def __init__(self, inFolder, filename, algo,pca, whiten, outFolder='../resultData/nucleus',n_iteration =10, **kwargs):
'''
pca : None pour pas de PCA, nombre de composantes principales a garder sinon
dans kwargs je mets les parametres de la methode de clustering
n'oublions pas qu'il n'y a que 3,000 elements dans le training set donc tout va bien :))
'''
assert algo in methods, 'Given algorithm is not implemented'
#assert sorted(params[algo]) == sorted(kwargs.keys()), 'Parameters for given algorithm are not given'
self.file=os.path.join(inFolder, filename)
self.algo = algo
self.iterations= n_iteration
self.outFolder = outFolder
self.outFile = outFile.format(self.algo)
self.parameters = kwargs
self.pca = pca
self.whiten= whiten
try:
self.k = self.parameters["n_clusters"]
except KeyError:
self.k = self.parameters["n_components"]
def plotMoy(outFolder='../resultData/nucleus', show=False):
f=p.figure(figsize=(24,17))
for i, algo in enumerate(["gaussianmixture", 'mini-batchk-means', 'kernelk-means','spectralclustering']):
file_=open(os.path.join(outFolder, outFile.format(algo)), 'r')
resultDict = pickle.load(file_); file_.close()
perClass = []; perCluster = []
for parameter_set in resultDict:
currLperClass=[]
currLperCluster = []
for morphoClass in resultDict[parameter_set]:
currLperClass.append(np.mean(resultDict[parameter_set][morphoClass][0]))
currLperCluster.append(np.mean(resultDict[parameter_set][morphoClass][1]))
perClass.append(currLperClass)
perCluster.append(currLperCluster)
ax=f.add_subplot(2,2,i)
for k in range(len(perClass)):
ax.errorbar(np.mean(perCluster[k]), np.mean(perClass[k]), xerr = np.std(perCluster[k]), yerr=np.std(perClass[k]),
fmt = markers[methods.index(algo)],
label = '{}'.format(algo))
ax.grid(True)
ax.set_xlim(0,1)
ax.set_ylim(0,1)
ax.set_title("Algorithm {}, on average on all morphological classes".format(algo))
ax.set_xlabel("Nb of class elements in cluster/cluster size")
ax.set_ylabel("Nb of class elements in cluster/class size")
if show:
p.show()
else:
p.savefig(os.path.join(outFolder, 'figure_MOY.png'.format(algo)))
f=p.figure(figsize=(24,17))
for i, algo in enumerate(["gaussianmixture", 'mini-batchk-means', 'kernelk-means','spectralclustering']):
file_=open(os.path.join(outFolder, outFile.format(algo)), 'r')
resultDict = pickle.load(file_); file_.close()
perClass = []; perCluster = []
for parameter_set in resultDict:
currLperClass=[]
currLperCluster = []
for morphoClass in resultDict[parameter_set]:
currLperClass.append(np.mean(resultDict[parameter_set][morphoClass][2]))
currLperCluster.append(np.mean(resultDict[parameter_set][morphoClass][3]))
perClass.append(currLperClass)
perCluster.append(currLperCluster)
ax=f.add_subplot(2,2,i)
for k in range(len(perClass)):
ax.errorbar(np.mean(perCluster[k]), np.mean(perClass[k]), xerr = np.std(perCluster[k]), yerr=np.std(perClass[k]),
fmt = markers[methods.index(algo)],
label = '{}'.format(algo))
ax.grid(True)
ax.set_xlim(0,1)
ax.set_ylim(0,1)
ax.set_title("Algorithm {}, on average on all morphological classes".format(algo))
ax.set_xlabel("Cluster entropy")
ax.set_ylabel("Class entropy")
if show:
p.show()
else:
p.savefig(os.path.join(outFolder, 'figure_ENT_MOY.png'.format(algo)))
