def cluster(request, dataset, gridshape, threshold):
if dataset == 'dps':
data = pd.read_pickle(os.path.abspath(
'./prediction/dataset/DPSUSC.pkl'))
ignoreFirst = 225
lon_min = -118.301895
lon_max = -118.27
lat_min = 34.015
lat_max = 34.0366
print(data)
elif dataset == 'la':
data = pd.read_pickle(os.path.abspath(
'./prediction/dataset/LAdata.pkl'))
lon_min = -118.301895
lon_max = -118.27
lat_min = 34.015
lat_max = 34.0366
ignoreFirst = 104
else:
response = HttpResponse(
'Wrong dataset. Should choose from \'dps\' or \'la\'')
response.status_code = 422
return response
try:
clusters, realCrimes = computeClustersAndOrganizeData(
data, gridshape, ignoreFirst, threshold, 1)
border_result = []
crime_counts = []
for geometry in clusters.Geometry:
num_of_crimes = 0
geometry_array = geometry.toarray()
border_set = set()
for i in range(len(geometry_array)):
row = geometry_array[i]
for j in range(len(row)):
if row[j] == 0:
continue
borders = getBorderCordinates(
lon_max, lon_min, lat_max, lat_min, gridshape, i, j)
for border in borders:
if border not in border_set:
border_set.add(border)
else:
border_set.remove(border)
num_of_crimes += row[j]
border_result.append(list(border_set))
crime_counts.append(num_of_crimes)
num_of_crimes = 0
response = HttpResponse(pd.io.json.dumps(
[border_result, crime_counts]))
response.status_code = 200
return response
except:
response = HttpResponse('Internal server error with the followint inputs:\ndataset: {}, gridshape: {}, threshold: {}'.format(
dataset, gridshape, threshold))
response.status_code = 400
return response
def cluster2(request):
print("CLUSTERING")
pd.options.display.precision = 10
body_unicode = request.body.decode('utf-8')
body = json.loads(body_unicode)
features = body['features']
threshold = int(body['threshold'])
gridshape = literal_eval(body['gridShape'])
entries = []
lon_min = -118.297
lon_max = -118.27
lat_min = 34.015
lat_max = 34.038
print(len(features))
for f in features:
d = f['properties']['time'].split('T')[0]
y, m, d = map(int, d.split('-'))
if y == 0:
continue
if float(f['properties']['latitude']) >= lat_min and float(f['properties']['latitude']) <= lat_max and float(f['properties']['longitude']) >= lon_min and float(f['properties']['longitude']) <= lon_max:
entries.append([f['properties']['Category'], float(f['properties']['latitude']), float(f['properties']['longitude']), datetime.date(y, m, d)])
print("DONE PREPROCESSING")
data = pd.DataFrame(np.array(entries), columns=['Category', 'Latitude', 'Longitude', "Date"])
data.sort_values(['Latitude', 'Longitude', 'Date'], inplace=True)
data = data.reset_index(drop=True)
ignoreFirst = 225
clusters, realCrimes = computeClustersAndOrganizeData(data, gridshape, ignoreFirst, threshold, 1)
border_result = []
crime_counts = []
for geometry in clusters.Geometry:
num_of_crimes = 0
geometry_array = geometry.toarray()
border_set = set()
for i in range(len(geometry_array)):
row = geometry_array[i]
for j in range(len(row)):
if row[j] == 0:
continue
borders = getBorderCordinates(
lon_max, lon_min, lat_max, lat_min, gridshape, i, j)
for border in borders:
if border not in border_set:
border_set.add(border)
else:
border_set.remove(border)
num_of_crimes += row[j]
border_result.append(list(border_set))
crime_counts.append(num_of_crimes)
num_of_crimes = 0
print(pd.io.json.dumps([border_result, crime_counts]))
return HttpResponse(pd.io.json.dumps([border_result, crime_counts]))
def heterogeneousCluster(request):
pd.options.display.precision = 10
body_unicode = request.body.decode('utf-8')
body = json.loads(body_unicode)
features = body['features']
threshold = int(body['threshold'])
gridshape = literal_eval(body['gridShape'])
data = convertFromFeaturesToData(features)
ignoreFirst = 225
clusters, realCrimes = computeClustersAndOrganizeData(
data, gridshape, ignoreFirst, threshold, 1)
border_result = []
crime_counts = []
for geometry in clusters.Geometry:
num_of_crimes = 0
geometry_array = geometry.toarray()
border_set = set()
for i in range(len(geometry_array)):
row = geometry_array[i]
for j in range(len(row)):
if row[j] == 0:
continue
borders = getBorderCordinates(lon_max, lon_min, lat_max,
lat_min, gridshape, i, j)
for border in borders:
if border not in border_set:
border_set.add(border)
else:
border_set.remove(border)
num_of_crimes += row[j]
neighbor_map = {}
for border in border_set:
addEdge(neighbor_map, border[:2], border[2:])
print('Start Finding Eulerian path...')
