted, AssocRulesSorted):
+    # Print the results
+    import time; time.sleep(.5)
+    print('\n')
+    print('RESULTS:\n')
+    print('Frequent itemsets:')
+    for i,item in enumerate(FrequentItemsetsSorted):
+        print('Item: {0}'.format(item))
+    print('\n')
+    print('Association rules:')
+    for i,item in enumerate(AssocRulesSorted):
+        print('Rule: {0}'.format(item))    
-- 
cgit v1.2.3