imsciences 0.9.6.6__py3-none-any.whl → 0.9.6.8__py3-none-any.whl

imsciences/pull.py

@@ -13,6 +13,8 @@ import holidays
 from dateutil.easter import easter
 import urllib.request
 from geopy.geocoders import Nominatim
+import importlib
+import workalendar
 
 from imsciences.mmm import dataprocessing
 
@@ -379,7 +381,7 @@ class datapull:
         
     ###############################################################  Seasonality  ##########################################################################
 
-    def pull_seasonality(self, week_commencing, start_date, countries):
+    def pull_seasonality(week_commencing, start_date, countries):
             """
             Generates a DataFrame with weekly seasonality features.
 
@@ -388,7 +390,7 @@ class datapull:
                 start_date (str): The start date in 'YYYY-MM-DD' format.
                 countries (list): A list of country codes (e.g., ['GB', 'US']) for holidays.
 
-            Returns:
+             Returns:
                 pd.DataFrame: A DataFrame indexed by week start date, containing various
                             seasonal dummy variables, holidays, trend, and constant.
                             The date column is named 'OBS'.
@@ -399,6 +401,343 @@ class datapull:
             day_dict = {"mon": 0, "tue": 1, "wed": 2, "thu": 3, "fri": 4, "sat": 5, "sun": 6}
             if week_commencing not in day_dict:
                 raise ValueError(f"Invalid week_commencing value: {week_commencing}. Use one of {list(day_dict.keys())}")
+            
+            # ---------------------------------------------------------------------
+            # 0.2 Setup: dictionary continents and countries
+            # ---------------------------------------------------------------------
+            COUNTRY_TO_CONTINENT = {
+            #Europe
+                "Austria": "europe",
+                "Belarus": "europe",
+                "Belgium": "europe",
+                "Bulgaria": "europe",
+                "Croatia": "europe",
+                "Cyprus": "europe",
+                "Czechia": "europe",
+                "CzechRepublic": "europe",
+                "Denmark": "europe",
+                "Estonia": "europe",
+                "EuropeanCentralBank": "europe",
+                "Finland": "europe",
+                "France": "europe",
+                "FranceAlsaceMoselle": "europe",
+                "Germany": "europe",
+                "GermanyBaden": "europe",
+                "GermanyBavaria": "europe",
+                "GermanyBerlin": "europe",
+                "GermanyBrandenburg": "europe",
+                "GermanyBremen": "europe",
+                "GermanyHamburg": "europe",
+                "GermanyHesse": "europe",
+                "GermanyLowerSaxony": "europe",
+                "GermanyMecklenburgVorpommern": "europe",
+                "GermanyNorthRhineWestphalia": "europe",
+                "GermanyRhinelandPalatinate": "europe",
+                "GermanySaarland": "europe",
+                "GermanySaxony": "europe",
+                "GermanySaxonyAnhalt": "europe",
+                "GermanySchleswigHolstein": "europe",
+                "GermanyThuringia": "europe",
+                "Greece": "europe",
+                "Hungary": "europe",
+                "Iceland": "europe",
+                "Ireland": "europe",
+                "Italy": "europe",
+                "Latvia": "europe",
+                "Lithuania": "europe",
+                "Luxembourg": "europe",
+                "Malta": "europe",
+                "Monaco": "europe",
+                "Netherlands": "europe",
+                "Norway": "europe",
+                "Poland": "europe",
+                "Portugal": "europe",
+                "Romania": "europe",
+                "Russia": "europe",
+                "Serbia": "europe",
+                "Slovakia": "europe",
+                "Slovenia": "europe",
+                "Spain": "europe",
+                "SpainAndalusia": "europe",
+                "SpainAragon": "europe",
+                "SpainAsturias": "europe",
+                "SpainBalearicIslands": "europe",
+                "SpainBasqueCountry": "europe",
+                "SpainCanaryIslands": "europe",
+                "SpainCantabria": "europe",
+                "SpainCastileAndLeon": "europe",
+                "SpainCastillaLaMancha": "europe",
+                "SpainCatalonia": "europe",
+                "SpainExtremadura": "europe",
+                "SpainGalicia": "europe",
+                "SpainLaRioja": "europe",
+                "SpainMadrid": "europe",
+                "SpainMurcia": "europe",
+                "SpainNavarre": "europe",
+                "SpainValencia": "europe",
+                "Sweden": "europe",
+                "Switzerland": "europe",
+                "Ukraine": "europe",
