pdist | Calculate mean of pairwise weighted distances | Machine Learning library

I have a dataset constructed as a sparse weighted matrix for which I want to calculate weighted Jaccard index for downstream grouping/clustering, with inspiration from below article: http://static.googleusercontent.com/media/research.google.com/en//pubs/archive/36928.pdf

I'm facing a slight issue in finding the optimal way for doing the above calculation in Python. My current function to test my hypothesis is the following:

I have a data frame with shape:

I have a dendrogram calculated from some data points labeled 0-9.

How do I retrieve which datapoints (0-9) are in each node from the output of scipy.cluster.hiearchy.dendrogram? I want to label each node by its average (x,y) value. I know I can retrieve the clusters using the clustering algorithm (Scikit learn agglomerative clustering for example) but I want to label the whole dendrogram by the average value in each node.

Thank you for reading this. Currently I have a lot of latitude and longitude for many locations, and I need to create a matrix of distances for locations within 10km. (It's okay to fill the matrix with 0 distances between locations far more than 10km).

Data looks like:

I am comparing the Jaccard distance matrix I get when I process a dataset using pdist and a DIY Jaccard distance matrix function. I'm getting different results in my output distance matrices and I'm not sure why.

I think one of the following is the cause:

• My implementation of jaccard distance calculation is wrong
• scipy.spatial.distance.pdist(metric = 'jaccard') and scipy.spatial.distance.jaccard calculate jaccard distance in different ways (seems unlikely as their both in scipy.spatial.distance)
• squareform is doing something to my data, potentially a normalisation

The docs for squareform go a bit over my head so some form of normalisation might be what's happening. However, the squareform-ed distance matrix does not have the same relative distance magnitudes between cells which is confusing (e.g. row 0 in my DIY distance matrix is 0, 0.571429, 1, and with pdist is 0, 1, 1 - the middle value is twice as high with pdist).

Can anyone explain the why I'm getting a different distance matrix when it's being analysed with the same metric?

My code:

This question: Numpy where function multiple conditions asks how to use np.where with two conditions. This answer suggests to use the & operator between conditions, which works if we have a low number of conditions which can be typed. This answer suggests using the np.logical_and, which can take only two arguments.

This thread: Numpy "where" with multiple conditions also discusses multiple conditions for np.where, but the number of conditions are known in advance.

I am looking for a way to evaluate an np.where expression without knowing the number of conditions in advance.

I have a 2D array:

I have 2 classes in model and I would like to validate that value in a field from one class is smaller than field from second class. I went through Fluent documentation but I cannot find a real example.

sorry for my bad english. I am trying to compare two faces using python3 module 'face_recognition'

here is an example of calculating euclidean distance in python

pdist([vector1, vector2], 'euclidean')

I want to calculate euclidean distance only in SQL query, because all faces(theirs vectors) will be stored in my database, but I do not know how to do this with a SQL query.

Information:

MariaDB version: 10.5.11

Python: 3.9.2