def testCase():
"""
Get docs from file, get list of titles+content, calculate (40) topics using 3,4 ngrams
map topics Add list of topics to each entry of the given allEntryDict for each topic
that has an LDA fuzzy relevance (see fuzzywuzzy process) of greater than the
specified threshold. Calculate SoftCosine-Similarity matrix with WordEmbeddings
fasttext_model300 (dimension 300) or GloVe (dimension 50)
save matrix to file
do spectral analysis and dimension reduction (PCA method) on similarity matrix
plotScatter3D with tool tips
"""
allDict = loadAllFeedsFromFile()
sm = smallDict(allDict, 500)
docl = getDocList(sm,
limit=None,
reloaddocs=False,
stop_list=getCustomStopWords())
topics = deriveTopicMaps(docl, maxNum=20, ngram_range=(3, 4))
updateDictionaryByFuzzyRelevanceofTopics(topics,
sm,
limit=None,
threshold=60,
remove=True)
trix = deriveSoftCosineSimilarityMatrix(sm)
saveDFPickle(trix)
do3DPlotOfCosineSimilarity(sm, None, trix)
return
def preparePyLDAvisData(allDict, limit=None, numTopics=30):
docsZip = getDocList(allDict,
limit,
stop_list=getCustomStopWords(),
with_ids=True)
documents = []
ids = []
for i, j in docsZip:
documents.append(j)
ids.append(i)
# Create gensim Dictionary of unique IDs of all words in all documents
# pyDAVis param "d"
dictionary = corpora.Dictionary(
[simple_preprocess(doc) for doc in documents])
# Convert the sentences into bag-of-words vectors.
sentences = [] # pyDAVis param "c"
for doc in documents:
sentences.append(dictionary.doc2bow(simple_preprocess(doc)))
ldamodel = models.ldamodel.LdaModel(sentences,
num_topics=numTopics,
id2word=dictionary,
passes=50)
return (ldamodel, sentences, dictionary)
def preparePyLDAvisData(allDict, limit=None, numTopics=30):
docsZip = getDocList(allDict,
limit,
stop_list=getCustomStopWords(),
with_ids=True)
documents = []
ids = []
for i, j in docsZip:
documents.append(j)
ids.append(i)
model = getWordEmbeddingModel()
# Create gensim Dictionary of unique IDs of all words in all documents
# pyDAVis param "d"
dictionary = corpora.Dictionary(
[simple_preprocess(doc) for doc in documents])
# Prepare the similarity matrix
# TODO Check if some of these parameters can be used to begin with rather than filtering later
similarity_matrix = model.similarity_matrix(dictionary,
tfidf=None,
threshold=0.0,
exponent=2.0,
nonzero_limit=100)
# Convert the sentences into bag-of-words vectors.
sentences = [] # pyDAVis param "c"
for doc in documents:
sentences.append(dictionary.doc2bow(simple_preprocess(doc)))
ldamodel = models.ldamodel.LdaModel(sentences,
num_topics=numTopics,
id2word=dictionary,
passes=50)
return (ldamodel, sentences, dictionary)
def deriveSoftCosineSimilarityMatrix(allDict,
limit=None,
weName="glove-wiki-gigaword-50",
simThreshold=0.3):
# documents=getTestDocuments()
docsZip = getDocList(allDict,
limit,
stop_list=getCustomStopWords(),
with_ids=True)
documents = []
ids = []
for i, j in docsZip:
documents.append(j)
ids.append(i)
model = getWordEmbeddingModel(weName=weName)
# Create gensim Dictionary of unique IDs of all words in all documents
# pyDAVis param "d"
dictionary = corpora.Dictionary(
[simple_preprocess(doc) for doc in documents])
# Convert the sentences into bag-of-words vectors.
sentences = [] # pyDAVis param "c"
for doc in documents:
sentences.append(dictionary.doc2bow(simple_preprocess(doc)))
# Create a TF-IDF model. TF-IDF encoding represents words as their
# relative importance to the whole document in a collection of documents,
# i.e. the sentences.
# pyDAVis param "lda"
tf_idf = models.TfidfModel(sentences)
# Prepare the similarity matrix
similarity_matrix = model.similarity_matrix(dictionary,
tfidf=tf_idf,
threshold=simThreshold,
exponent=2.0,
nonzero_limit=100)
# create 1xN vector filled with 1,2,..N
len_array = np.arange(len(sentences))
# create NxN array filled with 1..N down, 1..N across
xx, yy = np.meshgrid(len_array, len_array)
# Iterate over the 2d matrix calculating
theMatrix = [[
round(softcossim(sentences[i], sentences[j], similarity_matrix), 2)
for i, j in zip(x, y)
] for y, x in zip(xx, yy)]
cossim_mat = pd.DataFrame(theMatrix, index=ids, columns=ids)
return cossim_mat
def testDisplayTopics(numArticles=None, numTopics=30, dict=None):
if not dict:
dict = loadAllFeedsFromFile()
if bool(numArticles):
small = smallDict(dict, numArticles)
else:
small = dict
docl = getDocList(small, reloaddocs=False, stop_list=getCustomStopWords())
# docl=getDocList(small, reloaddocs=False)
topics = deriveTopicMaps(docl, maxNum=numTopics, ngram_range=(3, 3))
updateDictionaryByFuzzyRelevanceofTopics(topics, small, limit=30)
displayTopics(topics)
return