+                "UnitedKingdom": "europe",
+
+            # Americas
+                "Argentina": "america",
+                "Barbados": "america",
+                "Brazil": "america",
+                "Canada": "america",
+                "Chile": "america",
+                "Colombia": "america",
+                "Mexico": "america",
+                "Panama": "america",
+                "Paraguay": "america",
+                "Peru": "america",
+                "UnitedStates": "usa",
+
+            #US States
+                "Alabama": "usa.states",
+                "Alaska": "usa.states",
+                "Arizona": "usa.states",
+                "Arkansas": "usa.states",
+                "California": "usa.states",
+                "Colorado": "usa.states",
+                "Connecticut": "usa.states",
+                "Delaware": "usa.states",
+                "DistrictOfColumbia": "usa.states",
+                "Florida": "usa.states",
+                "Georgia": "usa.states",
+                "Hawaii": "usa.states",
+                "Idaho": "usa.states",
+                "Illinois": "usa.states",
+                "Indiana": "usa.states",
+                "Iowa": "usa.states",
+                "Kansas": "usa.states",
+                "Kentucky": "usa.states",
+                "Louisiana": "usa.states",
+                "Maine": "usa.states",
+                "Maryland": "usa.states",
+                "Massachusetts": "usa.states",
+                "Michigan": "usa.states",
+                "Minnesota": "usa.states",
+                "Mississippi": "usa.states",
+                "Missouri": "usa.states",
+                "Montana": "usa.states",
+                "Nebraska": "usa.states",
+                "Nevada": "usa.states",
+                "NewHampshire": "usa.states",
+                "NewJersey": "usa.states",
+                "NewMexico": "usa.states",
+                "NewYork": "usa.states",
+                "NorthCarolina": "usa.states",
+                "NorthDakota": "usa.states",
+                "Ohio": "usa.states",
+                "Oklahoma": "usa.states",
+                "Oregon": "usa.states",
+                "Pennsylvania": "usa.states",
+                "RhodeIsland": "usa.states",
+                "SouthCarolina": "usa.states",
+                "SouthDakota": "usa.states",
+                "Tennessee": "usa.states",
+                "Texas": "usa.states",
+                "Utah": "usa.states",
+                "Vermont": "usa.states",
+                "Virginia": "usa.states",
+                "Washington": "usa.states",
+                "WestVirginia": "usa.states",
+                "Wisconsin": "usa.states",
+                "Wyoming": "usa.states",
+
+            #Oceania
+                "Australia": "oceania",
+                "AustraliaCapitalTerritory": "oceania",
+                "AustraliaNewSouthWales": "oceania",
+                "AustraliaNorthernTerritory": "oceania",
+                "AustraliaQueensland": "oceania",
+                "AustraliaSouthAustralia": "oceania",
+                "AustraliaTasmania": "oceania",
+                "AustraliaVictoria": "oceania",
+                "AustraliaWesternAustralia": "oceania",
+                "MarshallIslands": "oceania",
+                "NewZealand": "oceania",
+
+            #Asia
+                "China": "asia",
+                "HongKong": "asia",
+                "India": "asia",
+                "Israel": "asia",
+                "Japan": "asia",
+                "Kazakhstan": "asia",
+                "Malaysia": "asia",
+                "Qatar": "asia",
+                "Singapore": "asia",
+                "SouthKorea": "asia",
+                "Taiwan": "asia",
+                "Turkey": "asia",
+                "Vietnam": "asia",
+
+            #Africa
+                "Algeria": "africa",
+                "Angola": "africa",
+                "Benin": "africa",
+                "IvoryCoast": "africa",
+                "Kenya": "africa",
+                "Madagascar": "africa",
+                "Nigeria": "africa",
+                "SaoTomeAndPrincipe": "africa",
+                "SouthAfrica": "africa",
+            }
+
+            # Dictionary mapping ISO country codes to their corresponding workalendar country names
+            holiday_country = {
+                # Major countries with required formats
+                "GB": "UnitedKingdom",
+                "US": "UnitedStates",
+                "USA": "UnitedStates",     # Alternative code for US
+                "CA": "Canada",
+                "ZA": "SouthAfrica",
+                "FR": "France",
+                "DE": "Germany",
+                "AU": "Australia",
+                "AUS": "Australia",        # Alternative code for Australia
+                
