3 data/20200301_article_labelings.json_SUCCESS:
6 data/20200301_article_labelings_sample.json:sample_training_labels.py
7 source ./bin/activate; \
8 ./sample_training_labels.py
11 data/article_sample.csv:sample_articles.py
12 source ./bin/activate; \
13 start_spark_and_run.sh 1 sample_articles.py
15 data/scored_article_sample.feather:data/article_sample_set.csv ores_scores_sample.py
16 source ./bin/activate; \
17 python3 ores_scores_sample.py data/article_sample_set.parquet data/scored_article_sample.feather
19 # run this step on kibo
20 data/20200301_al_sample_revisions.w_text.json:data/20200301_article_labelings_sample.json
21 source ./bin/activate; \
22 python3 articlequality/utility fetch_text \
23 --api-host=https://en.wikipedia.org \
24 --labelings=data/20200301_article_labelings_sample.json \
25 --output=data/20200301_al_sample_revisions.w_text.json \
27 # run this step on kibo
28 data/20200301_al_sample_revisions.w_scores.json:data/20200301_al_sample_revisions.w_text.json
29 python3 score_sample_labels.py
31 models/ordinal_quality.RDS:data/20200301_al_sample_revisions.w_text.json ordinal_quality_models.R
32 Rscript ordinal_quality_models.R
37 PHONY: data/20200301_article_labelings.json