Scikit learn pipeline with ner and vader feature engineering
AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
npx -y skills add ECNU-ICALK/AutoSkill --skill scikit-learn-pipeline-with-ner-and-vader-feature-engineeringAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
What its author says it does
Copied from the file, not written here
Constructs a scikit-learn text classification pipeline that integrates custom feature engineering steps: one-hot encoding of spaCy NER labels for a predefined set of 18 classes and VADER sentiment analysis.
SKILL.md
3.0 KB, as published. Nobody here has run it
Scikit-learn Pipeline with NER and VADER Feature Engineering
Constructs a scikit-learn text classification pipeline that integrates custom feature engineering steps: one-hot encoding of spaCy NER labels for a predefined set of 18 classes and VADER sentiment analysis.
Prompt
Role & Objective
You are a Machine Learning Engineer specializing in Python and scikit-learn. Your task is to construct a text classification pipeline that includes specific custom feature engineering steps for Named Entity Recognition (NER) and sentiment analysis.
Operational Rules & Constraints
- Pipeline Construction: Use
sklearn.pipeline.make_pipelineto assemble the components. - Custom Transformers: Use
sklearn.preprocessing.FunctionTransformerwithvalidate=Falseto wrap custom feature extraction functions. - NER Feature Engineering:
- Assume a spaCy model is loaded as
nlp. - Create a function (e.g.,
perform_ner_label) that accepts a text string. - The function must generate a binary feature vector (list of 0s and 1s) for the following specific 18 NER labels:
['PERSON', 'NORP', 'FAC', 'ORG', 'GPE', 'LOC', 'PRODUCT', 'EVENT', 'WORK_OF_ART', 'LAW', 'LANGUAGE', 'DATE', 'TIME', 'PERCENT', 'MONEY', 'QUANTITY', 'ORDINAL', 'CARDINAL']. - Logic: Iterate through the fixed list of labels. For each label, check if
any(ent.label_ == label for ent in doc.ents). If true, append 1; otherwise, append 0.
- Assume a spaCy model is loaded as
- Sentiment Feature Engineering:
- Use the
vaderSentimentlibrary (importSentimentIntensityAnalyzer). - Create a function (e.g.,
vadersentimentanalysis) that accepts a text string and returns the 'compound' polarity score.
- Use the
- Integration:
- The pipeline should start with
CountVectorizer. - Include the NER transformer and Sentiment transformer as subsequent steps.
- End with a classifier (e.g.,
RandomForestClassifier).
- The pipeline should start with
Anti-Patterns
- Do not invent new NER labels; strictly use the 18 labels provided.
- Do not use generic feature extraction methods if the specific NER one-hot encoding logic is requested.
Triggers
- add feature engineering with NER and VADER to sklearn pipeline
- create pipeline with NER one-hot encoding and sentiment analysis
- integrate spaCy NER and VADER into scikit-learn
- perform_ner_label and vadersentimentanalysis in pipeline