+                # European countries
+                "AT": "Austria",
+                "BY": "Belarus",
+                "BE": "Belgium",
+                "BG": "Bulgaria",
+                "HR": "Croatia",
+                "CY": "Cyprus",
+                "CZ": "Czechia",
+                "DK": "Denmark",
+                "EE": "Estonia",
+                "FI": "Finland",
+                "GR": "Greece",
+                "HU": "Hungary",
+                "IS": "Iceland",
+                "IE": "Ireland",
+                "IT": "Italy",
+                "LV": "Latvia",
+                "LT": "Lithuania",
+                "LU": "Luxembourg",
+                "MT": "Malta",
+                "MC": "Monaco",
+                "NL": "Netherlands",
+                "NO": "Norway",
+                "PL": "Poland",
+                "PT": "Portugal",
+                "RO": "Romania",
+                "RU": "Russia",
+                "RS": "Serbia",
+                "SK": "Slovakia",
+                "SI": "Slovenia",
+                "ES": "Spain",
+                "SE": "Sweden",
+                "CH": "Switzerland",
+                "UA": "Ukraine",
+                
+                # Americas
+                "AR": "Argentina",
+                "BB": "Barbados",
+                "BR": "Brazil",
+                "CL": "Chile",
+                "CO": "Colombia",
+                "MX": "Mexico",
+                "PA": "Panama",
+                "PY": "Paraguay",
+                "PE": "Peru",
+                
+                # USA States (using common abbreviations)
+                "AL": "Alabama",
+                "AK": "Alaska",
+                "AZ": "Arizona",
+                "AR": "Arkansas",
+                "CA_US": "California", 
+                "CO_US": "Colorado",   
+                "CT": "Connecticut",
+                "DE_US": "Delaware",    
+                "DC": "DistrictOfColumbia",
+                "FL": "Florida",
+                "GA": "Georgia",
+                "HI": "Hawaii",
+                "ID": "Idaho",
+                "IL": "Illinois",
+                "IN": "Indiana",
+                "IA": "Iowa",
+                "KS": "Kansas",
+                "KY": "Kentucky",
+                "LA": "Louisiana",
+                "ME": "Maine",
+                "MD": "Maryland",
+                "MA": "Massachusetts",
+                "MI": "Michigan",
+                "MN": "Minnesota",
+                "MS": "Mississippi",
+                "MO": "Missouri",
+                "MT": "Montana",
+                "NE": "Nebraska",
+                "NV": "Nevada",
+                "NH": "NewHampshire",
+                "NJ": "NewJersey",
+                "NM": "NewMexico",
+                "NY": "NewYork",
+                "NC": "NorthCarolina",
+                "ND": "NorthDakota",
+                "OH": "Ohio",
+                "OK": "Oklahoma",
+                "OR": "Oregon",
+                "PA_US": "Pennsylvania", 
+                "RI": "RhodeIsland",
+                "SC": "SouthCarolina",
+                "SD": "SouthDakota",
+                "TN": "Tennessee",
+                "TX": "Texas",
+                "UT": "Utah",
+                "VT": "Vermont",
+                "VA": "Virginia",
+                "WA": "Washington",
+                "WV": "WestVirginia",
+                "WI": "Wisconsin",
+                "WY": "Wyoming",
+                
+                # Australia territories
+                "ACT": "AustraliaCapitalTerritory",
+                "NSW": "AustraliaNewSouthWales",
+                "NT": "AustraliaNorthernTerritory",
+                "QLD": "AustraliaQueensland",
+                "SA": "AustraliaSouthAustralia",
+                "TAS": "AustraliaTasmania",
+                "VIC": "AustraliaVictoria",
+                "WA_AU": "AustraliaWesternAustralia", 
+                
+                # Asian countries
+                "CN": "China",
+                "HK": "HongKong",
+                "IN": "India",
+                "IL": "Israel",
+                "JP": "Japan",
+                "KZ": "Kazakhstan",
+                "MY": "Malaysia",
+                "QA": "Qatar",
+                "SG": "Singapore",
+                "KR": "SouthKorea",
+                "TW": "Taiwan",
+                "TR": "Turkey",
+                "VN": "Vietnam",
+                
+                # Other Oceania countries
+                "MH": "MarshallIslands",
+                "NZ": "NewZealand",
+                
+                # African countries
+                "DZ": "Algeria",
+                "AO": "Angola",
+                "BJ": "Benin",
+                "CI": "IvoryCoast",
+                "KE": "Kenya",
+                "MG": "Madagascar",
+                "NG": "Nigeria",
+                "ST": "SaoTomeAndPrincipe"
+            }
+
 
