imsciences 0.9.5.9__tar.gz → 0.9.6.3__tar.gz

{imsciences-0.9.5.9 → imsciences-0.9.6.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.9.5.9
+Version: 0.9.6.3
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.9.5.9 → imsciences-0.9.6.3}/imsciences/pull.py

@@ -133,7 +133,7 @@ class datapull:
 
         Args:
             week_commencing (str): The starting day of the week for aggregation.
-                                Options are "mon", "tue", "wed", "thur", "fri", "sat", "sun".
+                                Options are "mon", "tue", "wed", "thu", "fri", "sat", "sun".
                                 Default is "mon".
             max_retries (int): Maximum number of retries to fetch data in case of failure. Default is 5.
             delay (int): Delay in seconds between retry attempts. Default is 5.
@@ -144,7 +144,7 @@ class datapull:
                         and 'macro_boe_intr_rate' contains the average interest rate for the week.
         """
         # Week commencing dictionary
-        day_dict = {"mon": 0, "tue": 1, "wed": 2, "thur": 3, "fri": 4, "sat": 5, "sun": 6}
+        day_dict = {"mon": 0, "tue": 1, "wed": 2, "thu": 3, "fri": 4, "sat": 5, "sun": 6}
 
         # URL of the Bank of England data page
         url = 'https://www.bankofengland.co.uk/boeapps/database/Bank-Rate.asp'
@@ -209,7 +209,7 @@ class datapull:
         Args:
             country (list): A string containing a 3-letter code the of country of interest (E.g: "GBR", "FRA", "USA", "DEU")
             week_commencing (str): The starting day of the week for aggregation. 
-                                Options are "mon", "tue", "wed", "thur", "fri", "sat", "sun".
+                                Options are "mon", "tue", "wed", "thu", "fri", "sat", "sun".
             start_date (str): Dataset start date in the format "YYYY-MM-DD"
 
         Returns:
@@ -383,7 +383,7 @@ class datapull:
         # ---------------------------------------------------------------------
         # 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}
+        day_dict = {"mon": 0, "tue": 1, "wed": 2, "thu": 3, "fri": 4, "sat": 5, "sun": 6}
 
         # ---------------------------------------------------------------------
         # 1. Create daily date range from start_date to today
@@ -668,7 +668,7 @@ class datapull:
             raise ValueError("country_codes must be a list/tuple or a single string.")
 
         # --- Setup / Constants --- #
-        day_dict = {"mon": 0, "tue": 1, "wed": 2, "thur": 3, "fri": 4, "sat": 5, "sun": 6}
+        day_dict = {"mon": 0, "tue": 1, "wed": 2, "thu": 3, "fri": 4, "sat": 5, "sun": 6}
         # Map each 2-letter code to a key
         country_dict = {
             "US": "US_STATES",
@@ -1171,74 +1171,110 @@ class datapull:
         
     def pull_macro_ons_uk(self, cdid_list=None, week_start_day="mon", sector=None):
         """
-        Fetches time series data for multiple CDIDs from the ONS API, converts it to daily frequency, 
+        Fetches time series data for multiple CDIDs from the ONS API, converts it to daily frequency,
         aggregates it to weekly averages, and renames variables based on specified rules.
 
         Parameters:
-            cdid_list (list): A list of additional CDIDs to fetch (e.g., ['JP9Z', 'UKPOP']). Defaults to None.
-            week_start_day (str): The day the week starts on (e.g., 'Monday', 'Sunday').
-            sector (str): The sector for which the standard CDIDs are fetched (e.g., 'fast_food', 'retail').
+            cdid_list (list, optional): A list of additional CDIDs to fetch (e.g., ['JP9Z', 'UKPOP']). Defaults to None.
+            week_start_day (str, optional): The day the week starts on ('mon', 'tue', 'wed', 'thu', 'fri', 'sat', 'sun'). Defaults to 'mon'.
+            sector (str or list, optional): The sector(s) for which the standard CDIDs are fetched
+                                             (e.g., 'fast_food', ['fast_food', 'retail']). Defaults to None (only default CDIDs).
 
         Returns:
-            pd.DataFrame: A DataFrame with weekly frequency, containing a 'week_commencing' column 
-                        and all series as renamed columns.
+            pd.DataFrame: A DataFrame with weekly frequency, containing an 'OBS' column (week commencing date)
+                          and all series as renamed columns (e.g., 'macro_retail_sales_uk').
+                          Returns an empty DataFrame if no data is fetched or processed.
         """
         # Define CDIDs for sectors and defaults
-        sector_cdids = {
+        sector_cdids_map = {
             "fast_food": ["L7TD", "L78Q", "DOAD"],
+            "clothing_footwear": ["D7BW","D7GO","CHBJ"],
+            "fuel": ["A9FS","L7FP","CHOL"],
+            "cars":["D7E8","D7E9","D7CO"],
             "default": ["D7G7", "MGSX", "UKPOP", "IHYQ", "YBEZ", "MS77"],
         }
 
