upgini 1.2.29a1__py3-none-any.whl → 1.2.29a3__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.29a1"
+__version__ = "1.2.29a3"

upgini/utils/datetime_utils.py

@@ -109,54 +109,60 @@ class DateTimeSearchKeyConverter:
 
         df = self.clean_old_dates(df)
 
+        # Define function to apply sine and cosine transformations
+        def add_cyclical_features(df, column, period):
+            period_suffix = f"_{period}" if column != 'day_in_quarter' else ""
+            sin_feature = f"datetime_{column}_sin{period_suffix}"
+            cos_feature = f"datetime_{column}_cos{period_suffix}"
+            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)
+
+        df["quarter"] = df[self.date_column].dt.quarter
+
+        # Calculate the start date of the quarter for each timestamp
+        df["quarter_start"] = df[self.date_column].dt.to_period("Q").dt.start_time
+
+        # Calculate the day in the quarter
+        df["day_in_quarter"] = (df[self.date_column] - df["quarter_start"]).dt.days + 1
+
+        # Vectorized calculation of days_in_quarter
+        quarter = df["quarter"]
+        start = df["quarter_start"]
+        year = start.dt.year
+        month = start.dt.month
+
+        quarter_end_year = np.where(quarter == 4, year + 1, year)
+        quarter_end_month = np.where(quarter == 4, 1, month + 3)
+
+        end = pd.to_datetime({"year": quarter_end_year, "month": quarter_end_month, "day": 1})
+
+        df["days_in_quarter"] = (end - start).dt.days
+
+        add_cyclical_features(df, "day_in_quarter", df["days_in_quarter"])  # Days in the quarter
+
+        df.drop(columns=["quarter", "quarter_start", "day_in_quarter", "days_in_quarter"], inplace=True)
+
         df[seconds] = (df[self.date_column] - df[self.date_column].dt.floor("D")).dt.seconds
 
         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")
 
-            # Extract time components
+            # Extract basic 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
+
+            # Apply cyclical transformations
             add_cyclical_features(df, "second", 60)  # Seconds in a minute
             add_cyclical_features(df, "minute", 60)  # Minutes in an hour
+            add_cyclical_features(df, "minute", 30)  # Minutes in half 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"])
+
+            # Drop intermediate columns if not needed
+            df.drop(columns=["second", "minute", "hour"], inplace=True)
 
         df.drop(columns=seconds, inplace=True)
 

{upgini-1.2.29a1.dist-info → upgini-1.2.29a3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.29a1
+Version: 1.2.29a3
 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-1.2.29a1.dist-info → upgini-1.2.29a3.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=YYK80OZpX7RU3u94Dr87MhqDbFFuOvIk3V5if415BD8,25
+upgini/__about__.py,sha256=g5pIOn0QIK7AYvLSK8cOcem2I_ZfKqz9pqOf071XTPQ,25
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=iPFiMJtk4HF1ytw9wCQr8H9RfoOKj_TIo8XYZKWgcMc,31331
@@ -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=Aw1e8e137PF_KMCUQrKPmnnukYjGJWvNGKSwXzsVLRs,13051
+upgini/utils/datetime_utils.py,sha256=GiJhOXE4taDtC0PEBYloSN7jeLwN26AchOQnMSTUDpc,12996
 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-1.2.29a1.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,,
+upgini-1.2.29a3.dist-info/METADATA,sha256=Ek9umOS0JA_zCCYMq7PWIcokbDM59DB0lbwQappDk1g,48580
+upgini-1.2.29a3.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.29a3.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.29a3.dist-info/RECORD,,