upgini 1.2.98a3922.dev3__py3-none-any.whl → 1.2.99a3922.dev4__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.98a3922.dev3"
+__version__ = "1.2.99a3922.dev4"

upgini/autofe/feature.py

@@ -1,5 +1,6 @@
 import hashlib
 import itertools
+import logging
 from typing import Dict, List, Optional, Set, Tuple, Union
 
 import numpy as np
@@ -18,10 +19,7 @@ class Column:
         self.data = data
         self.calculate_all = calculate_all
 
-    def get_display_name(self, cache: bool = True, shorten: bool = False, **kwargs) -> str:
-        return self.name
-
-    def set_op_params(self, params: Dict[str, str]) -> "Column":
+    def set_op_params(self, params: Dict[str, str], **kwargs) -> "Column":
         return self
 
     def get_op_params(self, **kwargs):
@@ -37,8 +35,21 @@ class Column:
     def get_column_nodes(self) -> List["Column"]:
         return [self]
 
-    def get_columns(self, **kwargs) -> List[str]:
-        return [self.name]
+    def get_columns(self, unhash=False, **kwargs):
+        name = self.name
+        return [self._unhash(name) if unhash else name]
+
+    def get_display_name(self, cache: bool = True, shorten: bool = False, **kwargs) -> str:
+        return self.get_columns(**kwargs)[0]
+
+    def _unhash(self, feature_name: str) -> str:
+        last_component_idx = feature_name.rfind("_")
+        if not feature_name.startswith("f_"):
+            return feature_name  # etalon feature
+        elif last_component_idx == 1:
+            return feature_name[2:]  # fully hashed name, cannot unhash
+        else:
+            return feature_name[2:last_component_idx]
 
     @property
     def children(self) -> List[Union["Feature", "Column"]]:
@@ -81,7 +92,7 @@ class Feature:
         self.cached_display_name = cached_display_name
         self.alias = alias
 
-    def set_op_params(self, params: Optional[Dict[str, str]]) -> "Feature":
+    def set_op_params(self, params: Optional[Dict[str, str]], **kwargs) -> "Feature":
         obj_dict = pydantic_dump_method(self.op)().copy()
         obj_dict.update(params or {})
         self.op = pydantic_parse_method(self.op.__class__)(obj_dict)
@@ -89,13 +100,13 @@ class Feature:
 
         for child in self.children:
             child_params = {
-                k[len(child.get_display_name()) + 1 :]: v
+                k[len(child.get_display_name(**kwargs)) + 1 :]: v
                 for k, v in params.items()
-                if k.startswith(child.get_display_name())
+                if k.startswith(child.get_display_name(**kwargs))
             }
             if not child_params:
                 child_params = params
-            child.set_op_params(child_params)
+            child.set_op_params(child_params, **kwargs)
         return self
 
     def get_op_params(self, **kwargs) -> Dict[str, str]:
@@ -341,6 +352,12 @@ class Feature:
                 base_features.reverse()
                 return Feature(op, base_features)
 
+    def set_logger(self, logger: logging.Logger):
+        self.op.set_logger(logger)
+        for child in self.children:
+            child.set_logger(logger)
+        return self
+
 
 class FeatureGroup:
     def __init__(

upgini/autofe/operator.py

@@ -1,9 +1,10 @@
 import abc
+import logging
 from typing import Dict, List, Optional, Tuple, Union
 
 import numpy as np
 import pandas as pd
-from pydantic import BaseModel
+from pydantic import BaseModel, PrivateAttr
 
 
 class OperatorRegistry(type(BaseModel)):
@@ -64,6 +65,8 @@ class Operator(BaseModel, metaclass=OperatorRegistry):
     is_distribution_dependent: bool = False
     params: Optional[Dict[str, str]] = None
 
+    _logger: logging.Logger = PrivateAttr(default=logging.getLogger(__name__))
+
     def set_params(self, params: Dict[str, str]):
         self.params = params
         return self
@@ -79,6 +82,10 @@ class Operator(BaseModel, metaclass=OperatorRegistry):
     def get_hash_component(self) -> str:
         return self.to_formula()
 
+    def set_logger(self, logger: logging.Logger):
+        self._logger = logger
+        return self
+
 
 class ParametrizedOperator(Operator, abc.ABC):
 

upgini/autofe/unary.py

@@ -3,7 +3,7 @@ from typing import Dict, List, Optional
 import numpy as np
 import pandas as pd
 
-from upgini.autofe.operator import PandasOperator, VectorizableMixin
+from upgini.autofe.operator import PandasOperator, ParametrizedOperator, VectorizableMixin
 from upgini.autofe.utils import pydantic_validator
 
