# \#off-topic **URL:** https://support.prodi.gy/tag/off-topic/40.md [Latest](https://support.prodi.gy/latest.md) · [Categories](https://support.prodi.gy/categories.md) · [Tags](https://support.prodi.gy/tags.md) --- ## [Dragon Scales](https://support.prodi.gy/t/dragon-scales/6554)
**Author:** [@Bennett](https://support.prodi.gy/u/Bennett)\ **Replies:** 1\ **Last updated:** [May 22, 2023, 12:47pm UTC](https://support.prodi.gy/t/dragon-scales/6554 "2023-05-22T12:47:12Z")
My student can’t find the last mythical epic dragon scale. --- ## [Python code error, can you help me please?](https://support.prodi.gy/t/python-code-error-can-you-help-me-please/6299)
**Author:** [@Andrix951](https://support.prodi.gy/u/Andrix951)\ **Replies:** 1\ **Last updated:** [January 30, 2023, 12:23pm UTC](https://support.prodi.gy/t/python-code-error-can-you-help-me-please/6299 "2023-01-30T12:23:29Z")
the code of the error is this, string 12: import random import json import pickle import numpy as np import nltk from nltk.stem import WordNetLemmatizer from tensorflow.keras.models import load\_model lemmatizer =… --- ## [How do I fix error 418?](https://support.prodi.gy/t/how-do-i-fix-error-418/5957)
**Author:** [@karma](https://support.prodi.gy/u/karma)\ **Replies:** 1\ **Last updated:** [September 22, 2022, 10:37am UTC](https://support.prodi.gy/t/how-do-i-fix-error-418/5957 "2022-09-22T10:37:05Z")
When I finish a battle in "Prodigy Math Game" I get error 418 and It equips a cloud mount that I dont have in my inventory. --- ## [Pattern Matching on Custom Attributes](https://support.prodi.gy/t/pattern-matching-on-custom-attributes/3015)
**Author:** [@Fourthought](https://support.prodi.gy/u/Fourthought)\ **Replies:** 2\ **Last updated:** [September 22, 2021, 4:45pm UTC](https://support.prodi.gy/t/pattern-matching-on-custom-attributes/3015 "2021-09-22T16:45:08Z")
Hi There, I'm trying to create a pipeline component for which identifies terms to describe an "outgroup". In the following sentence, for example, an "outgroup" would be "Taliban Regime". The outgroup in this instance is… --- ## [Training the NER pipeline component of an existing model](https://support.prodi.gy/t/training-the-ner-pipeline-component-of-an-existing-model/4672)
**Author:** [@NNN](https://support.prodi.gy/u/NNN)\ **Replies:** 2\ **Last updated:** [September 14, 2021, 10:05am UTC](https://support.prodi.gy/t/training-the-ner-pipeline-component-of-an-existing-model/4672 "2021-09-14T10:05:20Z")
Hi, I'm learning from your online course (https://course.spacy.io/en/chapter4) and am trying to train the NEW pipeline component of an existing pre-trained model (lg/trf). Is is possible to train all models? I read a … --- ## [NER plus Relationship Extraction (RE) on document](https://support.prodi.gy/t/ner-plus-relationship-extraction-re-on-document/4622)
**Author:** [@KMayank29](https://support.prodi.gy/u/KMayank29)\ **Replies:** 2\ **Last updated:** [August 27, 2021, 12:17pm UTC](https://support.prodi.gy/t/ner-plus-relationship-extraction-re-on-document/4622 "2021-08-27T12:17:06Z")
I have scrapped few news articles that talk about not very famous personalities. The task is to extract structured information out of these articles. The structured information is as follows: Get NER tags for PER, OR… --- ## [spaCy Tokenization issue](https://support.prodi.gy/t/spacy-tokenization-issue/4578)