-        default_cdids = sector_cdids["default"]
-        sector_specific_cdids = sector_cdids.get(sector, [])
-        standard_cdids = list(set(default_cdids + sector_specific_cdids))  # Avoid duplicates
+        default_cdids = sector_cdids_map["default"]
+        sector_specific_cdids = [] # Initialize empty list for sector CDIDs
+
+        if sector: # Check if sector is not None or empty
+            if isinstance(sector, str):
+                # If it's a single string, wrap it in a list
+                sector_list = [sector]
+            elif isinstance(sector, list):
+                # If it's already a list, use it directly
+                sector_list = sector
+            else:
+                raise TypeError("`sector` parameter must be a string or a list of strings.")
+
+            # Iterate through the list of sectors and collect their CDIDs
+            for sec in sector_list:
+                sector_specific_cdids.extend(sector_cdids_map.get(sec, [])) # Use extend to add items from the list
+
+        standard_cdids = list(set(default_cdids + sector_specific_cdids))  # Combine default and selected sector CDIDs, ensure uniqueness
 
-        # Combine standard CDIDs and additional CDIDs
+        # Combine standard CDIDs and any additional user-provided CDIDs
         if cdid_list is None:
             cdid_list = []
-        cdid_list = list(set(standard_cdids + cdid_list))  # Avoid duplicates
+        final_cdid_list = list(set(standard_cdids + cdid_list))  # Ensure uniqueness in the final list
 
         base_search_url = "https://api.beta.ons.gov.uk/v1/search?content_type=timeseries&cdids="
         base_data_url = "https://api.beta.ons.gov.uk/v1/data?uri="
         combined_df = pd.DataFrame()
 
         # Map week start day to pandas weekday convention
-        days_map = {"mon": 0, "tue": 1, "wed": 2, "thur": 3, "fri": 4, "sat": 5, "sun": 6}
-        if week_start_day not in days_map:
+        days_map = {"mon": 0, "tue": 1, "wed": 2, "thu": 3, "fri": 4, "sat": 5, "sun": 6}
+        if week_start_day.lower() not in days_map:
             raise ValueError("Invalid week start day. Choose from: " + ", ".join(days_map.keys()))
-        week_start = days_map[week_start_day]
+        week_start = days_map[week_start_day.lower()] # Use lower() for case-insensitivity
 
-        for cdid in cdid_list:
+        for cdid in final_cdid_list: # Use the final combined list
             try:
                 # Search for the series
                 search_url = f"{base_search_url}{cdid}"
-                search_response = requests.get(search_url)
+                search_response = requests.get(search_url, timeout=30) # Add timeout
                 search_response.raise_for_status()
                 search_data = search_response.json()
 
                 items = search_data.get("items", [])
                 if not items:
-                    print(f"No data found for CDID: {cdid}")
+                    print(f"Warning: No data found for CDID: {cdid}")
                     continue
 
                 # Extract series name and latest release URI
-                series_name = items[0].get("title", f"Series_{cdid}")
-                latest_date = max(
-                    datetime.fromisoformat(item["release_date"].replace("Z", "+00:00"))
-                    for item in items if "release_date" in item
-                )
-                latest_uri = next(
-                    item["uri"] for item in items
-                    if "release_date" in item and datetime.fromisoformat(item["release_date"].replace("Z", "+00:00")) == latest_date
-                )
+                # Find the item with the most recent release_date
+                latest_item = None
+                latest_date = None
+                for item in items:
+                    if "release_date" in item:
+                        try:
+                            # Ensure timezone awareness for comparison
+                            current_date = datetime.fromisoformat(item["release_date"].replace("Z", "+00:00"))
+                            if latest_date is None or current_date > latest_date:
+                                latest_date = current_date
+                                latest_item = item
+                        except ValueError:
+                            print(f"Warning: Could not parse release_date '{item['release_date']}' for CDID {cdid}")
+                            continue # Skip this item if date is invalid
+
+                if latest_item is None:
+                     print(f"Warning: No valid release date found for CDID: {cdid}")
+                     continue
+
+                series_name = latest_item.get("title", f"Series_{cdid}") # Use title from the latest item
+                latest_uri = latest_item.get("uri")
+                if not latest_uri:
+                     print(f"Warning: No URI found for the latest release of CDID: {cdid}")
+                     continue
 
                 # Fetch the dataset
                 data_url = f"{base_data_url}{latest_uri}"
-                data_response = requests.get(data_url)
+                data_response = requests.get(data_url, timeout=30) # Add timeout
                 data_response.raise_for_status()
                 data_json = data_response.json()
 
                 # Detect the frequency and process accordingly
+                frequency_key = None
                 if "months" in data_json and data_json["months"]:
                     frequency_key = "months"
                 elif "quarters" in data_json and data_json["quarters"]:
@@ -1246,72 +1282,142 @@ class datapull:
                 elif "years" in data_json and data_json["years"]:
                     frequency_key = "years"
                 else:
-                    print(f"Unsupported frequency or no data for CDID: {cdid}")
+                    print(f"Warning: Unsupported frequency or no data values found for CDID: {cdid} at URI {latest_uri}")
                     continue
 
