def plot_curves(plot_file_name, curve_names, mrs, homogeneity_scores, completeness_scores, number_of_embeddings):
"""
Plots all specified curves and saves the plot into a file.
:param plot_file_name: String value of save file name
:param curve_names: Set of names used in legend to describe this curve
:param mrs: 2D Matrix, each row describes one dataset of misclassification rates for a curve
:param homogeneity_scores: 2D Matrix, each row describes one dataset of homogeneity scores for a curve
:param completeness_scores: 2D Matrix, each row describes one dataset of completeness scores for a curve
:param number_of_embeddings: set of integers, each integer describes how many embeddings is in this curve
"""
logger = get_logger('analysis', logging.INFO)
logger.info('Plot results')
logger.info(plot_file_name)
min_mrs = []
for mr in mrs:
min_mrs.append(np.min(mr))
min_mrs, curve_names, mrs, homogeneity_scores, completeness_scores, number_of_embeddings = \
(list(t) for t in
zip(*sorted(zip(min_mrs, curve_names, mrs, homogeneity_scores, completeness_scores, number_of_embeddings))))
# How many lines to plot
number_of_lines = len(curve_names)
# Get various colors needed to plot
color_map = plt.get_cmap('gist_rainbow')
colors = [color_map(i) for i in np.linspace(0, 1, number_of_lines)]
# Define number of figures
fig1 = plt.figure(1)
fig1.set_size_inches(16, 8)
# Define Plots
mr_plot = plt.subplot2grid((2, 3), (0, 0), colspan=2)
mr_plot.set_ylabel('MR')
mr_plot.set_xlabel('number of clusters')
plt.ylim([-0.02, 1.02])
completeness_scores_plot = add_cluster_subplot(fig1, 234, 'completeness_scores')
homogeneity_scores_plot = add_cluster_subplot(fig1, 235, 'homogeneity_scores')
# Define curves and their values
curves = [[mr_plot, mrs],
[homogeneity_scores_plot, homogeneity_scores],
[completeness_scores_plot, completeness_scores]]
# Plot all curves
for index in range(number_of_lines):
label = curve_names[index] + '\n min MR: ' + str(min_mrs[index])
color = colors[index]
number_of_clusters = np.arange(number_of_embeddings[index], 0, -1)
for plot, value in curves:
plot.plot(number_of_clusters, value[index], color=color, label=label)
# Add legend and save the plot
fig1.legend()
# fig1.show()
fig1.savefig(get_result_png(plot_file_name))
fig1.savefig(get_result_png(plot_file_name + '.svg'), format='svg')
def plot_curves(plot_file_name, curve_names, mrs, homogeneity_scores, completeness_scores, number_of_embeddings):
"""
Plots all specified curves and saves the plot into a file.
"""
logger = get_logger('analysis', logging.INFO)
logger.info('Plot results')
# How many lines to plot
number_of_lines = len(curve_names)
# Get various colors needed to plot
color_map = plt.get_cmap('gist_rainbow')
colors = [color_map(i) for i in np.linspace(0, 1, number_of_lines)]
# Define number of figures
fig1 = plt.figure(1)
fig1.set_size_inches(32, 24)
# Define Plots
mr_plot = plt.subplot2grid((2, 2), (0, 0), colspan=2)
mr_plot.set_title('MR')
mr_plot.set_xlabel('number of clusters')
mr_plot.axis([0, 80, 0, 1])
completeness_scores_plot = add_cluster_subplot(fig1, 223, 'completeness_scores')
homogeneity_scores_plot = add_cluster_subplot(fig1, 224, 'homogeneity_scores')
# Define curves and their values
curves = [[mr_plot, mrs],
[homogeneity_scores_plot, homogeneity_scores],
[completeness_scores_plot, completeness_scores]]
# Plot all curves
for index in range(number_of_lines):
label = curve_names[index]
color = colors[index]
number_of_clusters = np.arange(number_of_embeddings[index], 1, -1)
for plot, value in curves:
plot.plot(number_of_clusters, value[index], color=color, label=label)
min_mr = np.min(mrs[index])
mr_plot.annotate(str(min_mr), xy=(0, min_mr))
# Add legend and save the plot
fig1.legend()
# fig1.show()
fig1.savefig(get_result_png(plot_file_name))
def plot_curves(plot_file_name, loaded_dict, loaded_dict2, loaded_dict3,
loaded_dict4):
"""
Plots all specified curves and saves the plot into a file.
