def setUpClass(cls):
file_name = "datasets/cstr.mat"
matlab_dict = loadmat(file_name)
X = matlab_dict['fea'] # numpy.ndarray
model = CoclustMod(n_clusters=4)
model.fit(X)
cls.model = model
def setUpClass(cls):
file_name = "datasets/classic3.mat"
matlab_dict = loadmat(file_name)
X = matlab_dict['A'] # scipy.sparse.csc.csc_matrix
model = CoclustMod(n_clusters=3)
model.fit(X)
cls.model = model
def setUpClass(cls):
file_name = "datasets/classic3.mat"
matlab_dict = loadmat(file_name)
X = matlab_dict['A'] # scipy.sparse.csc.csc_matrix
model = CoclustMod(n_clusters=3)
model.fit(X)
cls.model = model
def setUpClass(cls):
file_name = "datasets/cstr.mat"
matlab_dict = loadmat(file_name)
X = matlab_dict['fea'] # numpy.ndarray
model = CoclustMod(n_clusters=4)
model.fit(X)
cls.model = model
def run_coclust(self):
# co-clustering
model = CoclustMod(n_clusters=4)
model.fit(
self.doc_term_mat
) # No errors? Is this right? Gensim types have plug-and-play support?
top_term_plt = plot_cluster_top_terms(in_data=self.doc_term_mat,
all_terms=self.vocab,
nb_top_terms=5,
model=model,
do_plot=False)
# print(get_term_graph(X=doc_term_mat,
# model=model,
# terms=vocab,
# n_cluster=2,
# n_top_terms=10,
# n_neighbors=2,
# stopwords=[]))
clus_sz_plt = plot_cluster_sizes(model=model, do_plot=False)
mat_plot = plot_reorganized_matrix(X=self.doc_term_mat,
model=model,
do_plot=False)
return (top_term_plt, clus_sz_plt, mat_plot)
def cluster(self, data):
global weighted_edge_list, matrix, model, row_order, column_order, rowMap, colMap, subModels, row_sums_map, column_sums_map
subModels = {}
# num_clusters = 9
weighted_edge_list = data[[
"RECHTSTRAEGER", "MEDIUM_MEDIENINHABER", "EURO"
]]
weighted_edge_list = weighted_edge_list.groupby(
by=["RECHTSTRAEGER", "MEDIUM_MEDIENINHABER"]).sum().reset_index()
G = nx.from_pandas_dataframe(weighted_edge_list,
"RECHTSTRAEGER",
"MEDIUM_MEDIENINHABER",
"EURO",
create_using=nx.DiGraph())
row_order = np.sort(np.unique(weighted_edge_list["RECHTSTRAEGER"]))
column_order = np.sort(
np.unique(weighted_edge_list["MEDIUM_MEDIENINHABER"]))
matrix_real = biadjacency_matrix(G,
row_order,
column_order=column_order,
weight="EURO")
matrix = matrix_real.toarray()
row_sums = matrix.sum(axis=1).round(2)
row_sums_map = dict(zip(row_order, row_sums))
row_sums_map = {k: float(v) for k, v in row_sums_map.items()}
column_sums = matrix.sum(axis=0).round(2)
column_sums_map = dict(zip(column_order, column_sums))
column_sums_map = {k: float(v) for k, v in column_sums_map.items()}
model = CoclustMod(min(min(matrix.shape), num_clusters),
random_state=0) #n_init=500
model.fit(matrix)
#test andere liste senden
rowMap = dict(zip(row_order, list(map(str, model.row_labels_))))
colMap = dict(zip(column_order, list(map(str, model.column_labels_))))
ret = []
wel = weighted_edge_list.copy()
wel["RECHTSTRAEGER"].update(wel["RECHTSTRAEGER"].map(rowMap))
wel["MEDIUM_MEDIENINHABER"].update(
wel["MEDIUM_MEDIENINHABER"].map(colMap))
ret = wel.as_matrix().tolist()
clusters = self.getElementsbyCluster()
return {"data": ret, "clusters": clusters}
def subcluster3(self, clusterID):
global subModels
clusterID_array = [int(x) for x in clusterID.split('.')]
