Reference¶
PIT¶
-
sisu.pit.gismo_wrapper.
COVID19_TEXT_GETTERS
= {'abstract': <function get_abstract>, 'content': <function get_content>, 'title': <function get_title>}¶ Getters for the covid dataset. MOVE TO COVID SUBMODULE.
-
sisu.pit.gismo_wrapper.
RE_EMAIL
= re.compile('https?://[a-zA-Z.:0-9]+|www.[a-zA-Z.:0-9]+.*|www.|.org|[a-zA-Z.:0-9]+/')¶ regexp for email detection.
-
sisu.pit.gismo_wrapper.
RE_NOISE
= re.compile('[,.:;()0-9+=%\\[\\]_]')¶ regexp for useless text.
-
sisu.pit.gismo_wrapper.
RE_REFERENCE
= re.compile('\\[\\d+,\\s\\d+\\]|\\[\\d+\\]|\\(\\d+,\\s\\d+\\)|\\(\\d+\\)')¶ regexp for citations.
-
sisu.pit.gismo_wrapper.
document_to_text
(document: dict, text_getters=None) → str[source]¶ NOT WORKING
Convert a document (e.g. from COVID-19 dataset) to a string.
- Parameters
- Returns
- Return type
The str representing the input document.
Examples
NO EXAMPLE, REMOVE THIS FUNCTION.
-
sisu.pit.gismo_wrapper.
initialize_embedding
(documents: list, stop_words: Optional[list] = None, max_ngram: int = 1, min_df: float = 0.02, max_df: float = 0.85, document_to_text=<function simplified_document_to_string>, preprocessor=None) → gismo.embedding.Embedding[source]¶ Initializes an embedding, fitting it from documents
- Parameters
documents – A list of dict representing documents with strings in the values.
stop_words – A list of words to ignore in the vocabulary.
max_ngram – the maximum length of ngrams to take into account (e.g. 2 if bigrams in vocabulary).
min_df – minimum frequency of a word to be considered in the vocabulary, if an int the word must be contained in at least min_df documents.
max_df (maximum frequency of a word to be considered in the vocabulary.) –
document_to_text – Callback(Document) -> str.
preprocessor –
- Returns
The embedding fitted on the documents.
- Return type
Embedding
-
sisu.pit.gismo_wrapper.
make_gismo
(documents: list, alpha: float = 0.2, other_embedding: Optional[gismo.embedding.Embedding] = None, is_documents_embedding: bool = False, document_to_text=<function simplified_document_to_string>) → gismo.gismo.Gismo[source]¶ Make a Gismo object from a list of documents. :param documents: A list of documents with strings in the values. :param alpha: A float in [0, 1] indicating the damping factor used in the D-iteration used by Gismo. :param other_embedding: embedding already fitted on a corpus. :param document_to_text: Callback(Document) -> str.
- Returns
A Gismo object made from the given documents and embedding.
-
sisu.pit.gismo_wrapper.
old_make_gismo
(documents: list, alpha: float = 0.2, other_embedding: Optional[gismo.embedding.Embedding] = None, is_documents_embedding: bool = False, document_to_text=<function simplified_document_to_string>) → gismo.gismo.Gismo[source]¶ Make a Gismo object from a list of documents. :param documents: A list of documents with strings in the values. :param alpha: A float in [0, 1] indicating the damping factor used in the D-iteration used by Gismo. :param other_embedding: embedding already fitted on a corpus. :param document_to_text: Callback(Document) -> str.
- Returns
A Gismo object made from the given documents and embedding.
-
sisu.pit.gismo_wrapper.
sanitize_text
(text: str) → str[source]¶ Sanitize a text. This is done to improve the Embedding quality.
- Parameters
text (
str
) – Text to clean.- Returns
The corresponding sanitized str instance.
- Return type
Examples
>>> sanitize_text("This is a mail: santa@northpole.com!") 'This is a mail santa@northpolecom!' >>> sanitize_text("This is a !*[ url: https://www.ens.fr!") 'This is a !* url /' >>> sanitize_text("This are references [3, 17].") 'This are references '
-
sisu.pit.gismo_wrapper.
simplified_document_to_string
(doc: dict) → str[source]¶ Transforms a dict into a string made of its values.
- Parameters
doc (
dict
) – A dict representing a document of “depth one”, all the values are strings.- Returns
Concatenation of doc values.
- Return type
Examples
>>> from sisu.pit.preprocessing.sentences import toy_article >>> simplified_document_to_string(toy_article) "Predator In the jungle, no-one hears you far cry. And vice-versa. They say to make a long abstract, with the number 42 in it, so here I am. There is no-one in the trees. Is there? Predators don't like to lose."
