def __init__(self, data, k_min=4, clusters=5):
self._data = data
#save the names
snames = pd.DataFrame({'samples': data.columns})
snames['id'] = [str(uuid.uuid4()) for x in range(0, snames.shape[0])]
self.snames = snames
#get the clusters
cd = data.corr()
acd = cluster_ordered_agglomerative(cd, clusters)
# add the k nearest neighbors from the tsne every point to its cluster point
tcd = TSNE(2).fit_transform(cd)
tcd = pd.DataFrame(tcd)
tcd.columns = ['x', 'y']
tcd.index = cd.columns
nns = pd.DataFrame(
NearestNeighbors(n_neighbors=k_min +
1).fit(tcd).kneighbors_graph(tcd).toarray())
nns.columns = cd.columns.copy()
nns.columns.name = 'sample_2'
nns.index = cd.columns.copy()
nns.index.name = 'sample_1'
nns = nns.unstack().reset_index().rename(columns={0: 'match'})
nns = nns[nns['match'] != 0]
nns = nns[nns['sample_1'] != nns['sample_2']]
## For each cluster samples add in nn samples
clusters = {}
for cluster_id in acd['cluster_id'].unique():
#print(cluster_id)
clusters[cluster_id] = set(
acd[acd['cluster_id'] == cluster_id].index)
for member in list(clusters[cluster_id]):
#print(member)
## add each points nearest neighbors
ns = list(nns.loc[nns['sample_1'] == member, 'sample_2'])
clusters[cluster_id] |= set(ns)
self.clusters = clusters
models = {}
for cluster_id in self.clusters:
models[cluster_id] = data[list(clusters[cluster_id])].\
apply(lambda x: pd.Series(OrderedDict(zip(
['min','max','mean','std','values'],
[np.min(x),np.max(x),np.mean(x),np.std(x)]+[list(x)]
))),1)
self.models = models
# 第 1 主成分と第 2 主成分の散布図 (転移温度の値でサンプルに色付け)
plt.scatter(score.iloc[:, 0],
score.iloc[:, 1],
c=dataset.iloc[:, 86],
cmap=plt.get_cmap('jet'))
plt.colorbar()
plt.xlabel('t_1 (PCA)')
plt.ylabel('t_2 (PCA)')
plt.show()
# t-SNE
selected_indexes = np.arange(0, autoscaled_x.shape[0], 5)
autoscaled_x = autoscaled_x.iloc[selected_indexes, :]
t = TSNE(perplexity=perplexity, n_components=2, init='pca',
random_state=10).fit_transform(autoscaled_x)
t = pd.DataFrame(t,
index=autoscaled_x.index,
columns=['t_1 (t-SNE)', 't_2 (t-SNE)'])
t.columns = ['t_1 (t-SNE)', 't_2 (t-SNE)']
t.to_csv('tsne_t.csv')
# t1 と t2 の散布図 (転移温度の値でサンプルに色付け)
plt.rcParams['font.size'] = 18
plt.scatter(t.iloc[:, 0],
t.iloc[:, 1],
c=dataset.iloc[selected_indexes, 86],
cmap=plt.get_cmap('jet'))
plt.colorbar()
plt.xlabel('t_1 (t-SNE)')
plt.ylabel('t_2 (t-SNE)')
plt.show()
#train_topics=get_top_topics(nmf, spleen.index, n_top_words)
#print_top_words(nmf, spleen.index, n_top_words)
##-----------------------------------------------------------------------------
##visualization
pca = PCA(n_components=2)
embedding = pca.fit_transform(topic_matrix)
embedding = pd.DataFrame(embedding)
embedding.columns=['PC1','PC2']
f=sns.lmplot(x='PC1', y='PC2',data=embedding,
fit_reg=False,legend=False,scatter_kws={"s": 5})
f.savefig("pca",dpi=300)
embedding = TSNE(n_components=2).fit_transform(topic_matrix)
embedding = pd.DataFrame(embedding)
embedding.columns=['tSNE1','tSNE2']
sns.lmplot(x='tSNE1', y='tSNE2',data=embedding,
fit_reg=False,legend=False,scatter_kws={"s": 5,"color":"red"})
plt.savefig("tsne",dpi=300)
embedding = umap.UMAP(n_neighbors=5,
min_dist=0.3,
metric='correlation').fit_transform(topic_matrix)
embedding = pd.DataFrame(embedding)
embedding.columns=['UMAP1','UMAP2']
sns.lmplot(x='UMAP1', y='UMAP2',data=embedding,
fit_reg=False,legend=False,scatter_kws={"s": 5,"color":"green"})
plt.savefig("UMAP",dpi=300)
##-----------------------------------------------------------------------------
##clustering
