From a6c69264b65f51a73edc74aba246177b4ca75fd1 Mon Sep 17 00:00:00 2001
From: Lorenzo Volpi <lorenzo.volpi@outlook.com>
Date: Fri, 27 Oct 2023 17:05:01 +0200
Subject: [PATCH] TODO updated, dataset imdb parameter added

---
 TODO.md          | 5 +++++
 quacc/dataset.py | 3 ++-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/TODO.md b/TODO.md
index f5ce0a2..e2a47de 100644
--- a/TODO.md
+++ b/TODO.md
@@ -29,3 +29,8 @@
 - [x] salvare il best score ottenuto da ogni applicazione di GridSearchQ
     - nel caso di bin fare media dei due best score
 - [x] import baselines
+
+- [ ] testare anche su imbd
+- [ ] plot avg con train prevalence sull'asse x e media su test prevalecne
+- [ ] realizzare grid search per task specifico partendo da GridSearchhQ
+- [ ] provare PACC come quantificatore
\ No newline at end of file
diff --git a/quacc/dataset.py b/quacc/dataset.py
index 9362da8..2d3228c 100644
--- a/quacc/dataset.py
+++ b/quacc/dataset.py
@@ -42,8 +42,9 @@ class Dataset:
     def __spambase(self):
         return qp.datasets.fetch_UCIDataset("spambase", verbose=False).train_test
 
+    # provare min_df=5
     def __imdb(self):
-        return qp.datasets.fetch_reviews("imdb", tfidf=True).train_test
+        return qp.datasets.fetch_reviews("imdb", tfidf=True, min_df=3).train_test
 
     def __rcv1(self):
         n_train = 23149