sibi-dst 2025.1.11__py3-none-any.whl → 2025.1.12__py3-none-any.whl

sibi_dst/utils/date_utils.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import datetime
 from typing import Union, Tuple, Callable, Dict, Optional
 
@@ -306,64 +308,62 @@ class FileAgeChecker:
 
 
 # --- Vectorized Helper Functions ---
-# These replace the slow, row-by-row .apply() logic. They operate
-# on entire DataFrame partitions for maximum efficiency.
-
-def _vectorized_busday_count(
-        partition: pd.DataFrame,
-        begin_col: str,
-        end_col: str,
-        holidays: list
-) -> pd.Series:
-    """Vectorized function to count business days on a DataFrame partition."""
-    if partition.empty:
-        return pd.Series([], dtype=float)
-
-    # Convert entire columns to datetime at once, coercing errors to NaT
-    start_dates = pd.to_datetime(partition[begin_col], errors='coerce').dt.date
-    end_dates = pd.to_datetime(partition[end_col], errors='coerce').dt.date
-
-    # Create a result series filled with NaN to handle rows with invalid dates
-    result = pd.Series(np.nan, index=partition.index, dtype=float)
-
-    # Create a boolean mask for valid, non-NaT date pairs
+
+def _vectorized_busday_count(partition, begin_col, end_col, holidays):
+    """
+    Calculates the number of business days between a start and end date.
+    """
+    # Extract the raw columns
+    start_dates_raw = partition[begin_col]
+    end_dates_raw = partition[end_col]
+
+
+    start_dates = pd.to_datetime(start_dates_raw, errors='coerce')
+    end_dates = pd.to_datetime(end_dates_raw, errors='coerce')
+
+    # Initialize the result Series with NaN, as the output is a number
+    result = pd.Series(np.nan, index=partition.index)
+
+    # Create a mask for rows where both start and end dates are valid
     valid_mask = pd.notna(start_dates) & pd.notna(end_dates)
 
-    # Perform the vectorized calculation only on the valid subset of dates
+    # Perform the vectorized calculation only on the valid subset
+    # Convert to NumPy arrays of date type for the calculation
     result.loc[valid_mask] = np.busday_count(
-        start_dates[valid_mask],
-        end_dates[valid_mask],
+        start_dates[valid_mask].values.astype('datetime64[D]'),
+        end_dates[valid_mask].values.astype('datetime64[D]'),
         holidays=holidays
     )
-    return result
 
+    return result
 
-def _vectorized_sla_end_date(
-        partition: pd.DataFrame,
-        start_col: str,
-        n_days_col: str,
-        holidays: list
-) -> pd.Series:
-    """Vectorized function to calculate the SLA end date on a DataFrame partition."""
-    if partition.empty:
-        return pd.Series([], dtype='datetime64[ns]')
 
-    start_dates = pd.to_datetime(partition[start_col], errors='coerce').dt.date
+def _vectorized_sla_end_date(partition, start_col, n_days_col, holidays):
+    """
+    Calculates the end date of an SLA, skipping weekends and holidays.
+    """
+    # Extract the relevant columns as pandas Series
+    start_dates_raw = partition[start_col]
     sla_days = partition[n_days_col]
 
-    # Create a result series filled with NaT for rows with invalid start dates
+
+    start_dates = pd.to_datetime(start_dates_raw, errors='coerce')
+
+    # Initialize the result Series with NaT (Not a Time)
     result = pd.Series(pd.NaT, index=partition.index, dtype='datetime64[ns]')
 
-    # Create a boolean mask for valid start dates and sla_days
+    # Create a mask for rows that have valid start dates and SLA days
     valid_mask = pd.notna(start_dates) & pd.notna(sla_days)
 