:param plot_file_name: String value of save file name
:param curve_names: Set of names used in legend to describe this curve
:param mrs: 2D Matrix, each row describes one dataset of misclassification rates for a curve
:param homogeneity_scores: 2D Matrix, each row describes one dataset of homogeneity scores for a curve
:param completeness_scores: 2D Matrix, each row describes one dataset of completeness scores for a curve
:param number_of_embeddings: set of integers, each integer describes how many embeddings is in this curve
"""
logger = get_logger('analysis', logging.INFO)
logger.info('Plot results')
num_clusters = [j for j in range(1, 41)]
print(num_clusters)
tot_clus = []
hierach_MR = []
kmeans_mr = []
ds_mr = []
list_64_0 = []
list_64_1 = []
list_64_2 = []
list_64_3 = []
list_64_4 = []
list_64_5 = []
list_64_6 = []
list_64_7 = []
list_128_0 = []
list_128_1 = []
list_128_2 = []
list_128_3 = []
list_256_0 = []
list_256_1 = []
list_512 = []
for x in loaded_dict:
print(x)
for x in loaded_dict:
tot_clus.append(x)
if "64_0" in x:
list_64_0.append(loaded_dict[x])
elif "64_1" in x:
list_64_1.append(loaded_dict[x])
elif "64_2" in x:
list_64_2.append(loaded_dict[x])
elif "64_3" in x:
list_64_3.append(loaded_dict[x])
elif "64_4" in x:
list_64_4.append(loaded_dict[x])
elif "64_5" in x:
list_64_5.append(loaded_dict[x])
elif "64_6" in x:
list_64_6.append(loaded_dict[x])
elif "64_7" in x:
list_64_7.append(loaded_dict[x])
elif "128_0" in x:
list_128_0.append(loaded_dict[x])
elif "128_1" in x:
list_128_1.append(loaded_dict[x])
elif "128_2" in x:
list_128_2.append(loaded_dict[x])
elif "128_3" in x:
list_128_3.append(loaded_dict[x])
elif "256_0" in x:
list_256_0.append(loaded_dict[x])
elif "256_1" in x:
list_256_1.append(loaded_dict[x])
elif "512" in x:
list_512.append(loaded_dict[x])
# print("\n")
# print("Hierachial MR")
# hierach_MR.sort()
# print(hierach_MR)
# list_128 = [s for s in num_clusters if "128" in s]
# list_512 = [s for s in num_clusters if "512" in s]
list_64_0.sort()
list_64_1.sort()
list_64_2.sort()
list_64_3.sort()
list_64_4.sort()
list_64_5.sort()
list_64_6.sort()
list_64_7.sort()
list_128_0.sort()
list_128_1.sort()
list_128_2.sort()
list_128_3.sort()
list_256_0.sort()
list_256_1.sort()
list_512.sort()
print(list_64_0)
print(list_64_1)
print(list_64_2)
print(list_64_3)
print(list_64_4)
print(list_64_5)
print(list_64_6)
print(list_64_7)
print("\n")
print(list_128_0)
print(list_128_1)
print(list_128_2)
print(list_128_3)
print("\n")
print(list_256_0)
print(list_256_1)
print("\n")
print(list_512)
maxc = max(num_clusters)
minc = min(num_clusters)
# Get various colors needed to plot
color_map = plt.get_cmap('gist_rainbow')
colors = [color_map(i) for i in np.linspace(0, 2, 15)]
# Define number of figures
fig1 = plt.figure(1)
fig1.set_size_inches(16, 8)
# # Define Plots
# mr_plot = plt.subplot2grid((1, 1), (0, 0), colspan=1)
# mr_plot.set_ylabel('MR')
# mr_plot.set_xlabel('Number of clusters')
# # plt.grid(True)
plt.title('Embeddings Plot for hierarchical MR ')
plt.axis([(int(minc) - 0.1), (int(maxc) + 0.1), -0.02, 0.5])
plt.xlabel('Number of clusters')
plt.ylabel("MR")
# value = [list_64_0, list_64_1, list_64_2, list_64_3, list_64_4, list_64_5, list_64_6, list_64_7, list_128_0, list_128_1, list_128_2, list_128_3, list_256_0, list_256_1, list_512]
value = [
list_128_0, list_128_1, list_128_2, list_128_3, list_256_0, list_256_1,
list_512
]
# curves = [[mr_plot, value]]
# algorithm = ["64_0", "64_1", "64_2", "64_3", "64_4", "64_5", "64_6", "64_7", "128_0", "128_1", "128_2", "128_3", "256_0", "256_1", "512"]
algorithm = ["128_0", "128_1", "128_2", "128_3", "256_0", "256_1", "512"]
# Plot all curves
for index in range(7):
