upgini 1.2.28__py3-none-any.whl → 1.2.29a1__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.28"
+__version__ = "1.2.29a1"

upgini/resource_bundle/strings.properties

@@ -82,7 +82,7 @@ unregistered_only_personal_keys=Only personal search keys used. Api_key from pro
 search_key_not_found=Column `{}` from search_keys was not found in X dataframe: {}
 numeric_search_key_not_found=Index {} in search_keys is out of bounds for {} columns of X dataframe
 unsupported_search_key_type=Unsupported type of key in search_keys: {}
-unsupported_type_of_search_key=Unsupported type of search key: {}. It should be a member of SearcKey
+unsupported_type_of_search_key=Unsupported type of search key: {}. It should be a member of SearchKey
 search_key_country_and_country_code=SearchKey.COUNTRY and country_code parameter were passed simultaniously. Parameter country_code will be ignored
 empty_search_key=Search key {} is empty. Please fill values or remove this search key
 single_constant_search_key=Constant value detected for the {} search key in the X dataframe: {}.\nThat search key will add constant features for different y values.\nPlease add extra search keys with non constant values, like the COUNTRY, POSTAL_CODE, DATE, PHONE NUMBER, EMAIL/HEM or IPv4

upgini/utils/datetime_utils.py

@@ -114,16 +114,50 @@ class DateTimeSearchKeyConverter:
         seconds_without_na = df[seconds].dropna()
         if (seconds_without_na != 0).any() and seconds_without_na.nunique() > 1:
             self.logger.info("Time found in date search key. Add extra features based on time")
-            seconds_in_day = 60 * 60 * 24
-            orders = [1, 2, 24, 48]
-            for order in orders:
-                sin_feature = f"datetime_time_sin_{order}"
-                cos_feature = f"datetime_time_cos_{order}"
-                df[sin_feature] = np.round(np.sin(2 * np.pi * order * df[seconds] / seconds_in_day), 10)
-                df[cos_feature] = np.round(np.cos(2 * np.pi * order * df[seconds] / seconds_in_day), 10)
+
+            # Extract time components
+            df["second"] = df[self.date_column].dt.second
+            df["minute"] = df[self.date_column].dt.minute
+            df["hour"] = df[self.date_column].dt.hour
+            df["day"] = df[self.date_column].dt.day
+            df["month"] = df[self.date_column].dt.month
+
+            # Get the actual number of days in each month
+            df["days_in_month"] = df[self.date_column].dt.days_in_month
+
+            # Define function to apply sine and cosine transformations
+            def add_cyclical_features(df, column, period):
+                sin_feature = f"datetime_{column}_sin_{period}"
+                cos_feature = f"datetime_{column}_cos_{period}"
+                df[sin_feature] = np.sin(2 * np.pi * df[column] / period)
+                df[cos_feature] = np.cos(2 * np.pi * df[column] / period)
                 self.generated_features.append(sin_feature)
                 self.generated_features.append(cos_feature)
 
+            # Apply transformations using vectorized operations
+            add_cyclical_features(df, "second", 60)  # Seconds in a minute
+            add_cyclical_features(df, "minute", 60)  # Minutes in an hour
+            add_cyclical_features(df, "hour", 24)  # Hours in a day
+            add_cyclical_features(df, "day", df["days_in_month"])  # Days in the specific month
+            add_cyclical_features(df, "month", 12)  # Months in a year
+
+            # Extract quarter information
+            df["quarter"] = df[self.date_column].dt.quarter
+
+            # Apply transformations for quarters
+            add_cyclical_features(df, "quarter", 4)  # Quarters in a year
+            # seconds_in_day = 60 * 60 * 24
+            # orders = [1, 2, 24, 48]
+            # for order in orders:
+            #     sin_feature = f"datetime_time_sin_{order}"
+            #     cos_feature = f"datetime_time_cos_{order}"
+            #     df[sin_feature] = np.round(np.sin(2 * np.pi * order * df[seconds] / seconds_in_day), 10)
+            #     df[cos_feature] = np.round(np.cos(2 * np.pi * order * df[seconds] / seconds_in_day), 10)
+            #     self.generated_features.append(sin_feature)
+            #     self.generated_features.append(cos_feature)
+
+            df.drop(columns=["second", "minute", "hour", "day", "month", "days_in_month", "quarter"])
+
         df.drop(columns=seconds, inplace=True)
 
         if keep_time:

{upgini-1.2.28.dist-info → upgini-1.2.29a1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.28
+Version: 1.2.29a1
 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-1.2.28.dist-info → upgini-1.2.29a1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=sZoYrdh97RjbwC1rg-3mt6kqvjxTxWL7ejhDDrG6mVM,23
+upgini/__about__.py,sha256=YYK80OZpX7RU3u94Dr87MhqDbFFuOvIk3V5if415BD8,25
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=iPFiMJtk4HF1ytw9wCQr8H9RfoOKj_TIo8XYZKWgcMc,31331
@@ -30,7 +30,7 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 upgini/normalizer/normalize_utils.py,sha256=Ft2MwSgVoBilXAORAOYAuwPD79GOLfwn4qQE3IUFzzg,7218
 upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=wn98wl2DNFPaGTMSdZAVr43P6t97i74PCqqwa762-V0,26673
+upgini/resource_bundle/strings.properties,sha256=fOAeLTsnx8xvJK-7RPFXprATG0n56jeCdse8sQTuVX8,26674
 upgini/resource_bundle/strings_widget.properties,sha256=gOdqvZWntP2LCza_tyVk1_yRYcG4c04K9sQOAVhF_gw,1577
 upgini/sampler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/sampler/base.py,sha256=7GpjYqjOp58vYcJLiX__1R5wjUlyQbxvHJ2klFnup_M,6389
@@ -43,7 +43,7 @@ upgini/utils/blocked_time_series.py,sha256=Uqr3vp4YqNclj2-PzEYqVy763GSXHn86sbpIl
 upgini/utils/country_utils.py,sha256=lY-eXWwFVegdVENFttbvLcgGDjFO17Sex8hd2PyJaRk,6937
 upgini/utils/custom_loss_utils.py,sha256=kieNZYBYZm5ZGBltF1F_jOSF4ea6C29rYuCyiDcqVNY,3857
 upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
-upgini/utils/datetime_utils.py,sha256=a8X4jX2y3-6E7ZNZIG5z61qfzCvsvaNEjR1Bi5KUqfM,11279
+upgini/utils/datetime_utils.py,sha256=Aw1e8e137PF_KMCUQrKPmnnukYjGJWvNGKSwXzsVLRs,13051
 upgini/utils/deduplicate_utils.py,sha256=SMZx9IKIhWI5HqXepfKiQb3uDJrogQZtG6jcWuMo5Z4,8855
 upgini/utils/display_utils.py,sha256=DsBjJ8jEYAh8BPgfAbzq5imoGFV6IACP20PQ78BQCX0,11964
 upgini/utils/email_utils.py,sha256=j0Ug1R_0AnCg1Y92zIZ4XMwvKo3G5_pcOlBN1OH_gZs,5191
@@ -58,7 +58,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=PU77nIhTz7IHbC4rpTpxrVxib6cdpRL9F1dhkjIffLY,10225
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.28.dist-info/METADATA,sha256=qGINKPrh43Q1LFXWRlS1v6CSpME6rOmScAy0ShKxL_0,48578
-upgini-1.2.28.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.28.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.28.dist-info/RECORD,,
+upgini-1.2.29a1.dist-info/METADATA,sha256=mVTEnNe3cUe5o_q3SoNHSydY6A8wv1LLMC2IpWkndMg,48580
+upgini-1.2.29a1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.29a1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.29a1.dist-info/RECORD,,