def main(dataset_fn, output_fn, clusters_no):
geo_locs = []
# read location data from csv file and store each location as a Point(latit,longit) object
df = pd.read_csv(dataset_fn)
for index, row in df.iterrows():
loc_ = Point(float(row['LAT']), float(row['LON'])) #tuples for location
geo_locs.append(loc_)
# run k_means clustering
model = KMeans(geo_locs, clusters_no)
flag = model.fit(True)
if flag == -1:
print("No of points are less than cluster number!")
else:
# save clustering results is a list of lists where each list represents one cluster
model.save(output_fn)
def main(dataset_fn, output_fn, clusters_no, w):
geo_locs = []
# read location data from csv file and store each location as a Point(latit,longit) object
df = pd.read_csv(dataset_fn)
for index, row in df.iterrows():
loc_ = Node(
[float(row['X']),
float(row['Y']),
float(row['PreChange'])], row['ID'])
geo_locs.append(loc_)
# run k_means clustering
w = np.array(w)
model = KMeans(geo_locs, clusters_no, w)
flag = model.fit(True)
if flag == -1:
print("No of points are less than cluster number!")
else:
# save clustering results is a list of lists where each list represents one cluster
model.save(output_fn)
model.showresult(True)
