def main_evaluate_feature_setting(year=2010, crime_t=['total']):
feature_settings = [['demo'], ['demo', 'poi'], ['demo', 'taxi'], ['demo', 'poi', 'taxi'],
['demo', 'geo'], ['demo', 'geo', 'poi'], ['demo', 'geo', 'taxi'], ['all']]
Y, D, P, Tf, Gd = extract_raw_samples(year, crime_t)
H = [0.08, 0.09, 0.1, 0.15, 0.2, 0.3, 0.5]
nb_MAEs = []
nb_MREs = []
gwnbr_MAEs = []
gwnbr_MREs = []
for feature_setting in feature_settings:
mae, mre = leaveOneOut_error(Y, D, P, Tf, Y, Gd, Y, feature_setting)
nb_MAEs.append(mae)
nb_MREs.append(mre)
# Tune bandwidth for GWR model
gwr_mae = sys.maxint
gwr_mre = 1.0
for h in H:
gwr_gamma = generate_GWR_weight(h)
mae, mre = leaveOneOut_error(Y, D, P, Tf, Y, Gd, Y, feature_setting, gwr_gamma)
if mae < gwr_mae:
gwr_mae = mae
gwr_mre = mre
gwnbr_MAEs.append(gwr_mae)
gwnbr_MREs.append(gwr_mre)
print "Settings\t",
for f in feature_settings:
feature_header = [ele[0] for ele in f]
print '+'.join(feature_header) + "\t",
print ""
print "NB_MAE\t" + '\t'.join(map(str, nb_MAEs))
print "NB_MRE\t" + '\t'.join(map(str, nb_MREs))
print "GWNBR_MAE\t" + '\t'.join(map(str, gwnbr_MAEs))
print "GWNBR_MRE\t" + '\t'.join(map(str, gwnbr_MREs))
def main_evaluate_feature_setting(year=2010, crime_t=['total']):
feature_settings = [['demo'], ['demo', 'poi'], ['demo', 'taxi'], ['demo', 'poi', 'taxi'],
['demo', 'geo'], ['demo', 'geo', 'poi'], ['demo', 'geo', 'taxi'], ['all']]
Y, D, P, Tf, Gd = extract_raw_samples(year, crime_t)
H = [0.08, 0.09, 0.1, 0.15, 0.2, 0.3, 0.5]
nb_MAEs = []
nb_MREs = []
gwnbr_MAEs = []
gwnbr_MREs = []
for feature_setting in feature_settings:
mae, mre = leaveOneOut_error(Y, D, P, Tf, Y, Gd, Y, feature_setting)
nb_MAEs.append(mae)
nb_MREs.append(mre)
# Tune bandwidth for GWR model
gwr_mae = sys.maxint
gwr_mre = 1.0
for h in H:
gwr_gamma = generate_GWR_weight(h)
mae, mre = leaveOneOut_error(Y, D, P, Tf, Y, Gd, Y, feature_setting, gwr_gamma)
if mae < gwr_mae:
gwr_mae = mae
gwr_mre = mre
gwnbr_MAEs.append(gwr_mae)
gwnbr_MREs.append(gwr_mre)
print "Settings\t",
for f in feature_settings:
feature_header = [ele[0] for ele in f]
print '+'.join(feature_header) + "\t",
print ""
print "NB_MAE\t" + '\t'.join(map(str, nb_MAEs))
print "NB_MRE\t" + '\t'.join(map(str, nb_MREs))
print "GWNBR_MAE\t" + '\t'.join(map(str, gwnbr_MAEs))
print "GWNBR_MRE\t" + '\t'.join(map(str, gwnbr_MREs))
def main_compare_taxi_normalization_method():
H = [0.08, 0.09, 0.1, 0.15, 0.2, 0.3, 0.5]
for year in range(2010, 2015):
print year
Y, D, P, Tf, Gd = extract_raw_samples(year, ["total"])
for taxi_norm in ["bydestination", "bysource", "none"]:
gwr_mae = sys.maxint
gwr_mre = 1.0
best_h = 0
for h in H:
gwr_gamma = generate_GWR_weight(h)
mae, mre = leaveOneOut_error(Y, D, P, Tf, Y, Gd, Y, ["all"], gwr_gamma, taxi_norm)
if mae < gwr_mae:
gwr_mae = mae
gwr_mre = mre
best_h = h
print taxi_norm, gwr_mae, gwr_mre, best_h
def main_compare_taxi_normalization_method():
H = [0.08, 0.09, 0.1, 0.15, 0.2, 0.3, 0.5]
for year in range(2010, 2015):
print year
Y, D, P, Tf, Gd = extract_raw_samples(year, ["total"])
for taxi_norm in ["bydestination", "bysource", "none"]:
gwr_mae = sys.maxint
gwr_mre = 1.0
best_h = 0
for h in H:
gwr_gamma = generate_GWR_weight(h)
mae, mre = leaveOneOut_error(Y, D, P, Tf, Y, Gd, Y, ["all"], gwr_gamma, taxi_norm)
if mae < gwr_mae:
gwr_mae = mae
gwr_mre = mre
best_h = h
print taxi_norm, gwr_mae, gwr_mre, best_h
