upgini 1.2.3__tar.gz → 1.2.5__tar.gz

{upgini-1.2.3 → upgini-1.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.3
+Version: 1.2.5
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -260,7 +260,9 @@ We do dataset verification and cleaning under the hood, but still there are some
 *Search keys* columns will be used to match records from all potential external data sources / features.   
 Define one or multiple columns as a search keys with `FeaturesEnricher` class initialization.  
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -346,7 +348,9 @@ enricher = FeaturesEnricher(
 
 For the meaning types <tt>SearchKey.DATE</tt>/<tt>SearchKey.DATETIME</tt> with dtypes <tt>object</tt> or <tt>string</tt> you have to clarify date/datetime format by passing <tt>date_format</tt> parameter to `FeaturesEnricher`. For example:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -367,7 +371,9 @@ df["date"] = df.date.astype("datetime64").dt.tz_localize("Europe/Warsaw")
 
 Single country for the whole training dataset can be passed with `country_code` parameter:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -386,7 +392,8 @@ Create instance of the `FeaturesEnricher` class and call:
 Let's try it out!
 ```python
 import pandas as pd
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
 
 # load labeled training dataset to initiate search
 train_df = pd.read_csv("customer_churn_prediction_train.csv")
@@ -477,7 +484,9 @@ We detect ML task under the hood based on label column values. Currently we supp
 
 But for certain search datasets you can pass parameter to `FeaturesEnricher` with correct ML taks type:
 ```python
-from upgini import ModelTaskType
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey, ModelTaskType
+
 enricher = FeaturesEnricher(
 	search_keys={"subscription_activation_date": SearchKey.DATE},
 	model_task_type=ModelTaskType.REGRESSION
@@ -490,7 +499,9 @@ enricher = FeaturesEnricher(
 
 To initiate feature search you can pass cross-validation type parameter to `FeaturesEnricher` with time series specific CV type:
 ```python
-from upgini.metadata import CVType
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey, CVType
+
 enricher = FeaturesEnricher(
 	search_keys={"sales_date": SearchKey.DATE},
 	cv=CVType.time_series
@@ -624,7 +635,9 @@ But you can easily define new split by passing child of BaseCrossValidator to pa
 
 Example with more tips-and-tricks:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(search_keys={"registration_date": SearchKey.DATE})
 
 # Fit with default setup for metrics calculation
@@ -797,7 +810,7 @@ You may publish ANY data which you consider as royalty / license free ([Open Dat
 2. Copy *Upgini API key* from profile and upload your data from Upgini python library with this key:
 ```python
 import pandas as pd
-from upgini import SearchKey
+from upgini.metadata import SearchKey
 from upgini.ads import upload_user_ads
 import os
 os.environ["UPGINI_API_KEY"] = "your_long_string_api_key_goes_here"

{upgini-1.2.3 → upgini-1.2.5}/README.md

@@ -217,7 +217,9 @@ We do dataset verification and cleaning under the hood, but still there are some
 *Search keys* columns will be used to match records from all potential external data sources / features.   
 Define one or multiple columns as a search keys with `FeaturesEnricher` class initialization.  
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -303,7 +305,9 @@ enricher = FeaturesEnricher(
 
 For the meaning types <tt>SearchKey.DATE</tt>/<tt>SearchKey.DATETIME</tt> with dtypes <tt>object</tt> or <tt>string</tt> you have to clarify date/datetime format by passing <tt>date_format</tt> parameter to `FeaturesEnricher`. For example:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -324,7 +328,9 @@ df["date"] = df.date.astype("datetime64").dt.tz_localize("Europe/Warsaw")
 
