Co-occurrence Matrix from list of words in Python

2020-02-05 07:21发布

问题:

I have a list of names like:

names = ['A', 'B', 'C', 'D']

and a list of documents, that in each documents some of these names are mentioned.

document =[['A', 'B'], ['C', 'B', 'K'],['A', 'B', 'C', 'D', 'Z']]

I would like to get an output as a matrix of co-occurrences like:

  A  B  C  D
A 0  2  1  1
B 2  0  2  1
C 1  2  0  1
D 1  1  1  0

There is a solution (Creating co-occurrence matrix) for this problem in R, but I couldn't do it in Python. I am thinking of doing it in Pandas, but yet no progress!

回答1:

Obviously this can be extended for your purposes, but it performs the general operation in mind:

import math

for a in 'ABCD':
    for b in 'ABCD':
        count = 0

        for x in document:
            if a != b:
                if a in x and b in x:
                    count += 1

            else:
                n = x.count(a)
                if n >= 2:
                    count += math.factorial(n)/math.factorial(n - 2)/2

        print '{} x {} = {}'.format(a, b, count)


回答2:

Another option is to use the constructor csr_matrix((data, (row_ind, col_ind)), [shape=(M, N)]) from scipy.sparse.csr_matrix where data, row_ind and col_ind satisfy the relationship a[row_ind[k], col_ind[k]] = data[k].

The trick is to generate row_ind and col_ind by iterating over the documents and creating a list of tuples (doc_id, word_id). data would simply be a vector of ones of the same length.

Multiplying the docs-words matrix by its transpose would give you the co-occurences matrix.

Additionally, this is efficient in terms of both run times and memory usage, so it should also handle big corpuses.

import numpy as np
import itertools
from scipy.sparse import csr_matrix


def create_co_occurences_matrix(allowed_words, documents):
    print(f"allowed_words:\n{allowed_words}")
    print(f"documents:\n{documents}")
    word_to_id = dict(zip(allowed_words, range(len(allowed_words))))
    documents_as_ids = [np.sort([word_to_id[w] for w in doc if w in word_to_id]).astype('uint32') for doc in documents]
    row_ind, col_ind = zip(*itertools.chain(*[[(i, w) for w in doc] for i, doc in enumerate(documents_as_ids)]))
    data = np.ones(len(row_ind), dtype='uint32')  # use unsigned int for better memory utilization
    max_word_id = max(itertools.chain(*documents_as_ids)) + 1
    docs_words_matrix = csr_matrix((data, (row_ind, col_ind)), shape=(len(documents_as_ids), max_word_id))  # efficient arithmetic operations with CSR * CSR
    words_cooc_matrix = docs_words_matrix.T * docs_words_matrix  # multiplying docs_words_matrix with its transpose matrix would generate the co-occurences matrix
    words_cooc_matrix.setdiag(0)
    print(f"words_cooc_matrix:\n{words_cooc_matrix.todense()}")
    return words_cooc_matrix, word_to_id 

Run example:

allowed_words = ['A', 'B', 'C', 'D']
documents = [['A', 'B'], ['C', 'B', 'K'],['A', 'B', 'C', 'D', 'Z']]
words_cooc_matrix, word_to_id = create_co_occurences_matrix(allowed_words, documents)

Output:

allowed_words:
['A', 'B', 'C', 'D']

documents:
[['A', 'B'], ['C', 'B', 'K'], ['A', 'B', 'C', 'D', 'Z']]

words_cooc_matrix:
[[0 2 1 1]
 [2 0 2 1]
 [1 2 0 1]
 [1 1 1 0]]


回答3:

from collections import OrderedDict

document = [['A', 'B'], ['C', 'B'], ['A', 'B', 'C', 'D']]
names = ['A', 'B', 'C', 'D']

occurrences = OrderedDict((name, OrderedDict((name, 0) for name in names)) for name in names)

# Find the co-occurrences:
for l in document:
    for i in range(len(l)):
        for item in l[:i] + l[i + 1:]:
            occurrences[l[i]][item] += 1

# Print the matrix:
print(' ', ' '.join(occurrences.keys()))
for name, values in occurrences.items():
    print(name, ' '.join(str(i) for i in values.values()))

Output;