# print(clusterID_array)
# print("subModels",subModels)
subMatrix = model.get_submatrix(matrix, clusterID_array[0])
sub_row_order = row_order[model.get_indices(clusterID_array[0])[0]]
sub_column_order = column_order[model.get_indices(
clusterID_array[0])[1]]
for i, cID in enumerate(clusterID_array[1:]):
smID = '.'.join(str(x) for x in clusterID_array[:(i + 1)])
print("smID", smID)
sm = subModels[smID]
subMatrix = sm.get_submatrix(subMatrix, cID)
sub_row_order = sub_row_order[sm.get_indices(cID)[0]]
sub_column_order = sub_column_order[sm.get_indices(cID)[1]]
zeros_cols = np.where(~subMatrix.any(axis=0))[0]
zeros_rows = np.where(~subMatrix.any(axis=1))[0]
subMatrix = np.delete(subMatrix, zeros_cols, 1)
subMatrix = np.delete(subMatrix, zeros_rows, 0)
sub_row_order = np.delete(sub_row_order, zeros_rows)
sub_column_order = np.delete(sub_column_order, zeros_cols)
num_clusters2 = min(min(subMatrix.shape), num_clusters)
subModel = CoclustMod(num_clusters2, random_state=0)
subModels[clusterID] = subModel
# print("subModels",subModels)
subModel.fit(subMatrix)
for i, label in enumerate(subModel.row_labels_):
rowMap[sub_row_order[i]] = str(clusterID) + "." + str(label)
for i, label in enumerate(subModel.column_labels_):
colMap[sub_column_order[i]] = str(clusterID) + "." + str(label)
# ret = []
# wel = weighted_edge_list.copy()
# wel["RECHTSTRAEGER"].update(wel["RECHTSTRAEGER"].map(rowMap))
# wel["MEDIUM_MEDIENINHABER"].update(wel["MEDIUM_MEDIENINHABER"].map(colMap))
rowLabelSet = set(
[str(clusterID) + "." + str(x) for x in subModel.row_labels_])
colLabelSet = set(
[str(clusterID) + "." + str(x) for x in subModel.column_labels_])
#---
rowMap2 = {
k: (v if v in rowLabelSet else "Sonstige")
for k, v in rowMap.items()
}
colMap2 = {
k: (v if v in colLabelSet else "Sonstige")
for k, v in colMap.items()
}
wel = weighted_edge_list.copy()
# print(rowLabelSet)
wel["RECHTSTRAEGER"].update(wel["RECHTSTRAEGER"].map(rowMap2))
wel["MEDIUM_MEDIENINHABER"].update(
wel["MEDIUM_MEDIENINHABER"].map(colMap2))
idc = wel[(
wel["RECHTSTRAEGER"].astype(str).str[:len(clusterID)] != clusterID)
& (wel["MEDIUM_MEDIENINHABER"].astype(
str).str[:len(clusterID)] != clusterID)].index
wel = wel.drop(idc)
wel2 = weighted_edge_list.copy()
wel2 = wel2.drop(idc)
row_sums_map2 = wel2.groupby(
by=["RECHTSTRAEGER"]).sum().to_dict()["EURO"]
row_sums_map2 = {k: float(v) for k, v in row_sums_map2.items()}
column_sums_map2 = wel2.groupby(
by=["MEDIUM_MEDIENINHABER"]).sum().to_dict()["EURO"]
column_sums_map2 = {k: float(v) for k, v in column_sums_map2.items()}
ret = []
ret = wel.as_matrix().tolist()
# clusters = self.getElementsbyCluster()
inv_rowMap2 = {}
for k, v in rowMap2.items():
inv_rowMap2.setdefault(v, []).append(k)
inv_colMap2 = {}
for k, v in colMap2.items():
inv_colMap2.setdefault(v, []).append(k)
clusters = {}
for label in inv_rowMap2:
clusters[label] = {
"rows": {
k: row_sums_map2[k]
for k in inv_rowMap2[label] if k in row_sums_map2
},
"columns": {
k: column_sums_map2[k]
for k in inv_colMap2[label] if k in column_sums_map2
}
}
return {"data": ret, "clusters": clusters}
