def assignClasses(self):
"""
get labels of all samples. label == index number of cluster.
"""
clusterer = kdtree.KDTreeClustering(bucket_size=self.bucket_size)
train_locs = self.df_train[['lat', 'lon']].values
clusterer.fit(train_locs)
clusters = clusterer.get_clusters()
cluster_points = defaultdict(list)
for i, cluster in enumerate(clusters):
cluster_points[cluster].append(train_locs[i])
print('# the number of clusterer labels is: %d' % len(cluster_points))
self.cluster_median = OrderedDict()
for cluster in sorted(cluster_points):
points = cluster_points[cluster]
median_lat = np.median([p[0] for p in points])
median_lon = np.median([p[1] for p in points])
self.cluster_median[cluster] = (median_lat, median_lon)
dev_locs = self.df_dev[['lat', 'lon']].values
test_locs = self.df_test[['lat', 'lon']].values
nnbr = NearestNeighbors(n_neighbors=1,
algorithm='brute',
leaf_size=1,
metric=haversine,
n_jobs=4)
nnbr.fit(np.array(list(self.cluster_median.values())))
self.dev_classes = nnbr.kneighbors(dev_locs,
n_neighbors=1,
return_distance=False)[:, 0]
self.test_classes = nnbr.kneighbors(test_locs,
n_neighbors=1,
return_distance=False)[:, 0]
self.train_classes = clusters
if self.one_hot_labels:
num_labels = np.max(self.train_classes) + 1
y_train = np.zeros((len(self.train_classes), num_labels),
dtype=np.float32)
y_train[np.arange(len(self.train_classes)), self.train_classes] = 1
y_dev = np.zeros((len(self.dev_classes), num_labels),
dtype=np.float32)
y_dev[np.arange(len(self.dev_classes)), self.dev_classes] = 1
y_test = np.zeros((len(self.test_classes), num_labels),
dtype=np.float32)
y_test[np.arange(len(self.test_classes)), self.test_classes] = 1
self.train_classes = y_train
self.dev_classes = y_dev
self.test_classes = y_test
def draw_kd_clusters(self, filename, figsize=(4, 3)):
import matplotlib as mpl
mpl.use('Agg')
import matplotlib.patches as mpatches
import matplotlib.pyplot as plt
from mpl_toolkits.basemap import Basemap, cm, maskoceans
#from matplotlib import style
#import seaborn as sns
#sns.set_style("white")
#plt.rc('text', usetex=True)
#plt.rc('font', family='serif')
#plt.rcParams['axes.facecolor']='white'
fig = plt.figure(figsize=figsize)
lllat = 24.396308
lllon = -124.848974
urlat = 49.384358
urlon = -66.885444
m = Basemap(llcrnrlat=lllat,
urcrnrlat=urlat,
llcrnrlon=lllon,
urcrnrlon=urlon,
resolution='c',
projection='cyl')
m.drawmapboundary(fill_color='white')
m.drawcoastlines(linewidth=0.2)
m.drawcountries(linewidth=0.2)
ax = plt.gca()
#fig = plt.figure() # figsize=(4,4.2)
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['bottom'].set_visible(False)
ax.spines['left'].set_visible(False)
clusterer = kdtree.KDTreeClustering(bucket_size=self.bucket_size)
train_locs = self.df_train[['lat', 'lon']].values
mlon, mlat = m(*(train_locs[:, 1], train_locs[:, 0]))
train_locs = np.transpose(np.vstack((mlat, mlon)))
clusterer.fit(train_locs)
clusters = clusterer.get_clusters()
cluster_points = dd(list)
for i, cluster in enumerate(clusters):
cluster_points[cluster].append(train_locs[i])
corners = []
for i in clusters:
points = np.vstack(cluster_points[i])
min_lat, min_lon = points.min(axis=0)
max_lat, max_lon = points.max(axis=0)
min_lon, min_lat = m(min_lon, min_lat)
max_lon, max_lat = m(max_lon, max_lat)
corners.append([min_lat, min_lon, max_lat, max_lon])
patches = []
for corner in corners:
min_lat, min_lon, max_lat, max_lon = corner
rect = mpatches.Rectangle((min_lon, min_lat),
max_lon - min_lon,
max_lat - min_lat,
facecolor=None,
fill=False,
linewidth=0.7)
patches.append(rect)
ax.add_collection(PatchCollection(patches))
ax.set_xlim([-125, -60]) # pylab.xlim([-400, 400])
ax.set_ylim([25, 50])
plt.setp(ax.get_yticklabels(), visible=False)
plt.setp(ax.get_xticklabels(), visible=False)
ax.yaxis.set_tick_params(size=0)
ax.xaxis.set_tick_params(size=0)
#plt.tick_params(axis='both', which='major', labelsize=25)
#ax.labelsize = '25'
#plt.subplots_adjust(bottom=0.2)
m.drawlsmask(land_color='gray', ocean_color="#b0c4de", lakes=True)
plt.tight_layout()
plt.savefig(filename)
#plt.close()
print("the plot saved in " + filename)
def assignClasses(self):
# kd聚类器
clusterer = kdtree.KDTreeClustering(bucket_size=self.bucket_size) # 50
# <class 'tuple'>: (5685, 2)
train_locs = self.df_train[['lat', 'lon']].values
clusterer.fit(train_locs)
clusters = clusterer.get_clusters() # <class 'tuple'>: (5685,)
cluster_points = defaultdict(list) # 分类后user的经纬度
for i, cluster in enumerate(clusters):
cluster_points[cluster].append(
train_locs[i]) # train_locs未分类的5686个user的经纬度
print('# the number of clusterer labels is: %d' % len(cluster_points))
self.cluster_median = OrderedDict()
for cluster in sorted(cluster_points):
points = cluster_points[cluster]
median_lat = np.median([p[0] for p in points])
median_lon = np.median([p[1] for p in points])
self.cluster_median[cluster] = (
median_lat, median_lon) # self.cluster_median129个类经纬度
dev_locs = self.df_dev[['lat', 'lon']].values # 1895经纬度
test_locs = self.df_test[['lat', 'lon']].values
# nnbr = NearestNeighbors(n_neighbors=1, algorithm='brute', leaf_size=1, metric=haversine, n_jobs=4)
nnbr = NearestNeighbors(
n_neighbors=1,
algorithm='brute',
leaf_size=1,
metric=haversine)
nnbr.fit(np.array(list(self.cluster_median.values())))
'''
self.dev_classes<class 'tuple'>: (1895,) 样本对应的类？
self.test_classes<class 'tuple'>: (1895,) 样本对应的类
self.train_classes<class 'tuple'>: (5685,) 样本对应的类
'''
self.dev_classes = nnbr.kneighbors(
dev_locs, n_neighbors=1, return_distance=False)[:, 0]
self.test_classes = nnbr.kneighbors(
test_locs, n_neighbors=1, return_distance=False)[:, 0]
self.train_classes = clusters
if self.one_hot_labels:
num_labels = np.max(self.train_classes) + 1
y_train = np.zeros(
(len(
self.train_classes),
num_labels),
dtype=np.float32)
y_train[np.arange(len(self.train_classes)), self.train_classes] = 1
y_dev = np.zeros(
(len(
self.dev_classes),
num_labels),
dtype=np.float32)
y_dev[np.arange(len(self.dev_classes)), self.dev_classes] = 1
y_test = np.zeros(
(len(
self.test_classes),
num_labels),
dtype=np.float32)
y_test[np.arange(len(self.test_classes)), self.test_classes] = 1
self.train_classes = y_train
self.dev_classes = y_dev
self.test_classes = y_test