LogicalRegression

LogisticRegression/.project

@@ -0,0 +1,17 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<projectDescription>
+	<name>LogisticRegression</name>
+	<comment></comment>
+	<projects>
+	</projects>
+	<buildSpec>
+		<buildCommand>
+			<name>org.python.pydev.PyDevBuilder</name>
+			<arguments>
+			</arguments>
+		</buildCommand>
+	</buildSpec>
+	<natures>
+		<nature>org.python.pydev.pythonNature</nature>
+	</natures>
+</projectDescription>

LogisticRegression/.pydevproject

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<?eclipse-pydev version="1.0"?>
+
+<pydev_project>
+<pydev_pathproperty name="org.python.pydev.PROJECT_SOURCE_PATH">
+<path>/LogisticRegression</path>
+</pydev_pathproperty>
+<pydev_property name="org.python.pydev.PYTHON_PROJECT_VERSION">python 2.7</pydev_property>
+<pydev_property name="org.python.pydev.PYTHON_PROJECT_INTERPRETER">Default</pydev_property>
+</pydev_project>

LogisticRegression/src/LR.py

@@ -0,0 +1,63 @@
+import matplotlib.pyplot as plt
+from numpy import *
+
+
+def loadDataSet():
+    dataMat = []; labelMat = []
+    fr = open('/Users/hakuri/Desktop/testSet.txt')
+    for line in fr.readlines():
+        lineArr = line.strip().split()
+        dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])])
+        labelMat.append(int(lineArr[2]))
+    return dataMat,labelMat
+
+def sigmoid(inX):
+    return 1.0/(1+exp(-inX))
+
+def gradAscent(dataMatIn, classLabels):
+    dataMatrix = mat(dataMatIn)             #convert to NumPy matrix
+    labelMat = mat(classLabels).transpose() #convert to NumPy matrix
+
+    m,n = shape(dataMatrix)
+    alpha = 0.001
+    maxCycles = 500
+    weights = ones((n,1))
+
+    for k in range(maxCycles):              #heavy on matrix operations
+        h = sigmoid(dataMatrix*weights)     #matrix mult
+        error = (labelMat - h)              #vector subtraction
+        weights = weights + alpha * dataMatrix.transpose()* error #matrix mult
+    return weights
+
+def GetResult():
+    dataMat,labelMat=loadDataSet()
+    weights=gradAscent(dataMat,labelMat)
+    print weights
+    plotBestFit(weights)
+
+
+def plotBestFit(weights):
+
+    dataMat,labelMat=loadDataSet()
+    dataArr = array(dataMat)
+    n = shape(dataArr)[0] 
+    xcord1 = []; ycord1 = []
+    xcord2 = []; ycord2 = []
+    for i in range(n):
+        if int(labelMat[i])== 1:
+            xcord1.append(dataArr[i,1]); ycord1.append(dataArr[i,2])
+        else:
+            xcord2.append(dataArr[i,1]); ycord2.append(dataArr[i,2])
+    fig = plt.figure()
+    ax = fig.add_subplot(111)
+    ax.scatter(xcord1, ycord1, s=30, c='red', marker='s')
+    ax.scatter(xcord2, ycord2, s=30, c='green')
+    x = arange(-3.0, 3.0, 0.1)   
+    y=(0.48*x+4.12414)/(0.616)
+#     y = (-weights[0]-weights[1]*x)/weights[2]    
+    ax.plot(x,y)
+    plt.xlabel('X1'); plt.ylabel('X2');
+    plt.show()    
+
+if __name__=='__main__':
+    GetResult()