 
@@ -198,3 +198,24 @@ class Cluster(PandasOperator):
     input_type: Optional[str] = "vector"
     output_type: Optional[str] = "category"
     is_categorical: bool = True
+
+
+class OutlierDistance(PandasOperator, ParametrizedOperator):
+    name: str = "outlier_dist"
+    is_unary: bool = True
+    input_type: Optional[str] = "vector"
+    output_type: Optional[str] = "float"
+    class_value: Optional[str] = None
+
+    def to_formula(self) -> str:
+        return f"outlier_dist_{self.class_value if self.class_value is not None else 'all'}"
+
+    @classmethod
+    def from_formula(cls, formula: str) -> Optional["OutlierDistance"]:
+        if formula == "outlier_dist":
+            return cls()
+
+        if formula.startswith("outlier_dist_"):
+            class_value = formula.split("_")[-1]
+            return cls(class_value=None if class_value == "all" else class_value)
+        return None

upgini/autofe/vector.py

@@ -1,4 +1,4 @@
-from typing import Dict, List, Optional
+from typing import List, Optional
 
 import pandas as pd
 

upgini/features_enricher.py

@@ -4174,7 +4174,7 @@ if response.status_code == 200:
 
                 description = {}
 
-                feature_meta = get_feature_by_name(autofe_feature.get_display_name(shorten=True))
+                feature_meta = get_feature_by_name(autofe_feature.get_display_name(shorten=True, unhash=True))
                 if feature_meta is None:
                     self.logger.warning(f"Feature meta for display index {m.display_index} not found")
                     continue

upgini/metrics.py

@@ -399,14 +399,14 @@ class EstimatorWrapper:
                 self.converted_to_str.append(c)
             elif c in self.cat_features:
                 if x[c].dtype == "bool" or (x[c].dtype == "category" and x[c].cat.categories.dtype == "bool"):
-                    x[c] = x[c].astype(np.int64)
+                    x[c] = x[c].astype(pd.Int64Dtype())
                     self.converted_to_int.append(c)
                 elif x[c].dtype == "category" and is_integer_dtype(x[c].cat.categories):
                     self.logger.info(
                         f"Convert categorical feature {c} with integer categories"
                         " to int64 and remove from cat_features"
                     )
-                    x[c] = x[c].astype(np.int64)
+                    x[c] = x[c].astype(pd.Int64Dtype())
                     self.converted_to_int.append(c)
                     self.cat_features.remove(c)
                 elif is_float_dtype(x[c]) or (x[c].dtype == "category" and is_float_dtype(x[c].cat.categories)):
@@ -419,7 +419,7 @@ class EstimatorWrapper:
             else:
                 if x[c].dtype == "bool" or (x[c].dtype == "category" and x[c].cat.categories.dtype == "bool"):
                     self.logger.info(f"Convert bool feature {c} to int64")
-                    x[c] = x[c].astype(np.int64)
+                    x[c] = x[c].astype(pd.Int64Dtype())
                     self.converted_to_int.append(c)
                 elif not is_valid_numeric_array_data(x[c]) and not is_numeric_dtype(x[c]):
                     try:
@@ -442,7 +442,7 @@ class EstimatorWrapper:
         if self.converted_to_int:
             self.logger.info(f"Convert to int features on calculate metrics: {self.converted_to_int}")
             for c in self.converted_to_int:
-                x[c] = x[c].astype(np.int64)
+                x[c] = x[c].astype(pd.Int64Dtype())
 
         if self.converted_to_str:
             self.logger.info(f"Convert to str features on calculate metrics: {self.converted_to_str}")
@@ -896,7 +896,7 @@ class LightGBMWrapper(EstimatorWrapper):
                     x[c] = x[c].astype("category")
 
         for c in x.columns:
-            if x[c].dtype not in ["category", "int64", "float64", "bool"]:
+            if x[c].dtype not in ["category", "int64", "float64", "bool", "Int64"]:
                 self.logger.warning(f"Feature {c} is not numeric and will be dropped")
                 self.dropped_features.append(c)
                 x = x.drop(columns=c, errors="ignore")
@@ -987,7 +987,7 @@ class OtherEstimatorWrapper(EstimatorWrapper):
                     x[c] = x[c].astype("category")
             params["cat_features"] = self.cat_features
         for c in x.columns:
-            if x[c].dtype not in ["category", "int64", "float64", "bool"]:
+            if x[c].dtype not in ["category", "int64", "float64", "bool", "Int64"]:
                 self.logger.warning(f"Feature {c} is not numeric and will be dropped")
                 self.dropped_features.append(c)
                 x = x.drop(columns=c, errors="ignore")

{upgini-1.2.98a3922.dev3.dist-info → upgini-1.2.99a3922.dev4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.98a3922.dev3
+Version: 1.2.99a3922.dev4
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

