#print header
#survived0,pclass1-0,name2,sex3-1,age4-2,sibsp5-3,parch6-4,ticket7,fare8-5,cabin9,embarked10
outputs = np.matrix(data[0:, 0]).T.astype(int)
inputs = data[0:, (1, 3, 4, 5, 6, 8)]
inputs[:, 1] = lr.eapply(lambda x: int(x), data[0::,3] == "male")
def liq(x):
if x == '': return 0
else: return x
inputs = np.matrix(lr.eapply(liq, inputs))
inputs = np.matrix(inputs).T.astype(float)
w, e = lr.batchGradientDescent(inputs, outputs, np.matrix([[0] * 7]).T, 0.5, -0.01, 100)
print e[0:4], '...'
print e[-5:-1]
"""s = 0.0
for m in range(outputs.shape[0]):
s = s + np.abs(lr.calcLogReg(w, inputs[:, m], 0.5) - outputs[m])
print float(s) / outputs.shape[0]"""
csv_file_objectT = csv.reader(open('test.csv', 'rb')) #Load in the csv file
headerT = csv_file_objectT.next() #Skip the fist line as it is a header
import numpy as np from random import seed, gauss import LogisticRegression as lr i = np.matrix([ [1,1], [1,2], [1,3], [2,1], [2,2], [2,3], [3,1], [3,2], [3,3] ]).T o = np.matrix([[0, 0, 1, 0, 1, 1, 1, 1, 1]]).T w = lr.batchGradientDescent( lr.LogisticDerivative, i, o, np.matrix([[0], [0], [0]]), 0.5, -0.5, 70) print w for i in xrange(3): for v in xrange(3): print i, v, lr.calcLogReg(w, np.matrix([i+1,v+1]).T, 0.5) print lr.calcLogReg(w, np.matrix([3,0.85352157]).T, 0.5)