-
sisu.pit.building_summary.
is_relevant_sentence
(sentence: str, min_num_words: int = 6, max_num_words: int = 60) → bool[source]¶ Ignore sentences that are too short, too long, that contain a URL or a citation.
- Parameters
- Returns
Is the sentence OK?
- Return type
Examples
>>> is_relevant_sentence("This is a short sentence!") False >>> is_relevant_sentence("This is a sentence with reference to the url http://www.ix.com!") False >>> is_relevant_sentence("This is a a sentence with some citations [3, 7]!") False >>> is_relevant_sentence("I have many things to say in that sentence, to the point " ... "I do not know if I will stop anytime soon but don't let it stop" ... "you from reading this meaninless garbage and this goes on and " ... "this goes on and this goes on and this goes on and this goes on and " ... " this goes on and this goes on and this goes on and this goes on " ... "and this goes on and this goes on and this goes on and this goes " ... "on and this goes on and this goes on and this goes on and this goes " ... "on and this goes on and ") False >>> is_relevant_sentence("This sentence is not too short and not too long, without URL and without citation.") True
-
sisu.pit.building_summary.
make_query
(sentence: str, language='en') → str[source]¶ Builds a query from a sentence.
- Parameters
- Returns
- Return type
A string corresponding to the query.
Examples
>>> make_query("Life is something nice!") 'life nice' >>> make_query("La vie est belle !", language='fr') 'vie belle'
-
sisu.pit.building_summary.
make_tree
(documents: list, query: str = '', depth: int = 1, trees: Optional[list] = None, documents_gismo: Optional[gismo.gismo.Gismo] = None, num_documents: Optional[int] = None, num_sentences: Optional[int] = None, embedding: Optional[gismo.embedding.Embedding] = None, used_sentences: Optional[set] = None) → list[source]¶ Builds a hierarchical summary.
- Parameters
documents (
list
ofdict
) – A list of dict corresponding to documents, only the values of the “content” key will be summarized.query (
str
, optional) – Textual query to focus the summary on one subject.depth (
int
, optional) – An int giving the depth of the summary (depth one is a sequential summary).trees (
list
, optional) – A list of dict being completed, necessary for the recursivity.documents_gismo (
Gismo
) – Pre-existing Gismonum_documents (
int
, optional) – Number of top documents to be taking into account for the summary.num_sentences (
int
, optional) – Number of sentences wanted in the summary.embedding (
Embedding
, optional) – An Embedding fitted on a bigger corpus than documents.used_sentences (
set
, optional) – A set of “forbidden” sentences. Will be updated inplace.
- Returns
A list of dict corresponding to the hierarchical summary
- Return type
Examples
>>> from gismo.datasets.reuters import get_reuters_news >>> make_tree(get_reuters_news(), query="Orange", num_documents=10, num_sentences=3, depth=2) [{'text': 'But some analysts still believe Orange is overvalued.', 'current_keywords': ['orange', 'one', 'is', 'at', 'on', 'in', 'and', 'its', 'shares', 'has', 'analysts', 'of', 'market', 'believe', 'overvalued'], 'url': None, 'children': [{'text': 'Trading sources said China was staying out of the market, and that Indian meal was currently overvalued by a good $20 a tonne.', 'current_keywords': ['orange', 'overvalued', 'analysts', 'that', 'and', 'are', 'compared', 'believe', 'market', 'but', 'some', 'still', 'of', 'said', 'we'], 'url': None, 'children': []}, {'text': 'Since the purchase, widely seen by analysts as overvalued, Quaker has struggled with the line of ready-to-drink teas and juices.', 'current_keywords': ['orange', 'overvalued', 'analysts', 'that', 'and', 'are', 'compared', 'believe', 'market', 'but', 'some', 'still', 'of', 'said', 'we'], 'url': None, 'children': []}, {'text': '"No question that if the dollar continues to be overvalued and continues to be strong, we\'ll see some price erosion later in the year."', 'current_keywords': ['orange', 'overvalued', 'analysts', 'that', 'and', 'are', 'compared', 'believe', 'market', 'but', 'some', 'still', 'of', 'said', 'we'], 'url': None, 'children': []}]}, {'text': 'Orange shares were 2.5p higher at 188p on Friday.', 'current_keywords': ['orange', 'one', 'is', 'at', 'on', 'in', 'and', 'its', 'shares', 'has', 'analysts', 'of', 'market', 'believe', 'overvalued'], 'url': None, 'children': [{'text': 'Orange, Calif.