imsciences 0.8__py3-none-any.whl → 0.9__py3-none-any.whl

imsciences/datafunctions.py

@@ -16,6 +16,7 @@ import xml.etree.ElementTree as ET
 from bs4 import BeautifulSoup
 import yfinance as yf
 import holidays
+from dateutil.easter import easter
 
 class dataprocessing:
     
@@ -2123,18 +2124,35 @@ class datapull:
     ###############################################################  Seasonality  ##########################################################################
 
     def pull_seasonality(self, week_commencing, start_date, countries):
-        # Week commencing dictionary
+        # ---------------------------------------------------------------------
+        # 0. Setup: dictionary for 'week_commencing' to Python weekday() integer
+        # ---------------------------------------------------------------------
         day_dict = {"mon": 0, "tue": 1, "wed": 2, "thur": 3, "fri": 4, "sat": 5, "sun": 6}
-        
-        # Create daily date range dataframe starting from start_date
-        date_range = pd.date_range(start=pd.to_datetime(start_date), end=datetime.today(), freq="d")
+
+        # ---------------------------------------------------------------------
+        # 1. Create daily date range from start_date to today
+        # ---------------------------------------------------------------------
+        date_range = pd.date_range(
+            start=pd.to_datetime(start_date), 
+            end=datetime.today(), 
+            freq="D"
+        )
         df_daily = pd.DataFrame(date_range, columns=["Date"])
 
-        # Create weekly date range dataframe
-        df_daily['week_start'] = df_daily["Date"].apply(lambda x: x - pd.Timedelta(days=(x.weekday() - day_dict[week_commencing]) % 7))
+        # ---------------------------------------------------------------------
+        # 1.1 Identify "week_start" for each daily row, based on week_commencing
+        # ---------------------------------------------------------------------
+        df_daily['week_start'] = df_daily["Date"].apply(
+            lambda x: x - pd.Timedelta(days=(x.weekday() - day_dict[week_commencing]) % 7)
+        )
+
+        # ---------------------------------------------------------------------
+        # 2. Build a weekly index (df_weekly_start) with dummy columns
+        # ---------------------------------------------------------------------
         df_weekly_start = df_daily[['week_start']].drop_duplicates().reset_index(drop=True)
         df_weekly_start.rename(columns={'week_start': "Date"}, inplace=True)
         
+        # Set index to weekly "start of week"
         df_weekly_start.index = np.arange(1, len(df_weekly_start) + 1)
         df_weekly_start.set_index("Date", inplace=True)
 
@@ -2144,79 +2162,236 @@ class datapull:
             col_name = f"dum_{df_weekly_start.index[i].strftime('%Y_%m_%d')}"
             dummy_columns[col_name] = [0] * len(df_weekly_start)
             dummy_columns[col_name][i] = 1
-        
+
         df_dummies = pd.DataFrame(dummy_columns, index=df_weekly_start.index)
         df_weekly_start = pd.concat([df_weekly_start, df_dummies], axis=1)
 
-        # Add public holidays for each country and holiday type
+        # ---------------------------------------------------------------------
+        # 3. Public holidays (daily) from 'holidays' package + each holiday name
+        # ---------------------------------------------------------------------
         for country in countries:
-            country_holidays = holidays.CountryHoliday(country, years=range(int(start_date[:4]), datetime.today().year + 1))
-            df_daily[f"seas_holiday_{country.lower()}"] = df_daily["Date"].apply(lambda x: 1 if x in country_holidays else 0)
-
-            # Extract specific holidays
-            for date, name in country_holidays.items():
+            country_holidays = holidays.CountryHoliday(
+                country, 
+                years=range(int(start_date[:4]), datetime.today().year + 1)
+            )
+            # 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 country_holidays.items():
                 col_name = f"seas_{name.replace(' ', '_').lower()}_{country.lower()}"
                 if col_name not in df_daily.columns:
                     df_daily[col_name] = 0
-                df_daily.loc[df_daily["Date"] == pd.Timestamp(date), col_name] = 1
+                df_daily.loc[df_daily["Date"] == pd.Timestamp(date_hol), col_name] = 1
+
+        # ---------------------------------------------------------------------
+        # 3.1 Additional Special Days (Father's Day, Mother's Day, etc.)
+        #     We'll add daily columns for each. 
+        # ---------------------------------------------------------------------
+        # Initialize columns
+        extra_cols = [
+            "seas_valentines_day", 
+            "seas_halloween", 
+            "seas_fathers_day_us_uk",
+            "seas_mothers_day_us",
+            "seas_mothers_day_uk",
+            "seas_good_friday",
+            "seas_easter_monday",
+            "seas_black_friday",
+            "seas_cyber_monday",
+        ]
+        for c in extra_cols:
+            df_daily[c] = 0  # default zero
 
-        # Map daily holidays to weekly aggregation
-        df_daily['week_start'] = df_daily["Date"].apply(lambda x: x - pd.Timedelta(days=(x.weekday() - day_dict[week_commencing]) % 7))
-        df_holidays = df_daily.groupby('week_start').sum(numeric_only=True).reset_index().rename(columns={'week_start': "Date"})
-        df_holidays.set_index("Date", inplace=True)
+        # Helper: nth_weekday_of_month(year, month, weekday, nth=1 => first, 2 => second, etc.)
+        # weekday: Monday=0, Tuesday=1, ... Sunday=6
+        def nth_weekday_of_month(year, month, weekday, nth):
+            """
+            Returns date of the nth <weekday> in <month> of <year>.
+            E.g. nth_weekday_of_month(2023, 6, 6, 3) => 3rd Sunday of June 2023.
+            """
+            # 1st day of the month
+            d = datetime(year, month, 1)
+            # What is the weekday of day #1?
+            w = d.weekday()  # Monday=0, Tuesday=1, ... Sunday=6
+            # If we want, e.g. Sunday=6, we see how many days to add
+            delta = (weekday - w) % 7
+            # This is the first <weekday> in that month
+            first_weekday = d + timedelta(days=delta)
+            # Now add 7*(nth-1) days
+            return first_weekday + timedelta(days=7 * (nth-1))
+
+        def get_good_friday(year):
+            """Good Friday is 2 days before Easter Sunday."""
+            return easter(year) - timedelta(days=2)
+
+        def get_easter_monday(year):
+            """Easter Monday is 1 day after Easter Sunday."""
+            return easter(year) + timedelta(days=1)
+
+        def get_black_friday(year):
+            """
+            Black Friday = day after US Thanksgiving, 
+            and US Thanksgiving is the 4th Thursday in November.
+            """
+            # 4th Thursday in November
+            fourth_thursday = nth_weekday_of_month(year, 11, 3, 4)  # weekday=3 => Thursday
+            return fourth_thursday + timedelta(days=1)
+
+        def get_cyber_monday(year):
+            """Cyber Monday = Monday after US Thanksgiving, i.e. 4 days after 4th Thursday in Nov."""
+            # 4th Thursday in November
+            fourth_thursday = nth_weekday_of_month(year, 11, 3, 4)
+            return fourth_thursday + timedelta(days=4)  # Monday after Thanksgiving
+
+        # Loop over each year in range
+        start_yr = int(start_date[:4])
+        end_yr = datetime.today().year
+
+        for yr in range(start_yr, end_yr + 1):
+            # Valentines = Feb 14
+            valentines_day = datetime(yr, 2, 14)
+            # Halloween = Oct 31
+            halloween_day  = datetime(yr, 10, 31)
+            # Father's Day (US & UK) = 3rd Sunday in June
+            fathers_day    = nth_weekday_of_month(yr, 6, 6, 3)  # Sunday=6
+            # Mother's Day US = 2nd Sunday in May
+            mothers_day_us = nth_weekday_of_month(yr, 5, 6, 2)
+            # Mother's Day UK: 4th Sunday in Lent => "Mothering Sunday"
+            #   We can approximate as: Easter Sunday - 21 days 
+            #   BUT we also must ensure it's actually Sunday 
+            #   (the 4th Sunday in Lent can shift. We'll do the official approach below.)
+            #   Another approach: Easter Sunday - 7 * (4 weeks) is the 4th Sunday prior to Easter.
+            #   But that might overshoot if Lent started mid-week. 
+            # Let's do a quick approach:
+            #   Officially: Mothering Sunday = 3 weeks before Easter Sunday (the 4th Sunday is Easter Sunday itself).
+            #   So Easter - 21 days should be the Sunday, but let's confirm with weekday check.
+            mothering_sunday = easter(yr) - timedelta(days=21)
+            # If for some reason that's not a Sunday (rare corner cases), shift to Sunday:
+            while mothering_sunday.weekday() != 6:  # Sunday=6
+                mothering_sunday -= timedelta(days=1)
+
+            # Good Friday, Easter Monday
+            gf = get_good_friday(yr)
+            em = get_easter_monday(yr)
+
+            # Black Friday, Cyber Monday
+            bf = get_black_friday(yr)
+            cm = get_cyber_monday(yr)
+
+            # Mark them in df_daily if in range
+            for special_date, col in [
+                (valentines_day, "seas_valentines_day"),
+                (halloween_day,  "seas_halloween"),
+                (fathers_day,    "seas_fathers_day_us_uk"),
+                (mothers_day_us, "seas_mothers_day_us"),
+                (mothering_sunday, "seas_mothers_day_uk"),
+                (gf, "seas_good_friday"),
+                (em, "seas_easter_monday"),
+                (bf, "seas_black_friday"),
+                (cm, "seas_cyber_monday"),
+            ]:
+                # Convert to pd.Timestamp:
+                special_ts = pd.Timestamp(special_date)
+
+                # Only set if it's within your daily range
+                if (special_ts >= df_daily["Date"].min()) and (special_ts <= df_daily["Date"].max()):
+                    df_daily.loc[df_daily["Date"] == special_ts, col] = 1
+
+        # ---------------------------------------------------------------------
+        # 4. Add daily indicators for last day & last Friday of month
+        #    Then aggregate them to weekly level using .max()
+        # ---------------------------------------------------------------------
+        # Last day of month (daily)
+        df_daily["seas_last_day_of_month"] = df_daily["Date"].apply(
+            lambda d: 1 if d == d.to_period("M").to_timestamp("M") else 0
+        )
 
-        # Create monthly dummies (separately from holidays)
-        df_daily["Month"] = df_daily["Date"].dt.month_name().str.lower()
-        df_monthly_dummies = pd.get_dummies(df_daily, prefix="seas", columns=["Month"], dtype=int)
-        df_monthly_dummies['week_start'] = df_daily["Date"].apply(lambda x: x - pd.Timedelta(days=(x.weekday() - day_dict[week_commencing]) % 7))
-        df_monthly_dummies = df_monthly_dummies.groupby('week_start').sum(numeric_only=True).reset_index().rename(columns={'week_start': "Date"})
-        df_monthly_dummies.set_index("Date", inplace=True)
+        # Last Friday of month (daily)
+        def is_last_friday(date):
+            # last day of the month
+            last_day_of_month = date.to_period("M").to_timestamp("M")
+            last_day_weekday = last_day_of_month.weekday()  # Monday=0,...Sunday=6
+            # Determine how many days we go back from the last day to get Friday (weekday=4)
+            if last_day_weekday >= 4:
+                days_to_subtract = last_day_weekday - 4
+            else:
+                days_to_subtract = last_day_weekday + 3
+            last_friday = last_day_of_month - pd.Timedelta(days=days_to_subtract)
+            return 1 if date == last_friday else 0
 
-        # Divide only the monthly dummy columns by 7 (exclude holiday-related columns)
-        monthly_cols = [col for col in df_monthly_dummies.columns if not col.startswith("seas_holiday") and not col.startswith("seas_")]
+        df_daily["seas_last_friday_of_month"] = df_daily["Date"].apply(is_last_friday)
+
+        # ---------------------------------------------------------------------
+        # 5. Weekly aggregation for holiday columns & monthly dummies
+        # ---------------------------------------------------------------------
+        # For monthly dummies, create a daily col "Month", then get_dummies
+        df_daily["Month"] = df_daily["Date"].dt.month_name().str.lower()
+        df_monthly_dummies = pd.get_dummies(
+            df_daily, 
+            prefix="seas", 
+            columns=["Month"], 
+            dtype=int
+        )
+        # Recalculate 'week_start' (already in df_daily, but just to be sure)
+        df_monthly_dummies['week_start'] = df_daily['week_start']
+
+        # Group monthly dummies by .sum() or .mean()—we often spread them across the week
+        df_monthly_dummies = (
+            df_monthly_dummies
+            .groupby('week_start')
+            .sum(numeric_only=True)    # sum the daily flags
+            .reset_index()
+            .rename(columns={'week_start': "Date"})
+            .set_index("Date")
+        )
+        # Spread monthly dummies by 7 to distribute across that week
+        monthly_cols = [c for c in df_monthly_dummies.columns if c.startswith("seas_month_")]
         df_monthly_dummies[monthly_cols] = df_monthly_dummies[monthly_cols] / 7
 
-        # Merge weekly dummies, monthly dummies, and holidays
-        df_combined = pd.concat([df_weekly_start, df_monthly_dummies], axis=1)  # Combine weekly and monthly first
-        df_combined = pd.concat([df_combined, df_holidays], axis=1)  # Add holidays separately
+        # Group holiday & special-day columns by .max() => binary at weekly level
+        df_holidays = (
+            df_daily
+            .groupby('week_start')
+            .max(numeric_only=True)   # if any day=1 in that week, entire week=1
+            .reset_index()
+            .rename(columns={'week_start': "Date"})
+            .set_index("Date")
+        )
 
-        # Drop duplicate columns if any exist (this ensures holidays are not duplicated)
+        # ---------------------------------------------------------------------
+        # 6. Combine weekly start, monthly dummies, holiday flags
+        # ---------------------------------------------------------------------
+        df_combined = pd.concat([df_weekly_start, df_monthly_dummies], axis=1)
+        df_combined = pd.concat([df_combined, df_holidays], axis=1)
         df_combined = df_combined.loc[:, ~df_combined.columns.duplicated()]
 
-        # Create weekly dummies
+        # ---------------------------------------------------------------------
+        # 7. Create weekly dummies for Week of Year & yearly dummies
+        # ---------------------------------------------------------------------
         df_combined.reset_index(inplace=True)
+        df_combined.rename(columns={"index": "old_index"}, inplace=True)  # just in case
+        
         df_combined["Week"] = df_combined["Date"].dt.isocalendar().week
         df_combined = pd.get_dummies(df_combined, prefix="seas", columns=["Week"], dtype=int)
         
-        # Create yearly dummies
         df_combined["Year"] = df_combined["Date"].dt.year
         df_combined = pd.get_dummies(df_combined, prefix="seas", columns=["Year"], dtype=int)
         
-        # Add constant
+        # ---------------------------------------------------------------------
+        # 8. Add constant & trend
+        # ---------------------------------------------------------------------
         df_combined["Constant"] = 1
-        
-        # Add trend
         df_combined["Trend"] = df_combined.index + 1
-
-        # Create seasonal indicators for the last day and last Friday of the month
-        df_combined['seas_last_day_of_month'] = df_combined["Date"].apply(lambda x: 1 if x == x.to_period('M').to_timestamp('M') else 0)
         
-        def is_last_friday(date):
-            last_day_of_month = date.to_period('M').to_timestamp('M')
-            last_day_weekday = last_day_of_month.dayofweek
-            if last_day_weekday >= 4:
-                days_to_subtract = last_day_weekday - 4
-            else:
-                days_to_subtract = last_day_weekday + 3
-            last_friday = last_day_of_month - pd.Timedelta(days=days_to_subtract)
-            return 1 if date == last_friday else 0
-        
-        df_combined['seas_last_friday_of_month'] = df_combined["Date"].apply(is_last_friday)
-        
-        # Rename Date to OBS
+        # ---------------------------------------------------------------------
+        # 9. Rename Date -> OBS and return
+        # ---------------------------------------------------------------------
         df_combined.rename(columns={"Date": "OBS"}, inplace=True)
         
         return df_combined
+
     
     def pull_weather(self, week_commencing, country) -> pd.DataFrame:
         import pandas as pd

{imsciences-0.8.dist-info → imsciences-0.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.8
+Version: 0.9
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com
@@ -35,97 +35,97 @@ The **IMSciences package** is a Python library designed to process incoming data
 
 ---
 
-## Table of Contents
+Table of Contents
+=================
 
-1. [Data Processing](#data-processing)
-2. [Data Pulling](#data-pulling)
-3. [Installation](#installation)
-4. [Useage](#useage)
-5. [License](#license)
+1. [Data Processing](#Data-Processing)
+2. [Data Pulling](#Data-Pulling)
+3. [Installation](#Installation)
+4. [Useage](#Useage)
+5. [License](#License)
 
 ---
 
 ## Data Processing
 
-
-## 1. `get_wd_levels`
+## 1. get_wd_levels
 - **Description**: Get the working directory with the option of moving up parents.
 - **Usage**: `get_wd_levels(levels)`
 - **Example**: `get_wd_levels(0)`
 
 ---
 
-## 2. `remove_rows`
+## 2. remove_rows
 - **Description**: Removes a specified number of rows from a pandas DataFrame.
 - **Usage**: `remove_rows(data_frame, num_rows_to_remove)`
 - **Example**: `remove_rows(df, 2)`
 
 ---
 
-## 3. `aggregate_daily_to_wc_long`
+## 3. aggregate_daily_to_wc_long
 - **Description**: Aggregates daily data into weekly data, grouping and summing specified columns, starting on a specified day of the week.
 - **Usage**: `aggregate_daily_to_wc_long(df, date_column, group_columns, sum_columns, wc, aggregation='sum')`
 - **Example**: `aggregate_daily_to_wc_long(df, 'date', ['platform'], ['cost', 'impressions', 'clicks'], 'mon', 'average')`
 
 ---
 
-## 4. `convert_monthly_to_daily`
+## 4. convert_monthly_to_daily
 - **Description**: Converts monthly data in a DataFrame to daily data by expanding and dividing the numeric values.
 - **Usage**: `convert_monthly_to_daily(df, date_column, divide)`
 - **Example**: `convert_monthly_to_daily(df, 'date')`
 
 ---
 
-## 5. `plot_two`
+## 5. plot_two
 - **Description**: Plots specified columns from two different DataFrames using a shared date column. Useful for comparing data.
 - **Usage**: `plot_two(df1, col1, df2, col2, date_column, same_axis=True)`
 - **Example**: `plot_two(df1, 'cost', df2, 'cost', 'obs', True)`
 
 ---
 
-## 6. `remove_nan_rows`
+## 6. remove_nan_rows
 - **Description**: Removes rows from a DataFrame where the specified column has NaN values.
 - **Usage**: `remove_nan_rows(df, col_to_remove_rows)`
 - **Example**: `remove_nan_rows(df, 'date')`
 
 ---
 
-## 7. `filter_rows`
+## 7. filter_rows
 - **Description**: Filters the DataFrame based on whether the values in a specified column are in a provided list.
 - **Usage**: `filter_rows(df, col_to_filter, list_of_filters)`
 - **Example**: `filter_rows(df, 'country', ['UK', 'IE'])`
 
 ---
 
-## 8. `plot_one`
+## 8. plot_one
 - **Description**: Plots a specified column from a DataFrame.
 - **Usage**: `plot_one(df1, col1, date_column)`
 - **Example**: `plot_one(df, 'Spend', 'OBS')`
 
 ---
 
-## 9. `week_of_year_mapping`
+## 9. week_of_year_mapping
 - **Description**: Converts a week column in `yyyy-Www` or `yyyy-ww` format to week commencing date.
 - **Usage**: `week_of_year_mapping(df, week_col, start_day_str)`
 - **Example**: `week_of_year_mapping(df, 'week', 'mon')`
 
 ---
 
-## 10. `exclude_rows`
+## 10. exclude_rows
 - **Description**: Removes rows from a DataFrame based on whether the values in a specified column are not in a provided list.
 - **Usage**: `exclude_rows(df, col_to_filter, list_of_filters)`
 - **Example**: `exclude_rows(df, 'week', ['2022-W20', '2022-W21'])`
 
 ---
 
-## 11. `rename_cols`
+## 11. rename_cols
 - **Description**: Renames columns in a pandas DataFrame.
 - **Usage**: `rename_cols(df, name)`
 - **Example**: `rename_cols(df, 'ame_facebook')`
 
 ---
 
-## 12. `merge_new_and_old`
+## 12. merge_new_and_old
 - **Description**: Creates a new DataFrame with two columns: one for dates and one for merged numeric values.
   - Merges numeric values from specified columns in the old and new DataFrames based on a given cutoff date.
 - **Usage**: `merge_new_and_old(old_df, old_col, new_df, new_col, cutoff_date, date_col_name='OBS')`
@@ -133,21 +133,21 @@ The **IMSciences package** is a Python library designed to process incoming data
 
 ---
 
-## 13. `merge_dataframes_on_date`
+## 13. merge_dataframes_on_date
 - **Description**: Merge a list of DataFrames on a common column.
 - **Usage**: `merge_dataframes_on_date(dataframes, common_column='OBS', merge_how='outer')`
 - **Example**: `merge_dataframes_on_date([df1, df2, df3], common_column='OBS', merge_how='outer')`
 
 ---
 
-## 14. `merge_and_update_dfs`
+## 14. merge_and_update_dfs
 - **Description**: Merges two dataframes on a key column, updates the first dataframe's columns with the second's where available, and returns a dataframe sorted by the key column.
 - **Usage**: `merge_and_update_dfs(df1, df2, key_column)`
 - **Example**: `merge_and_update_dfs(processed_facebook, finalised_meta, 'OBS')`
 
 ---
 
-## 15. `convert_us_to_uk_dates`
+## 15. convert_us_to_uk_dates
 - **Description**: Convert a DataFrame column with mixed date formats to datetime.
 - **Usage**: `convert_us_to_uk_dates(df, date_col)`
 - **Example**: `convert_us_to_uk_dates(df, 'date')`
@@ -161,189 +161,189 @@ The **IMSciences package** is a Python library designed to process incoming data
 
 ---
 
-## 17. `pivot_table`
+## 17. pivot_table
 - **Description**: Dynamically pivots a DataFrame based on specified columns.
 - **Usage**: `pivot_table(df, index_col, columns, values_col, filters_dict=None, fill_value=0, aggfunc='sum', margins=False, margins_name='Total', datetime_trans_needed=True, reverse_header_order=False, fill_missing_weekly_dates=False, week_commencing='W-MON')`
 - **Example**: `pivot_table(df, 'OBS', 'Channel Short Names', 'Value', filters_dict={'Master Include': ' == 1', 'OBS': ' >= datetime(2019,9,9)', 'Metric Short Names': ' == spd'}, fill_value=0, aggfunc='sum', margins=False, margins_name='Total', datetime_trans_needed=True, reverse_header_order=True, fill_missing_weekly_dates=True, week_commencing='W-MON')`
 
 ---
 
-## 18. `apply_lookup_table_for_columns`
+## 18. apply_lookup_table_for_columns
 - **Description**: Equivalent of XLOOKUP in Excel. Allows mapping of a dictionary of substrings within a column.
 - **Usage**: `apply_lookup_table_for_columns(df, col_names, to_find_dict, if_not_in_dict='Other', new_column_name='Mapping')`
 - **Example**: `apply_lookup_table_for_columns(df, col_names, {'spend': 'spd', 'clicks': 'clk'}, if_not_in_dict='Other', new_column_name='Metrics Short')`
 
 ---
 
-## 19. `aggregate_daily_to_wc_wide`
+## 19. aggregate_daily_to_wc_wide
 - **Description**: Aggregates daily data into weekly data, grouping and summing specified columns, starting on a specified day of the week.
 - **Usage**: `aggregate_daily_to_wc_wide(df, date_column, group_columns, sum_columns, wc, aggregation='sum', include_totals=False)`
 - **Example**: `aggregate_daily_to_wc_wide(df, 'date', ['platform'], ['cost', 'impressions', 'clicks'], 'mon', 'average', True)`
 
 ---
 
-## 20. `merge_cols_with_seperator`
+## 20. merge_cols_with_seperator
 - **Description**: Merges multiple columns in a DataFrame into one column with a separator `_`. Useful for lookup tables.
 - **Usage**: `merge_cols_with_seperator(df, col_names, seperator='_', output_column_name='Merged', starting_prefix_str=None, ending_prefix_str=None)`
 - **Example**: `merge_cols_with_seperator(df, ['Campaign', 'Product'], seperator='|', output_column_name='Merged Columns', starting_prefix_str='start_', ending_prefix_str='_end')`
 
 ---
 
-## 21. `check_sum_of_df_cols_are_equal`
+## 21. check_sum_of_df_cols_are_equal
 - **Description**: Checks if the sum of two columns in two DataFrames are the same, and provides the sums and differences.
 - **Usage**: `check_sum_of_df_cols_are_equal(df_1, df_2, cols_1, cols_2)`
 - **Example**: `check_sum_of_df_cols_are_equal(df_1, df_2, 'Media Cost', 'Spend')`
 
 ---
 
-## 22. `convert_2_df_cols_to_dict`
+## 22. convert_2_df_cols_to_dict
 - **Description**: Creates a dictionary using two columns in a DataFrame.
 - **Usage**: `convert_2_df_cols_to_dict(df, key_col, value_col)`
 - **Example**: `convert_2_df_cols_to_dict(df, 'Campaign', 'Channel')`
 
 ---
 
-## 23. `create_FY_and_H_columns`
+## 23. create_FY_and_H_columns
 - **Description**: Creates financial year, half-year, and financial half-year columns.
 - **Usage**: `create_FY_and_H_columns(df, index_col, start_date, starting_FY, short_format='No', half_years='No', combined_FY_and_H='No')`
 - **Example**: `create_FY_and_H_columns(df, 'Week (M-S)', '2022-10-03', 'FY2023', short_format='Yes', half_years='Yes', combined_FY_and_H='Yes')`
 
 ---
 
-## 24. `keyword_lookup_replacement`
+## 24. keyword_lookup_replacement
 - **Description**: Updates chosen values in a specified column of the DataFrame based on a lookup dictionary.
 - **Usage**: `keyword_lookup_replacement(df, col, replacement_rows, cols_to_merge, replacement_lookup_dict, output_column_name='Updated Column')`
 - **Example**: `keyword_lookup_replacement(df, 'channel', 'Paid Search Generic', ['channel', 'segment', 'product'], qlik_dict_for_channel, output_column_name='Channel New')`
 
 ---
 
-## 25. `create_new_version_of_col_using_LUT`
+## 25. create_new_version_of_col_using_LUT
 - **Description**: Creates a new column in a DataFrame by mapping values from an old column using a lookup table.
 - **Usage**: `create_new_version_of_col_using_LUT(df, keys_col, value_col, dict_for_specific_changes, new_col_name='New Version of Old Col')`
 - **Example**: `create_new_version_of_col_using_LUT(df, 'Campaign Name', 'Campaign Type', search_campaign_name_retag_lut, 'Campaign Name New')`
 
 ---
 
-## 26. `convert_df_wide_2_long`
+## 26. convert_df_wide_2_long
 - **Description**: Converts a DataFrame from wide to long format.
 - **Usage**: `convert_df_wide_2_long(df, value_cols, variable_col_name='Stacked', value_col_name='Value')`
 - **Example**: `convert_df_wide_2_long(df, ['Media Cost', 'Impressions', 'Clicks'], variable_col_name='Metric')`
 
 ---
 
-## 27. `manually_edit_data`
+## 27. manually_edit_data
 - **Description**: Enables manual updates to DataFrame cells by applying filters and editing a column.
 - **Usage**: `manually_edit_data(df, filters_dict, col_to_change, new_value, change_in_existing_df_col='No', new_col_to_change_name='New', manual_edit_col_name=None, add_notes='No', existing_note_col_name=None, note=None)`
 - **Example**: `manually_edit_data(df, {'OBS': ' <= datetime(2023,1,23)', 'File_Name': ' == France media'}, 'Master Include', 1, change_in_existing_df_col='Yes', new_col_to_change_name='Master Include', manual_edit_col_name='Manual Changes')`
 
 ---
 
-## 28. `format_numbers_with_commas`
+## 28. format_numbers_with_commas
 - **Description**: Formats numeric data into numbers with commas and specified decimal places.
 - **Usage**: `format_numbers_with_commas(df, decimal_length_chosen=2)`
 - **Example**: `format_numbers_with_commas(df, 1)`
 
 ---
 
-## 29. `filter_df_on_multiple_conditions`
+## 29. filter_df_on_multiple_conditions
 - **Description**: Filters a DataFrame based on multiple conditions from a dictionary.
 - **Usage**: `filter_df_on_multiple_conditions(df, filters_dict)`
 - **Example**: `filter_df_on_multiple_conditions(df, {'OBS': ' <= datetime(2023,1,23)', 'File_Name': ' == France media'})`
 
 ---
 
-## 30. `read_and_concatenate_files`
+## 30. read_and_concatenate_files
 - **Description**: Reads and concatenates all files of a specified type in a folder.
 - **Usage**: `read_and_concatenate_files(folder_path, file_type='csv')`
 - **Example**: `read_and_concatenate_files(folder_path, file_type='csv')`
 
 ---
 
-## 31. `remove_zero_values`
+## 31. remove_zero_values
 - **Description**: Removes rows with zero values in a specified column.
 - **Usage**: `remove_zero_values(data_frame, column_to_filter)`
 - **Example**: `remove_zero_values(df, 'Funeral_Delivery')`
 
 ---
 
-## 32. `upgrade_outdated_packages`
+## 32. upgrade_outdated_packages
 - **Description**: Upgrades all outdated packages in the environment.
 - **Usage**: `upgrade_outdated_packages()`
 - **Example**: `upgrade_outdated_packages()`
 
 ---
 
-## 33. `convert_mixed_formats_dates`
+## 33. convert_mixed_formats_dates
 - **Description**: Converts a mix of US and UK date formats to datetime.
 - **Usage**: `convert_mixed_formats_dates(df, date_col)`
 - **Example**: `convert_mixed_formats_dates(df, 'OBS')`
 
 ---
 
-## 34. `fill_weekly_date_range`
+## 34. fill_weekly_date_range
 - **Description**: Fills in missing weeks with zero values.
 - **Usage**: `fill_weekly_date_range(df, date_column, freq)`
 - **Example**: `fill_weekly_date_range(df, 'OBS', 'W-MON')`
 
 ---
 
-## 35. `add_prefix_and_suffix`
+## 35. add_prefix_and_suffix
 - **Description**: Adds prefixes and/or suffixes to column headers.
 - **Usage**: `add_prefix_and_suffix(df, prefix='', suffix='', date_col=None)`
 - **Example**: `add_prefix_and_suffix(df, prefix='media_', suffix='_spd', date_col='obs')`
 
 ---
 
-## 36. `create_dummies`
+## 36. create_dummies
 - **Description**: Converts time series into binary indicators based on a threshold.
 - **Usage**: `create_dummies(df, date_col=None, dummy_threshold=0, add_total_dummy_col='No', total_col_name='total')`
 - **Example**: `create_dummies(df, date_col='obs', dummy_threshold=100, add_total_dummy_col='Yes', total_col_name='med_total_dum')`
 
 ---
 
-## 37. `replace_substrings`
+## 37. replace_substrings
 - **Description**: Replaces substrings in a column of strings using a dictionary and can change column values to lowercase.
 - **Usage**: `replace_substrings(df, column, replacements, to_lower=False, new_column=None)`
 - **Example**: `replace_substrings(df, 'Influencer Handle', replacement_dict, to_lower=True, new_column='Short Version')`
 
 ---
 
-## 38. `add_total_column`
+## 38. `add_total_column
 - **Description**: Sums all columns (excluding a specified column) to create a total column.
 - **Usage**: `add_total_column(df, exclude_col=None, total_col_name='Total')`
 - **Example**: `add_total_column(df, exclude_col='obs', total_col_name='total_media_spd')`
 
 ---
 
-## 39. `apply_lookup_table_based_on_substring`
+## 39. apply_lookup_table_based_on_substring
 - **Description**: Maps substrings in a column to values using a lookup dictionary.
 - **Usage**: `apply_lookup_table_based_on_substring(df, column_name, category_dict, new_col_name='Category', other_label='Other')`
 - **Example**: `apply_lookup_table_based_on_substring(df, 'Campaign Name', campaign_dict, new_col_name='Campaign Name Short', other_label='Full Funnel')`
 
 ---
 
-## 40. `compare_overlap`
+## 40. compare_overlap
 - **Description**: Compares matching rows and columns in two DataFrames and outputs the differences.
 - **Usage**: `compare_overlap(df1, df2, date_col)`
 - **Example**: `compare_overlap(df_1, df_2, 'obs')`
 
 ---
 
-## 41. `week_commencing_2_week_commencing_conversion`
+## 41. week_commencing_2_week_commencing_conversion
 - **Description**: Converts a week commencing column to a different start day.
 - **Usage**: `week_commencing_2_week_commencing_conversion(df, date_col, week_commencing='sun')`
 - **Example**: `week_commencing_2_week_commencing_conversion(df, 'obs', week_commencing='mon')`
 
 ---
 
-## 42. `plot_chart`
+## 42. plot_chart
 - **Description**: Plots various chart types including line, area, scatter, and bar.
 - **Usage**: `plot_chart(df, date_col, value_cols, chart_type='line', title='Chart', x_title='Date', y_title='Values', **kwargs)`
 - **Example**: `plot_chart(df, 'obs', df.cols, chart_type='line', title='Spend Over Time', x_title='Date', y_title='Spend')`
 
 ---
 
-## 43. `plot_two_with_common_cols`
+## 43. plot_two_with_common_cols
 - **Description**: Plots charts for two DataFrames based on common column names.
 - **Usage**: `plot_two_with_common_cols(df1, df2, date_column, same_axis=True)`
 - **Example**: `plot_two_with_common_cols(df_1, df_2, date_column='obs')`
@@ -411,7 +411,7 @@ The **IMSciences package** is a Python library designed to process incoming data
 Install the IMS package via pip:
 
 ```bash
-pip install ims-package
+pip install imsciences
 ```
 
 ---

{imsciences-0.8.dist-info → imsciences-0.9.dist-info}/RECORD

@@ -3,15 +3,15 @@ dataprocessing/data-processing-functions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nF
 dataprocessing/datafunctions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nFydwGkvzHXf2f1Y,41
 imsciences/__init__.py,sha256=7CfK2dMjPnBBw6I4st-20MdMlLjZULviFVXF2eMD9NI,80
 imsciences/datafunctions-IMS-24Ltp-3.py,sha256=3Snv-0iE_03StmyjtT-riOU9f4v8TaJWLoyZLJp6l8Y,141406
-imsciences/datafunctions.py,sha256=KbZuvjJF-1gydPsb2qFlvpbVLwuG6y-lhLKt-wZ5JDI,156389
+imsciences/datafunctions.py,sha256=NGJ3j1HIXX2G2bE529Tlvq6AXaAxSye6YjobUF_QpL4,164562
 imsciences/datapull.py,sha256=TPY0LDgOkcKTBk8OekbD0Grg5x0SomAK2dZ7MuT6X1E,19000
 imsciences/unittesting.py,sha256=d9H5HN8y7oof59hqN9mGqkjulExqFd93BEW-X8w_Id8,58142
 imsciencesdataprocessing/__init__.py,sha256=quSwsLs6IuLoA5Rzi0ZD40xZaQudwDteF7_ai9JfTPk,32
 imsciencesdataprocessing/datafunctions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nFydwGkvzHXf2f1Y,41
 imsdataprocessing/__init__.py,sha256=quSwsLs6IuLoA5Rzi0ZD40xZaQudwDteF7_ai9JfTPk,32
 imsdataprocessing/datafunctions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nFydwGkvzHXf2f1Y,41
-imsciences-0.8.dist-info/METADATA,sha256=moylR64i_w4kk3TPPZMpFmAPc9f0A4xJgjAY-Zy-Tac,17845
-imsciences-0.8.dist-info/PKG-INFO-IMS-24Ltp-3,sha256=yqZbigwHjnYoqyI81PGz_AeofRFfOrwH_Vyawyef-mg,854
-imsciences-0.8.dist-info/WHEEL,sha256=ixB2d4u7mugx_bCBycvM9OzZ5yD7NmPXFRtKlORZS2Y,91
-imsciences-0.8.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
-imsciences-0.8.dist-info/RECORD,,
+imsciences-0.9.dist-info/METADATA,sha256=KZSjJgbi89Oon07qhMCo9nlP_kE3GIUeRM29vs50tds,17775
+imsciences-0.9.dist-info/PKG-INFO-IMS-24Ltp-3,sha256=yqZbigwHjnYoqyI81PGz_AeofRFfOrwH_Vyawyef-mg,854
+imsciences-0.9.dist-info/WHEEL,sha256=ixB2d4u7mugx_bCBycvM9OzZ5yD7NmPXFRtKlORZS2Y,91
+imsciences-0.9.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
+imsciences-0.9.dist-info/RECORD,,