from scipy.io import loadmat from coclust.coclustering import CoclustMod file_name = "/home/sayon/Dropbox/MyModules/Canvass/cclust_package/datasets/som.mat" matlab_dict = loadmat(file_name) X = matlab_dict['fea'] model = CoclustMod(n_clusters=4) model.fit(X) print(model.modularity) predicted_row_labels = model.row_labels_ predicted_column_labels = model.column_labels_
plt.matshow(euclidean_distances(Feafile.values, Feafile.values))
plt.colorbar()
plt.title('Show the Euclidean distance matrix')
plt.show()
# %%Combined usage
# The following example shows how easy coclust is to run several algorithms on the same dataset
import matplotlib.pyplot
import numpy as np, scipy.sparse as sp, scipy.io as io
from sklearn.metrics import confusion_matrix
from coclust.coclustering import (CoclustMod, CoclustSpecMod, CoclustInfo)
from coclust.visualization import plot_reorganized_matrix
X = Feafile.values
model_1 = CoclustMod(n_clusters=4, n_init=4)
model_1.fit(X)
model_2 = CoclustSpecMod(n_clusters=4, n_init=4)
model_2.fit(X)
model_3 = CoclustInfo(n_row_clusters=3, n_col_clusters=4, n_init=4)
model_3.fit(X)
plt.figure()
plt.title(' plot three reorganized matrices for the dataset')
plt.subplot(131)
plot_reorganized_matrix(X, model_1)
plt.subplot(132)
plot_reorganized_matrix(X, model_2)
plt.subplot(133)
plot_reorganized_matrix(X, model_3)
plt.show()
# plot the resulting reorganized matrices in order to have a first visual grasp of what can be expected from the different algorithms. A plot of three different reorganized matrices
def setUpClass(cls):
model = CoclustMod(n_clusters=3)
X = np.diag(range(1, 200))
model.fit(X)
cls.model = model
def setUpClass(cls):
model = CoclustMod(n_clusters=3)
X = np.diag(range(1, 200))
model.fit(X)
cls.model = model
def genes_articles():
print(request.json)
tfidf = request.json["tfidf"]
distance = request.json["distance"]
coclust = int(request.json["coclust"])
selected_genes = [v["label"] for v in request.json["genes"]]
nb_cluster = int(request.json["nb"])
genes_articles_str = [
' '.join(str(x) for x in genesjson[g]) for g in selected_genes
]
if tfidf:
vec = TfidfVectorizer()
else:
vec = CountVectorizer()
X = vec.fit_transform(genes_articles_str)
nb = nb_cluster
if nb_cluster == 0 and coclust != 3:
xn = X.shape[0]
step = round(xn / 10) if round(xn / 10) > 0 else 1
rng = range(1, xn, step)
# _, modularities = best_modularity_partition(X, rng, n_rand_init=1)
# nb = rng[np.argmax(modularities)]
modularities = []
for x in rng:
print(x)
m = CoclustMod(n_clusters=x, n_init=1).fit(X)
modularities.append(m.modularity)
nb = rng[np.argmax(modularities)]
if coclust == 1:
model = CoclustMod(n_clusters=nb, random_state=0)
if coclust == 2:
model = CoclustSpecMod(n_clusters=nb, random_state=0)
if coclust == 3:
model = CoclustInfo()
dt = X.toarray()
model.fit(dt)
fit_data = dt[np.argsort(model.row_labels_)]
fit_data = fit_data[:, np.argsort(model.column_labels_)]
plt.figure(figsize=(22, 5))
if nb_cluster == 0 and coclust != 3:
plt.subplot(131)
plt.plot(rng, modularities, 'ro-')
plt.xlabel("Number of cluster")
plt.ylabel("Modularity")
plt.title("Max modularity for " + str(nb) + " clusters (" +
str(round(np.max(modularities), 3)) + ")")
plt.axvline(x=nb, color='r', linestyle='-')
plt.subplot(132)
sns.heatmap(dt,
cmap="BuPu",
yticklabels=False,
xticklabels=False,