             # ---------------------------------------------------------------------
             # 1. Create daily date range from start_date to today
@@ -452,44 +791,136 @@ class datapull:
             df_dummies = pd.DataFrame(dummy_columns, index=df_weekly_start.index)
             df_weekly_start = pd.concat([df_weekly_start, df_dummies], axis=1)
 
+
             # ---------------------------------------------------------------------
-            # 3. Public holidays (daily) from 'holidays' package + each holiday name
+            # 3. Public holidays (daily) using WorkCalendar 
             # ---------------------------------------------------------------------
             start_year = start_dt.year
             end_year = end_dt.year
             years_range = range(start_year, end_year + 1)
-
-            for country in countries:
+            
+            # Dictionary to store holiday dummies for each country
+            country_holiday_dummies = {}
+            
+            for country_code in countries:
+                # Skip if country code not found in holiday_country dictionary
+                if country_code not in holiday_country:
+                    print(f"Warning: Country code '{country_code}' not found in country code dictionary. Skipping.")
+                    continue
+                    
+                country = holiday_country[country_code]
+                
+                # Skip if country not found in continent lookup dictionary
+                if country not in COUNTRY_TO_CONTINENT:
+                    print(f"Warning: Country '{country}' not found in continent lookup dictionary. Skipping.")
+                    continue
+                    
+                continent = COUNTRY_TO_CONTINENT[country]
+                module_path = f'workalendar.{continent}' 
                 try:
-                    country_holidays = holidays.CountryHoliday(
-                        country,
-                        years=years_range,
-                        observed=False # Typically you want the actual date, not observed substitute
-                    )
-                    # Handle cases like UK where specific subdivisions might be needed for some holidays
-                    # Example: if country == 'GB': country_holidays.observed = True # If observed are needed
-                except KeyError:
-                    print(f"Warning: Country code '{country}' not found in holidays library. Skipping.")
-                    continue # Skip to next country
-
-                # Daily indicator: 1 if that date is a holiday
-                df_daily[f"seas_holiday_{country.lower()}"] = df_daily["Date"].apply(
-                    lambda x: 1 if x in country_holidays else 0
-                )
-                # Create columns for specific holiday names
-                for date_hol, name in sorted(country_holidays.items()): # Sort for consistent column order
-                    # Clean name: lower, replace space with underscore, remove non-alphanumeric (except underscore)
-                    clean_name = ''.join(c for c in name if c.isalnum() or c == ' ').strip().replace(' ', '_').lower()
-                    clean_name = clean_name.replace('_(observed)', '').replace("'", "") # specific cleaning
-                    col_name = f"seas_{clean_name}_{country.lower()}"
-
-                    # Only create column if the holiday occurs within the df_daily date range
-                    if pd.Timestamp(date_hol).year in years_range:
-                        if col_name not in df_daily.columns:
-                            df_daily[col_name] = 0
-                        # Ensure date_hol is within the actual daily range before assigning
-                        if (pd.Timestamp(date_hol) >= df_daily["Date"].min()) and (pd.Timestamp(date_hol) <= df_daily["Date"].max()):
-                            df_daily.loc[df_daily["Date"] == pd.Timestamp(date_hol), col_name] = 1
+                    module = importlib.import_module(module_path)
+                    calendar_class = getattr(module, country)
+                    cal = calendar_class()
+                except (ImportError, AttributeError) as e:
+                    print(f"Error importing calendar for {country}: {e}. Skipping.")
+                    continue
+                    
+                # Collect holidays
+                holidays_list = []
+                for year in years_range:
+                    holidays_list.extend(cal.holidays(year))
+                    
+                holidays_df = pd.DataFrame(holidays_list, columns=['Date', 'Holiday'])
+                holidays_df['Date'] = pd.to_datetime(holidays_df['Date'])
+                
+                # Filter out any holidays with "shift" or "substitute" in their name
+                holidays_df = holidays_df[~(holidays_df['Holiday'].str.lower().str.contains('shift') | 
+                                            holidays_df['Holiday'].str.lower().str.contains('substitute'))]
+                
+                # Filter by date range
+                holidays_df = holidays_df[(holidays_df['Date'] >= start_dt) & (holidays_df['Date'] <= end_dt)]
+            # ---------------------------------------------------------------------
