def ordinary_kriging_evaluation(year):
"""
Under leave-one-out setting, use only crime rate.
"""
from pykrige.ok import OrdinaryKriging
from sklearn.model_selection import LeaveOneOut
y_cnt = retrieve_crime_count(year)
demo = generate_corina_features()
population = demo[1][:,0].reshape(demo[1].shape[0], 1)
Y = y_cnt / population * 10000
coords = get_centroid_ca()
data = np.concatenate((coords, Y), axis=1)
loo = LeaveOneOut()
errors = []
for train_idx, test_idx in loo.split(data):
x_train = data[train_idx,:]
coords_test = data[test_idx, [0,1]]
y_test = data[test_idx, 2]
OK = OrdinaryKriging(x_train[:,0], x_train[:,1], x_train[:,2], variogram_model="linear")
z, var = OK.execute("points", coords_test[0], coords_test[1])
errors.append(abs(z[0] - y_test[0]))
print np.mean(errors), np.mean(errors) / np.mean(Y)
return errors
def predict_crime_with_embedding():
ge = get_graph_embedding_features("taxi_all.txt")
y_cnt = retrieve_crime_count(2010)
demo = generate_corina_features()
population = demo[1][:,0].reshape(demo[1].shape[0], 1)
y = y_cnt / population * 10000
er = leaveOneOut_error(y, ge)
print er
return er
def predict_crime_with_embedding():
ge = get_graph_embedding_features("taxi_all.txt")
y_cnt = retrieve_crime_count(2010)
demo = generate_corina_features()
population = demo[1][:, 0].reshape(demo[1].shape[0], 1)
y = y_cnt / population * 10000
er = leaveOneOut_error(y, ge)
print er
return er
def extract_raw_samples(year=2010, crime_t=['total'], crime_rate=True):
"""
Extract all samples with raw labels and features. Return None if the
corresponding feature is not selected.
This function is called once only to avoid unnecessary disk I/O.
Input:
year - which year to study
crime_t - crime types of interest, e.g. 'total'
crime_rate - predict crime_rate or not (count)
Output:
Y - crime rate / count
D - demo feature
P - POI feature
Tf - taxi flow matrix (count)
Gd - geo weight matrix
"""
# Crime count
y_cnt = retrieve_crime_count(year, col = crime_t)
# Crime rate / count
demo = generate_corina_features()
population = demo[1][:,0].reshape(demo[1].shape[0], 1)
Y = y_cnt / population * 10000 if crime_rate else y_cnt
assert(Y.shape == (N,1))
# Demo features
D = demo[1]
# POI features
P = getFourSquarePOIDistribution(useRatio=False)
# Taxi flow matrix
Tf = getTaxiFlow(normalization="none")
# Geo weight matrix
Gd = generate_geographical_SpatialLag_ca()
return Y, D, P, Tf, Gd
def extract_raw_samples(year=2010, crime_t=['total'], crime_rate=True):
"""
Extract all samples with raw labels and features. Return None if the
corresponding feature is not selected.
This function is called once only to avoid unnecessary disk I/O.
Input:
year - which year to study
crime_t - crime types of interest, e.g. 'total'
crime_rate - predict crime_rate or not (count)
Output:
Y - crime rate / count
D - demo feature
P - POI feature
Tf - taxi flow matrix (count)
Gd - geo weight matrix
"""
# Crime count
y_cnt = retrieve_crime_count(year, col = crime_t)
# Crime rate / count
demo = generate_corina_features()
population = demo[1][:,0].reshape(demo[1].shape[0], 1)
Y = y_cnt / population * 10000 if crime_rate else y_cnt
assert(Y.shape == (77,1))
# Demo features
D = demo[1]
# POI features
P = getFourSquarePOIDistribution(useRatio=False)
# Taxi flow matrix
Tf = getTaxiFlow(normalization="none")
# Geo weight matrix
Gd = generate_geographical_SpatialLag_ca()
return Y, D, P, Tf, Gd
mf = pickle.load(fin)
line = pickle.load(fin)
dwt = pickle.load(fin)
dws = pickle.load(fin)
hdge = pickle.load(fin)
for h in range(24):
Fn = similarityMatrix(hdge[h])
x, y, xp, yp, lp = generate_point(Fn, Y)
f = plt.figure()
plt.scatter(x, y, color='red')
plt.show()
demo = generate_corina_features()
y_cnt = retrieve_crime_count(2013)
population = demo[1][:, 0].reshape(demo[1].shape[0], 1)
Y = y_cnt / population * 10000
F = getTaxiFlow(normalization="none")
x, y, xp, yp, lp = generate_point(F, Y)
plt.rc("axes", linewidth=2)
f = plt.figure(figsize=(8, 6))
plt.scatter(x, y, s=16)
plt.plot([-100, -100, 3500, -100], [3000, -3000, 0, 3000],
linewidth=2,
color='blue')