     # Perform the vectorized calculation only on the valid subset
+    # Note: np.busday_offset requires a NumPy array, so we use .values
     result.loc[valid_mask] = np.busday_offset(
-        start_dates[valid_mask],
+        start_dates[valid_mask].values.astype('datetime64[D]'),  # Convert to numpy array of dates
         sla_days[valid_mask].astype(int),  # Ensure days are integers
         roll='forward',
         holidays=holidays
     )
+
     return result
 
 
@@ -452,6 +452,7 @@ class BusinessDays:
                 meta=(result_col, 'datetime64[ns]')
             )}
         )
+
 # Class enhancements
 # DateUtils.register_period('next_week', lambda: (datetime.date.today() + datetime.timedelta(days=7),
 #                                                 datetime.date.today() + datetime.timedelta(days=13)))

{sibi_dst-2025.1.11.dist-info → sibi_dst-2025.1.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sibi-dst
-Version: 2025.1.11
+Version: 2025.1.12
 Summary: Data Science Toolkit
 Author: Luis Valverde
 Author-email: lvalverdeb@gmail.com

{sibi_dst-2025.1.11.dist-info → sibi_dst-2025.1.12.dist-info}/RECORD

@@ -39,7 +39,7 @@ sibi_dst/utils/credentials.py,sha256=cHJPPsmVyijqbUQIq7WWPe-lIallA-mI5RAy3YUuRME
 sibi_dst/utils/data_from_http_source.py,sha256=AcpKNsqTgN2ClNwuhgUpuNCx62r5_DdsAiKY8vcHEBA,1867
 sibi_dst/utils/data_utils.py,sha256=MqbwXk33BuANWeKKmsabHouhb8GZswSmbM-VetWWE-M,10357
 sibi_dst/utils/data_wrapper.py,sha256=9aYXorbrqDX53NVJ5oUnNQy6FbXYhs5osxzeMcdZpC4,9609
-sibi_dst/utils/date_utils.py,sha256=T0uXNIG2IQfgs0AyQNsF9S6-cTujtA4GDC1IalvZVSU,18040
+sibi_dst/utils/date_utils.py,sha256=fV2X9HZND92CV-sRvOOGMs6Iv82gaLURQ8M78xAWfTY,17996
 sibi_dst/utils/df_utils.py,sha256=TzIAUCLbgOn3bvCFvzkc1S9YU-OlZTImdCj-88dtg8g,11401
 sibi_dst/utils/file_utils.py,sha256=Z99CZ_4nPDIaZqbCfzzUDfAYJjSudWDj-mwEO8grhbc,1253
 sibi_dst/utils/filepath_generator.py,sha256=-HHO0U-PR8fysDDFwnWdHRlgqksh_RkmgBZLWv9hM7s,6669
@@ -71,6 +71,6 @@ sibi_dst/v2/df_helper/core/_params_config.py,sha256=DYx2drDz3uF-lSPzizPkchhy-kxR
 sibi_dst/v2/df_helper/core/_query_config.py,sha256=Y8LVSyaKuVkrPluRDkQoOwuXHQxner1pFWG3HPfnDHM,441
 sibi_dst/v2/utils/__init__.py,sha256=6H4cvhqTiFufnFPETBF0f8beVVMpfJfvUs6Ne0TQZNY,58
 sibi_dst/v2/utils/log_utils.py,sha256=rfk5VsLAt-FKpv6aPTC1FToIPiyrnHAFFBAkHme24po,4123
-sibi_dst-2025.1.11.dist-info/METADATA,sha256=7iwn7RFfaDF_9dfpWvnNl2Al_8NHWu7l8vGhzO9BAac,2611
-sibi_dst-2025.1.11.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-sibi_dst-2025.1.11.dist-info/RECORD,,
+sibi_dst-2025.1.12.dist-info/METADATA,sha256=dkWXdBL5nk_gpqEqwfg8UCKCtsKw1eqLKIn4v0BtDy8,2611
+sibi_dst-2025.1.12.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+sibi_dst-2025.1.12.dist-info/RECORD,,