def fit(self, X, y=None):
self._sklearn_model = SKLModel(**self._hyperparams)
if (y is not None):
self._sklearn_model.fit(X, y)
else:
self._sklearn_model.fit(X)
return self
def __init__(self,
n_components=None,
whiten=False,
copy=True,
batch_size=None):
self._hyperparams = {
'n_components': n_components,
'whiten': whiten,
'copy': copy,
'batch_size': batch_size
}
self._wrapped_model = SKLModel(**self._hyperparams)
def __init__(self,
X_train,
freq_itemset_dict,
rule_list,
contrast_params,
epsilon=5e-5,
eps_step=0.1,
reduced_rate=None):
self.rule_list = rule_list
self.freq_itemset_dict = freq_itemset_dict
self.original_features = X_train
self.sample_features = X_train
self.contrast_params = contrast_params
self.epsilon = epsilon
self.eps_step = eps_step
if reduced_rate is not None:
ncomponents = int(X_train.shape[1] * reduced_rate)
pca = IncrementalPCA(n_components=ncomponents)
self.sample_features = pca.fit_transform(X_train)
class IncrementalPCAImpl():
def __init__(self,
n_components=None,
whiten=False,
copy=True,
batch_size=None):
self._hyperparams = {
'n_components': n_components,
'whiten': whiten,
'copy': copy,
'batch_size': batch_size
}
def fit(self, X, y=None):
self._sklearn_model = SKLModel(**self._hyperparams)
if (y is not None):
self._sklearn_model.fit(X, y)
else:
self._sklearn_model.fit(X)
return self
def transform(self, X):
return self._sklearn_model.transform(X)
config = CommandArgs({'feature' : ('', 'Path of features file'),
'cluster' : ('', 'Path of clusters file'),
'output' : ('', 'Path of output file'),
'title' : ('Dataset', 'Title of charts')
})
if not config.load(sys.argv):
print ('Argument is not correct. Please try again')
sys.exit(2)
X, association_rules = load_feature_vectors(config.get_value('feature'))
m = 2
print('dimensional reduce: ' + str(m))
pca = IncrementalPCA(n_components = X.shape[1]//m)
new_X = pca.fit_transform(X)
clusters, number_of_clusters = load_clusters(config.get_value('cluster'))
print (number_of_clusters)
unique_colors = get_N_HexCol(number_of_clusters + 1)
Y = []
for rule in association_rules:
cluster_id = clusters[rule]
Y.append(unique_colors[cluster_id + 1])
#plt.scatter(new_X[:,0], new_X[:,1], c = np.array(Y), alpha = 0.9, s = 10)
#plt.title(config.get_value('title'))
#plt.savefig(config.get_value('output'), format='PNG',bbox_inches='tight')
print()
# show PCA
pca_queries = [
"ID:wrapper", "ID:container", "ID:msg", "ID:alert", "ID:list",
"ID:seq", "ID:lst", "ID:list", "LIT:error"
]
pca_vectors = []
pca_labels = []
for _, name in enumerate(pca_queries):
if name.startswith("LIT:"):
print_name = "\"" + name.replace(
"LIT:", "") + "\"" # assumes string literals only
else:
print_name = name.replace("ID:", "")
pca_labels.append(print_name)
pca_vectors.append(model.wv[name])
ipca = IncrementalPCA(n_components=2)
reduced_vectors = ipca.fit_transform(pca_vectors)
fig, ax = pyplot.subplots()
x = reduced_vectors[:, 0]
y = reduced_vectors[:, 1]
ax.scatter(x, y)
for idx, label in enumerate(pca_labels):
#escaped_label = re.escape(label)
ax.annotate(label, (x[idx], y[idx]))
pyplot.show()
'FunctionTransformer':FunctionTransformer(), 'GMM':GMM(), 'GaussianMixture':GaussianMixture(), 'GaussianNB':GaussianNB(), 'GaussianProcess':GaussianProcess(), 'GaussianProcessClassifier':GaussianProcessClassifier(), 'GaussianProcessRegressor':GaussianProcessRegressor(), 'GaussianRandomProjection':GaussianRandomProjection(), 'GenericUnivariateSelect':GenericUnivariateSelect(), 'GradientBoostingClassifier':GradientBoostingClassifier(), 'GradientBoostingRegressor':GradientBoostingRegressor(), 'GraphLasso':GraphLasso(), 'GraphLassoCV':GraphLassoCV(), 'HuberRegressor':HuberRegressor(), 'Imputer':Imputer(), 'IncrementalPCA':IncrementalPCA(), 'IsolationForest':IsolationForest(), 'Isomap':Isomap(), 'KMeans':KMeans(), 'KNeighborsClassifier':KNeighborsClassifier(), 'KNeighborsRegressor':KNeighborsRegressor(), 'KernelCenterer':KernelCenterer(), 'KernelDensity':KernelDensity(), 'KernelPCA':KernelPCA(), 'KernelRidge':KernelRidge(), 'LSHForest':LSHForest(), 'LabelPropagation':LabelPropagation(), 'LabelSpreading':LabelSpreading(), 'Lars':Lars(), 'LarsCV':LarsCV(), 'Lasso':Lasso(),