def linearRegression(inputFiles, i = 1, quarters = 4, dataReduction = False):
k = 1
regr = linear_model.LinearRegression(fit_intercept=False)
for File in inputFiles:
data = tools.readData(File)
data [np.argsort(data[:, 0])]
limit = quarters * (len(data)/4)
Z = tools.createZ(data[:, 0], i)
theta = regress(Z, data[:, 1])
Y_hat = YHat(theta, data[:, 0])
plt.subplot(2,2,k)
plt.scatter(data[:, 0], data[:, 1], color="green")
X = data[:, 0]
plt.plot(X, Y_hat, color="red", lw=3, label = "Original Method")
k = k + 1
if (dataReduction == False):
regr.fit(Z, data[:, 1])
#plt.plot(X, regr.predict(Z), color="blue", lw="1", label ="Python functions")
else:
Z = tools.createZ(data[0:limit, 0], i)
theta = regress(Z, data[0:limit, 1])
Y_hat_small = YHat(theta, data[:, 0])
plt.plot(X, Y_hat_small, color="blue", lw = 1, label = "Reduced Data Set")
plt.title("Reduced Data %sn/4" % quarters)
plt.suptitle("Single Variable Degree: %s" % i)
plt.show()
def linearRegressionKFold(inputFiles, i=1):
print "\nSingle Variable, Degree: %s" % i
print "###########################"
for File in inputFiles:
print "==========================="
print "Data Set %s" % File
data = tools.readData(File)
X = data[:, 0]
Y = data[:, 1]
kf = KFold(len(data), n_folds=10, shuffle=True)
TrainError = 0
TestError = 0
for train, test in kf:
Z = tools.createZ(X[train], i)
theta = regress(Z, Y[train])
Y_hat = YHat(theta, X[train])
Y_hat_test = YHat(theta, X[test])
TrainError = TrainError + tools.findError(theta, Y[train])
TestError = TestError + tools.findError(theta, Y[test])
TestError = TestError / len(kf)
TrainError = TrainError / len(kf)
print "---------------------------"
print "Test Error: %s" % TestError
print "Train Error: %s" % TrainError
py_linearRegression(X, Y)
return TestError