+            # 3.1 Additional Public Holidays for Canada due to poor API data 
+            # ---------------------------------------------------------------------
+                if country_code == 'CA':
+                    # Add Canada Day (July 1st) if not already in the list
+                    for year in years_range:
+                        canada_day = pd.Timestamp(f"{year}-07-01")
+                        if canada_day >= start_dt and canada_day <= end_dt:
+                            if not ((holidays_df['Date'] == canada_day) & 
+                                    (holidays_df['Holiday'].str.lower().str.contains('canada day'))).any():
+                                holidays_df = pd.concat([holidays_df, 
+                                                        pd.DataFrame({'Date': [canada_day], 
+                                                                        'Holiday': ['Canada Day']})], 
+                                                        ignore_index=True)
+                    
+                    # Add Labour Day (first Monday in September)
+                    for year in years_range:
+                        # Get first day of September
+                        first_day = pd.Timestamp(f"{year}-09-01")
+                        # Calculate days until first Monday (Monday is weekday 0)
+                        days_until_monday = (7 - first_day.weekday()) % 7
+                        if days_until_monday == 0:  # If first day is already Monday
+                            labour_day = first_day
+                        else:
+                            labour_day = first_day + pd.Timedelta(days=days_until_monday)
+                        
+                        if labour_day >= start_dt and labour_day <= end_dt:
+                            if not ((holidays_df['Date'] == labour_day) & 
+                                    (holidays_df['Holiday'].str.lower().str.contains('labour day'))).any():
+                                holidays_df = pd.concat([holidays_df, 
+                                                        pd.DataFrame({'Date': [labour_day], 
+                                                                        'Holiday': ['Labour Day']})], 
+                                                        ignore_index=True)
+                    
+                    # Add Thanksgiving (second Monday in October)
+                    for year in years_range:
+                        # Get first day of October
+                        first_day = pd.Timestamp(f"{year}-10-01")
+                        # Calculate days until first Monday
+                        days_until_monday = (7 - first_day.weekday()) % 7
+                        if days_until_monday == 0:  # If first day is already Monday
+                            first_monday = first_day
+                        else:
+                            first_monday = first_day + pd.Timedelta(days=days_until_monday)
+                        
+                        # Second Monday is 7 days after first Monday
+                        thanksgiving = first_monday + pd.Timedelta(days=7)
+                        
+                        if thanksgiving >= start_dt and thanksgiving <= end_dt:
+                            if not ((holidays_df['Date'] == thanksgiving) & 
+                                    (holidays_df['Holiday'].str.lower().str.contains('thanksgiving'))).any():
+                                holidays_df = pd.concat([holidays_df, 
+                                                        pd.DataFrame({'Date': [thanksgiving], 
+                                                                        'Holiday': ['Thanksgiving']})], 
+                                                        ignore_index=True)
+                
+                # Now process the collected holidays and add to df_daily
+                for _, row in holidays_df.iterrows():
+                    holiday_date = row['Date']
+                    # Create column name without modifying original holiday names
+                    holiday_name = row['Holiday'].lower().replace(' ', '_')
+                    
+                    # Remove "_shift" or "_substitute" if they appear as standalone suffixes
+                    if holiday_name.endswith('_shift'):
+                        holiday_name = holiday_name[:-6]
+                    elif holiday_name.endswith('_substitute'):
+                        holiday_name = holiday_name[:-11]
+                    
+                    column_name = f"seas_{holiday_name}_{country_code.lower()}"
+                    
+                    if column_name not in df_daily.columns:
+                        df_daily[column_name] = 0
+                    
+                    # Mark the specific holiday date
+                    df_daily.loc[df_daily["Date"] == holiday_date, column_name] = 1
+                    
+                    # Also mark a general holiday indicator for each country
+                    holiday_indicator = f"seas_holiday_{country_code.lower()}"
+                    if holiday_indicator not in df_daily.columns:
+                        df_daily[holiday_indicator] = 0
+                    df_daily.loc[df_daily["Date"] == holiday_date, holiday_indicator] = 1
+
 