                 # Prepare the DataFrame
+                if not data_json[frequency_key]: # Check if the list of values is empty
+                     print(f"Warning: Empty data list for frequency '{frequency_key}' for CDID: {cdid}")
+                     continue
+
                 df = pd.DataFrame(data_json[frequency_key])
 
-                # Parse the 'date' field based on frequency
-                if frequency_key == "months":
-                    df["date"] = pd.to_datetime(df["date"], format="%Y %b", errors="coerce")
-                elif frequency_key == "quarters":
-                    def parse_quarter(quarter_str):
-                        year, qtr = quarter_str.split(" Q")
-                        month = {"1": 1, "2": 4, "3": 7, "4": 10}[qtr]
-                        return datetime(int(year), month, 1)
-                    df["date"] = df["date"].apply(parse_quarter)
-                elif frequency_key == "years":
-                    df["date"] = pd.to_datetime(df["date"], format="%Y", errors="coerce")
+                # Check if essential columns exist
+                if "date" not in df.columns or "value" not in df.columns:
+                    print(f"Warning: Missing 'date' or 'value' column for CDID: {cdid}")
+                    continue
 
+                # Parse the 'date' field based on frequency
+                try:
+                    if frequency_key == "months":
+                        # Handles "YYYY Mon" format (e.g., "2023 FEB") - adjust if format differs
+                        df["date"] = pd.to_datetime(df["date"], format="%Y %b", errors="coerce")
+                    elif frequency_key == "quarters":
+                        def parse_quarter(quarter_str):
+                            try:
+                                year, qtr = quarter_str.split(" Q")
+                                month = {"1": 1, "2": 4, "3": 7, "4": 10}[qtr]
+                                return datetime(int(year), month, 1)
+                            except (ValueError, KeyError):
+                                return pd.NaT # Return Not a Time for parsing errors
+                        df["date"] = df["date"].apply(parse_quarter)
+                    elif frequency_key == "years":
+                        df["date"] = pd.to_datetime(df["date"], format="%Y", errors="coerce")
+                except Exception as e:
+                    print(f"Error parsing date for CDID {cdid} with frequency {frequency_key}: {e}")
+                    continue # Skip this series if date parsing fails
+
+                # Coerce value to numeric, handle potential errors
                 df["value"] = pd.to_numeric(df["value"], errors="coerce")
+
+                # Drop rows where date or value parsing failed
+                df.dropna(subset=["date", "value"], inplace=True)
+
+                if df.empty:
+                    print(f"Warning: No valid data points after processing for CDID: {cdid}")
+                    continue
+
                 df.rename(columns={"value": series_name}, inplace=True)
 
                 # Combine data
-                df = df.loc[:, ["date", series_name]].dropna().reset_index(drop=True)
+                df_subset = df.loc[:, ["date", series_name]].reset_index(drop=True) # Explicitly select columns
                 if combined_df.empty:
-                    combined_df = df
+                    combined_df = df_subset
                 else:
-                    combined_df = pd.merge(combined_df, df, on="date", how="outer")
+                    # Use outer merge to keep all dates, sort afterwards
+                    combined_df = pd.merge(combined_df, df_subset, on="date", how="outer")
 
             except requests.exceptions.RequestException as e:
                 print(f"Error fetching data for CDID {cdid}: {e}")
-            except (KeyError, ValueError) as e:
+            except (KeyError, ValueError, TypeError) as e: # Added TypeError
                 print(f"Error processing data for CDID {cdid}: {e}")
+            except Exception as e: # Catch unexpected errors
+                 print(f"An unexpected error occurred for CDID {cdid}: {e}")
+
 
         if not combined_df.empty:
+            # Sort by date after merging to ensure correct forward fill
+            combined_df.sort_values(by="date", inplace=True)
+            combined_df.reset_index(drop=True, inplace=True)
+
+            # Create a complete daily date range
             min_date = combined_df["date"].min()
-            max_date = datetime.today()
+            # Ensure max_date is timezone-naive if min_date is, or consistent otherwise
+            max_date = pd.Timestamp(datetime.today().date()) # Use today's date, timezone-naive
+
+            if pd.isna(min_date):
+                 print("Error: Minimum date is NaT, cannot create date range.")
+                 return pd.DataFrame()
+
+            # Make sure min_date is not NaT before creating the range
             date_range = pd.date_range(start=min_date, end=max_date, freq='D')
             daily_df = pd.DataFrame(date_range, columns=['date'])
+
+            # Merge with original data and forward fill
             daily_df = pd.merge(daily_df, combined_df, on="date", how="left")
             daily_df = daily_df.ffill()
 
