Tomaz Bratanic tomasonjo

## docs_gds_keyword.csv

          
            keyword
            mentions

            
              graph
              259

            
              algorithm
              188

            
              node
              127

            
              neo4j graph
              88

            
              neo4j
              76

## docs_keyword.csv

          
            keyword
            mentions

            
              node
              1194

            
              neo4j
              983

            
              clipboard
              868

            
              graph
              596

            
              java
              537

## docs_pagerank.csv

          
            score
            url
            pagerank

            
              598.00
              https://neo4j.com/developer/kb
              38.593852

            
              55.0
              https://neo4j.com/graphconnect-2018
              21.989673

            
              21.0
              https://neo4j.com/labs/apoc/4.4/graph-querying/node-querying
              12.607568

            
              21.0
              https://neo4j.com/labs/apoc/4.3/graph-querying/node-querying
              12.420046

            
              70.0
              https://neo4j.com/docs/operations-manual/5/reference/configuration-settings
              12.392406

## docs_degree.csv

          
            score
            url

            
              598.0
              https://neo4j.com/developer/kb

            
              391.0
              https://neo4j.com/developer-blog/tagged/neo4j

            
              235.0
              https://neo4j.com/developer-blog/tagged/graph-database

            
              165.0
              https://neo4j.com/graphgists/categories/web-amp-social

            
              165.0
              https://neo4j.com/graphgists/categories/finance

## docs_outside.csv

          
            page
            links

            
              http://localhost:7474
              38

            
              https://github.com/neo4j-contrib/neo4j-apoc-procedures/releases/tag/4.3.0.12
              38

            
              https://github.com/neo4j-contrib/neo4j-apoc-procedures/releases/tag/4.4.0.12
              37

            
              https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/quickstarts/text-analytics-sdk
              37

            
              https://docs.aws.amazon.com/IAM/latest/UserGuide/id_credentials_access-keys.html
              37

## embeddings.py
from sentence_transformers import SentenceTransformer

model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")

def generate_embeddings(text):
    embeddings = model.encode(text)
    return [float(x) for x in embeddings.tolist()]

## keyword_tokens.py
def extract_keywords(text):
    """
    Extract keywords and construct them back from tokens
    """
    result = list()
    keyword = ""
    for token in nlp(text):
        if token['entity'] == 'I-KEY':
            keyword += token['word'][2:] if \
              token['word'].startswith("##") else f" {token['word']}"

## keyword.py
tokenizer = AutoTokenizer.from_pretrained("yanekyuk/bert-uncased-keyword-extractor")
model = AutoModelForTokenClassification.from_pretrained(
    "yanekyuk/bert-uncased-keyword-extractor"
)

nlp = pipeline("ner", model=model, tokenizer=tokenizer)

## ice_families.csv

          
            last_name
            count

            
              Frey
              91

            
              Targaryen
              66

            
              Stark
              51

            
              Lannister
              30

            
              Hightower
              28

            
              Velaryon
              21

            
              Baratheon
              21

            
              Greyjoy
              19

            
              Rivers
              15

## ice_size.csv

          
            componentId
            componentSize

            
              5
              785

            
              457
              19

            
              111
              12

            
              938
              11

            
              193
              10
	keyword	mentions
	graph	259
	algorithm	188
	node	127
	neo4j graph	88
	neo4j	76
score	url	pagerank
598.00	https://neo4j.com/developer/kb	38.593852
55.0	https://neo4j.com/graphconnect-2018	21.989673
21.0	https://neo4j.com/labs/apoc/4.4/graph-querying/node-querying	12.607568
21.0	https://neo4j.com/labs/apoc/4.3/graph-querying/node-querying	12.420046
70.0	https://neo4j.com/docs/operations-manual/5/reference/configuration-settings	12.392406
	score	url
	598.0	https://neo4j.com/developer/kb
	391.0	https://neo4j.com/developer-blog/tagged/neo4j
	235.0	https://neo4j.com/developer-blog/tagged/graph-database
	165.0	https://neo4j.com/graphgists/categories/web-amp-social
	165.0	https://neo4j.com/graphgists/categories/finance
	page	links
	http://localhost:7474	38
	https://github.com/neo4j-contrib/neo4j-apoc-procedures/releases/tag/4.3.0.12	38
	https://github.com/neo4j-contrib/neo4j-apoc-procedures/releases/tag/4.4.0.12	37
	https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/quickstarts/text-analytics-sdk	37
	https://docs.aws.amazon.com/IAM/latest/UserGuide/id_credentials_access-keys.html	37
	from sentence_transformers import SentenceTransformer

	model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")

	def generate_embeddings(text):
	embeddings = model.encode(text)
	return [float(x) for x in embeddings.tolist()]
	def extract_keywords(text):
	"""
	Extract keywords and construct them back from tokens
	"""
	result = list()
	keyword = ""
	for token in nlp(text):
	if token['entity'] == 'I-KEY':
	keyword += token['word'][2:] if \
	token['word'].startswith("##") else f" {token['word']}"
	tokenizer = AutoTokenizer.from_pretrained("yanekyuk/bert-uncased-keyword-extractor")
	model = AutoModelForTokenClassification.from_pretrained(
	"yanekyuk/bert-uncased-keyword-extractor"
	)

	nlp = pipeline("ner", model=model, tokenizer=tokenizer)
	last_name	count
	Frey	91
	Targaryen	66
	Stark	51
	Lannister	30
	Hightower	28
	Velaryon	21
	Baratheon	21
	Greyjoy	19
	Rivers	15