How To Create A Frequency Tensor Out Of Two Tensor In Tensorflow

I have a tensor like this in which the values are the frequency and the rows are the index(0 to 6): tf_docs = [[0, 2], [1, 2], [2, 1], [5, 0], [0, 1], [7, 8], [9, 6]] I hav

Solution 1:

Let nonzero_tf_docs be defined as:

zero_tf_docs = tf.cast(tf.equal(tf_docs, tf.zeros_like(tf_docs)), tf.int32)
nonzero_tf_docs = 1 - tf.reduce_max(zero_tf_docs, axis=-1)

The OP is asking to compute the sum nonzero_tf_docs[i] + nonzero_tf_docs[j] for each pair of indices i, j in tf_topics and display the result in a matrix. This can be achieved as follows:

def compute_result(tf_topics_, nonzero_tf_docs, tf_docs):
    # Find matrix lower part
    values = tf.reduce_sum(tf.gather(nonzero_tf_docs, tf_topics_), axis=-1)
    max_index = tf.reduce_max(tf_topics) + 1
    out_sparse = tf.sparse.SparseTensor(indices=tf_topics_, values=values, dense_shape=[max_index, max_index])
    out_sparse = tf.cast(out_sparse, dtype=tf.int32)
    out_sparse = tf.sparse.reorder(out_sparse)
    out_dense = tf.sparse.to_dense(out_sparse, default_value=-1)
    out_lower = tf.matrix_band_part(out_dense, -1, 0)

    # Compute diagonal
    diag_values = tf.reduce_sum(tf_docs, axis=-1)
    diag = tf.slice(diag_values,
                    begin=[0],
                    size=[max_index])

    # Construct output matrix
    out = out_lower + tf.transpose(out_lower)
    mask = tf.eye(max_index, dtype=tf.int32)
    out = (1 - mask) * out + mask * diag

    return out


# Find docs without zeros
zero_tf_docs = tf.cast(tf.equal(tf_docs, tf.zeros_like(tf_docs)), tf.int32)
nonzero_tf_docs = 1 - tf.reduce_max(zero_tf_docs, axis=-1)

# Transform counts into matrix format
tf_topics = tf.cast(tf_topics, dtype=tf.int64)
tf_topics_reversed = tf.reverse(tf_topics, [-1])
tf_topics_ = tf_topics_reversed
out_1 = compute_result(tf_topics_, nonzero_tf_docs, tf_docs)
out_2 = compute_result(tf_topics, nonzero_tf_docs, tf_docs)
out = tf.maximum(out_1, out_2)

with tf.Session() as sess:
    r = sess.run(out)
    print(r)  # prints [[ 2110 -1]
              #         [ 13211]
              #         [ 12311]
              #         [ 01150]
              #         [-11101]]

Solution 2:

Thanks to your latest edits and to rvinas' answer I think I finally understood what you need. One of the things that was confusing me was the fact that there are "null" cells in the output matrix. Anyway, here is a way to do that:

import tensorflow as tf

deffreq_matrix(tf_docs, tf_topics):
    tf_docs = tf.convert_to_tensor(tf_docs)
    tf_topics = tf.convert_to_tensor(tf_topics)
    # Sort indices to make upper diagonal
    tf_topics = tf.sort(tf_topics, axis=1)
    # Largest index
    m = tf.reduce_max(tf_topics) + 1# Remove duplicates
    topics_flat = tf_topics[:, 0] * m + tf_topics[:, 1]
    topics_uniq, _ = tf.unique(topics_flat)
    tf_topics = tf.stack([topics_uniq // m, topics_uniq % m], axis=1)
    # Make diagonal
    diag = tf.reduce_sum(tf_docs[:m], axis=1)
    # Find non-zero positions in docs
    docs_nz = tf.not_equal(tf_docs, 0)
    # Get for each pair
    docs_g = tf.gather(docs_nz, tf_topics)
    # Find number of matches
    matches = tf.math.logical_and(docs_g[:, 0], docs_g[:, 1])
    freq = tf.reduce_sum(tf.dtypes.cast(matches, tf_docs.dtype), axis=1)
    # Add one to all values to subtract one at the end
    diag += 1
    freq += 1# Make upper diagonal
    out = tf.scatter_nd(tf_topics, freq, [m, m])
    # Make symmetric
    out += tf.transpose(out)
    # Add diagonal
    out += tf.linalg.diag(diag)
    # Subtract one to mark empty cells
    out -= 1return out

# Test
tf_docs = tf.constant([[0, 2], [1, 2], [2, 1], [5, 0], [0, 1], [7, 8], [9, 6]])
tf_topics = tf.constant([[1, 2], [1, 3], [1, 0], [2, 3], [2, 0], [3, 0],
                         [3, 4], [3, 2], [3, 1], [4, 2], [4, 1], [2, 1]])
print(freq_matrix(tf_docs, tf_topics).numpy())
# [[ 2  1  1  0 -1]#  [ 1  3  2  1  1]#  [ 1  2  3  1  1]#  [ 0  1  1  5  0]#  [-1  1  1  0  1]]