# ymax = max(value[index])
# xpos = value[index].index(ymax)
# print("xpos " + str(xpos))
# xmax = num_clusters[xpos]
#
# temp = 'Max Value : ' + str((xmax, ymax))
#
# # plt.annotate(temp , xy=(xmax, ymax), xytext=(xmax-50, ymax + 0.05),
# # arrowprops=dict(facecolor=colors[index], shrink=0.03 ),)
print("plotting " + algorithm[index])
label = algorithm[index]
color = colors[index]
plt.plot(num_clusters, value[index], color=color, label=label)
# for plot, value in curves:
# # plot.plot(ks,value[index], color=color, label=label)
# Add legend and save the plot
fig1.legend()
fig1.show()
fig1.savefig(get_result_png(plot_file_name))
print("Plot File saved in " + get_result_png(plot_file_name))
fig1.savefig(get_result_png(plot_file_name + '.svg'), format='svg')
def plot_curves(plot_file_name, curve_names, mrs, homogeneity_scores, completeness_scores, number_of_embeddings,loaded_dict,loaded_dict2,loaded_dict3):
"""
Plots all specified curves and saves the plot into a file.
:param plot_file_name: String value of save file name
:param curve_names: Set of names used in legend to describe this curve
:param mrs: 2D Matrix, each row describes one dataset of misclassification rates for a curve
:param homogeneity_scores: 2D Matrix, each row describes one dataset of homogeneity scores for a curve
:param completeness_scores: 2D Matrix, each row describes one dataset of completeness scores for a curve
:param number_of_embeddings: set of integers, each integer describes how many embeddings is in this curve
"""
logger = get_logger('analysis', logging.INFO)
logger.info('Plot results')
logger.info(plot_file_name)
min_mrs = []
for mr in mrs:
min_mrs.append(np.min(mr))
num_clusters=[]
hierach_MR = []
kmeans_mr = []
ds_mr = []
for x in loaded_dict:
num_clusters.append(x)
hierach_MR.append(loaded_dict[x])
# print(str(loaded_dict[x]) + " appended to " + str(x))
print("\n")
print("Hierachial MR")
print(hierach_MR)
for x in loaded_dict2:
kmeans_mr.append(loaded_dict2[x])
# print(str(loaded_dict[x]) + " appended to " + str(x))
print("\n")
print("Kmeans MR")
print(kmeans_mr)
for x in loaded_dict3:
ds_mr.append(loaded_dict3[x])
# print(str(loaded_dict[x]) + " appended to " + str(x))
print("\n")
print("DS MR")
print(ds_mr)
ks = list(loaded_dict)
ks = list(map(int, ks))
print("\n")
print("Cluster Count")
print(ks)
print("Minimum Cluster : " + str(min(ks)))
print("Maximum CLuster : " + str(max(ks))+ "\n")
maxc = max(ks)
minc = min(ks)
# x = zip(*sorted(zip(min_mrs, curve_names, mrs, homogeneity_scores, completeness_scores, number_of_embeddings)))
#
#
# print("\n")
# print(tuple(x))
# print("\n")
#
# min_mrs, curve_names, mrs, homogeneity_scores, completeness_scores, number_of_embeddings = \
# (list(t) for t in x)
# How many lines to plot
number_of_lines = len(curve_names)
# Get various colors needed to plot
color_map = plt.get_cmap('gist_rainbow')
colors = [color_map(i) for i in np.linspace(0, 1, number_of_lines)]
# Define number of figures
fig1 = plt.figure(1)
fig1.set_size_inches(16, 8)
# Define Plots
mr_plot = plt.subplot2grid((2, 3), (0, 0), colspan=2)
mr_plot.set_ylabel('MR')
mr_plot.set_xlabel('Number of clusters')
plt.grid(True)
plt.axis([minc,maxc, -0.02,1.2])
# print(mrs)
#
#
# for i in range(1,len(mrs),2):
# print(mrs[i])
# print(mrs[i][0])
# kmeans_mr.append(mrs[i][0])
# print(str(mrs[i][0]) + " appended "
completeness_scores_plot = add_cluster_subplot(fig1, 234, 'completeness_scores')
homogeneity_scores_plot = add_cluster_subplot(fig1, 235, 'homogeneity_scores')
value = [hierach_MR , kmeans_mr, ds_mr]
# Define curves and their values
curves = [[mr_plot, value]]
algorithm = ["Agglomerative_Hierachial_Clustering",
"K_Means_Clustering",
"DominantSets_Clustering"]
# Plot all curves
for index in range(3):
label = algorithm[index]
color = colors[index]