             # ---------------------------------------------------------------------
             # 3.1 Additional Special Days (Father's Day, Mother's Day, etc.)
@@ -597,7 +1028,7 @@ class datapull:
 
 
             # ---------------------------------------------------------------------
-            # 4. Add daily indicators for last day & last Friday of month
+            # 4. Add daily indicators for last day & last Friday of month & payday
             # ---------------------------------------------------------------------
             df_daily["is_last_day_of_month"] = df_daily["Date"].dt.is_month_end
 
@@ -608,22 +1039,27 @@ class datapull:
                 # Check if next Friday is in the next month
                 next_friday = date + timedelta(days=7)
                 return 1 if next_friday.month != date.month else 0
+            
+            def is_payday(date):
+                return 1 if date.day >= 25 else 0
 
             df_daily["is_last_friday_of_month"] = df_daily["Date"].apply(is_last_friday)
-
+            
+            df_daily["is_payday"] = df_daily["Date"].apply(is_payday)
+            
             # Rename for clarity prefix
             df_daily.rename(columns={
                 "is_last_day_of_month": "seas_last_day_of_month",
-                "is_last_friday_of_month": "seas_last_friday_of_month"
+                "is_last_friday_of_month": "seas_last_friday_of_month",
+                "is_payday": "seas_payday"
             }, inplace=True)
 
-
             # ---------------------------------------------------------------------
             # 5. Weekly aggregation
             # ---------------------------------------------------------------------
 
             # Select only columns that are indicators/flags (intended for max aggregation)
-            flag_cols = [col for col in df_daily.columns if col.startswith('seas_') or col.startswith('is_')]
+            flag_cols = [col for col in df_daily.columns if (col.startswith('seas_') or col.startswith('is_')) and col != "seas_payday"]
             # Ensure 'week_start' is present for grouping
             df_to_agg = df_daily[['week_start'] + flag_cols]
 
@@ -635,7 +1071,26 @@ class datapull:
                 .rename(columns={'week_start': "Date"})
                 .set_index("Date")
             )
+            
+            # Do specific aggregation for payday
+            # Make sure 'date' column exists in df_daily
+            df_daily["month"] = df_daily["Date"].dt.month
+            df_daily["year"] = df_daily["Date"].dt.year
+            
+            # Sum of seas_payday flags per week
+            week_payday_sum = df_daily.groupby("week_start")["seas_payday"].sum()
+
+            # Divide the number of payday flags by number of paydays per month
+            payday_days_in_month = (
+                df_daily.groupby(["year", "month"])["seas_payday"].sum()
+            )
+            week_month = df_daily.groupby("week_start").first()[["month", "year"]]
+            week_days_in_month = week_month.apply(lambda row: payday_days_in_month.loc[(row["year"], row["month"])], axis=1)
+            df_weekly_flags["seas_payday"] = (week_payday_sum / week_days_in_month).fillna(0).values
 
+            # # Drop intermediate columns
+            # df_weekly_flags = df_weekly_flags.drop(columns=["month", "year"])
+            
             # --- Aggregate Week Number using MODE ---
             # Define aggregation function for mode (handling potential multi-modal cases by taking the first)
             def get_mode(x):
@@ -678,7 +1133,6 @@ class datapull:
             df_weekly_monthly_dummies.rename(columns={'week_start': 'Date'}, inplace=True)
             df_weekly_monthly_dummies.set_index('Date', inplace=True)
 
-
             # ---------------------------------------------------------------------
             # 6. Combine all weekly components
             # ---------------------------------------------------------------------
@@ -697,15 +1151,15 @@ class datapull:
 
