def clusterRegularVerbs_AgglomerativeClustering():
from sklearn.cluster import AgglomerativeClustering
from sklearn import metrics
from sklearn.datasets.samples_generator import make_blobs
from sklearn.preprocessing import StandardScaler
from numpy import genfromtxt
my_data = genfromtxt('FeatureMatrix_number.csv', delimiter=',', skip_header=1)
clustering = AgglomerativeClustering(linkage='complete', n_clusters=11)
clustering.fit(my_data)
params = clustering.get_params(deep=True)
return clustering
def perform_hierarchial(self, no_clusters, params={}):
hierarchial_clusterer = AgglomerativeClustering(n_clusters=no_clusters,
**params)
hierarchial_clusterer.fit(self.data, hdf5_file=self.hdf5_file)
self.hierarchial_results = {
"parameters": hierarchial_clusterer.get_params(),
"labels": hierarchial_clusterer.labels_,
"n_clusters": no_clusters,
'clusters': label_cnt_dict(hierarchial_clusterer.labels_)
}
print_dict(self.hierarchial_results)
def baseline_ac(data_matrix, k, plot_params={'plotit':True,
'x': 'latitude',
'y': 'longitude',
'show': True}):
# Baseline AC clusters using banned library
model = AgglomerativeClustering(n_clusters=k, affinity='euclidean', linkage='average')
labels = model.fit_predict(data_matrix)
print('Model Params: ')
print( model.get_params() )
if plot_params['plotit']:
x = plot_params['x']
y = plot_params['y']
plot(data_matrix, labels, title=plot_params['title'], show=plot_params['show'], xlabel=x, ylabel=y )
return
affinities = ('cosine', )
linkages = ('complete', 'average')
n_clusterss = (5, 10, 20, 30)
tau = 0.9
methods = list()
if algo == "agglomerative":
# agglomerative
for affinity, linkage, n_clusters in itertools.product(
affinities, linkages, n_clusterss):
agg = AgglomerativeClustering(n_clusters=n_clusters,
affinity=affinity,
linkage=linkage)
params = agg.get_params()
params.pop('memory')
params.pop('pooling_func')
info = {
'name': 'Agglomerative Clustering',
"rep": rep,
"rep_params": rep_params,
'params': params
}
methods.append((agg, info))
elif algo == "kmeans" or algo == "k-means":
# k-means
for n_clusters in n_clusterss:
km = KMeans(n_clusters=n_clusters,
n_jobs=-1,
def _agglomerative_clustering(table,
input_cols,
prediction_col='prediction',
linkage='ward',
affinity='euclidean',
n_clusters=2,
compute_full_tree_auto=True,
compute_full_tree=None):
feature_names, inputarr = check_col_type(table, input_cols)
_compute_full_tree = 'auto' if compute_full_tree_auto else compute_full_tree
_affinity = 'euclidean' if linkage == 'ward' else affinity
ac = AgglomerativeClustering(linkage=linkage,
affinity=_affinity,
n_clusters=n_clusters,
compute_full_tree=_compute_full_tree)
ac.fit(inputarr)
label_name = {
'linkage': 'Linkage',
'affinity': 'Affinity',
'n_clusters': 'N Clusters',
'compute_full_tree': 'Compute Full Tree'
}
get_param = ac.get_params()
param_table = pd.DataFrame.from_items(
[['Parameter', list(label_name.values())],
['Value', [get_param[x] for x in list(label_name.keys())]]])
labels = ac.labels_
colors = cm.nipy_spectral(np.arange(n_clusters).astype(float) / n_clusters)
if len(feature_names) > 1:
pca2_model = PCA(n_components=2).fit(inputarr)
pca2 = pca2_model.transform(inputarr)
fig_samples = _agglomerative_clustering_samples_plot(
labels, table, input_cols, 100, n_clusters, colors) if len(
table.index) > 100 else _agglomerative_clustering_samples_plot(
labels, table, input_cols, None, n_clusters, colors)
if len(feature_names) > 1:
fig_pca = _agglomerative_clustering_pca_plot(labels, pca2_model, pca2,
n_clusters, colors)
rb = BrtcReprBuilder()
rb.addMD(
strip_margin("""
| ## Spectral Clustering Result
| ### Samples
| {fig_samples}
| {fig_pca}
| ### Parameters
| {params}
""".format(fig_pca=fig_pca,
fig_samples=fig_samples,
params=pandasDF2MD(param_table))))
else:
rb = BrtcReprBuilder()
rb.addMD(
strip_margin("""
| ## Mean Shift Result
| - Samples
| {fig_samples}
| ### Parameters
| {params}
""".format(fig_samples=fig_samples, params=pandasDF2MD(param_table))))
model = _model_dict('agglomerative_clustering')
model['model'] = ac
model['input_cols'] = input_cols
model['_repr_brtc_'] = rb.get()
out_table = table.copy()
out_table[prediction_col] = labels
return {'out_table': out_table, 'model': model}
from sklearn.cluster import AgglomerativeClustering
import numpy as np
data = np.loadtxt(r'sp3combined.test.txt',
delimiter=',',
skiprows=19995,
usecols=(4, 5, 6, 7, 8, 9, 10))
for d in data:
estimator = AgglomerativeClustering(n_clusters=2)
estimator.fit_predict(d)
estimator.get_params(d)
# ======================================================================= # data # ======================================================================= X = np.array([[1, 2], [1, 4], [1, 0], [4, 2], [4, 4], [4, 0]]) X_test = np.array([[1, 3], [2, 4]]) # ======================================================================= # clustering # ======================================================================= clustering = AgglomerativeClustering() clustering.fit(X) print(clustering) print(clustering.get_params()) print(clustering.labels_) print(clustering.n_leaves_) print(clustering.n_components_) print(clustering.children_) predictions = clustering.fit_predict(X_test) print(predictions)
