[MNT] rename RKMETextSpecification

learnware/market/easy2/checker.py

@@ -82,9 +82,9 @@ class EasyStatisticalChecker(BaseChecker):
                 input_shape = learnware_model.input_shape
 
             # Check rkme dimension
-            is_text = "RKMETextStatSpecification" in learnware.get_specification().stat_spec
+            is_text = "RKMETextSpecification" in learnware.get_specification().stat_spec
             if is_text:
-                stat_spec = learnware.get_specification().get_stat_spec_by_name("RKMETextStatSpecification")
+                stat_spec = learnware.get_specification().get_stat_spec_by_name("RKMETextSpecification")
             else:
                 stat_spec = learnware.get_specification().get_stat_spec_by_name("RKMETableSpecification")
             if stat_spec is not None and not is_text:

learnware/market/easy2/searcher.py

@@ -438,7 +438,7 @@ class EasyStatSearcher(BaseSearcher):
             if self.stat_info_name not in learnware.specification.stat_spec:
                 continue
             rkme = learnware.specification.get_stat_spec_by_name(self.stat_info_name)
-            if self.stat_info_name == "RKMETextStatSpecification":
+            if self.stat_info_name == "RKMETextSpecification":
                 if not set(user_rkme.language).issubset(set(rkme.language)):
                     continue
             rkme_dim = str(list(rkme.get_z().shape)[1:])
@@ -557,8 +557,8 @@ class EasyStatSearcher(BaseSearcher):
         max_search_num: int = 5,
         search_method: str = "greedy",
     ) -> Tuple[List[float], List[Learnware], float, List[Learnware]]:
-        if "RKMETextStatSpecification" in user_info.stat_info:
-            self.stat_info_name = "RKMETextStatSpecification"
+        if "RKMETextSpecification" in user_info.stat_info:
+            self.stat_info_name = "RKMETextSpecification"
         else:
             self.stat_info_name = "RKMETableSpecification"
         user_rkme = user_info.stat_info[self.stat_info_name]
@@ -636,7 +636,7 @@ class EasySearcher(BaseSearcher):
             return [], [], 0.0, []
         elif "RKMETableSpecification" in user_info.stat_info:
             return self.stat_searcher(learnware_list, user_info, max_search_num, search_method)
-        elif "RKMETextStatSpecification" in user_info.stat_info:
+        elif "RKMETextSpecification" in user_info.stat_info:
             return self.stat_searcher(learnware_list, user_info, max_search_num, search_method)
         else:
             return None, learnware_list, 0.0, None

learnware/reuse/job_selector.py

@@ -9,7 +9,7 @@ from sklearn.metrics import accuracy_score
 from learnware.learnware import Learnware
 import learnware.specification as specification
 from .base import BaseReuser
-from ..specification import RKMETableSpecification, RKMETextStatSpecification
+from ..specification import RKMETableSpecification, RKMETextSpecification
 from ..logger import get_module_logger
 
 logger = get_module_logger("job_selector_reuse")
@@ -47,7 +47,7 @@ class JobSelectorReuser(BaseReuser):
         """
         ori_user_data = user_data
         if isinstance(user_data[0], str):
-            user_data = RKMETextStatSpecification.get_sentence_embedding(user_data)
+            user_data = RKMETextSpecification.get_sentence_embedding(user_data)
 
         select_result = self.job_selector(user_data)
         pred_y_list = []
@@ -93,10 +93,10 @@ class JobSelectorReuser(BaseReuser):
         else:
             ori_user_data = user_data
             if isinstance(user_data[0], str):
-                user_data = RKMETextStatSpecification.get_sentence_embedding(user_data)
+                user_data = RKMETextSpecification.get_sentence_embedding(user_data)
             spec_name = "RKMETableSpecification"
-            if len(self.learnware_list) and "RKMETextStatSpecification" in self.learnware_list[0].specification.stat_spec:
-                spec_name = "RKMETextStatSpecification"
+            if len(self.learnware_list) and "RKMETextSpecification" in self.learnware_list[0].specification.stat_spec:
+                spec_name = "RKMETextSpecification"
             learnware_rkme_spec_list = [
                 learnware.specification.get_stat_spec_by_name(spec_name) for learnware in self.learnware_list
             ]
@@ -180,7 +180,7 @@ class JobSelectorReuser(BaseReuser):
         """
         task_num = len(task_rkme_list)
         if isinstance(user_data[0], str):
-            user_data = RKMETextStatSpecification.get_sentence_embedding(user_data)
+            user_data = RKMETextSpecification.get_sentence_embedding(user_data)
         user_rkme_spec = specification.utils.generate_rkme_spec(X=user_data, reduce=False)
         K = task_rkme_matrix
         v = np.array([user_rkme_spec.inner_prod(task_rkme) for task_rkme in task_rkme_list])

learnware/specification/__init__.py

@@ -1,3 +1,3 @@
 from .utils import generate_stat_spec, generate_rkme_spec, generate_rkme_image_spec
 from .base import Specification, BaseStatSpecification
-from .regular import RegularStatsSpecification, RKMEStatSpecification, RKMETableSpecification, RKMEImageSpecification
+from .regular import RegularStatsSpecification, RKMEStatSpecification, RKMETableSpecification, RKMEImageSpecification, RKMETextSpecification

learnware/specification/regular/__init__.py

@@ -1,4 +1,4 @@
-from .text import RKMETextStatSpecification
+from .text import RKMETextSpecification
 from .table import RKMETableSpecification, RKMEStatSpecification
 from .image import RKMEImageSpecification
 from .base import RegularStatsSpecification

learnware/specification/regular/text/__init__.py

@@ -1 +1 @@
-from .rkme import RKMETextStatSpecification
+from .rkme import RKMETextSpecification

learnware/specification/regular/text/rkme.py

@@ -5,10 +5,10 @@ import os
 import langdetect
 from ....logger import get_module_logger
 
