upgini 1.1.278a1__py3-none-any.whl → 1.1.279__py3-none-any.whl

upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.279"

upgini/ads_management/ads_manager.py

@@ -1,9 +1,11 @@
 import time
-from typing import Dict, Optional
 import uuid
+from typing import Dict, Optional
+
+import pandas as pd
+
 from upgini.http import get_rest_client
 from upgini.spinner import Spinner
-import pandas as pd
 
 
 class AdsManager:

upgini/autofe/all_operands.py

@@ -1,9 +1,10 @@
 from typing import Dict
+
+from upgini.autofe.binary import Add, Divide, Max, Min, Multiply, Sim, Subtract
 from upgini.autofe.date import DateDiff, DateDiffType2, DateListDiff, DateListDiffBounded
 from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
 from upgini.autofe.operand import Operand
-from upgini.autofe.unary import Abs, Log, Residual, Sqrt, Square, Sigmoid, Floor, Freq
-from upgini.autofe.binary import Min, Max, Add, Subtract, Multiply, Divide, Sim
+from upgini.autofe.unary import Abs, Floor, Freq, Log, Residual, Sigmoid, Sqrt, Square
 from upgini.autofe.vector import Mean, Sum
 
 ALL_OPERANDS: Dict[str, Operand] = {

upgini/autofe/binary.py

@@ -1,9 +1,10 @@
-from upgini.autofe.operand import PandasOperand, VectorizableMixin
 import numpy as np
 import pandas as pd
 from numpy import dot
 from numpy.linalg import norm
 
+from upgini.autofe.operand import PandasOperand, VectorizableMixin
+
 
 class Min(PandasOperand):
     name = "min"

upgini/autofe/date.py

@@ -1,8 +1,9 @@
 from typing import Any, Optional, Union
+
 import numpy as np
 import pandas as pd
-from pydantic import BaseModel
 from pandas.core.arrays.timedeltas import TimedeltaArray
+from pydantic import BaseModel
 
 from upgini.autofe.operand import PandasOperand
 

upgini/autofe/feature.py

@@ -215,7 +215,7 @@ class Feature:
             return Column(string)
 
         def is_trivial_char(c: str) -> bool:
-            return not (c in "()+-*/,")
+            return c not in "()+-*/,"
 
         def find_prev(string: str) -> int:
             if string[-1] != ")":

upgini/autofe/groupby.py

@@ -1,7 +1,9 @@
-from upgini.autofe.operand import PandasOperand, VectorizableMixin
 from typing import Optional
+
 import pandas as pd
 
+from upgini.autofe.operand import PandasOperand, VectorizableMixin
+
 
 class GroupByThenAgg(PandasOperand, VectorizableMixin):
     agg: Optional[str]

upgini/autofe/operand.py

@@ -1,8 +1,9 @@
-from pydantic import BaseModel
-from typing import Dict, List, Optional, Tuple, Union
 import abc
-import pandas as pd
+from typing import Dict, List, Optional, Tuple, Union
+
 import numpy as np
+import pandas as pd
+from pydantic import BaseModel
 
 
 class Operand(BaseModel):

upgini/autofe/unary.py

@@ -1,7 +1,8 @@
-from upgini.autofe.operand import PandasOperand, VectorizableMixin
 import numpy as np
 import pandas as pd
 
+from upgini.autofe.operand import PandasOperand, VectorizableMixin
+
 
 class Abs(PandasOperand, VectorizableMixin):
     name = "abs"

upgini/autofe/vector.py

@@ -1,5 +1,7 @@
 from typing import List
+
 import pandas as pd
+
 from upgini.autofe.operand import PandasOperand, VectorizableMixin
 
