def permutation_Test_LR(Y, f):
Y = Y.reshape((len(Y), ))
loo = cross_validation.LeaveOneOut(len(Y))
errors = []
for train_idx, test_idx in loo:
f_train, f_test = f[train_idx], f[test_idx]
Y_train, Y_test = Y[train_idx], Y[test_idx]
r = linearRegression(f_train, Y_train)
y = r.predict(f_test)
errors.append(np.abs(Y_test - y))
mae = np.mean(errors)
mre = mae / Y.mean()
return mae, mre
def permutation_Test_LR(Y, f):
Y = Y.reshape((len(Y),))
loo = cross_validation.LeaveOneOut(len(Y))
errors = []
for train_idx, test_idx in loo:
f_train, f_test = f[train_idx], f[test_idx]
Y_train, Y_test = Y[train_idx], Y[test_idx]
r = linearRegression(f_train, Y_train)
y = r.predict(f_test)
errors.append(np.abs(Y_test - y))
mae = np.mean(errors)
mre = mae / Y.mean()
return mae, mre
def LR_training_python(lrf, Y, verboseoutput):
Y = Y.reshape((len(Y), ))
loo = cross_validation.LeaveOneOut(len(Y))
mae2 = 0
errors2 = []
for train_idx, test_idx in loo:
f_train, f_test = lrf[train_idx], lrf[test_idx]
Y_train, Y_test = Y[train_idx], Y[test_idx]
if not np.any(np.isnan(f_train)) and np.all(np.isfinite(f_train)):
r2 = linearRegression(f_train, Y_train)
y2 = r2.predict(f_test)
errors2.append(np.abs(Y_test - y2))
if verboseoutput:
print Y_test[0], y2[0]
else:
print 'nan or infinite'
pass
mae2 = np.mean(errors2)
var2 = np.sqrt(np.var(errors2))
mre2 = mae2 / Y.mean()
return mae2, var2, mre2
def LR_training_python(lrf, Y, verboseoutput):
Y = Y.reshape((len(Y),))
loo = cross_validation.LeaveOneOut(len(Y))
mae2 = 0
errors2 = []
for train_idx, test_idx in loo:
f_train, f_test = lrf[train_idx], lrf[test_idx]
Y_train, Y_test = Y[train_idx], Y[test_idx]
if not np.any(np.isnan(f_train)) and np.all(np.isfinite(f_train)):
r2 = linearRegression(f_train, Y_train)
y2 = r2.predict(f_test)
errors2.append( np.abs( Y_test - y2 ) )
if verboseoutput:
print Y_test[0], y2[0]
else:
print 'nan or infinite'
pass
mae2 = np.mean(errors2)
var2 = np.sqrt( np.var(errors2) )
mre2 = mae2 / Y.mean()
return mae2, var2, mre2
def tenFoldCV_onChicagoCrimeData(features=['corina'],
CVmethod='10Fold',
P=10,
NUM_ITER=20,
SHUFFLE=True):
"""
Use different years data to train the NB model
"""
YEARS = range(2003, 2014)
Y = []
C = []
FL = []
GL = []
T = []
for year in YEARS:
W = generate_transition_SocialLag(year, lehd_type=0)
Yhat = retrieve_crime_count(year - 1, ['total'])
y = retrieve_crime_count(year, ['total'])
c = generate_corina_features()
popul = c[1][:, 0].reshape((77, 1))
# crime count is normalized by the total population as crime rate
# here we use the crime count per 10 thousand residents
y = np.divide(y, popul) * 10000
Yhat = np.divide(Yhat, popul) * 10000
W2 = generate_geographical_SpatialLag_ca()
f1 = np.dot(W, Yhat)
f2 = np.dot(W2, Yhat)
FL.append(f1)
GL.append(f2)
Y.append(y)
T.append(Yhat)
C.append(c[1])
Y = np.concatenate(Y, axis=0)
columnName = ['intercept']
f = np.ones(Y.shape)
if 'corina' in features:
C = np.concatenate(C, axis=0)
f = np.concatenate((f, C), axis=1)
columnName += c[0]
if 'sociallag' in features:
FL = np.concatenate(FL, axis=0)
f = np.concatenate((f, FL), axis=1)
columnName += ['sociallag']
if 'spatiallag' in features:
GL = np.concatenate(GL, axis=0)
f = np.concatenate((f, GL), axis=1)
columnName += ['spatiallag']
if 'temporallag' in features:
T = np.concatenate(T, axis=0)
f = np.concatenate((f, T), axis=1)
columnName += ['temporallag']
if SHUFFLE:
f, Y = shuffle(f, Y)
if CVmethod == '10Fold':
splt = cross_validation.KFold(n=f.shape[0], n_folds=10, shuffle=True)
elif CVmethod == 'leaveOneOut':
splt = cross_validation.LeaveOneOut(n=f.shape[0])
elif CVmethod == 'leavePOut':
splt = cross_validation.LeavePOut(n=f.shape[0], p=P)
mae1 = []
mae2 = []
mre1 = []
mre2 = []
sd_mae1 = []
sd_mae2 = []
sd_mre1 = []
sd_mre2 = []
med_mae1 = []
med_mae2 = []
med_mre1 = []
med_mre2 = []
cnt = 0
if CVmethod == 'leaveOneOut':
y_gnd = []
y_lr = []
for train_idx, test_idx in splt:
cnt += 1
if cnt > NUM_ITER:
break
f_train, f_test = f[train_idx, :], f[test_idx, :]
Y_train, Y_test = Y[train_idx, :], Y[test_idx, :]
# write file for invoking NB regression in R
np.savetxt("Y_train.csv", Y_train, delimiter=",")
np.savetxt("Y_test.csv", Y_test, delimiter=",")
pd.DataFrame(f_train, columns=columnName).to_csv("f_train.csv",
sep=",",
index=False)
pd.DataFrame(f_test, columns=columnName).to_csv("f_test.csv",
sep=",",
index=False)
# NB regression
nbres = subprocess.check_output(['Rscript',
'nbr_eval_kfold.R']).split(" ")
y1 = np.array([float(e) for e in nbres])
y1 = y1.reshape((y1.shape[0], 1))
a = np.abs(Y_test - y1)
mae1.append(np.mean(a))
sd_mae1.append(np.std(a))
med_mae1 += a.tolist()
r = a / Y_test
mre1.append(np.mean(r))
sd_mre1.append(np.std(r))
med_mre1 += r.tolist()
# Linear regression
r2 = linearRegression(f_train, Y_train)
y2 = r2.predict(f_test)
y2 = y2.reshape((y2.shape[0], 1))
ae = np.abs(Y_test - y2)
mae2.append(np.mean(ae))
sd_mae2.append(np.std(ae))
med_mae2 += ae.tolist()
re = ae / Y_test
mre2.append(np.mean(re))
sd_mre2.append(np.std(re))
med_mre2 += re.tolist()
if CVmethod == 'leaveOneOut':
y_gnd.append(Y_test)
y_lr.append(y2)
if CVmethod == 'leaveOneOut':
print np.mean(mae1), np.median(mae1), np.mean(mre1), np.median(mre1),
print np.mean(mae2), np.median(mae2), np.mean(mre2), np.median(mre2)
return y_gnd, y_lr
else:
print np.mean(mae1), np.mean(sd_mae1), np.median(med_mae1), np.mean(
mre1), np.mean(sd_mre1), np.median(med_mre1),
print np.mean(mae2), np.mean(sd_mae2), np.median(med_mae2), np.mean(
mre2), np.mean(sd_mre2), np.median(med_mre2)
return mae1, mae2
def tenFoldCV_onChicagoCrimeData(features=['corina'], CVmethod='10Fold', P = 10, NUM_ITER=20, SHUFFLE=True):
"""
Use different years data to train the NB model
"""
YEARS = range(2003, 2014)
Y = []
C = []
FL = []
GL = []
T = []
for year in YEARS:
W = generate_transition_SocialLag(year, lehd_type=0)
Yhat = retrieve_crime_count(year-1, ['total'])
y = retrieve_crime_count(year, ['total'])
c = generate_corina_features()
popul = c[1][:,0].reshape((77,1))
