imsciences 0.6.3.2__py3-none-any.whl → 0.8__py3-none-any.whl

imsciences/__init__.py

@@ -1,3 +1,2 @@
 from .datafunctions import dataprocessing
 from .datafunctions import datapull
-from .unittesting import TestDataProcessor

imsciences/datafunctions.py

@@ -4,21 +4,18 @@ import os
 import plotly.express as px
 import plotly.graph_objs as go
 import numpy as np
-import datetime
 import re
 from fredapi import Fred
 import time
-from datetime import datetime, timedelta  # noqa: F811
+from datetime import datetime, timedelta
 from io import StringIO
-import urllib
-import requests_cache  # noqa: F401
-import urllib.request  # noqa: F401
 import requests
-from geopy.geocoders import Nominatim  # noqa: F401
 import subprocess
 import json
 import xml.etree.ElementTree as ET
 from bs4 import BeautifulSoup
+import yfinance as yf
+import holidays
 
 class dataprocessing:
     
@@ -1767,17 +1764,6 @@ class dataprocessing:
 ########################################################################################################################################
 ########################################################################################################################################
 
-
-
-
-
-
-
-
-
-
-
-    
 ims_proc = dataprocessing()
     
 class datapull:
@@ -1788,38 +1774,43 @@ class datapull:
         print("\n1. pull_fred_data")
         print("   - Description: Get data from FRED by using series id tokens.")
         print("   - Usage: pull_fred_data(week_commencing, series_id_list)")
-        print("   - Example: pull_fred_data('mon', ['GPDIC1', 'Y057RX1Q020SBEA', 'GCEC1', 'ND000333Q', 'Y006RX1Q020SBEA'])")
+        print("   - Example: pull_fred_data('mon', ['GPDIC1'])")
 
         print("\n2. pull_boe_data")
         print("   - Description: Fetch and process Bank of England interest rate data.")
         print("   - Usage: pull_boe_data(week_commencing)")
         print("   - Example: pull_boe_data('mon')")
 
-        print("\n3. pull_ons_data")
-        print("   - Description: Fetch and process time series data from the ONS API.")
-        print("   - Usage: pull_ons_data(series_list, week_commencing)")
-        print("   - Example: pull_ons_data([{'series_id': 'LMSBSA', 'dataset_id': 'LMS'}], 'mon')")
-
-        print("\n4. pull_oecd")
+        print("\n3. pull_oecd")
         print("   - Description: Fetch macroeconomic data from OECD for a specified country.")
-        print("   - Usage: pull_oecd(country='GBR', week_commencing='mon', start_date: '1950-01-01')")
-        print("   - Example: pull_oecd('GBR', 'mon', '1950-01-01')")
+        print("   - Usage: pull_oecd(country='GBR', week_commencing='mon', start_date: '2020-01-01')")
+        print("   - Example: pull_oecd('GBR', 'mon', '2000-01-01')")
 
-        print("\n5. get_google_mobility_data")
+        print("\n4. get_google_mobility_data")
         print("   - Description: Fetch Google Mobility data for the specified country.")
         print("   - Usage: get_google_mobility_data(country, wc)")
         print("   - Example: get_google_mobility_data('United Kingdom', 'mon')")
 
-        print("\n6. pull_combined_dummies")
+        print("\n5. pull_seasonality")
         print("   - Description: Generate combined dummy variables for seasonality, trends, and COVID lockdowns.")
-        print("   - Usage: pull_combined_dummies(week_commencing)")
-        print("   - Example: pull_combined_dummies('mon')")
+        print("   - Usage: pull_seasonality(week_commencing, start_date, countries)")
+        print("   - Example: pull_seasonality('mon', '2020-01-01', ['US', 'GB'])")
 
-        print("\n7. pull_weather")
+        print("\n6. pull_weather")
         print("   - Description: Fetch and process historical weather data for the specified country.")
         print("   - Usage: pull_weather(week_commencing, country)")
         print("   - Example: pull_weather('mon', 'GBR')")
-    
+        
+        print("\n7. pull_macro_ons_uk")
+        print("   - Description: Fetch and process time series data from the Beta ONS API.")
+        print("   - Usage: pull_macro_ons_uk(aditional_list, week_commencing, sector)")
+        print("   - Example: pull_macro_ons_uk(['HBOI'], 'mon', 'fast_food')")
+        
+        print("\n8. pull_yfinance")
+        print("   - Description: Fetch and process time series data from the Beta ONS API.")
+        print("   - Usage: pull_yfinance(tickers, week_start_day)")
+        print("   - Example: pull_yfinance(['^FTMC', '^IXIC'], 'mon')")
+
     ###############################################################  MACRO ##########################################################################
 