-based Bergen is the largest U.S. distributor of generic drugs, while Miami-based Ivax is a generic drug manufacturing giant.', 'current_keywords': ['orange', 'higher', 'shares', 'friday', 'on', 'at', 'and', 'in', 'its', 'of', 'percent', 'one', 'mobile', 'to', 'market'], 'url': None, 'children': []}, {'text': 'One-2-One and Orange ORA.L, which offer only digital services, are due to release their connection figures next week.', 'current_keywords': ['orange', 'higher', 'shares', 'friday', 'on', 'at', 'and', 'in', 'its', 'of', 'percent', 'one', 'mobile', 'to', 'market'], 'url': None, 'children': []}, {'text': "Dodd noted that BT's plans to raise the price of calls to Orange and One 2 One handsets would be beneficial.", 'current_keywords': ['orange', 'higher', 'shares', 'friday', 'on', 'at', 'and', 'in', 'its', 'of', 'percent', 'one', 'mobile', 'to', 'market'], 'url': None, 'children': []}]}, {'text': 'Orange already has a full roaming agreement in Germany and a partial one in France, centred on Paris.', 'current_keywords': ['orange', 'one', 'is', 'at', 'on', 'in', 'and', 'its', 'shares', 'has', 'analysts', 'of', 'market', 'believe', 'overvalued'], 'url': None, 'children': [{'text': 'Orange says its offer of roaming services between the UK and other countries is part of its aim to provide customers with the best value for money.', 'current_keywords': ['orange', 'roaming', 'partial', 'centred', 'paris', 'france', 'germany', 'agreement', 'full', 'on', 'and', 'in', 'of', 'for', 'with'], 'url': None, 'children': []}, {'text': 'As with all roaming agreements, the financial details of the Swiss deal remain a trade secret.', 'current_keywords': ['orange', 'roaming', 'partial', 'centred', 'paris', 'france', 'germany', 'agreement', 'full', 'on', 'and', 'in', 'of', 'for', 'with'], 'url': None, 'children': []}, {'text': '"We look forward in 1997 to continuing to move ahead and to extending our international service through new roaming agreements and the introduction of dual band handsets."', 'current_keywords': ['orange', 'roaming', 'partial', 'centred', 'paris', 'france', 'germany', 'agreement', 'full', 'on', 'and', 'in', 'of', 'for', 'with'], 'url': None, 'children': []}]}]
-
sisu.pit.building_summary.
summarize
(documents, query='', num_documents=None, num_sentences=None, ratio=0.05, embedding=None, num_keywords: int = 15, size_generic_query: int = 5, used_sentences: Optional[set] = None, get_content=<function <lambda>>) → tuple[source]¶ Produces a list of sentences and a list of keywords.
- Parameters
documents (
list
) – A list of documents.query (
str
, optional) – Textual query to focus the summary on one subject.num_documents (
int
, optional) – Number of top documents to be taking into account for the summary.num_sentences (
int
, optional) – Number of sentences wanted in the summary. Overrides ratio.ratio (
float
in ]0, 1], optional) – length of the summary as a proportion of the length of the num_documents kept.embedding (
Embedding
, optional) – An Embedding fitted on a bigger corpus than documents.num_keywords (
int
, optional) – An int corresponding to the number of keywords returnedsize_generic_query (
int
, optional) – size generic queryused_sentences (
set
, optional) – A set of “forbidden” sentences. Will be updated inplace.get_content (callable, optional) – A function that allows the retrieval of a document’s content.
- Returns
A list of the summary sentences, A list of keywords.
- Return type
Examples
>>> from gismo.datasets.reuters import get_reuters_news >>> summarize(get_reuters_news(), num_documents=10, num_sentences=4) (['Gum arabic has a history dating back to ancient times.', 'Hungry nomads pluck gum arabic as they pass with grazing goats and cattle.', 'For impoverished sub-Saharan states producing the bulk of world demand, gum arabic simply means export currency.', "After years of war-induced poverty, gum arabic is offering drought-stricken Chad's rural poor a lifeline to the production plants of the world's food and beverage giants."], ['norilsk', 'icewine', 'amiel', 'gum', 'arabic', 'her', 'tibet', 'chad', 'deng', 'oil', 'grapes', 'she', 'his', 'czechs', 'chechnya']) >>> summarize(get_reuters_news(), query="Ericsson", num_documents=10, num_sentences=5) (['The restraints are few in areas such as consumer products, while in sectors such as banking, distribution and insurance, foreign firms are kept on a very tight leash.', 'These latest wins follow a recent $350 million contract win with Telefon AB L.M.', 'Pocket is the first from the high-priced 1996 auction known to have filed for bankruptcy protection.', '"That is, assuming the deal is done right," she added.', '"Generally speaking, the easiest place to make a profit tends to be in the consumer industry, usually fairly small-scale operations," said Anne Stevenson-Yang, director of China operations for the U.S.-China Business Council.'], ['ericsson', 'sweden', 'motorola', 'telecommuncation', 'communciation', 'bolstering', 'priced', 'sectors', 'makers', 'equipment', 'schaumberg', 'lm', 'done', 'manufacturing', 'consumer'])