Final improvements

.idea/runConfigurations/unimore_bda_6.xml

@@ -4,16 +4,9 @@
     <option name="INTERPRETER_OPTIONS" value="" />
     <option name="PARENT_ENVS" value="true" />
     <envs>
-      <env name="CONFIRM_OVERWRITE" value="False" />
-      <env name="EVALUATION_SET_SIZE" value="4000" />
       <env name="NLTK_DATA" value="./data/nltk" />
       <env name="PYTHONUNBUFFERED" value="1" />
-      <env name="TENSORFLOW_EMBEDDING_SIZE" value="64" />
-      <env name="TENSORFLOW_MAX_FEATURES" value="1000000" />
       <env name="TF_CPP_MIN_LOG_LEVEL" value="2" />
-      <env name="TRAINING_SET_SIZE" value="4000" />
-      <env name="VALIDATION_SET_SIZE" value="100" />
-      <env name="WORKING_SET_SIZE" value="100000" />
       <env name="XLA_FLAGS" value="--xla_gpu_cuda_data_dir=/opt/cuda" />
     </envs>
     <option name="SDK_HOME" value="$PROJECT_DIR$/.venv/bin/python" />
@@ -26,7 +19,7 @@
     <option name="SCRIPT_NAME" value="unimore_bda_6" />
     <option name="PARAMETERS" value="" />
     <option name="SHOW_COMMAND_LINE" value="false" />
-    <option name="EMULATE_TERMINAL" value="false" />
+    <option name="EMULATE_TERMINAL" value="true" />
     <option name="MODULE_MODE" value="true" />
     <option name="REDIRECT_INPUT" value="false" />
     <option name="INPUT_FILE" value="" />

unimore_bda_6/__main__.py

@@ -41,22 +41,22 @@ def main():
             slog.debug("Selected sample_func: %s", sample_func.__name__)
 
             for SentimentAnalyzer in [
-                # ThreeCheat,
+                ThreeCheat,
+                NLTKSentimentAnalyzer,
                 TensorflowPolarSentimentAnalyzer,
                 TensorflowCategorySentimentAnalyzer,
-                NLTKSentimentAnalyzer,
             ]:
 
                 slog = logging.getLogger(f"{__name__}.{sample_func.__name__}.{SentimentAnalyzer.__name__}")
                 slog.debug("Selected SentimentAnalyzer: %s", SentimentAnalyzer.__name__)
 
                 for Tokenizer in [
-                    PottsTokenizer,
                     PlainTokenizer,
-                    HuggingBertTokenizer,
-                    PottsTokenizerWithNegation,
                     LowercaseTokenizer,
                     NLTKWordTokenizer,
+                    PottsTokenizer,
+                    PottsTokenizerWithNegation,
+                    HuggingBertTokenizer,
                 ]:
 
                     slog = logging.getLogger(f"{__name__}.{sample_func.__name__}.{SentimentAnalyzer.__name__}.{Tokenizer.__name__}")

unimore_bda_6/config.py

@@ -34,10 +34,10 @@ def WORKING_SET_SIZE(val: str | None) -> int:
     The number of reviews to consider from the database.
     Set this to a low number to prevent slowness due to the dataset's huge size.
 
-    Defaults to `10000`.
+    Defaults to `1000000`.
     """
     if val is None:
-        return 10000
+        return 1000000
     try:
         return int(val)
     except ValueError:
@@ -49,10 +49,10 @@ def TRAINING_SET_SIZE(val: str | None) -> int:
     """
     The number of reviews from each category to fetch for the training dataset.
 
-    Defaults to `5000`.
+    Defaults to `4000`.
     """
     if val is None:
-        return 5000
+        return 4000
     try:
         return int(val)
     except ValueError:
@@ -94,10 +94,10 @@ def TENSORFLOW_MAX_FEATURES(val: str | None) -> int:
     """
     The maximum number of features to use in Tensorflow models.
 
-    Defaults to `30000`.
+    Defaults to `300000`.
     """
     if val is None:
-        return 30000
+        return 300000
     try:
         return int(val)
     except ValueError: