imsciences 0.6.0.2__tar.gz → 0.6.0.3__tar.gz

{imsciences-0.6.0.2 → imsciences-0.6.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.6.0.2
+Version: 0.6.0.3
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.6.0.2 → imsciences-0.6.0.3}/imsciences/datafunctions.py

@@ -184,7 +184,12 @@ class dataprocessing:
         print("\n32. upgrade all packages")
         print("   - Description: Upgrades all packages.")
         print("   - Usage: upgrade_outdated_packages()")
-        print("   - Example: upgrade_outdated_packages()")       
+        print("   - Example: upgrade_outdated_packages()")
+        
+        print("\n33. Convert Mixed Formats Dates")
+        print("   - Description: Convert a mix of US and UK dates to datetime.")
+        print("   - Usage: convert_mixed_formats_dates(df, datecol)")
+        print("   - Example: convert_mixed_formats_dates(df, 'OBS')")     
     
     def get_wd_levels(self, levels):
         """
@@ -602,10 +607,6 @@ class dataprocessing:
         )
         return df
 
-        # Apply the fix to the specified column
-        df[date_col] = df[date_col].apply(lambda x: fix_date(x) if not pd.isnull(x) else x)
-        return df
-
     def combine_sheets(self, all_sheets):
         """
         Combines multiple DataFrames from a dictionary into a single DataFrame.
@@ -1229,6 +1230,37 @@ class dataprocessing:
         except Exception as e:
             print(f"An error occurred during the upgrade process: {e}")
 
+    def convert_mixed_formats_dates(self, df, column_name):
+        # Convert initial dates to datetime with coercion to handle errors
+        df[column_name] = pd.to_datetime(df[column_name], errors='coerce')
+        df[column_name] = df[column_name].astype(str)
+        corrected_dates = []
+        
+        for date_str in df[column_name]:
+            date_str = date_str.replace('-', '').replace('/', '')
+            if len(date_str) == 8:
+                year = date_str[:4]
+                month = date_str[4:6]
+                day = date_str[6:8]
+                if int(day) <= 12:
+                    # Swap month and day
+                    corrected_date_str = f"{year}-{day}-{month}"
+                else:
+                    corrected_date_str = f"{year}-{month}-{day}"
+                # Convert to datetime
+                corrected_date = pd.to_datetime(corrected_date_str, errors='coerce')
+            else:
+                corrected_date = pd.to_datetime(date_str, errors='coerce')
+            
+            corrected_dates.append(corrected_date)
+        
+        # Check length of the corrected_dates list
+        if len(corrected_dates) != len(df):
+            raise ValueError("Length of corrected_dates does not match the original DataFrame")
+        
+        # Assign the corrected dates back to the DataFrame
+        df[column_name] = corrected_dates
+        return df
 
 
 

{imsciences-0.6.0.2 → imsciences-0.6.0.3}/imsciences.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.6.0.2
+Version: 0.6.0.3
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.6.0.2 → imsciences-0.6.0.3}/setup.py

@@ -8,7 +8,7 @@ def read_md(file_name):
             return f.read()
     return ''
 
-VERSION = '0.6.0.2'
+VERSION = '0.6.0.3'
 DESCRIPTION = 'IMS Data Processing Package'
 LONG_DESCRIPTION = read_md('README.md')  # Reading from README.md