**Author:** [@vaibhav-01](https://support.prodi.gy/u/vaibhav-01)\ **Replies:** 1\ **Last updated:** [August 17, 2021, 11:12pm UTC](https://support.prodi.gy/t/spacy-tokenization-issue/4578 "2021-08-17T23:12:32Z")
Hi This is actually an issue related to spaCy but I didn't found a support page for spaCy and hence posting it here. Any help will be much appreciated. While creating a doc using nlp = spacy.load("en\_core\_web\_sm") doc… --- ## [I was just trying out displacy and encountered a weird error.](https://support.prodi.gy/t/i-was-just-trying-out-displacy-and-encountered-a-weird-error/4440)
**Author:** [@ENELPY](https://support.prodi.gy/u/ENELPY)\ **Replies:** 2\ **Last updated:** [July 15, 2021, 8:18am UTC](https://support.prodi.gy/t/i-was-just-trying-out-displacy-and-encountered-a-weird-error/4440 "2021-07-15T08:18:49Z")
I was just trying out displacy and this was my code import spacy from spacy import displacy import en\_core\_web\_md nlp = en\_core\_web\_md.load() doc = nlp('I have a ginger cat.') displacy.serve(doc, style='dep', port… --- ## [updating training pipline of NER from spacy 2 to spacy 3](https://support.prodi.gy/t/updating-training-pipline-of-ner-from-spacy-2-to-spacy-3/3592)
**Author:** [@robertto](https://support.prodi.gy/u/robertto)\ **Replies:** 4\ **Last updated:** [June 24, 2021, 1:36pm UTC](https://support.prodi.gy/t/updating-training-pipline-of-ner-from-spacy-2-to-spacy-3/3592 "2021-06-24T13:36:51Z")
first, congratulation on spacy 3, it looks very cool ! I've read a custom pipeline for training a custom NER in spacy 2, how can I integrate that to spacy 3 here is my code in spacy 2 @plac.annotations( model=("Mo… --- ## [Apple Macbook Pro M1 use GPU](https://support.prodi.gy/t/apple-macbook-pro-m1-use-gpu/4323)
**Author:** [@mart](https://support.prodi.gy/u/mart)\ **Replies:** 1\ **Last updated:** [June 14, 2021, 1:55am UTC](https://support.prodi.gy/t/apple-macbook-pro-m1-use-gpu/4323 "2021-06-14T01:55:44Z")
Hi, I have issues using the GPU on the new macbook pro with the M1 GPU. Using: import spacy activated = spacy.require\_gpu() nlp = spacy.load('en\_core\_web\_sm') print(activated) throws an error Traceback (most recent… --- ## [install scispacy](https://support.prodi.gy/t/install-scispacy/4297)
**Author:** [@aph61](https://support.prodi.gy/u/aph61)\ **Replies:** 2\ **Last updated:** [June 7, 2021, 1:08am UTC](https://support.prodi.gy/t/install-scispacy/4297 "2021-06-07T01:08:29Z")
Hi, I want to run scispacy, but I run into a set of problems. I have created a venv scispacy-env that runs python3.8 (I normally run python 3.6 but one way or another it has upgraded it to python 3.8). In this venv I ru… --- ## [How to output / compute an NER model F1 score under spaCy 3.0?](https://support.prodi.gy/t/how-to-output-compute-an-ner-model-f1-score-under-spacy-3-0/3946)
**Author:** [@TanjirouNezuko](https://support.prodi.gy/u/TanjirouNezuko)\ **Replies:** 1\ **Last updated:** [March 2, 2021, 8:25pm UTC](https://support.prodi.gy/t/how-to-output-compute-an-ner-model-f1-score-under-spacy-3-0/3946 "2021-03-02T20:25:04Z")
Hi I have been training a NER model with spacy 3.0. However, I didn't find any guide on how to output model's F1 score in the latest version. I have found some solutions of this question for the spacy version 2.0, but I… --- ## [en\_core\_web\_sm model](https://support.prodi.gy/t/en-core-web-sm-model/3914)