# number_of_clusters = np.arange(number_of_embeddings[index], 0, -1)
for plot, value in curves:
print(value[index])
plot.plot(ks,value[index], color=color, label=label)
# Add legend and save the plot
fig1.legend()
# fig1.show()
fig1.savefig(get_result_png(plot_file_name))
print("Plot File saved in " + get_result_png(plot_file_name) )
fig1.savefig(get_result_png(plot_file_name + '.svg'), format='svg')
def _plot_curves(plot_file_name, curve_names, metric_sets,
number_of_embeddings):
"""
Plots all specified curves and saves the plot into a file.
:param plot_file_name: String value of save file name
:param curve_names: Set of names used in legend to describe this curve
:param metric_sets: A list of 2D matrices, each row of a metrics 2D matrix describes one dataset for a curve
:param number_of_embeddings: set of integers, each integer describes how many embeddings is in this curve
"""
logger = get_logger('analysis', logging.INFO)
logger.info('Plot results')
config = load_config(None, join(get_common(), 'config.cfg'))
plot_width = config.getint('common', 'plot_width')
fig_width = config.getint('common', 'fig_width')
fig_height = config.getint('common', 'fig_height')
#Slice results to only 1-80 clusters
for i in range(0, len(metric_sets)):
for j in range(0, len(metric_sets[i])):
metric_sets[i][j] = metric_sets[i][j][-plot_width:]
print(len(metric_sets[i][j]))
best_results = [[] for _ in metric_names]
for m, min_value in enumerate(metric_min_values):
for results in metric_sets[m]:
if (metric_min_values[m] == 0):
best_results[m].append(np.max(results))
else:
best_results[m].append(np.min(results))
'''
This code is used to sort the lines by min mr. Because we now use mutliple metrics and dont sort by a single
metric, this code is not used anymore, but we keep it for now.
min_mrs, curve_names, mrs, acps, aris, homogeneity_scores, completeness_scores, number_of_embeddings = \
(list(t) for t in
zip(*sorted(zip(min_mrs, curve_names, mrs, acps, aris, homogeneity_scores, completeness_scores, number_of_embeddings))))
'''
# How many lines to plot
number_of_lines = len(curve_names)
# Get various colors needed to plot
color_map = plt.get_cmap('gist_rainbow')
colors = [color_map(i) for i in np.linspace(0, 1, number_of_lines)]
#Set fontsize for all plots
plt.rcParams.update({'font.size': 12})
# Define number of figures
fig1 = plt.figure(figsize=(fig_width, fig_height))
# Define Plots
plot_grid = (3, 2)
plots = [None] * len(metric_names)
plots[0] = _add_cluster_subplot(plot_grid, (0, 0), metric_names[0], 1)
plots[1] = _add_cluster_subplot(plot_grid, (0, 1), metric_names[1], 1)
plots[2] = _add_cluster_subplot(plot_grid, (1, 0), metric_names[2], 1)
plots[3] = _add_cluster_subplot(plot_grid, (1, 1), metric_names[3], 1)
#Set the horizontal space between subplots
plt.subplots_adjust(hspace=0.3)
# Define curves and their values
curves = [[] for _ in metric_names]
for m, metric_set in enumerate(metric_sets):
curves[m] = [plots[m], metric_set]
# Plot all curves
for index in range(number_of_lines):
label = curve_names[index]
for m, metric_name in enumerate(metric_names):
label = label + '\n {} {}: {}'.format(
'Max' if metric_min_values[m] == 0 else 'Min', metric_name,
str(best_results[m][index]))
color = colors[index]
number_of_clusters = np.arange(plot_width, 0, -1)
for plot, value in curves:
plot.plot(number_of_clusters,
value[index],
color=color,
label=label)
# Add legend and save the plot
fig1.legend(loc='upper center', bbox_to_anchor=(0.5, 0.33), ncol=4)
#fig1.show()
fig1.savefig(get_result_png(plot_file_name))
fig1.savefig(get_result_png(plot_file_name + '.svg'), format='svg')
def plot_curves(plot_file_name, loaded_dict, loaded_dict2, loaded_dict3):
"""
Plots all specified curves and saves the plot into a file.
