upgini 1.2.73a3659.dev2__py3-none-any.whl → 1.2.75__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.73a3659.dev2"
+__version__ = "1.2.75"

upgini/autofe/date.py

@@ -187,16 +187,21 @@ class DateListDiff(PandasOperator, DateDiffMixin, ParametrizedOperator):
 class DateListDiffBounded(DateListDiff, ParametrizedOperator):
     lower_bound: Optional[int] = None
     upper_bound: Optional[int] = None
+    normalize: Optional[bool] = None
 
     def to_formula(self) -> str:
         lower_bound = "minusinf" if self.lower_bound is None else self.lower_bound
         upper_bound = "plusinf" if self.upper_bound is None else self.upper_bound
-        return f"date_diff_{self.diff_unit}_{lower_bound}_{upper_bound}_{self.aggregation}"
+        norm = "_norm" if self.normalize else ""
+        return f"date_diff_{self.diff_unit}_{lower_bound}_{upper_bound}_{self.aggregation}{norm}"
 
     @classmethod
     def from_formula(cls, formula: str) -> Optional["DateListDiffBounded"]:
         import re
 
+        normalize = formula.endswith("_norm")
+        formula = formula.replace("_norm", "")
+
         pattern = r"^date_diff_([^_]+)_((minusinf|\d+))_((plusinf|\d+))_(\w+)$"
         match = re.match(pattern, formula)
 
@@ -207,8 +212,13 @@ class DateListDiffBounded(DateListDiff, ParametrizedOperator):
         lower_bound = None if match.group(2) == "minusinf" else int(match.group(2))
         upper_bound = None if match.group(4) == "plusinf" else int(match.group(4))
         aggregation = match.group(6)
-
-        return cls(diff_unit=diff_unit, lower_bound=lower_bound, upper_bound=upper_bound, aggregation=aggregation)
+        return cls(
+            diff_unit=diff_unit,
+            lower_bound=lower_bound,
+            upper_bound=upper_bound,
+            aggregation=aggregation,
+            normalize=normalize,
+        )
 
     def get_params(self) -> Dict[str, Optional[str]]:
         res = super().get_params()
@@ -216,14 +226,20 @@ class DateListDiffBounded(DateListDiff, ParametrizedOperator):
             res["lower_bound"] = str(self.lower_bound)
         if self.upper_bound is not None:
             res["upper_bound"] = str(self.upper_bound)
+        if self.normalize is not None:
+            res["normalize"] = str(self.normalize)
         return res
 
     def _agg(self, x):
+        orig_len = len(x)
         x = x[
             (x >= (self.lower_bound if self.lower_bound is not None else -np.inf))
             & (x < (self.upper_bound if self.upper_bound is not None else np.inf))
         ]
-        return super()._agg(x)
+        agg_res = super()._agg(x)
+        if self.normalize and orig_len > 0:
+            return agg_res / orig_len
+        return agg_res
 
 
 class DatePercentileBase(PandasOperator, abc.ABC):

upgini/autofe/feature.py

@@ -154,24 +154,34 @@ class Feature:
         for child in self.children:
             child.delete_data()
 
-    def get_op_display_name(self) -> str:
-        return (self.op.alias or self.op.to_formula()).lower()
+    def get_op_display_name(self, use_alias: bool = True) -> str:
+        return (self.op.alias or self.op.to_formula()).lower() if use_alias else self.op.to_formula()
 
-    def get_display_name(self, cache: bool = True, shorten: bool = False, **kwargs) -> str:
+    def get_display_name(self, cache: bool = True, shorten: bool = False, use_op_alias: bool = True, **kwargs) -> str:
         if self.cached_display_name is not None and cache:
             return self.cached_display_name
 
         should_stack_op = not isinstance(self.children[0], Column) if self.op.is_unary else False
-        prev_name = [self.children[0].get_op_display_name()] if should_stack_op else []
+        components = []
 
         if self.alias:
-            components = ["f_autofe", self.alias]
-        elif shorten and (not self.op.is_unary or should_stack_op):
-            components = ["f_autofe"] + prev_name + [self.get_op_display_name()]
-        else:
-            components = (
-                ["f_" + "_f_".join(self.get_columns(**kwargs))] + ["autofe"] + prev_name + [self.get_op_display_name()]
+            components.extend(["f_autofe", self.alias])
+        elif should_stack_op:
+            components.extend(
+                [
+                    self.children[0].get_display_name(
+                        cache=cache, shorten=shorten, use_op_alias=use_op_alias, **kwargs
+                    ),
+                    self.get_op_display_name(use_alias=use_op_alias),
+                ]
             )
+        elif shorten and not self.op.is_unary:
+            components.extend(["f_autofe", self.get_op_display_name(use_alias=use_op_alias)])
+        else:
+            components = ["f_" + "_f_".join(self.get_columns(**kwargs))] + [
+                "autofe",
+                self.get_op_display_name(use_alias=use_op_alias),
+            ]
         components.extend([str(self.display_index)] if self.display_index is not None else [])
         display_name = "_".join(components)
 