cbar=False)
plt.title("Heatmap on Original Data")
plt.subplot(133)
sns.heatmap(fit_data,
cmap="BuPu",
yticklabels=False,
xticklabels=False,
cbar=False)
plt.title("CoclustMod %i clusters" % nb)
plt.savefig("img-ga1.jpg", bbox_inches='tight', pad_inches=0)
# hierarchical clustering
Z = linkage(dt, 'single', 'euclidean')
plt.figure(figsize=(15, 7))
plt.xlabel('')
plt.ylabel('distance')
dendrogram(Z, labels=selected_genes)
plt.savefig("img-ga2.jpg", bbox_inches='tight', pad_inches=0)
plt.close('all')
return jsonify({"tab": 1})
def genes_termes():
tfidf = request.json["tfidf"]
coclust = int(request.json["coclust"])
selected_genes = [v["label"] for v in request.json["genes"]]
nb_cluster = int(request.json["nb"])
# get id articles from all genes
l = [genesjson[g] for g in selected_genes]
genes_articles = list(set([item for sublist in l for item in sublist]))
# get text from article
articles_text = [
' '.join(asthmajson[str(i)]["text"]) for i in genes_articles
]
if tfidf:
vec = TfidfVectorizer(max_df=0.7, min_df=0.01)
else:
vec = CountVectorizer(max_df=0.7, min_df=0.01)
dt = vec.fit_transform(articles_text)
matrix_article_terms = dt.toarray()
matrix_genes_terms = defaultdict(
lambda: np.zeros(matrix_article_terms.shape[1]).astype(np.float64))
for idx, row in enumerate(matrix_article_terms):
article = asthmajson[str(genes_articles[idx])]
for ge in article["genes"]:
if ge in selected_genes:
matrix_genes_terms[ge] += row
list_matrix_genes_terms = [v for k, v in matrix_genes_terms.items()]
list_genes = [k for k, v in matrix_genes_terms.items()]
#df3 = pd.DataFrame(list_matrix_genes_terms, columns=vec.get_feature_names())
if coclust == 1:
model = CoclustMod(n_clusters=nb_cluster, random_state=0)
if coclust == 2:
model = CoclustSpecMod(n_clusters=nb_cluster, random_state=0)
if coclust == 3:
model = CoclustInfo()
dt = np.array(list_matrix_genes_terms)
m1 = model.fit(dt)
fit_data = dt[np.argsort(model.row_labels_)]
fit_data = fit_data[:, np.argsort(model.column_labels_)]
plt.figure(figsize=(20, 8))
plt.subplot(121)
sns.heatmap(np.log(dt + 1),
cmap="BuPu",
yticklabels=False,
xticklabels=False,
cbar=False)
plt.title("Heatmap on Original Data", fontdict={'fontsize': 20})
plt.subplot(122)
sns.heatmap(np.log(fit_data + 1),
cmap="BuPu",
yticklabels=False,
xticklabels=False,
cbar=False)
plt.title("CoclustMod %i clusters" % nb_cluster, fontdict={'fontsize': 20})
plt.savefig("img-gt1.jpg", bbox_inches='tight', pad_inches=0)
# Top terms by cluster
nb_clust = np.unique(model.column_labels_)
nm = np.array(vec.get_feature_names())
dt_sum = np.sum(dt, axis=0)
col_label = np.array(model.column_labels_)
cluster = []
for c in nb_clust:
idx = np.argsort(-dt_sum[col_label == c])
col = nm[np.array(model.column_labels_) == c]
value = dt_sum[col_label == c][idx]
name = col[idx]
cluster.append({"name": list(name[0:8]), "value": list(value[0:8])})
# hierarchical clustering
Z = linkage(dt, 'single', 'euclidean')
plt.figure(figsize=(15, 7))
# plt.title('Hierarchical Clustering - Hamming')
plt.xlabel('')
plt.ylabel('distance')
dendrogram(Z, labels=list_genes)
plt.savefig("img-gt2.jpg", bbox_inches='tight', pad_inches=0)
plt.close('all')
return jsonify({"tab": 2, "cluster": cluster})