+            # Drop rows before the first valid data point after ffill
+            first_valid_index = daily_df.dropna(subset=daily_df.columns.difference(['date'])).index.min()
+            if pd.notna(first_valid_index):
+                 daily_df = daily_df.loc[first_valid_index:]
+            else:
+                 print("Warning: No valid data points found after forward filling.")
+                 return pd.DataFrame() # Return empty if ffill results in no data
+
+
             # Aggregate to weekly frequency
-            daily_df["week_commencing"] = daily_df["date"] - pd.to_timedelta((daily_df["date"].dt.weekday - week_start) % 7, unit='D')
+            # Ensure 'date' column is datetime type before dt accessor
+            daily_df['date'] = pd.to_datetime(daily_df['date'])
+            daily_df["week_commencing"] = daily_df["date"] - pd.to_timedelta((daily_df["date"].dt.weekday - week_start + 7) % 7, unit='D') # Corrected logic for week start
+            # Group by week_commencing and calculate mean for numeric columns only
             weekly_df = daily_df.groupby("week_commencing").mean(numeric_only=True).reset_index()
 
+
             def clean_column_name(name):
+                # Remove content within parentheses (e.g., CPI INDEX 00: ALL ITEMS 2015=100)
                 name = re.sub(r"\(.*?\)", "", name)
+                # Take only the part before the first colon if present
                 name = re.split(r":", name)[0]
-                name = re.sub(r"\d+", "", name)
+                # Remove digits
+                #name = re.sub(r"\d+", "", name) # Reconsider removing all digits, might be needed for some series
+                # Remove specific words like 'annual', 'rate' case-insensitively
                 name = re.sub(r"\b(annual|rate)\b", "", name, flags=re.IGNORECASE)
+                # Remove non-alphanumeric characters (except underscore and space)
                 name = re.sub(r"[^\w\s]", "", name)
+                # Replace spaces with underscores
+                name = name.strip() # Remove leading/trailing whitespace
                 name = name.replace(" ", "_")
+                # Replace multiple underscores with a single one
                 name = re.sub(r"_+", "_", name)
+                # Remove trailing underscores
                 name = name.rstrip("_")
+                # Add prefix and suffix
                 return f"macro_{name.lower()}_uk"
 
+            # Apply cleaning function to relevant columns
             weekly_df.columns = [clean_column_name(col) if col != "week_commencing" else col for col in weekly_df.columns]
-            weekly_df.rename(columns={"week_commencing": "OBS"}, inplace=True)
+            weekly_df.rename(columns={"week_commencing": "OBS"}, inplace=True) # Rename week commencing col
 
-            weekly_df = weekly_df.fillna(0)
+            # Optional: Fill remaining NaNs (e.g., at the beginning if ffill didn't cover) with 0
+            # Consider if 0 is the appropriate fill value for your use case
+            # weekly_df = weekly_df.fillna(0)
 
             return weekly_df
         else:
-            print("No data available to process.")
+            print("No data successfully fetched or processed.")
             return pd.DataFrame()
-
+        
     def pull_yfinance(self, tickers=None, week_start_day="mon"):
         """
         Fetches stock data for multiple tickers from Yahoo Finance, converts it to daily frequency, 
@@ -1337,7 +1443,7 @@ class datapull:
         end_date = datetime.today().strftime("%Y-%m-%d")
         
         # Mapping week start day to pandas weekday convention
-        days_map = {"mon": 0, "tue": 1, "wed": 2, "thur": 3, "fri": 4, "sat": 5, "sun": 6}
+        days_map = {"mon": 0, "tue": 1, "wed": 2, "thu": 3, "fri": 4, "sat": 5, "sun": 6}
         if week_start_day not in days_map:
             raise ValueError("Invalid week start day. Choose from: " + ", ".join(days_map.keys()))
         week_start = days_map[week_start_day]
@@ -1497,9 +1603,9 @@ class datapull:
             # Aggregate by week commencing
             day_offsets = {
                 'mon': 'W-MON',
-                'tues': 'W-TUE',
+                'tue': 'W-TUE',
                 'wed': 'W-WED',
-                'thurs': 'W-THU',
+                'thu': 'W-THU',
                 'fri': 'W-FRI',
                 'sat': 'W-SAT',
                 'sun': 'W-SUN'
@@ -1592,9 +1698,9 @@ class datapull:
             # Resample by week
             day_offsets = {
                 'mon': 'W-MON',
-                'tues': 'W-TUE',
+                'tue': 'W-TUE',
                 'wed': 'W-WED',
-                'thurs': 'W-THU',
+                'thu': 'W-THU',
                 'fri': 'W-FRI',
                 'sat': 'W-SAT',
                 'sun': 'W-SUN'

{imsciences-0.9.5.9 → imsciences-0.9.6.3}/imsciences.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.9.5.9
+Version: 0.9.6.3
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

imsciences-0.9.6.3/imsciences.egg-info/PKG-INFO-TomG-HP-290722

@@ -0,0 +1,355 @@
+Metadata-Version: 2.1
+Name: imsciences
+Version: 0.9.6.3
+Summary: IMS Data Processing Package
+Author: IMS
+Author-email: cam@im-sciences.com
+Keywords: data processing,apis,data analysis,data visualization,machine learning
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: Unix
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: Microsoft :: Windows
+Description-Content-Type: text/markdown
+License-File: LICENSE.txt
+Requires-Dist: pandas
+Requires-Dist: plotly
+Requires-Dist: numpy
+Requires-Dist: fredapi
+Requires-Dist: xgboost
+Requires-Dist: scikit-learn
+Requires-Dist: bs4
+Requires-Dist: yfinance
+Requires-Dist: holidays
+Requires-Dist: google-analytics-data
+Requires-Dist: geopandas
+Requires-Dist: geopy
+
+# IMS Package Documentation
+
+The **Independent Marketing Sciences** package is a Python library designed to process incoming data into a format tailored for projects, particularly those utilising weekly time series data. This package offers a suite of functions for efficient data collection, manipulation, visualisation and analysis.
+
+---
+
+## Key Features
+- Seamless data processing for time series workflows.
+- Aggregation, filtering, and transformation of time series data.
+- Visualising Data
+- Integration with external data sources like FRED, Bank of England and ONS.
+
+---
+
+Table of Contents
+=================
+
+1. [Usage](#usage)
+2. [Data Processing for Time Series](#data-processing-for-time-series)
+3. [Data Processing for Incrementality Testing](#data-processing-for-incrementality-testing)
+4. [Data Visualisations](#data-visualisations)
+5. [Data Pulling](#data-pulling)
+6. [Installation](#installation)
+7. [License](#license)
+8. [Roadmap](#roadmap)
+
+---
+
+## Usage 
+
+```bash
+from imsciences import dataprocessing, geoprocessing, datapull, datavis
+ims_proc = dataprocessing()
+ims_geo = geoprocessing()
+ims_pull = datapull()
+ims_vis = datavis()
+```
+
+## Data Processing for Time Series
+
+## 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. `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')`
+
+## 3. `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=True)`
+- **Example**: `convert_monthly_to_daily(df, 'date')`
+
+## 4. `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')`
+
+## 5. `rename_cols`
+- **Description**: Renames columns in a pandas DataFrame with a specified prefix or format.
+- **Usage**: `rename_cols(df, name='ame_')`
+- **Example**: `rename_cols(df, 'ame_facebook')`
+
+## 6. `merge_new_and_old`
+- **Description**: Creates a new DataFrame by merging old and new dataframes based on a cutoff date.
+- **Usage**: `merge_new_and_old(old_df, old_col, new_df, new_col, cutoff_date, date_col_name='OBS')`
+- **Example**: `merge_new_and_old(df1, 'old_col', df2, 'new_col', '2023-01-15')`
+
+## 7. `merge_dataframes_on_column`
+- **Description**: Merge a list of DataFrames on a common column.
+- **Usage**: `merge_dataframes_on_column(dataframes, common_column='OBS', merge_how='outer')`
+- **Example**: `merge_dataframes_on_column([df1, df2, df3], common_column='OBS', merge_how='outer')`
+
+## 8. `merge_and_update_dfs`
+- **Description**: Merges two dataframes, updating columns from the second dataframe where values are available.
+- **Usage**: `merge_and_update_dfs(df1, df2, key_column)`
+- **Example**: `merge_and_update_dfs(processed_facebook, finalised_meta, 'OBS')`
+
+## 9. `convert_us_to_uk_dates`
+- **Description**: Convert a DataFrame column with mixed US and UK date formats to datetime.
+- **Usage**: `convert_us_to_uk_dates(df, date_col)`
+- **Example**: `convert_us_to_uk_dates(df, 'date')`
+
+## 10. `combine_sheets`
+- **Description**: Combines multiple DataFrames from a dictionary into a single DataFrame.
+- **Usage**: `combine_sheets(all_sheets)`
+- **Example**: `combine_sheets({'Sheet1': df1, 'Sheet2': df2})`
+
+## 11. `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'}, fill_value=0)`
+
+## 12. `apply_lookup_table_for_columns`
+- **Description**: Maps substrings in columns to new values based on a dictionary.
+- **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'}, if_not_in_dict='Other', new_column_name='Metrics Short')`
+
+## 13. `aggregate_daily_to_wc_wide`
+- **Description**: Aggregates daily data into weekly data and pivots it to wide format.
+- **Usage**: `aggregate_daily_to_wc_wide(df, date_column, group_columns, sum_columns, wc='sun', aggregation='sum', include_totals=False)`
+- **Example**: `aggregate_daily_to_wc_wide(df, 'date', ['platform'], ['cost', 'impressions'], 'mon', 'average', True)`
+
+## 14. `merge_cols_with_seperator`
+- **Description**: Merges multiple columns in a DataFrame into one column with a specified separator.
+- **Usage**: `merge_cols_with_seperator(df, col_names, separator='_', output_column_name='Merged')`
+- **Example**: `merge_cols_with_seperator(df, ['Campaign', 'Product'], separator='|', output_column_name='Merged Columns')`
+
+## 15. `check_sum_of_df_cols_are_equal`
+- **Description**: Checks if the sum of two columns in two DataFrames are equal and provides the difference.
+- **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')`
+
+## 16. `convert_2_df_cols_to_dict`
+- **Description**: Creates a dictionary from two DataFrame columns.
+- **Usage**: `convert_2_df_cols_to_dict(df, key_col, value_col)`
+- **Example**: `convert_2_df_cols_to_dict(df, 'Campaign', 'Channel')`
+
+## 17. `create_FY_and_H_columns`
+- **Description**: Adds financial year and half-year columns to a DataFrame based on a start date.
+- **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', '2022-10-03', 'FY2023', short_format='Yes')`
+
+## 18. `keyword_lookup_replacement`
+- **Description**: Updates values in a column based on a lookup dictionary with conditional logic.
+- **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'], lookup_dict, output_column_name='Channel New')`
+
+## 19. `create_new_version_of_col_using_LUT`
+- **Description**: Creates a new column based on a lookup table applied to an existing column.
+- **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', lookup_dict)`
+
+## 20. `convert_df_wide_2_long`
+- **Description**: Converts a wide-format DataFrame into a long-format DataFrame.
+- **Usage**: `convert_df_wide_2_long(df, value_cols, variable_col_name='Stacked', value_col_name='Value')`
+- **Example**: `convert_df_wide_2_long(df, ['col1', 'col2'], variable_col_name='Var', value_col_name='Val')`
+
+## 21. `manually_edit_data`
+- **Description**: Manually updates specified cells in a DataFrame based on filters.
+- **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, {'col1': '== 1'}, 'col2', 'new_val', add_notes='Yes', note='Manual Update')`
+
+## 22. `format_numbers_with_commas`
+- **Description**: Formats numerical columns with commas and a specified number of decimal places.
+- **Usage**: `format_numbers_with_commas(df, decimal_length_chosen=2)`
+- **Example**: `format_numbers_with_commas(df, decimal_length_chosen=1)`
+
+## 23. `filter_df_on_multiple_conditions`
+- **Description**: Filters a DataFrame based on multiple column conditions.
+- **Usage**: `filter_df_on_multiple_conditions(df, filters_dict)`
+- **Example**: `filter_df_on_multiple_conditions(df, {'col1': '>= 5', 'col2': '== 'val''})`
+
+## 24. `read_and_concatenate_files`
+- **Description**: Reads and concatenates files from a specified folder into a single DataFrame.
+- **Usage**: `read_and_concatenate_files(folder_path, file_type='csv')`
+- **Example**: `read_and_concatenate_files('/path/to/files', file_type='xlsx')`
+
+## 25. `upgrade_outdated_packages`
+- **Description**: Upgrades all outdated Python packages except specified ones.
+- **Usage**: `upgrade_outdated_packages(exclude_packages=['twine'])`
+- **Example**: `upgrade_outdated_packages(exclude_packages=['pip', 'setuptools'])`
+
+## 26. `convert_mixed_formats_dates`
+- **Description**: Converts mixed-format date columns into standardized datetime format.
+- **Usage**: `convert_mixed_formats_dates(df, column_name)`
+- **Example**: `convert_mixed_formats_dates(df, 'date_col')`
+
+## 27. `fill_weekly_date_range`
+- **Description**: Fills in missing weekly dates in a DataFrame with a specified frequency.
+- **Usage**: `fill_weekly_date_range(df, date_column, freq='W-MON')`
+- **Example**: `fill_weekly_date_range(df, 'date_col')`
+
+## 28. `add_prefix_and_suffix`
+- **Description**: Adds prefixes and/or suffixes to column names, with an option to exclude a date column.
+- **Usage**: `add_prefix_and_suffix(df, prefix='', suffix='', date_col=None)`
+- **Example**: `add_prefix_and_suffix(df, prefix='pre_', suffix='_suf', date_col='date_col')`
+
+## 29. `create_dummies`
+- **Description**: Creates dummy variables for columns, with an option to add a total dummy column.
+- **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='date_col', dummy_threshold=1)`
+
+## 30. `replace_substrings`
+- **Description**: Replaces substrings in a column based on a dictionary, with options for case conversion and new column creation.
+- **Usage**: `replace_substrings(df, column, replacements, to_lower=False, new_column=None)`
+- **Example**: `replace_substrings(df, 'text_col', {'old': 'new'}, to_lower=True, new_column='updated_text')`
+
+## 31. `add_total_column`
+- **Description**: Adds a total column to a DataFrame by summing values across columns, optionally excluding one.
+- **Usage**: `add_total_column(df, exclude_col=None, total_col_name='Total')`
+- **Example**: `add_total_column(df, exclude_col='date_col')`
+
+## 32. `apply_lookup_table_based_on_substring`
+- **Description**: Categorizes text in a column using a lookup table based on substrings.
+- **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, 'text_col', {'sub1': 'cat1', 'sub2': 'cat2'})`
+
+## 33. `compare_overlap`
+- **Description**: Compares overlapping periods between two DataFrames and summarizes differences.
+- **Usage**: `compare_overlap(df1, df2, date_col)`
+- **Example**: `compare_overlap(df1, df2, 'date_col')`
+
+## 34. `week_commencing_2_week_commencing_conversion_isoweekday`
+- **Description**: Maps dates to the start of the current ISO week based on a specified weekday.
+- **Usage**: `week_commencing_2_week_commencing_conversion_isoweekday(df, date_col, week_commencing='mon')`
+- **Example**: `week_commencing_2_week_commencing_conversion_isoweekday(df, 'date_col', week_commencing='fri')`
+
+## 35. `seasonality_feature_extraction`
+- **Description**: Splits data into train/test sets, trains XGBoost and Random Forest on all features, extracts top features based on feature importance, merges them, optionally retrains models on top and combined features, and returns a dict of results.
+- **Usage**: `seasonality_feature_extraction(df, kpi_var, n_features=10, test_size=0.1, random_state=42, shuffle=False)`
+- **Example**: `seasonality_feature_extraction(df, 'kpi_total_sales', n_features=5, test_size=0.2, random_state=123, shuffle=True)`
+
+---
+
+## Data Processing for Incrementality Testing
+
+## 1. `pull_ga`
+- **Description**: Pull in GA4 data for geo experiments.
+- **Usage**: `pull_ga(credentials_file, property_id, start_date, country, metrics)`
+- **Example**: `pull_ga('GeoExperiment-31c5f5db2c39.json', '111111111', '2023-10-15', 'United Kingdom', ['totalUsers', 'newUsers'])`
+
+## 2. `process_itv_analysis`
+- **Description**: Processes region-level data for geo experiments by mapping ITV regions, grouping selected metrics, merging with media spend data, and saving the result.
+- **Usage**: `process_itv_analysis(self, raw_df, itv_path, cities_path, media_spend_path, output_path, test_group, control_group, columns_to_aggregate, aggregator_list)`
+- **Example**: `process_itv_analysis(df, 'itv regional mapping.csv', 'Geo_Mappings_with_Coordinates.xlsx', 'IMS.xlsx', 'itv_for_test_analysis_itvx.csv', ['West', 'Westcountry', 'Tyne Tees'], ['Central Scotland', 'North Scotland'], ['newUsers', 'transactions'], ['sum', 'sum'])`
+
+## 3. `process_city_analysis`
+- **Description**: Processes city-level data for geo experiments by grouping selected metrics, merging with media spend data, and saving the result.
+- **Usage**: `process_city_analysis(raw_df, spend_df, output_path, test_group, control_group, columns_to_aggregate, aggregator_list)`
+- **Example**: `process_city_analysis(df, spend, output, ['Barnsley'], ['Aberdeen'], ['newUsers', 'transactions'], ['sum', 'sum'])`
+
+---
+
+## Data Visualisations
+
+## 1. `plot_one`
+- **Description**: Plots a specified column from a DataFrame with white background and black axes.
+- **Usage**: `plot_one(df1, col1, date_column)`
+- **Example**: `plot_one(df, 'sales', 'date')`
+
+## 2. `plot_two`
+- **Description**: Plots specified columns from two DataFrames, optionally on the same or separate y-axes.
+- **Usage**: `plot_two(df1, col1, df2, col2, date_column, same_axis=True)`
+- **Example**: `plot_two(df1, 'sales', df2, 'revenue', 'date', same_axis=False)`
+
+## 3. `plot_chart`
+- **Description**: Plots various chart types using Plotly, including line, bar, scatter, area, pie, etc.
+- **Usage**: `plot_chart(df, date_col, value_cols, chart_type='line', title='Chart', x_title='Date', y_title='Values')`
+- **Example**: `plot_chart(df, 'date', ['sales', 'revenue'], chart_type='line', title='Sales and Revenue')`
+
+---
+
+## Data Pulling
+
+## 1. `pull_fred_data`
+- **Description**: Fetch data from FRED using series ID tokens.
+- **Usage**: `pull_fred_data(week_commencing, series_id_list)`
+- **Example**: `pull_fred_data('mon', ['GPDIC1', 'Y057RX1Q020SBEA', 'GCEC1', 'ND000333Q', 'Y006RX1Q020SBEA'])`
+
+## 2. `pull_boe_data`
+- **Description**: Fetch and process Bank of England interest rate data.
+- **Usage**: `pull_boe_data(week_commencing)`
+- **Example**: `pull_boe_data('mon')`
+
+## 3. `pull_oecd`
+- **Description**: Fetch macroeconomic data from OECD for a specified country.
+- **Usage**: `pull_oecd(country='GBR', week_commencing='mon', start_date='2020-01-01')`
+- **Example**: `pull_oecd('GBR', 'mon', '2000-01-01')`
+
+## 4. `get_google_mobility_data`
+- **Description**: Fetch Google Mobility data for the specified country.
+- **Usage**: `get_google_mobility_data(country, wc)`
+- **Example**: `get_google_mobility_data('United Kingdom', 'mon')`
+
+## 5. `pull_seasonality`
+- **Description**: Generate combined dummy variables for seasonality, trends, and COVID lockdowns.
+- **Usage**: `pull_seasonality(week_commencing, start_date, countries)`
+- **Example**: `pull_seasonality('mon', '2020-01-01', ['US', 'GB'])`
+
+## 6. `pull_weather`
+- **Description**: Fetch and process historical weather data for the specified country.
+- **Usage**: `pull_weather(week_commencing, start_date, country)`
+- **Example**: `pull_weather('mon', '2020-01-01', 'GBR')`
+
+## 7. `pull_macro_ons_uk`
+- **Description**: Fetch and process time series data from the Beta ONS API.
+- **Usage**: `pull_macro_ons_uk(additional_list, week_commencing, sector)`
+- **Example**: `pull_macro_ons_uk(['HBOI'], 'mon', 'fast_food')`
+
+## 8. `pull_yfinance`
+- **Description**: Fetch and process time series data from Yahoo Finance.
+- **Usage**: `pull_yfinance(tickers, week_start_day)`
+- **Example**: `pull_yfinance(['^FTMC', '^IXIC'], 'mon')`
+
+## 9. `pull_sports_events`
+- **Description**: Pull a veriety of sports events primaraly football and rugby.
+- **Usage**: `pull_sports_events(start_date, week_commencing)`
+- **Example**: `pull_sports_events('2020-01-01', 'mon')`
+
+---
+
+## Installation
+
+Install the IMS package via pip:
+
+```bash
+pip install imsciences
+```
+
+---
+
+## License
+
+This project is licensed under the MIT License. ![License](https://img.shields.io/badge/license-MIT-blue.svg)
+
+---
+
+## Roadmap
+
+- [Fixes]: Naming conventions are inconsistent/ have changed from previous seasonality tools (eg. 'seas_nyd' is named 'seas_new_years_day', 'week_1' is named 'seas_1')
+- [Fixes]: Naming conventions can be inconsistent within the data pull (suffix on some var is 'gb' on some it is 'uk' and for others there is no suffix) - furthermore, there is a lack of consistency for global holidays/events (Christmas, Easter, Halloween, etc) - some have regional suffix and others don't.
+- [Additions]: Need to add new data pulls for more macro and seasonal varibles
+
+---