{upgini-1.2.98a3922.dev3.dist-info → upgini-1.2.99a3922.dev4.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=c20ALjeM25Bh-ipz7uc8Eb_tWD5utgqiELwRRlqcRlw,33
+upgini/__about__.py,sha256=5Lrxh5wP8aiUGT1GPRS8K7nPnEINmj_I5a_XBymupWQ,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=e6JDYTZ2AwC5aF-dqclKZKkiKrHo2f6cFmMQO2ZZmjM,32724
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=4rKoV-3jM876Fk0fM4XlnW3fLwXvk1KN2ymcwlAfPm0,219941
+upgini/features_enricher.py,sha256=KSOEzO29nY79RIW0hdbf1qXQGxa3itKZ0PkcwVPPf9U,219954
 upgini/http.py,sha256=DNcoS7qdxG0mOJn6I8r6O5I6XdIJTdzDzW3hkz3NgG4,45443
 upgini/metadata.py,sha256=vsbbHyPCP3Rs8WkeDgQg99uAA_zmsbDStAT-NwDYhO4,12455
-upgini/metrics.py,sha256=UbKEsHB7XDzoyGNqDx846zbh1t65GpqdnnhViccdoKU,45615
+upgini/metrics.py,sha256=gXr2aiw5j9QBWBo1hZp40Is679hef5q8MrT6LJfjsBk,45661
 upgini/search_task.py,sha256=Q5HjBpLIB3OCxAD1zNv5yQ3ZNJx696WCK_-H35_y7Rs,17912
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -16,12 +16,12 @@ upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/autofe/all_operators.py,sha256=rdjF5eaE4bC6Q4eu_el5Z7ekYt8DjOFermz2bePPbUc,333
 upgini/autofe/binary.py,sha256=oOEECc4nRzZN2tYaiqx8F2XHnfWpk1bVvb7ZkZJ0lO8,7709
 upgini/autofe/date.py,sha256=MM1S-6imNSzCDOhbNnmsc_bwSqUWBcS8vWAdHF8j1kY,11134
-upgini/autofe/feature.py,sha256=cu4xXjzVVF13ZV4RxuTrysK2qCfezlRCMOzCKRo1rNs,15558
+upgini/autofe/feature.py,sha256=71IQXztYdG2nygVJ4AZ4mOsx5w8PN239rZguKy_4lnE,16250
 upgini/autofe/groupby.py,sha256=IYmQV9uoCdRcpkeWZj_kI3ObzoNCNx3ff3h8sTL01tk,3603
-upgini/autofe/operator.py,sha256=EOffJw6vKXpEh5yymqb1RFNJPxGxmnHdFRo9dB5SCFo,4969
-upgini/autofe/unary.py,sha256=N76Pehn-hO8FWlSdqJ2Wm-yoU1MSR7m6yb2GWYBcumU,5933
+upgini/autofe/operator.py,sha256=WpMd3C-7FpiNXhVDs3MQy7Benz9B6iq6jvXohnCms9c,5178
+upgini/autofe/unary.py,sha256=FFtvkQaT0cu_zPZ1jCLcsjik-UUh12qQFF3tUW8NqsE,6675
 upgini/autofe/utils.py,sha256=dYrtyAM8Vcc_R8u4dNo54IsGrHKagTHDJTKhGho0bRg,2967
-upgini/autofe/vector.py,sha256=NBvRLXVSQf8AU5WI-rXBlO2lfs-skX_XD0KaxkfBFW8,1283
+upgini/autofe/vector.py,sha256=9T7MEUK0SavXIJy0c9Kvu5qTcMtt3fzvdRDBDxcI0JA,1277
 upgini/autofe/timeseries/__init__.py,sha256=PGwwDAMwvkXl3el12tXVEmZUgDUvlmIPlXtROm6bD18,738
 upgini/autofe/timeseries/base.py,sha256=rWJqRuFAzTZEsUdWG5s1Vhif9zzRRmalASXvarufRxI,3610
 upgini/autofe/timeseries/cross.py,sha256=BTINVwuZSbm_4NKkVm0FGM68SrvZLENZKXN7-UyvhYI,5319
@@ -71,7 +71,7 @@ upgini/utils/target_utils.py,sha256=i3Xt5l9ybB2_nF_ma5cfPuL3OeFTs2dY2xDI0p4Azpg,
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.98a3922.dev3.dist-info/METADATA,sha256=N0PxLZz_XaDEyH77cUCwjKE3ocLXAOo6n5Cy_1xYb8w,49538
-upgini-1.2.98a3922.dev3.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.98a3922.dev3.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.98a3922.dev3.dist-info/RECORD,,
+upgini-1.2.99a3922.dev4.dist-info/METADATA,sha256=wYgu44FVyY6Bfof83_UJ1tWMWxrKTUoY_m1Q0QHDqJ8,49538
+upgini-1.2.99a3922.dev4.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.99a3922.dev4.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.99a3922.dev4.dist-info/RECORD,,