From 072834ebbd6c3386077141d0d0d17071ee995799 Mon Sep 17 00:00:00 2001 From: "b.ghazlane" Date: Sun, 25 Apr 2021 20:57:57 +0200 Subject: [PATCH] feat: add correction v1 --- .../projects/project2/project2_correction.md | 37 +++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 one_md_per_day_format/projects/project2/project2_correction.md diff --git a/one_md_per_day_format/projects/project2/project2_correction.md b/one_md_per_day_format/projects/project2/project2_correction.md new file mode 100644 index 0000000..3e18092 --- /dev/null +++ b/one_md_per_day_format/projects/project2/project2_correction.md @@ -0,0 +1,37 @@ +# NLP-enriched News Intelligence platform + +This is the correction of the project 1: **NLP-enriched News Intelligence platform**. + +## Deliverables + +``` +project +│ README.md +│ environment.yml +│ +└───data +│ │ topic_classification_data.csv +│ +└───results +│ │ topic_classifier.pkl +│ │ learning_curves.png +| +|───nlp_engine +│ + +``` + +## Validation +The project is validated if: + +### Scrapper +- There are at least 300 news articles stored in the file system or the database. +- Run the scrapper and fetch 3 documents. The scrapper is not expected to fetch n documents, you can stop it manually. + +### NLP engine +- Run the nlp_engine on the 3 documents you fetched. + + +### Topic classfier +- The **accuracy** on the test set is bigger then **95%**. +