clustering k-means are not spherical

Question

I'm a beginner in data science and I need your help I'm trying to test unsupervised machine learning with the K-means but I found that the result is not spherical. I normalized, I removed the outliers etc. I tried to find several way to correct it but it doesn't work

Here are pictures: (I took a little sample of the dataset to show you, it's actually 8000 rows)

enter image description here ...

What are you plotting? what are x-axis and y-axis?. Provide some piece of code, please — lsmor, Jan 24 '19 at 11:44

score 2 · Answer 1 · edited Jan 24 '19 at 12:43

2

from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler

pca = PCA(n_components=2)

principalComponents = pca.fit_transform(df)

principalDf = pd.DataFrame(data = principalComponents, columns = ['principal component 1', 'principal component 2'])

principalDf.head(5)

I used the PCA to reduce the 6 dimensions to 2 : It separates the data perfectly

Output: Output

edited Jan 24 '19 at 12:43

Venkatachalam

16,288
9
49
77

answered Jan 24 '19 at 11:54

Thao Ly

33
6

score 1 · Accepted Answer · answered Jan 24 '19 at 11:39

1

Your data have 6 dimensions. You can't visualize data above 2 dimension in a straight forward manner, you need to use PCA or TSNE to visualize them.

answered Jan 24 '19 at 11:39

Bhaskar Dhariyal

1,343
2
13
31

What did you try? Also try posting your answer as it will help some one else :) – Bhaskar Dhariyal Jan 24 '19 at 11:48
I used PCA to reduce the 6 dimension to 2 , yes I will post it :) – Thao Ly Jan 24 '19 at 11:50

clustering k-means are not spherical

2 Answers2