**Author:** [@ronaldcturner](https://support.prodi.gy/u/ronaldcturner)\ **Replies:** 1\ **Last updated:** [February 22, 2021, 1:36am UTC](https://support.prodi.gy/t/en-core-web-sm-model/3914 "2021-02-22T01:36:47Z")
I realize that this is not a Prodigy problem, but without a pipeline everything stopped working. After installing the latest spaCy and en\_core\_web\_sm, spacy.load ('en\_core\_web\_sm') fails as shown in this snippet: (… --- ## [How to add rules to the lemmatizer?](https://support.prodi.gy/t/how-to-add-rules-to-the-lemmatizer/3896)
**Author:** [@thalish](https://support.prodi.gy/u/thalish)\ **Replies:** 2\ **Last updated:** [February 17, 2021, 8:03pm UTC](https://support.prodi.gy/t/how-to-add-rules-to-the-lemmatizer/3896 "2021-02-17T20:03:29Z")
I'd like to find some documentation regarding how to tune the behavior of the spacy's lemmatizer (v2.2) For example - Currently words like media and data get changed to medium/datum. I'm interested in tweaking this to … --- ## [entity linking -- how to search candidates from knowledge base in case insensitive](https://support.prodi.gy/t/entity-linking-how-to-search-candidates-from-knowledge-base-in-case-insensitive/3883)
**Author:** [@mumud123](https://support.prodi.gy/u/mumud123)\ **Replies:** 1\ **Last updated:** [February 12, 2021, 7:49am UTC](https://support.prodi.gy/t/entity-linking-how-to-search-candidates-from-knowledge-base-in-case-insensitive/3883 "2021-02-12T07:49:56Z")
This is really only about spacy, but I couldn't find a spacy support forum, so apologies that I'm putting it here. I'm building an entity linking model, and I'm adding aliases to the knowledge base. Is there a way to se… --- ## [Span out of index Error](https://support.prodi.gy/t/span-out-of-index-error/3838)
**Author:** [@Srijha09](https://support.prodi.gy/u/Srijha09)\ **Replies:** 1\ **Last updated:** [February 4, 2021, 9:34pm UTC](https://support.prodi.gy/t/span-out-of-index-error/3838 "2021-02-04T21:34:47Z")
I have tried running a custom annotator model using textacy, scispacy and spacy. But I encountered this error. Any idea why this error might be caused? File "span.pyx", line 190, in spacy.tokens.span.Span.getitem Index… --- ## [Language support; spacy-stanza; russian](https://support.prodi.gy/t/language-support-spacy-stanza-russian/3786)
**Author:** [@aph61](https://support.prodi.gy/u/aph61)\ **Replies:** 2\ **Last updated:** [January 16, 2021, 4:24pm UTC](https://support.prodi.gy/t/language-support-spacy-stanza-russian/3786 "2021-01-16T16:24:43Z")
Hi all, I need to use a non-spacy language model (russian; syntagrus). There is a special pipeline component to read non-spacy languages into spacy (spacy-stanza), but the biggest problem for me is, "where do I downlo… --- ## [Pattern Matcher OR](https://support.prodi.gy/t/pattern-matcher-or/3760)
**Author:** [@mgiardinelli](https://support.prodi.gy/u/mgiardinelli)\ **Replies:** 1\ **Last updated:** [December 20, 2020, 11:07pm UTC](https://support.prodi.gy/t/pattern-matcher-or/3760 "2020-12-20T23:07:14Z")
Hi all, is there a way to use or apply "OR" logic to pattern matcher? If I have something like I can do with regex? I don't want to have to create individual parsers for each occurrence, if possible (car, boat, bus, for … --- ## [How to add my categories as a label to my pipeline ?](https://support.prodi.gy/t/how-to-add-my-categories-as-a-label-to-my-pipeline/3759)
