From 32cd81bca6c6560fb85c4aede600b4303285cd7f Mon Sep 17 00:00:00 2001
From: Stefano Pigozzi <me@steffo.eu>
Date: Fri, 3 Feb 2023 02:49:14 +0100
Subject: [PATCH] it works, but at what cost

---
 .idea/runConfigurations/unimore_bda_6.xml | 2 +-
 unimore_bda_6/__main__.py                 | 4 ++--
 unimore_bda_6/analysis/vanilla.py         | 4 +++-
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/.idea/runConfigurations/unimore_bda_6.xml b/.idea/runConfigurations/unimore_bda_6.xml
index 88d6f6a..f113c82 100644
--- a/.idea/runConfigurations/unimore_bda_6.xml
+++ b/.idea/runConfigurations/unimore_bda_6.xml
@@ -4,7 +4,7 @@
     <option name="INTERPRETER_OPTIONS" value="" />
     <option name="PARENT_ENVS" value="true" />
     <envs>
-      <env name="DATA_SET_SIZE" value="10000" />
+      <env name="DATA_SET_SIZE" value="750" />
       <env name="NLTK_DATA" value="./data/nltk" />
       <env name="PYTHONUNBUFFERED" value="1" />
       <env name="WORKING_SET_SIZE" value="1000000" />
diff --git a/unimore_bda_6/__main__.py b/unimore_bda_6/__main__.py
index 009b505..1073343 100644
--- a/unimore_bda_6/__main__.py
+++ b/unimore_bda_6/__main__.py
@@ -82,8 +82,8 @@ def main():
 
             try:
                 print("Model %s" % model)
-                while True:
-                    print(model.use(input()))
+                while inp := input():
+                    print(model.use(inp))
             except KeyboardInterrupt:
                 pass
 
diff --git a/unimore_bda_6/analysis/vanilla.py b/unimore_bda_6/analysis/vanilla.py
index 6f233d2..a1ea0cd 100644
--- a/unimore_bda_6/analysis/vanilla.py
+++ b/unimore_bda_6/analysis/vanilla.py
@@ -61,6 +61,7 @@ class VanillaSA(BaseSA):
 
         Does not use `SentimentAnalyzer.apply_features` due to unexpected behaviour when using iterators.
         """
+        count_passage("processed_features", 100)
         return self.model.extract_features(data[0]), data[1]
 
     def _train_from_dataset(self, dataset: t.Iterator[tuple[TokenBag, Category]]) -> None:
@@ -87,7 +88,8 @@ class VanillaSA(BaseSA):
             raise NotTrainedError()
 
         dataset_1 = map(self.__extract_features, dataset)
-        return self.model.evaluate(dataset_1)
+        # FIXME: This won't work with streams :(
+        return self.model.evaluate(list(dataset_1))
 
     def _use_from_tokenbag(self, tokens: TokenBag) -> Category:
         """