:param plot_file_name: String value of save file name
:param curve_names: Set of names used in legend to describe this curve
:param mrs: 2D Matrix, each row describes one dataset of misclassification rates for a curve
:param homogeneity_scores: 2D Matrix, each row describes one dataset of homogeneity scores for a curve
:param completeness_scores: 2D Matrix, each row describes one dataset of completeness scores for a curve
:param number_of_embeddings: set of integers, each integer describes how many embeddings is in this curve
"""
logger = get_logger('analysis', logging.INFO)
logger.info('Plot results')
num_clusters = []
hierach_MR = []
kmeans_mr = []
ds_mr = []
for x in loaded_dict:
num_clusters.append(x)
hierach_MR.append(loaded_dict[x])
# print(str(loaded_dict[x]) + " appended to " + str(x))
print("\n")
print("Hierachial MR")
hierach_MR.sort()
print(hierach_MR)
for x in loaded_dict2:
kmeans_mr.append(loaded_dict2[x])
# print(str(loaded_dict[x]) + " appended to " + str(x))
print("\n")
print("Kmeans MR")
kmeans_mr.sort()
print(kmeans_mr)
for x in loaded_dict3:
ds_mr.append(loaded_dict3[x])
# print(str(loaded_dict[x]) + " appended to " + str(x))
print("\n")
print("DS MR")
ds_mr.sort()
print(ds_mr)
print(num_clusters)
ks = list(loaded_dict3)
ks = list(map(int, ks))
print("\n")
print("Cluster Count")
ks.sort()
print(ks)
print("Minimum Cluster : " + str(min(ks)))
print("Maximum CLuster : " + str(max(ks)) + "\n")
maxc = max(ks)
minc = min(ks)
# Get various colors needed to plot
color_map = plt.get_cmap('gist_rainbow')
colors = [color_map(i) for i in np.linspace(0, 1, 5)]
# Define number of figures
fig1 = plt.figure(1)
fig1.set_size_inches(16, 8)
# # Define Plots
# mr_plot = plt.subplot2grid((1, 1), (0, 0), colspan=1)
# mr_plot.set_ylabel('MR')
# mr_plot.set_xlabel('Number of clusters')
# # plt.grid(True)
plt.title("Plot for DominantSets Clustering for pairwise_lstm")
plt.axis([(minc - 0.1), (maxc + 0.1), -0.02, 0.2])
plt.xlabel('Number of clusters')
plt.ylabel("MR")
value = [ds_mr, hierach_MR, kmeans_mr]
# Define curves and their values
# curves = [[mr_plot, value]]
algorithm = [
"DominantSets_Clustering", "Agglomerative_Hierachial_Clustering",
"K_Means_Clustering"
]
# Plot all curves
for index in range(1):
ymax = max(value[index])
xpos = value[index].index(ymax)
print("xpos " + str(xpos))
xmax = ks[xpos]
temp = 'Max Value : ' + str((xmax, ymax))
# plt.annotate(temp , xy=(xmax, ymax), xytext=(xmax-50, ymax + 0.05),
# arrowprops=dict(facecolor=colors[index], shrink=0.03 ),)
print("plotting " + algorithm[index])
label = algorithm[index]
color = colors[index]
plt.plot(ks, value[index], color=color, label=label)
# for plot, value in curves:
# # plot.plot(ks,value[index], color=color, label=label)
# Add legend and save the plot
fig1.legend()
fig1.show()
fig1.savefig(get_result_png(plot_file_name))
print("Plot File saved in " + get_result_png(plot_file_name))
fig1.savefig(get_result_png(plot_file_name + '.svg'), format='svg')