**Author:** [@Shahrzad\_Fa](https://support.prodi.gy/u/Shahrzad_Fa)\ **Replies:** 1\ **Last updated:** [December 20, 2020, 11:00pm UTC](https://support.prodi.gy/t/how-to-add-my-categories-as-a-label-to-my-pipeline/3759 "2020-12-20T23:00:35Z")
Hello, I am using Spacy and my dataset is a list of emails which as part of pre-processing, I cleaned up the data by removing stop words, disclaimers and greeting and each email belongs to a category and in total I have… --- ## [Is it possible to find uncertainties of spaCy POS tags?](https://support.prodi.gy/t/is-it-possible-to-find-uncertainties-of-spacy-pos-tags/3719)
**Author:** [@Joeytje50](https://support.prodi.gy/u/Joeytje50)\ **Replies:** 0\ **Last updated:** [December 9, 2020, 6:00pm UTC](https://support.prodi.gy/t/is-it-possible-to-find-uncertainties-of-spacy-pos-tags/3719 "2020-12-09T18:00:41Z")
(originally posted on https://stackoverflow.com/questions/65218606/is-it-possible-to-find-uncertainties-of-spacy-pos-tags) I am looking for a way to figure out the probabilities of certain tags set by spacy. So far, wit… --- ## [ValueError: a must be greater than 0 unless no samples are taken while pretraining using cli](https://support.prodi.gy/t/valueerror-a-must-be-greater-than-0-unless-no-samples-are-taken-while-pretraining-using-cli/3694)
**Author:** [@sagornsl](https://support.prodi.gy/u/sagornsl)\ **Replies:** 0\ **Last updated:** [December 2, 2020, 11:15am UTC](https://support.prodi.gy/t/valueerror-a-must-be-greater-than-0-unless-no-samples-are-taken-while-pretraining-using-cli/3694 "2020-12-02T11:15:14Z")
Hi, Sorry if this a duplicate question. I prepared a raw text data like the format spacy ask for. mydata.jsonl {"text": "ホッケーにはデンジャラスプレーの反則があるので、膝より上にボールを浮かすことは基本的に反則になるが、その例外の一つがこのスクープである。"} {"text": "また行きたい、そんな気持… --- ## [Extract consecutive entities into Dataframe](https://support.prodi.gy/t/extract-consecutive-entities-into-dataframe/3620)
**Author:** [@Abe\_sadi](https://support.prodi.gy/u/Abe_sadi)\ **Replies:** 2\ **Last updated:** [November 11, 2020, 3:44am UTC](https://support.prodi.gy/t/extract-consecutive-entities-into-dataframe/3620 "2020-11-11T03:44:35Z")
Dear Spacy contributors and community. I am quite new to spacy and python, and even being newbie, I am really liking how spacy works and it is awesome to see spacy in good hands. Believe me or not, without spacy I woul… --- ## [Spacy: remove a token](https://support.prodi.gy/t/spacy-remove-a-token/3613)
**Author:** [@fernandocouto](https://support.prodi.gy/u/fernandocouto)\ **Replies:** 0\ **Last updated:** [November 6, 2020, 11:13pm UTC](https://support.prodi.gy/t/spacy-remove-a-token/3613 "2020-11-06T23:13:25Z")
Hi! I'm using spacy in PT, I would like to do something like that: { (...) doc=nlp("Tu encontraste o livro independentemente dele ter dito alguma coisa.") for token in doc: --------- if token.pos\_ == 'ADV': -----… --- ## [word2vec model .bin](https://support.prodi.gy/t/word2vec-model-bin/3571)
**Author:** [@zazos](https://support.prodi.gy/u/zazos)\ **Replies:** 2\ **Last updated:** [November 4, 2020, 12:25am UTC](https://support.prodi.gy/t/word2vec-model-bin/3571 "2020-11-04T00:25:37Z")
I've downloaded a pre-trained word2vec Twitter model and i was wondering if it's possible to load that instead of a sense2vec vector or en\_core\_web\_(any\_size)? Tried passing it as input and got the following error: F… --- ## ['entity\_ruler' already exists in pipeline.](https://support.prodi.gy/t/entity-ruler-already-exists-in-pipeline/3580)