{imsciences-0.9.5.9 → imsciences-0.9.6.3}/imsciences.egg-info/SOURCES.txt

@@ -8,7 +8,7 @@ imsciences/pull.py
 imsciences/unittesting.py
 imsciences/vis.py
 imsciences.egg-info/PKG-INFO
-imsciences.egg-info/PKG-INFO-IMS-24Ltp-3
+imsciences.egg-info/PKG-INFO-TomG-HP-290722
 imsciences.egg-info/SOURCES.txt
 imsciences.egg-info/dependency_links.txt
 imsciences.egg-info/requires.txt

{imsciences-0.9.5.9 → imsciences-0.9.6.3}/setup.py

@@ -8,7 +8,7 @@ def read_md(file_name):
             return f.read()
     return ''
 
-VERSION = '0.9.5.9'
+VERSION = '0.9.6.3'
 DESCRIPTION = 'IMS Data Processing Package'
 LONG_DESCRIPTION = read_md('README.md') 
 
@@ -34,5 +34,5 @@ setup(
         "Operating System :: Unix",
         "Operating System :: MacOS :: MacOS X",
         "Operating System :: Microsoft :: Windows",
-    ]
+    ],
 )

imsciences-0.9.5.9/imsciences.egg-info/PKG-INFO-IMS-24Ltp-3

@@ -1,24 +0,0 @@
-Metadata-Version: 2.1
-Name: imsciences
-Version: 0.6.1.1
-Summary: IMS Data Processing Package
-Author: IMS
-Author-email: cam@im-sciences.com
-Keywords: python,data processing
-Classifier: Development Status :: 3 - Alpha
-Classifier: Intended Audience :: Developers
-Classifier: Programming Language :: Python :: 3
-Classifier: Operating System :: Unix
-Classifier: Operating System :: MacOS :: MacOS X
-Classifier: Operating System :: Microsoft :: Windows
-Description-Content-Type: text/markdown
-Requires-Dist: pandas
-
-# IMS Package Documentation
-
-The IMS package is a python library for processing incoming data into a format that can be used for projects. IMS processing offers a variety of functions to manipulate and analyze data efficiently. Here are the functionalities provided by the package:
-
-## Data Processing
-
-## Data Pulling
-