gistfile1.py

import seaborn as sns
from sklearn.decomposition import PCA

x_pca = PCA(n_components=2).fit_transform(X)
sns.jointplot("PCA_0", "PCA_1", x_pca)

import pylab as plt
from sklearn.metrics.pairwise import pairwise_distances
from sklearn.manifold import TSNE

model = TSNE(n_components=2, metric=pairwise_distances)
tsne_X = model.fit_transform(X) 
plt.scatter(tsne_X.tsne_1, tsne_X.tsne_2)

from sklearn.cluster import DBSCAN
db = DBSCAN(eps=0.5, min_samples=16).fit(tsne_X.values)



neigh = KNeighborsClassifier(n_neighbors=10,
                             weights='distance')
has_cluster = ~np.isnan(X_clustered.cluster)
train_dat = X_clustered[has_cluster][['PCA_0', 'PCA_1']]
y = X_clustered[has_cluster].cluster
neigh.fit(train_dat, y)
predict_data = X_clustered[~has_cluster][['PCA_0', 'PCA_1']]
neigh.predict(predice_data)