     def pull_fred_data(self, week_commencing: str = 'mon', series_id_list: list[str] = ["GPDIC1", "Y057RX1Q020SBEA", "GCEC1"]) -> pd.DataFrame:
@@ -1837,10 +1828,6 @@ class datapull:
         ----------
         pd.DataFrame
             Return a data frame with FRED data according to the series IDs provided
-
-        Example
-        ----------
-        pull_fred_data("mon", ["GCEC1", "SP500"])
         '''
         # Fred API
         fred = Fred(api_key='76f5f8156145fdb8fbaf66f1eb944f8a')
@@ -1958,107 +1945,7 @@ class datapull:
 
         return df_final
     
-    def pull_ons_data(self, series_list, week_commencing):
-        """
-        Fetch and process time series data from the ONS API.
-
-        Args:
-            series_list (list): A list of dictionaries where each dictionary represents a time series.
-                                Each dictionary should have the keys 'series_id' and 'dataset_id'.
-            week_commencing (str): The starting day of the week for aggregation. 
-                                Options are "mon", "tue", "wed", "thur", "fri", "sat", "sun".
-
-        Returns:
-            pd.DataFrame: A DataFrame with weekly aggregated ONS data. The 'OBS' column contains the week 
-                        commencing dates and other columns contain the aggregated time series values.
-        """ 
-        
-        def parse_quarter(date_str):
-            """Parses a string in 'YYYY Q#' format into a datetime object."""
-            year, quarter = date_str.split(' ')
-            quarter_number = int(quarter[1])
-            month = (quarter_number - 1) * 3 + 1
-            return pd.Timestamp(f"{year}-{month:02d}-01")
-
-        # Generate a date range from 1950-01-01 to today
-        date_range = pd.date_range(start="1950-01-01", end=datetime.today(), freq='D')
-        daily_df = pd.DataFrame(date_range, columns=['OBS'])
-        
-        # Keep track of the renamed value columns
-        value_columns = []
-
-        for series in series_list:
-            series_id = series['series_id']
-            dataset_id = series['dataset_id']
-            
-            # Construct the URL for data
-            data_url = f"https://api.ons.gov.uk/timeseries/{series_id}/dataset/{dataset_id}/data"
-            
-            # Make the request to the ONS API for data
-            data_response = requests.get(data_url)
-            
-            # Check if the request was successful
-            if data_response.status_code != 200:
-                print(f"Failed to fetch data for series {series_id}: {data_response.status_code} {data_response.text}")
-                continue
-            
-            # Parse the JSON response for data
-            data = data_response.json()
-            
-            # Attempt to extract the name of the time series from the data response
-            series_name = data.get('description', {}).get('title', 'Value')
-            
-            # Determine the most granular time series data available
-            if 'months' in data and data['months']:
-                time_series_data = data['months']
-            elif 'quarters' in data and data['quarters']:
-                time_series_data = data['quarters']
-            elif 'years' in data and data['years']:
-                time_series_data = data['years']
-            else:
-                print("No time series data found in the response")
-                continue
-            
-            # Create a DataFrame from the time series data
-            df = pd.DataFrame(time_series_data)
-            
-            # Handle different frequencies in the data
-            if 'date' in df.columns:
-                if any(df['date'].str.contains('Q')):  
-                    df['date'] = df['date'].apply(parse_quarter)
-                else:  
-                    df['date'] = pd.to_datetime(df['date'])
-            
-            df = df.rename(columns={'date': 'OBS', 'value': series_name})
-            
-            # Rename the value column
-            new_col_name = 'macro_' + series_name.lower().replace(':', '').replace(' ', '_').replace('-', '_')
-            df = df.rename(columns={series_name: new_col_name})
-            
-            # Track the renamed value column
-            value_columns.append(new_col_name)
-            
-            # Merge the data based on the observation date
-            daily_df = pd.merge_asof(daily_df, df[['OBS', new_col_name]], on='OBS', direction='backward')
-                
-        # Ensure columns are numeric
-        for col in value_columns:
-            if col in daily_df.columns:
-                daily_df[col] = pd.to_numeric(daily_df[col], errors='coerce').fillna(0)
-            else:
-                print(f"Column {col} not found in daily_df")
-        
-        # Aggregate results by week
-        ons_df_final = ims_proc.aggregate_daily_to_wc_wide(df=daily_df, 
-                                                    date_column="OBS", 
-                                                    group_columns=[], 
-                                                    sum_columns=value_columns,
-                                                    wc=week_commencing,
-                                                    aggregation="average")
-        
-        return ons_df_final
-    
-    def pull_oecd(self, country: str = "GBR", week_commencing: str = "mon", start_date: str = "1950-01-01") -> pd.DataFrame:
+    def pull_oecd(self, country: str = "GBR", week_commencing: str = "mon", start_date: str = "2020-01-01") -> pd.DataFrame:
         """
         Fetch and process time series data from the OECD API.
 