**Author:** [@mystuff](https://support.prodi.gy/u/mystuff)\ **Replies:** 0\ **Last updated:** [October 28, 2020, 2:53am UTC](https://support.prodi.gy/t/entity-ruler-already-exists-in-pipeline/3580 "2020-10-28T02:53:41Z")
Hi @ines, I am trying to create dataset using EntityRuler but leading to below error. de\_nlp = spacy.load('de\_core\_news\_lg', disable=\['ner'\]) e\_ruler = EntityRuler(de\_nlp, overwrite\_ents=True) e\_ruler.phrase\_matcher = … --- ## [PhraseMatcher or the EntityRuler?](https://support.prodi.gy/t/phrasematcher-or-the-entityruler/3575)
**Author:** [@aksh](https://support.prodi.gy/u/aksh)\ **Replies:** 0\ **Last updated:** [October 27, 2020, 2:12pm UTC](https://support.prodi.gy/t/phrasematcher-or-the-entityruler/3575 "2020-10-27T14:12:25Z")
Fairly new to python/spacy I am trying to do some basic NER for detecting PERSON names. However, I want to detect two kinds of person names. List 1 - Ones that are already in a list of names that I have access to List … --- ## [Vocabulary construction & embedding training information of blank:en LM](https://support.prodi.gy/t/vocabulary-construction-embedding-training-information-of-blank-en-lm/3563)
**Author:** [@atakanokan](https://support.prodi.gy/u/atakanokan)\ **Replies:** 1\ **Last updated:** [October 23, 2020, 8:57am UTC](https://support.prodi.gy/t/vocabulary-construction-embedding-training-information-of-blank-en-lm/3563 "2020-10-23T08:57:33Z")
Hi, I may have missed these but I couldn't find much information about the tokenization method, vocabulary construction (e.g. size) and embedding training (e.g. size of embeddings, which LM training objective is used du… --- ## [spacy server](https://support.prodi.gy/t/spacy-server/3530)
**Author:** [@sonias](https://support.prodi.gy/u/sonias)\ **Replies:** 1\ **Last updated:** [October 16, 2020, 2:53pm UTC](https://support.prodi.gy/t/spacy-server/3530 "2020-10-16T14:53:20Z")
I am quite new to spacy and prodigy environment, so sorry if my question is off the mark. I wish to create a server using spacy where I can push text paragraphs/ strings and I can receive NER objects in json format. An… --- ## [Extracting numeric token for several entities in order using Spacy](https://support.prodi.gy/t/extracting-numeric-token-for-several-entities-in-order-using-spacy/3475)
**Author:** [@nlp-guy](https://support.prodi.gy/u/nlp-guy)\ **Replies:** 0\ **Last updated:** [October 1, 2020, 8:38pm UTC](https://support.prodi.gy/t/extracting-numeric-token-for-several-entities-in-order-using-spacy/3475 "2020-10-01T20:38:50Z")
Hi All, I am new to information extraction and especially to Spacy so my apologies in advance if the question is too naive. I have the following text: In the last year, Medical AI firms had raised even more, with AIC… --- ## [Adding large patterns (500000 patterns) to EntityRuler runs for hours](https://support.prodi.gy/t/adding-large-patterns-500000-patterns-to-entityruler-runs-for-hours/3443)
**Author:** [@vmn](https://support.prodi.gy/u/vmn)\ **Replies:** 0\ **Last updated:** [September 25, 2020, 4:40am UTC](https://support.prodi.gy/t/adding-large-patterns-500000-patterns-to-entityruler-runs-for-hours/3443 "2020-09-25T04:40:44Z")
Hi I have a large dataset with 500000 patterns to add to add\_patterns of EntityRuler. I have tried disabling other pipes as suggested on the website but it still doesnt fix the issue. PFB my code and help me out. nlp =… [Next page](https://support.prodi.gy/tag/off-topic/40.md?match_all_tags=true&page=1&tags%5B%5D=off-topic)