-logger = get_module_logger("RKMETextStatSpecification", "INFO")
+logger = get_module_logger("RKMETextSpecification", "INFO")
 
 
-class RKMETextStatSpecification(RKMETableSpecification):
+class RKMETextSpecification(RKMETableSpecification):
     """Reduced Kernel Mean Embedding (RKME) Specification for Text"""
     def __init__(self, gamma: float = 0.1, cuda_idx: int = -1):
         RKMETableSpecification.__init__(self, gamma, cuda_idx)

learnware/specification/utils.py

@@ -4,7 +4,7 @@ import pandas as pd
 from typing import Union, List
 
 from .base import BaseStatSpecification
-from .regular import RKMETableSpecification, RKMEImageSpecification, RKMETextStatSpecification
+from .regular import RKMETableSpecification, RKMEImageSpecification, RKMETextSpecification
 from ..config import C
 
 
@@ -173,10 +173,10 @@ def generate_rkme_text_spec(
     nonnegative_beta: bool = True,
     reduce: bool = True,
     cuda_idx: int = None,
-) -> RKMETextStatSpecification:
+) -> RKMETextSpecification:
     """
         Interface for users to generate Reduced Kernel Mean Embedding (RKME) specification for Text.
-        Return a RKMETextStatSpecification object, use .save() method to save as json file.
+        Return a RKMETextSpecification object, use .save() method to save as json file.
 
     Parameters
     ----------
@@ -200,8 +200,8 @@ def generate_rkme_text_spec(
 
     Returns
     -------
-    RKMETextStatSpecification
-        A RKMETextStatSpecification object
+    RKMETextSpecification
+        A RKMETextSpecification object
     """
     # Check input type
     if not isinstance(X, list) or not all(isinstance(item, str) for item in X):
@@ -216,7 +216,7 @@ def generate_rkme_text_spec(
             cuda_idx = 0
 
     # Generate rkme text spec
-    rkme_text_spec = RKMETextStatSpecification(gamma=gamma, cuda_idx=cuda_idx)
+    rkme_text_spec = RKMETextSpecification(gamma=gamma, cuda_idx=cuda_idx)
     rkme_text_spec.generate_stat_spec_from_data(X, reduced_set_size, step_size, steps, nonnegative_beta, reduce)
     return rkme_text_spec
 

tests/test_specification/test_rkme.py

@@ -8,7 +8,7 @@ import tempfile
 import numpy as np
 
 import learnware.specification as specification
-from learnware.specification import RKMETableSpecification, RKMEImageSpecification, RKMETextStatSpecification
+from learnware.specification import RKMETableSpecification, RKMEImageSpecification, RKMETextSpecification
 from learnware.specification import generate_rkme_image_spec, generate_rkme_spec
 
 
@@ -79,11 +79,11 @@ class TestRKME(unittest.TestCase):
 
                 with open(rkme_path, "r") as f:
                     data = json.load(f)
-                    assert data["type"] == "RKMETextStatSpecification"
+                    assert data["type"] == "RKMETextSpecification"
 
-                rkme2 = RKMETextStatSpecification()
+                rkme2 = RKMETextSpecification()
                 rkme2.load(rkme_path)
-                assert rkme2.type == "RKMETextStatSpecification"
+                assert rkme2.type == "RKMETextSpecification"
 
                 return rkme2.get_z().shape[1]
 

tests/test_text_workflow/example_files/example_yaml.yaml

@@ -3,6 +3,6 @@ model:
   kwargs: {}
 stat_specifications:
   - module_path: learnware.specification
-    class_name: RKMETextStatSpecification
+    class_name: RKMETextSpecification
     file_name: rkme.json
     kwargs: {}  

tests/test_text_workflow/main.py

@@ -100,7 +100,7 @@ def prepare_learnware(data_path, model_path, init_file_path, yaml_path, save_roo
 
     st = time.time()
     # user_spec = specification.utils.generate_rkme_spec(X=X, gamma=0.1, cuda_idx=0)
-    user_spec = specification.RKMETextStatSpecification()
+    user_spec = specification.RKMETextSpecification()
     user_spec.generate_stat_spec_from_data(X=X)
     ed = time.time()
     logger.info("Stat spec generated in %.3f s" % (ed - st))
@@ -166,9 +166,9 @@ def test_search(gamma=0.1, load_market=True):
         # user_data = np.load(user_data_path)
         # user_label = np.load(user_label_path)
         # user_stat_spec = specification.utils.generate_rkme_spec(X=user_data, gamma=gamma, cuda_idx=0)
-        user_stat_spec = specification.RKMETextStatSpecification()
+        user_stat_spec = specification.RKMETextSpecification()
         user_stat_spec.generate_stat_spec_from_data(X=user_data)
-        user_info = BaseUserInfo(semantic_spec=user_semantic, stat_info={"RKMETextStatSpecification": user_stat_spec})
+        user_info = BaseUserInfo(semantic_spec=user_semantic, stat_info={"RKMETextSpecification": user_stat_spec})
         logger.info("Searching Market for user: %d" % (i))
         sorted_score_list, single_learnware_list, mixture_score, mixture_learnware_list = text_market.search_learnware(
             user_info
@@ -232,6 +232,6 @@ def test_search(gamma=0.1, load_market=True):
 
 
 if __name__ == "__main__":
-    # prepare_data()
-    # prepare_model()
-    test_search(load_market=True)
+    prepare_data()
+    prepare_model()
+    test_search(load_market=False)