for vehicle in wProfiles:
data.append([vehicle]+wProfiles[vehicle])
random.shuffle(data)
sampleN = 30000
data2 = []
chosen = []
for i in range(sampleN):
data2.append(data[i][1:])
chosen.append(data[i][0])
data = data[sampleN:]
CE = ClusteringExercise(data2)
CE.k_means(3)
# first plot and save the chosen centroids with confindence intervals on them
plt.figure(figsize=(5,1.5))
plt.rcParams["font.family"] = 'serif'
plt.rcParams["font.size"] = '8'
x = [8,24,40]
x_ticks = ['04:00','12:00','20:00']
locs = {'0':[2.68,-0.5],'1':[1.39,-0.7],'2':[0.1,-0.9],'3':[2.68,0.2],'4':[1.39,0.0]}
clrs = {'2':'g','3':'y','1':'b','0':'r','4':'c'}
clrs2 = {'2':'#CCFFCC','3':'#FFFFCC','1':'#CCCCFF','0':'#FFCCCC','4':'#CCFFFF'}
for i in range(0,48):
weProfiles[vehicle][i] = float(weProfiles[vehicle][i])/maxWeDist
weTotal[i] += weProfiles[vehicle][i]
data = []
for vehicle in wProfiles:
data.append(wProfiles[vehicle])
random.shuffle(data)
x = [8,24,40]
x_ticks = ['04:00','12:00','20:00']
sampleN = 30000
CE = ClusteringExercise(data[:sampleN])
x = [8,24,40]
x_ticks = ['04:00','12:00','20:00']
css = []
plt.figure(1)
plt.rcParams["font.family"] = 'serif'
plt.rcParams["font.size"] = '10'
for k in range(1,11):
plt.subplot(3,4,k)
CE.k_means(k)
css.append(CE.get_sum_of_squares())
#'''
for label in CE.clusters:
for vehicle in wProfiles:
for i in range(0, 48):
wProfiles[vehicle][i] = float(wProfiles[vehicle][i]) / maxWDist
wTotal[i] += wProfiles[vehicle][i]
for profile in test_data:
for i in range(48):
profile[i] = profile[i] / maxWDist
data = []
for vehicle in wProfiles:
data.append(wProfiles[vehicle])
random.shuffle(data)
sampleN = 30000
CE = ClusteringExercise(data[:sampleN])
x = [8, 24, 40]
x_ticks = ['04:00', '12:00', '20:00']
css = []
plt.figure(1)
plt.rcParams["font.family"] = 'serif'
plt.rcParams["font.size"] = '10'
CE.k_means(5)
n = 1
clrs = {'2': 'g', '3': 'y', '1': 'b', '0': 'r', '4': 'c'}
wTotal[i] += wProfiles[vehicle][i]
for vehicle in weProfiles:
for i in range(0,48):
weProfiles[vehicle][i] = float(weProfiles[vehicle][i])/maxWeDist
weTotal[i] += weProfiles[vehicle][i]
data = []
for vehicle in wProfiles:
data.append(wProfiles[vehicle])
random.shuffle(data)
sampleN = 30000
CE = ClusteringExercise(data[:sampleN])
x = [8,24,40]
x_ticks = ['04:00','12:00','20:00']
css = []
plt.figure(1)
plt.rcParams["font.family"] = 'serif'
plt.rcParams["font.size"] = '10'
for k in range(2,11):
plt.subplot(3,4,k-1)
CE.k_means(k)
css.append(CE.get_dist_closest_centroids())
#'''
for label in CE.clusters:
weTotal[i] += weProfiles[vehicle][i]
data = []
for vehicle in weProfiles:
data.append(weProfiles[vehicle])
'''
x = np.arange(8,48,8)
x_ticks = range(4,24,4)
for i in range(0,len(x_ticks)):
if x_ticks[i] < 10:
x_ticks[i] = '0'+str(x_ticks[i])+':00'
else:
x_ticks[i] = str(x_ticks[i])+':00'
'''
CE = ClusteringExercise(data[:10000])
plt.figure(1)
for k in range(2, 8):
plt.subplot(3, 2, k - 1)
CE.k_means(k)
for label in CE.clusters:
plt.plot(CE.clusters[label].mean,
label=str(CE.clusters[label].nPoints))
plt.legend()
CE.reset_clusters()
plt.title('k=' + str(k), y=0.8)
plt.show()
for vehicle in wProfiles:
data.append([vehicle] + wProfiles[vehicle])
nTotal = len(data)
random.shuffle(data)
sampleN = 1000
data2 = []
chosen = []
for i in range(sampleN):
data2.append(data[i][1:])
chosen.append(data[i][0])
data = data[sampleN:]
CE = ClusteringExercise(data2)
CE.k_means(3)
pts = {}
for c in range(3):
pts[c] = {}
for t in range(48):
pts[c][t] = []
# first get the training pts
trainingLabels = CE.labels
labels = {}
for i in range(sampleN):
labels[chosen[i]] = int(trainingLabels[i])
for t in range(48):
pts[int(trainingLabels[i])][t].append(data2[i][t])