 Single country for the whole training dataset can be passed with `country_code` parameter:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
@@ -343,7 +349,8 @@ Create instance of the `FeaturesEnricher` class and call:
 Let's try it out!
 ```python
 import pandas as pd
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
 
 # load labeled training dataset to initiate search
 train_df = pd.read_csv("customer_churn_prediction_train.csv")
@@ -434,7 +441,9 @@ We detect ML task under the hood based on label column values. Currently we supp
 
 But for certain search datasets you can pass parameter to `FeaturesEnricher` with correct ML taks type:
 ```python
-from upgini import ModelTaskType
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey, ModelTaskType
+
 enricher = FeaturesEnricher(
 	search_keys={"subscription_activation_date": SearchKey.DATE},
 	model_task_type=ModelTaskType.REGRESSION
@@ -447,7 +456,9 @@ enricher = FeaturesEnricher(
 
 To initiate feature search you can pass cross-validation type parameter to `FeaturesEnricher` with time series specific CV type:
 ```python
-from upgini.metadata import CVType
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey, CVType
+
 enricher = FeaturesEnricher(
 	search_keys={"sales_date": SearchKey.DATE},
 	cv=CVType.time_series
@@ -581,7 +592,9 @@ But you can easily define new split by passing child of BaseCrossValidator to pa
 
 Example with more tips-and-tricks:
 ```python
-from upgini import FeaturesEnricher, SearchKey
+from upgini.features_enricher import FeaturesEnricher
+from upgini.metadata import SearchKey
+
 enricher = FeaturesEnricher(search_keys={"registration_date": SearchKey.DATE})
 
 # Fit with default setup for metrics calculation
@@ -754,7 +767,7 @@ You may publish ANY data which you consider as royalty / license free ([Open Dat
 2. Copy *Upgini API key* from profile and upload your data from Upgini python library with this key:
 ```python
 import pandas as pd
-from upgini import SearchKey
+from upgini.metadata import SearchKey
 from upgini.ads import upload_user_ads
 import os
 os.environ["UPGINI_API_KEY"] = "your_long_string_api_key_goes_here"

upgini-1.2.5/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.5"

upgini-1.2.5/src/upgini/__init__.py

@@ -0,0 +1,13 @@
+import os
+
+from upgini.features_enricher import FeaturesEnricher  # noqa: F401
+from upgini.metadata import SearchKey, CVType, RuntimeParameters, ModelTaskType  # noqa: F401
+# from .lazy_import import LazyImport
+
+os.environ["SETUPTOOLS_USE_DISTUTILS"] = "stdlib"
+
+# FeaturesEnricher = LazyImport("upgini.features_enricher", "FeaturesEnricher")
+# SearchKey = LazyImport("upgini.metadata", "SearchKey")
+# RuntimeParameters = LazyImport("upgini.metadata", "RuntimeParameters")
+# CVType = LazyImport("upgini.metadata", "CVType")
+# ModelTaskType = LazyImport("upgini.metadata", "ModelTaskType")

{upgini-1.2.3 → upgini-1.2.5}/src/upgini/autofe/unary.py

@@ -12,10 +12,12 @@ class Abs(PandasOperand, VectorizableMixin):
     group_index: int = 0
 
     def calculate_unary(self, data: pd.Series) -> pd.Series:
-        return data.abs()
+        return data.astype(np.float64).abs()
+        # return data.abs()
 
     def calculate_group(self, data: pd.DataFrame, **kwargs) -> pd.DataFrame:
-        return data.abs()
+        return data.astype(np.float64).abs()
+        # return data.abs()
 
 
 class Log(PandasOperand, VectorizableMixin):

upgini-1.2.3/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.3"

upgini-1.2.3/src/upgini/__init__.py

@@ -1,11 +0,0 @@
-import os
-
-from .lazy_import import LazyImport
-
-os.environ["SETUPTOOLS_USE_DISTUTILS"] = "stdlib"
-
-FeaturesEnricher = LazyImport("upgini.features_enricher", "FeaturesEnricher")
-SearchKey = LazyImport("upgini.metadata", "SearchKey")
-RuntimeParameters = LazyImport("upgini.metadata", "RuntimeParameters")
-CVType = LazyImport("upgini.metadata", "CVType")
-ModelTaskType = LazyImport("upgini.metadata", "ModelTaskType")