upgini/autofe/unary.py

@@ -1,8 +1,10 @@
-from typing import Dict, Optional
+import json
+from typing import Dict, List, Optional
 import numpy as np
 import pandas as pd
 
 from upgini.autofe.operator import PandasOperator, VectorizableMixin
+from upgini.autofe.utils import pydantic_validator
 
 
 class Abs(PandasOperator, VectorizableMixin):
@@ -153,3 +155,38 @@ class Embeddings(PandasOperator):
     is_unary: bool = True
     input_type: Optional[str] = "string"
     output_type: Optional[str] = "vector"
+
+
+class Bin(PandasOperator):
+    name: str = "bin"
+    is_unary: bool = True
+    output_type: Optional[str] = "category"
+    bin_bounds: List[int] = []
+    is_categorical: bool = True
+
+    def calculate_unary(self, data: pd.Series) -> pd.Series:
+        return data.apply(self._bin, bounds=self.bin_bounds).fillna(-1).astype(int).astype("category")
+
+    def _bin(self, f, bounds):
+        if f is None or np.isnan(f):
+            return np.nan
+        hit = np.where(f >= np.array(bounds))[0]
+        if hit.size > 0:
+            return np.max(hit) + 1
+        else:
+            return np.nan
+
+    def get_params(self) -> Dict[str, Optional[str]]:
+        res = super().get_params()
+        res.update(
+            {
+                "bin_bounds": json.dumps(self.bin_bounds),
+            }
+        )
+        return res
+
+    @pydantic_validator("bin_bounds", mode="before")
+    def parse_bin_bounds(cls, value):
+        if isinstance(value, str):
+            return json.loads(value)
+        return value

upgini/autofe/vector.py

@@ -1,8 +1,8 @@
-from typing import Dict, List, Optional
+from typing import List, Optional
 
 import pandas as pd
 
-from upgini.autofe.operator import OperatorRegistry, PandasOperator, VectorizableMixin
+from upgini.autofe.operator import PandasOperator, VectorizableMixin
 
 
 class Mean(PandasOperator, VectorizableMixin):
@@ -24,23 +24,10 @@ class Sum(PandasOperator, VectorizableMixin):
         return pd.DataFrame(data).T.fillna(0).sum(axis=1)
 
 
-class OnnxModel(PandasOperator, metaclass=OperatorRegistry):
-    name: str = "onnx"
+class Vectorize(PandasOperator, VectorizableMixin):
+    name: str = "vectorize"
     is_vector: bool = True
-    output_type: Optional[str] = "float"
-    model_name: str = ""
-
-    def get_params(self) -> Dict[str, Optional[str]]:
-        res = super().get_params()
-        res.update(
-            {
-                "model_name": self.model_name,
-            }
-        )
-        return res
-
-    # def load_model(self):
-    #     ...
-
-    # def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
-    #     ...
+    group_index: int = 0
+
+    def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
+        return pd.DataFrame(data).T.apply(lambda x: x.to_list(), axis=1)

upgini/metrics.py

@@ -326,7 +326,7 @@ class EstimatorWrapper:
         for c in x.columns:
             if is_numeric_dtype(x[c]):
                 x[c] = x[c].astype(float)
-            else:
+            elif not x[c].dtype == "category":
                 x[c] = x[c].astype(str)
 
         if not isinstance(y, pd.Series):
@@ -481,7 +481,7 @@ class EstimatorWrapper:
             "logger": logger,
         }
         if estimator is None:
-            params = {}
+            params = {"random_state": DEFAULT_RANDOM_STATE}
             if target_type == ModelTaskType.MULTICLASS:
                 params = _get_add_params(params, LIGHTGBM_MULTICLASS_PARAMS)
                 params = _get_add_params(params, add_params)
@@ -749,6 +749,8 @@ class LightGBMWrapper(EstimatorWrapper):
         if self.target_type in [ModelTaskType.BINARY, ModelTaskType.MULTICLASS]:
             self.n_classes = len(np.unique(y_numpy))
         if LIGHTGBM_EARLY_STOPPING_ROUNDS is not None:
+            if self.target_type == ModelTaskType.BINARY:
+                params["eval_metric"] = "auc"
             params["callbacks"] = [lgb.early_stopping(stopping_rounds=LIGHTGBM_EARLY_STOPPING_ROUNDS, verbose=False)]
         self.cat_features = _get_cat_features(x)
         if self.cat_features:

{upgini-1.2.73a3659.dev2.dist-info → upgini-1.2.75.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.73a3659.dev2
+Version: 1.2.75
 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-1.2.73a3659.dev2.dist-info → upgini-1.2.75.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=Vn3aojC64D6rn5ZFKIFRFVE3tY8D8CLC3Y0V5pbn2Jo,33
+upgini/__about__.py,sha256=xPczHfrMrTuUNz8xC9lgCjhkHVDmW9TFPuLq9_c_Ms8,23
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=aspri7ZAgwkNNUiIgQ1GRXvw8XQii3F4RfNXSrF4wrw,35365
@@ -6,7 +6,7 @@ upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
 upgini/features_enricher.py,sha256=Li1sPihWVkPUPcma8HRbPFwpCqd9V9d2p5zQUgkpdpU,206998
 upgini/http.py,sha256=RvzcShpDXssLs6ycGN8xilkKi8ZV9XGUrrk8bwdUzbw,43607
 upgini/metadata.py,sha256=Yd6iW2f7Wz6vUkg5uvR4xylN16ANnCKVKqAsAkap7p8,12354
-upgini/metrics.py,sha256=a0bY4oTMb-MgB1yC1IuTcEtotKZxAxjgV_QV2Z4V8u4,38988
+upgini/metrics.py,sha256=pFRKBKyAri7xfe5pkNxcx241HQH95rV9afebgg8Tdiw,39156
 upgini/search_task.py,sha256=EuCGp0iCWz2fpuJgN6M47aP_CtIi3Oq9zw78w0mkKiU,17595
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -15,13 +15,13 @@ upgini/ads_management/ads_manager.py,sha256=igVbN2jz80Umb2BUJixmJVj-zx8unoKpecVo
 upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/autofe/all_operators.py,sha256=rdjF5eaE4bC6Q4eu_el5Z7ekYt8DjOFermz2bePPbUc,333
 upgini/autofe/binary.py,sha256=MnQuFiERpocjCPQUjOljlsq5FE-04GPfwtNjzvfNMyU,7671
-upgini/autofe/date.py,sha256=C86F7sPiscUGq2a45UtQA9ADWBWg0kt54mePHHzjbLE,10633
-upgini/autofe/feature.py,sha256=y1x3wijhTVBmloayQAHiscqKU9Ll8kLcGm1PdvS357I,14910
+upgini/autofe/date.py,sha256=MM1S-6imNSzCDOhbNnmsc_bwSqUWBcS8vWAdHF8j1kY,11134
+upgini/autofe/feature.py,sha256=G_YgnsauIoaMgByx9JXDPiKc4nqs0pwWZUfvoIGMKxY,15305
 upgini/autofe/groupby.py,sha256=IYmQV9uoCdRcpkeWZj_kI3ObzoNCNx3ff3h8sTL01tk,3603
 upgini/autofe/operator.py,sha256=EOffJw6vKXpEh5yymqb1RFNJPxGxmnHdFRo9dB5SCFo,4969
-upgini/autofe/unary.py,sha256=yVgPvtfnPSOhrii0YgezddmgWPwyOBCR0JutaIkdTTc,4658
+upgini/autofe/unary.py,sha256=Sx11IoHRh5nwyALzjgG9GQOrVNIs8NZ1JzunAJuN66A,5731
 upgini/autofe/utils.py,sha256=fK1am2_tQj3fL2vDslblye8lmyfWgGIUOX1beYVBz4k,2420
-upgini/autofe/vector.py,sha256=w7ipoFRvR0BcTYcvJR9EbKc_ycIn9cJ94RLgrgIi4Uc,1212
+upgini/autofe/vector.py,sha256=zehv1J9ChHdZKWjKlkRf6RpfQMCJduZmqCEePYNUfkQ,943
 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
@@ -70,7 +70,7 @@ upgini/utils/target_utils.py,sha256=P0cCVRaakWLydYwFjk3TEaQfr0p0hfsJCvKRD8qcxiE,
 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-1.2.73a3659.dev2.dist-info/METADATA,sha256=WImhNzA5wn2I_HyEYKvKAcUfpIWbQ0spUAI7tgu-fiQ,49101
-upgini-1.2.73a3659.dev2.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.73a3659.dev2.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.73a3659.dev2.dist-info/RECORD,,
+upgini-1.2.75.dist-info/METADATA,sha256=jUP3dTEC71e0OcENot-gdjVx1gxqUPVPWufkY-vRv60,49091
+upgini-1.2.75.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.75.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.75.dist-info/RECORD,,