 

upgini/dataset.py

@@ -15,17 +15,15 @@ from pandas.api.types import (
     is_float_dtype,
     is_integer_dtype,
     is_numeric_dtype,
+    is_object_dtype,
     is_period_dtype,
     is_string_dtype,
-    is_object_dtype,
 )
 
 from upgini.errors import ValidationError
 from upgini.http import ProgressStage, SearchProgress, _RestClient
 from upgini.metadata import (
-    ENTITY_SYSTEM_RECORD_ID,
     EVAL_SET_INDEX,
-    SEARCH_KEY_UNNEST,
     SYSTEM_COLUMNS,
     SYSTEM_RECORD_ID,
     TARGET,
@@ -81,7 +79,6 @@ class Dataset:  # (pd.DataFrame):
         path: Optional[str] = None,
         meaning_types: Optional[Dict[str, FileColumnMeaningType]] = None,
         search_keys: Optional[List[Tuple[str, ...]]] = None,
-        unnest_search_keys: Optional[Dict[str, str]] = None,
         model_task_type: Optional[ModelTaskType] = None,
         random_state: Optional[int] = None,
         rest_client: Optional[_RestClient] = None,
@@ -98,7 +95,7 @@ class Dataset:  # (pd.DataFrame):
                 data = pd.read_csv(path, **kwargs)
             else:
                 # try different separators: , ; \t ...
-                with open(path, mode="r") as csvfile:
+                with open(path) as csvfile:
                     sep = csv.Sniffer().sniff(csvfile.read(2048)).delimiter
                 kwargs["sep"] = sep
                 data = pd.read_csv(path, **kwargs)
@@ -116,7 +113,6 @@ class Dataset:  # (pd.DataFrame):
         self.description = description
         self.meaning_types = meaning_types
         self.search_keys = search_keys
-        self.unnest_search_keys = unnest_search_keys
         self.ignore_columns = []
         self.hierarchical_group_keys = []
         self.hierarchical_subgroup_keys = []
@@ -176,7 +172,7 @@ class Dataset:  # (pd.DataFrame):
         new_columns = []
         dup_counter = 0
         for column in self.data.columns:
-            if column in [TARGET, EVAL_SET_INDEX, SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID, SEARCH_KEY_UNNEST]:
+            if column in [TARGET, EVAL_SET_INDEX, SYSTEM_RECORD_ID]:
                 self.columns_renaming[column] = column
                 new_columns.append(column)
                 continue
@@ -255,7 +251,7 @@ class Dataset:  # (pd.DataFrame):
     @staticmethod
     def _ip_to_int(ip: Optional[_BaseAddress]) -> Optional[int]:
         try:
-            if isinstance(ip, IPv4Address) or isinstance(ip, IPv6Address):
+            if isinstance(ip, (IPv4Address, IPv6Address)):
                 return int(ip)
         except Exception:
             pass
@@ -263,7 +259,7 @@ class Dataset:  # (pd.DataFrame):
     @staticmethod
     def _ip_to_int_str(ip: Optional[_BaseAddress]) -> Optional[str]:
         try:
-            if isinstance(ip, IPv4Address) or isinstance(ip, IPv6Address):
+            if isinstance(ip, (IPv4Address, IPv6Address)):
                 return str(int(ip))
         except Exception:
             pass
@@ -357,9 +353,7 @@ class Dataset:  # (pd.DataFrame):
 
             if is_string_dtype(self.data[postal_code]) or is_object_dtype(self.data[postal_code]):
                 try:
-                    self.data[postal_code] = (
-                        self.data[postal_code].astype("string").astype("Float64").astype("Int64").astype("string")
-                    )
+                    self.data[postal_code] = self.data[postal_code].astype("float64").astype("Int64").astype("string")
                 except Exception:
                     pass
             elif is_float_dtype(self.data[postal_code]):
@@ -809,9 +803,6 @@ class Dataset:  # (pd.DataFrame):
                     meaningType=meaning_type,
                     minMaxValues=min_max_values,
                 )
-                if self.unnest_search_keys and column_meta.originalName in self.unnest_search_keys:
-                    column_meta.isUnnest = True
-                    column_meta.unnestKeyNames = self.unnest_search_keys[column_meta.originalName]
 
                 columns.append(column_meta)
 

upgini/errors.py

@@ -16,7 +16,7 @@ class UnauthorizedError(HttpError):
     """Unauthorized error from REST API."""
 
     def __init__(self, message, status_code):
-        message = "Unauthorized, please check your authorization token ({})".format(message)
+        message = f"Unauthorized, please check your authorization token ({message})"
         super(UnauthorizedError, self).__init__(message, status_code)