From 80ad02982caef21188ad587382bf7e0e12f09232 Mon Sep 17 00:00:00 2001
From: wenhuanhuan <xl123456>
Date: Fri, 3 Mar 2017 15:21:38 +0800
Subject: [PATCH] =?UTF-8?q?11=E3=80=81Aoriori?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 docs/11.使用Apriori算法进行关联分析.md       |  2 +-
 src/python/12.FrequentPattemTree/apriori.py  | 12 ++++++++++++
 src/python/12.FrequentPattemTree/fpGrowth.py | 19 +++++++++++++++++++
 src/python/12.FrequentPattemTree/test.py     |  5 +++++
 4 files changed, 37 insertions(+), 1 deletion(-)
 create mode 100644 src/python/12.FrequentPattemTree/apriori.py
 create mode 100644 src/python/12.FrequentPattemTree/fpGrowth.py
 create mode 100644 src/python/12.FrequentPattemTree/test.py

diff --git a/docs/11.使用Apriori算法进行关联分析.md b/docs/11.使用Apriori算法进行关联分析.md
index ad85b87a..71adb177 100644
--- a/docs/11.使用Apriori算法进行关联分析.md
+++ b/docs/11.使用Apriori算法进行关联分析.md
@@ -6,4 +6,4 @@
 2. 项集的支持度(support)：数据集中包含该项集的记录所占的比例
 3. 置信度（confidence)：置信度({A}->{B}) = 支持度{A,B}/支持度{A} 
 
-Apriori原理：如果某个项集是频繁的，那么它的所有子集也是频繁的，反之，一个项集是非频繁的，那么它的所有超集也是非频繁的
\ No newline at end of file
+Apriori原理：如果某个项集是频繁的，那么它的所有子集也是频繁的，反之，一个项集是非频繁的，那么它的所有超集也是非频繁的。
\ No newline at end of file
diff --git a/src/python/12.FrequentPattemTree/apriori.py b/src/python/12.FrequentPattemTree/apriori.py
new file mode 100644
index 00000000..e172b575
--- /dev/null
+++ b/src/python/12.FrequentPattemTree/apriori.py
@@ -0,0 +1,12 @@
+def loadDataSet():
+    return [[1,3,4],[2,3,5],[1,2,3,5],[2,5]]
+def createC1(dataSet):
+    c1=[]
+    for transaction in dataSet:
+        for item in transaction:
+            if not [item] in c1:
+                c1.append([item])
+    c1.sort()
+    return map(frozenset,c1)
+def scanD(D,ck,minSupport):
+    ssCnt = {}
\ No newline at end of file
diff --git a/src/python/12.FrequentPattemTree/fpGrowth.py b/src/python/12.FrequentPattemTree/fpGrowth.py
new file mode 100644
index 00000000..5e3898cc
--- /dev/null
+++ b/src/python/12.FrequentPattemTree/fpGrowth.py
@@ -0,0 +1,19 @@
+class treeNode:
+    def __init__(self,nameValue,numOccur,parentNode):
+        self.name = nameValue
+        self.count = numOccur
+        self.nodeLink = None
+        self.parent = parentNode
+        self.children = {}
+    def inc(self,numOccur):
+        self.count += numOccur
+    def disp(self,ind=1):
+        print(' '*ind,self.name,' ',self.count)
+        for child in self.children.values():
+            child.disp(ind+1)
+
+    if __name__ == "__main__":
+        import fpGrowth
+        rootNode = fpGrowth.treeNode('pyramid',9,None)
+        rootNode.children['eye']=fpGrowth.treeNode('eye',13,None)
+        rootNode.disp()
\ No newline at end of file
diff --git a/src/python/12.FrequentPattemTree/test.py b/src/python/12.FrequentPattemTree/test.py
new file mode 100644
index 00000000..8702723e
--- /dev/null
+++ b/src/python/12.FrequentPattemTree/test.py
@@ -0,0 +1,5 @@
+class Test:
+    if __name__ == "__main__":
+        fza=frozenset(['a','bc'])
+        adict={fza:1,'b':2}
+        print(adict)
\ No newline at end of file