Python list into numpy array

Question

I have seen lots of example of lists into arrays, but no examples of lists in this format into arrays, which is strange because the list format I present is the standard go-to way of defining a graph, point-to-point mapping that you would find in any table, csv, database, etc. I tried everything here with no luck. Thanks for any ideas.

Input and desired output

input= [[A, A, 0],
 [A, B, 5],
 [A, C, 3],
 [B, A, 5],
 [B, B, 0],
 [B, C, 6],
 [C, A, 3],
 [C, B, 6],
 [C, C, 0]]
desiredOutput= [[0, 5, 3],
 [5, 0, 6],
 [3, 6, 0]]

• user3431083: input= [[A, A, 0], [A, B, 5], [A, C, 3], [B, A, 5], [B, B, 0], [B, C, 6], [C, A, 3], [C, B, 6], [C, C, 0]] desiredOutput= [[0, 5, 3], [5, 0, 6], [3, 6, 0]]
• Julien Spronck: I think a module like pandas is often the way you can handle such data.

Answer 1

Here's one way to produce your adjacency matrix as a 2D Numpy array. It assumes that the input graph data is correct, in particular, that its length is a perfect square.

import numpy as np
graph_data = [
 ['A', 'A', 0], ['A', 'B', 5], ['A', 'C', 3],
 ['B', 'A', 5], ['B', 'B', 0], ['B', 'C', 6],
 ['C', 'A', 3], ['C', 'B', 6], ['C', 'C', 0],
]
size = np.sqrt(len(graph_data)).astype(np.int)
adjacency_matrix = np.array(graph_data)[:,-1].astype(np.int).reshape(size, size)
print(adjacency_matrix)

output

[[0 5 3]
 [5 0 6]
 [3 6 0]]

The above code also assumes that the graph data is in the proper order, since it ignores the letters. Of course, that's easily handled by sorting the graph data before attempting to convert it to an array. Eg,

graph_data.sort()

---

Here's a pure Python version that outputs a list of tuples:

graph_data = [
 ['A', 'A', 0], ['A', 'B', 5], ['A', 'C', 3],
 ['B', 'A', 5], ['B', 'B', 0], ['B', 'C', 6],
 ['C', 'A', 3], ['C', 'B', 6], ['C', 'C', 0],
]
graph_data.sort()
size = int(len(graph_data) ** 0.5)
it = iter(row[-1] for row in graph_data)
print(list(zip(*[it]*size)))

output

[(0, 5, 3), (5, 0, 6), (3, 6, 0)]

• user3431083: This solution was selected because it was exponentially faster than the other. Specifically, the solution which outputs a list of tuples, which then can be converted into a numpy array. Tested performance with a 1.8 million node example - the other suggestion took 10 seconds, but this solution was an amazing 0.3 seconds

Answer 2

You can just slice your array and reshape it:

input= [['A', 'A', 0], ['A', 'B', 5], ['A', 'C', 3], ['B', 'A', 5], ['B', 'B', 0], ['B', 'C', 6], ['C', 'A', 3], ['C', 'B', 6], ['C', 'C', 0]]
arr = np.array(input)
desiredOutput=arr[:, 2].reshape(3, 3).astype(np.float)
# array([[ 0., 5., 3.],
# [ 5., 0., 6.],
# [ 3., 6., 0.]])

• tobias_k: Provided that the entries in input are always in the correct order, i.e. the first two columns do not actually matter... (but if that's not the case, you could just sort the input)
• user3431083: Order is always alphabetical: order by col 1, then col 2.
• Julien Spronck: @tobias_k you're right ... it might not be the case.