  A B C D
A 0 2 1 1 
B 2 0 2 1 
C 1 2 0 1 
D 1 1 1 0 


回答4:

Here is another solution using itertools and the Counter class from the collections module.

import numpy
import itertools
from collections import Counter

document =[['A', 'B'], ['C', 'B'],['A', 'B', 'C', 'D']]

# Get all of the unique entries you have
varnames = tuple(sorted(set(itertools.chain(*document))))

# Get a list of all of the combinations you have
expanded = [tuple(itertools.combinations(d, 2)) for d in document]
expanded = itertools.chain(*expanded)

# Sort the combinations so that A,B and B,A are treated the same
expanded = [tuple(sorted(d)) for d in expanded]

# count the combinations
c = Counter(expanded)


# Create the table
table = numpy.zeros((len(varnames),len(varnames)), dtype=int)

for i, v1 in enumerate(varnames):
    for j, v2 in enumerate(varnames[i:]):        
        j = j + i 
        table[i, j] = c[v1, v2]
        table[j, i] = c[v1, v2]

# Display the output
for row in table:
    print(row)

The output (which could be easilty turned into a DataFrame) is:

[0 2 1 1]
[2 0 2 1]
[1 2 0 1]
[1 1 1 0]


回答5:

You can also use matrix tricks in order to find the co-occurrence matrix too. Hope this works well when you have bigger vocabulary.

import scipy.sparse as sp
voc2id = dict(zip(names, range(len(names))))
rows, cols, vals = [], [], []
for r, d in enumerate(document):
    for e in d:
        if voc2id.get(e) is not None:
            rows.append(r)
            cols.append(voc2id[e])
            vals.append(1)
X = sp.csr_matrix((vals, (rows, cols)))

Now, you can find coocurrence matrix by simple multiply X.T with X

Xc = (X.T * X) # coocurrence matrix
Xc.setdiag(0)
print(Xc.toarray())


回答6:

I was facing the same issue... So i came with this code. This code takes into account context window and then determines co_occurance matrix.

Hope this helps you...

def countOccurences(word,context_window): 

    """
    This function returns the count of context word.
    """ 
    return context_window.count(word)

def co_occurance(feature_dict,corpus,window = 5):
    """
    This function returns co_occurance matrix for the given window size. Default is 5.

    """
    length = len(feature_dict)
    co_matrix = np.zeros([length,length]) # n is the count of all words

    corpus_len = len(corpus)
    for focus_word in top_features:

        for context_word in top_features[top_features.index(focus_word):]:
            # print(feature_dict[context_word])
            if focus_word == context_word:
                co_matrix[feature_dict[focus_word],feature_dict[context_word]] = 0
            else:
                start_index = 0
                count = 0
                while(focus_word in corpus[start_index:]):

                    # get the index of focus word
                    start_index = corpus.index(focus_word,start_index)
                    fi,li = max(0,start_index - window) , min(corpus_len-1,start_index + window)

                    count += countOccurences(context_word,corpus[fi:li+1])
                    # updating start index
                    start_index += 1

                # update [Aij]
                co_matrix[feature_dict[focus_word],feature_dict[context_word]] = count
                # update [Aji]
                co_matrix[feature_dict[context_word],feature_dict[focus_word]] = count
    return co_matrix


回答7:

'''for a window of 2, data_corpus is the series consisting of text data, words is the list consisting of words for which co-occurence matrix is build'''

"co_oc is the co-occurence matrix"

co_oc=pd.DataFrame(index=words,columns=words)

for j in tqdm(data_corpus):

    k=j.split()

    for l in range(len(k)):

        if l>=5 and l<(len(k)-6):
            if k[l] in words:
                for m in range(l-5,l+6):
                    if m==l:
                        continue
                    elif k[m] in words:
                        co_oc[k[l]][k[m]]+=1

        elif l>=(len(k)-6):
            if k[l] in words:
                for m in range(l-5,len(k)):
                    if m==l:
                        continue
                    elif k[m] in words:
                        co_oc[k[l]][k[m]]+=1

        else:
            if k[l] in words:
                for m in range(0,l+5):
                    if m==l:
                        continue
                    elif k[m] in words:
                        co_oc[k[l]][k[m]]+=1
print(co_oc.head())