# crime count is normalized by the total population as crime rate
# here we use the crime count per 10 thousand residents
y = np.divide(y, popul) * 10000
Yhat = np.divide(Yhat, popul) * 10000
W2 = generate_geographical_SpatialLag_ca()
f1 = np.dot(W, Yhat)
f2 = np.dot(W2, Yhat)
FL.append(f1)
GL.append(f2)
Y.append(y)
T.append(Yhat)
C.append(c[1])
Y = np.concatenate(Y, axis=0)
columnName = ['intercept']
f = np.ones(Y.shape)
if 'corina' in features:
C = np.concatenate(C, axis=0)
f = np.concatenate( (f, C), axis=1 )
columnName += c[0]
if 'sociallag' in features:
FL = np.concatenate(FL, axis=0)
f = np.concatenate( (f, FL), axis = 1)
columnName += ['sociallag']
if 'spatiallag' in features:
GL = np.concatenate(GL, axis=0)
f = np.concatenate((f, GL), axis=1)
columnName += ['spatiallag']
if 'temporallag' in features:
T = np.concatenate(T, axis=0)
f = np.concatenate((f, T), axis=1)
columnName += ['temporallag']
if SHUFFLE:
f, Y = shuffle(f, Y)
if CVmethod == '10Fold':
splt = cross_validation.KFold(n=f.shape[0], n_folds=10, shuffle=True)
elif CVmethod == 'leaveOneOut':
splt = cross_validation.LeaveOneOut(n=f.shape[0])
elif CVmethod == 'leavePOut':
splt = cross_validation.LeavePOut(n=f.shape[0], p = P)
mae1 = []
mae2 = []
mre1 = []
mre2 = []
sd_mae1 = []
sd_mae2 = []
sd_mre1 = []
sd_mre2 = []
med_mae1 = []
med_mae2 = []
med_mre1 = []
med_mre2 = []
cnt = 0
if CVmethod == 'leaveOneOut':
y_gnd = []
y_lr = []
for train_idx, test_idx in splt:
cnt += 1
if cnt > NUM_ITER:
break
f_train, f_test = f[train_idx, :], f[test_idx, :]
Y_train, Y_test = Y[train_idx, :], Y[test_idx, :]
# write file for invoking NB regression in R
np.savetxt("Y_train.csv", Y_train, delimiter=",")
np.savetxt("Y_test.csv", Y_test, delimiter=",")
pd.DataFrame(f_train, columns = columnName).to_csv("f_train.csv", sep=",", index=False)
pd.DataFrame(f_test, columns = columnName).to_csv("f_test.csv", sep=",", index=False)
# NB regression
nbres = subprocess.check_output( ['Rscript', 'nbr_eval_kfold.R'] ).split(" ")
y1 = np.array([float(e) for e in nbres])
y1 = y1.reshape((y1.shape[0], 1))
a = np.abs( Y_test - y1 )
mae1.append(np.mean(a))
sd_mae1.append(np.std(a))
med_mae1 += a.tolist()
r = a / Y_test
mre1.append(np.mean(r))
sd_mre1.append(np.std(r))
med_mre1 += r.tolist()
# Linear regression
r2 = linearRegression(f_train, Y_train)
y2 = r2.predict(f_test)
y2 = y2.reshape((y2.shape[0], 1))
ae = np.abs(Y_test - y2)
mae2.append( np.mean(ae) )
sd_mae2.append( np.std(ae) )
med_mae2 += ae.tolist()
re = ae / Y_test
mre2.append( np.mean(re))
sd_mre2.append( np.std(re) )
med_mre2 += re.tolist()
if CVmethod == 'leaveOneOut':
y_gnd.append(Y_test)
y_lr.append(y2)
if CVmethod == 'leaveOneOut':
print np.mean(mae1), np.median(mae1), np.mean(mre1), np.median(mre1),
print np.mean(mae2), np.median(mae2), np.mean(mre2), np.median(mre2)
return y_gnd, y_lr
else:
print np.mean(mae1), np.mean(sd_mae1), np.median(med_mae1), np.mean(mre1), np.mean(sd_mre1), np.median(med_mre1),
print np.mean(mae2), np.mean(sd_mae2), np.median(med_mae2), np.mean(mre2), np.mean(sd_mre2), np.median(med_mre2)
return mae1, mae2