mirror of
https://github.com/Steffo99/unimore-bda-6.git
synced 2024-11-21 23:44:19 +00:00
it works, but at what cost
This commit is contained in:
parent
4e1a9f842f
commit
32cd81bca6
3 changed files with 6 additions and 4 deletions
|
@ -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" />
|
||||
|
|
|
@ -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
|
||||
|
||||
|
|
|
@ -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:
|
||||
"""
|
||||
|
|
Loading…
Reference in a new issue