             # Ensure correct types for flag columns (int)
             for col in df_weekly_flags.columns:
-                if col in df_combined.columns:
-                    df_combined[col] = df_combined[col].astype(int)
+                if col != 'seas_payday':
+                    if col in df_combined.columns:
+                        df_combined[col] = df_combined[col].astype(int)
 
             # Ensure correct types for month columns (float)
             for col in df_weekly_monthly_dummies.columns:
                 if col in df_combined.columns:
                     df_combined[col] = df_combined[col].astype(float)
 
-
             # ---------------------------------------------------------------------
             # 7. Create weekly dummies for Week of Year & yearly dummies from aggregated cols
             # ---------------------------------------------------------------------
@@ -737,7 +1191,7 @@ class datapull:
             # Filter out columns not in the desired order list (handles case where dum_ cols are off)
             final_cols = [col for col in cols_order if col in df_combined.columns]
             df_combined = df_combined[final_cols]
-
+            
             return df_combined
     
     def pull_weather(self, week_commencing, start_date, country_codes) -> pd.DataFrame:

{imsciences-0.9.6.6.dist-info → imsciences-0.9.6.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.9.6.6
+Version: 0.9.6.8
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.9.6.6.dist-info → imsciences-0.9.6.8.dist-info}/RECORD

@@ -1,12 +1,12 @@
 imsciences/__init__.py,sha256=_HuYeLbDMTdt7GpKI4r6-d7yRPZgcAQ7yOW0-ydR2Yo,117
 imsciences/geo.py,sha256=eenng7_BP_E2WD5Wt1G_oNxQS8W3t6lycRwJ91ngysY,15808
 imsciences/mmm.py,sha256=qMh0ccOepehfCcux7EeG8cq6piSEoFEz5iiJbDBWOS4,82214
-imsciences/pull.py,sha256=4NGKzNmsvfzADMucR8iLGTkYDyb5wdnqphe1CzepyWw,94992
+imsciences/pull.py,sha256=rHC4__gvfpcgAjgELABYvZrGyb1Ucg0qOW7724qiNns,114816
 imsciences/unittesting.py,sha256=U177_Txg0Lqn49zYRu5bl9OVe_X7MkNJ6V_Zd6DHOsU,45656
 imsciences/vis.py,sha256=2izdHQhmWEReerRqIxhY4Ai10VjL7xoUqyWyZC7-2XI,8931
-imsciences-0.9.6.6.dist-info/LICENSE.txt,sha256=lVq2QwcExPX4Kl2DHeEkRrikuItcDB1Pr7yF7FQ8_z8,1108
-imsciences-0.9.6.6.dist-info/METADATA,sha256=VO2fDn0xBsVhkPf42oeGOD5TEyC3uo1rHdylOmdaMu8,18846
-imsciences-0.9.6.6.dist-info/PKG-INFO-TomG-HP-290722,sha256=RMcthCSyWmU6IBsXGL-nYqw0RP06pzjPKK3dzOQcU-8,18846
-imsciences-0.9.6.6.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
-imsciences-0.9.6.6.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
-imsciences-0.9.6.6.dist-info/RECORD,,
+imsciences-0.9.6.8.dist-info/LICENSE.txt,sha256=lVq2QwcExPX4Kl2DHeEkRrikuItcDB1Pr7yF7FQ8_z8,1108
+imsciences-0.9.6.8.dist-info/METADATA,sha256=8M6I7Tw6M3mZsQYv08QxzyLKNQ4MclT8BvCRhhkuAgs,18846
+imsciences-0.9.6.8.dist-info/PKG-INFO-TomG-HP-290722,sha256=RMcthCSyWmU6IBsXGL-nYqw0RP06pzjPKK3dzOQcU-8,18846
+imsciences-0.9.6.8.dist-info/WHEEL,sha256=y4mX-SOX4fYIkonsAGA5N0Oy-8_gI4FXw5HNI1xqvWg,91
+imsciences-0.9.6.8.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
+imsciences-0.9.6.8.dist-info/RECORD,,

{imsciences-0.9.6.6.dist-info → imsciences-0.9.6.8.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.2.0)
+Generator: setuptools (70.2.0)
 Root-Is-Purelib: true
 Tag: py3-none-any