node_path = []
start_point = next(iter(border_set))[:2]
fleuryEulerianCircuit(neighbor_map, start_point, node_path)
border_result.append(node_path)
crime_counts.append(num_of_crimes)
resp = HttpResponse(
pd.io.json.dumps([border_result, crime_counts, clusters, realCrimes]))
resp['Access-Control-Allow-Origin'] = '*'
return resp
def evaluate(request):
maxDist = 1
ignoreFirst = 225
isModelEvaluation = True
body_unicode = request.body.decode('utf-8')
body = json.loads(body_unicode)
periodsAhead_list = [int(body['periodsAhead'])]
isRetrainingModel = True
features = body['features']
data = convertFromFeaturesToData(features)
thresholds = body['thresholds']
gridshapes = [tuple(gridshape) for gridshape in body['gridshapes']]
methods = body['methods']
resource_indexes = body['resource_indexes']
for gridshape in gridshapes:
for threshold in thresholds:
clusters, realCrimes = computeClustersAndOrganizeData(
data, gridshape, ignoreFirst, threshold, 1)
clusters = clusters.to_dict()
realCrimes = realCrimes.to_dict()
for method in methods:
if method == "LSTM":
result_path = forecast_LSTM(
clusters=clusters,
realCrimes=realCrimes,
periodsAhead_list=periodsAhead_list,
gridshape=gridshape,
ignoreFirst=ignoreFirst,
threshold=threshold,
maxDist=maxDist,
isRetraining=isRetrainingModel,
isModelEvaluation=isModelEvaluation)
elif method == "ARIMA" or method == "AR":
result_path = forecast_ARIMA(
method=method,
clusters=clusters,
realCrimes=realCrimes,
periodsAhead_list=periodsAhead_list,
gridshape=gridshape,
ignoreFirst=ignoreFirst,
threshold=threshold,
maxDist=maxDist,
isRetraining=isRetrainingModel,
isModelEvaluation=isModelEvaluation)
else:
result_path = forecast_MM(
method=method,
clusters=clusters,
realCrimes=realCrimes,
periodsAhead_list=periodsAhead_list,
gridshape=gridshape,
ignoreFirst=ignoreFirst,
threshold=threshold,
maxDist=maxDist,
isModelEvaluation=isModelEvaluation)
compute_resource_allocation(resource_indexes, 1, [gridshape],
periodsAhead_list, ignoreFirst,
[threshold], 1, [method], lon_min,
lon_max, lat_min, lat_max)
fig, ax = plt.subplots(1, len(methods), figsize=(18, 5), sharey=True)
if len(methods) == 1:
ax = [ax]
plot_resource_allocation(ax, gridshapes, periodsAhead_list[0], thresholds,
methods, ignoreFirst)
os.makedirs(os.path.abspath("results/"), exist_ok=True)
os.makedirs(os.path.abspath("results/plots"), exist_ok=True)
image_path = os.path.abspath('results/plots/{}-week-ahead.png'.format(
periodsAhead_list[0]))
plt.savefig(image_path, dpi=300)
with open(image_path, "rb") as imageFile:
image_data = base64.b64encode(imageFile.read())
response = HttpResponse(pd.io.json.dumps(image_data))
response['Access-Control-Allow-Origin'] = '*'
response.status_code = 200
return response