@@ -2235,12 +2122,12 @@ class datapull:
         
     ###############################################################  Seasonality  ##########################################################################
 
-    def pull_combined_dummies(self, week_commencing):
+    def pull_seasonality(self, week_commencing, start_date, countries):
         # Week commencing dictionary
         day_dict = {"mon": 0, "tue": 1, "wed": 2, "thur": 3, "fri": 4, "sat": 5, "sun": 6}
         
-        # Create daily date range dataframe
-        date_range = pd.date_range(datetime(2015, 1, 1), datetime.today(), freq="d")
+        # 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")
         df_daily = pd.DataFrame(date_range, columns=["Date"])
 
         # Create weekly date range dataframe
@@ -2250,7 +2137,7 @@ class datapull:
         
         df_weekly_start.index = np.arange(1, len(df_weekly_start) + 1)
         df_weekly_start.set_index("Date", inplace=True)
-        
+
         # Create individual weekly dummies
         dummy_columns = {}
         for i in range(len(df_weekly_start)):
@@ -2260,84 +2147,59 @@ 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)
-        
-        # Create monthly dummies
+
+        # Add public holidays for each country and holiday type
+        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():
+                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
+
+        # 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)
+
+        # 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"])
+        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)
-        df_monthly_dummies = df_monthly_dummies / 7
-        
-        # Combine weekly and monthly dataframes
-        df_combined = pd.concat([df_weekly_start, df_monthly_dummies], axis=1)
-        
+
+        # 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_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
+
+        # Drop duplicate columns if any exist (this ensures holidays are not duplicated)
+        df_combined = df_combined.loc[:, ~df_combined.columns.duplicated()]
+
         # Create weekly dummies
         df_combined.reset_index(inplace=True)
         df_combined["Week"] = df_combined["Date"].dt.isocalendar().week
-        df_combined = pd.get_dummies(df_combined, prefix="wk", columns=["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"])
+        df_combined = pd.get_dummies(df_combined, prefix="seas", columns=["Year"], dtype=int)
         
         # Add constant
         df_combined["Constant"] = 1
         
         # Add trend
         df_combined["Trend"] = df_combined.index + 1
-        
-        # Set date as index
-        df_combined.set_index("Date", inplace=True)
-        
-        # Create COVID lockdown dummies
-        lockdown_periods = [
-            # Lockdown 1
-            ("2020-03-23", "2020-05-24"),
-            # Lockdown 2
-            ("2020-11-05", "2020-12-02"),
-            # Lockdown 3
-            ("2021-01-04", "2021-03-08")
-        ]
-        
-        df_covid = pd.DataFrame(date_range, columns=["Date"])
-        df_covid["national_lockdown"] = 0
-        
-        for start, end in lockdown_periods:
-            df_covid.loc[(df_covid["Date"] >= start) & (df_covid["Date"] <= end), "national_lockdown"] = 1
-        
-        df_covid['week_start'] = df_covid["Date"].apply(lambda x: x - pd.Timedelta(days=(x.weekday() - day_dict[week_commencing]) % 7))
-        df_covid.drop("Date", axis=1, inplace=True)
-        df_covid.rename(columns={"week_start": "OBS"}, inplace=True)
-        df_national_lockdown_total = df_covid.groupby('OBS').sum(numeric_only=True)
-        df_national_lockdown_total.rename(columns={"national_lockdown": "covid_uk_national_lockdown_total"}, inplace=True)
-        
-        df_national_lockdown_1 = df_national_lockdown_total.copy(deep=True)
-        df_national_lockdown_2 = df_national_lockdown_total.copy(deep=True)
-        df_national_lockdown_3 = df_national_lockdown_total.copy(deep=True)
-
-        df_national_lockdown_1.loc[df_national_lockdown_1.index > "2020-05-24"] = 0
-        df_national_lockdown_1.rename(columns={"covid_uk_national_lockdown_total": "covid_uk_national_lockdown_1"}, inplace=True)
 
-        df_national_lockdown_2.loc[df_national_lockdown_2.index < "2020-11-05"] = 0
-        df_national_lockdown_2.loc[df_national_lockdown_2.index > "2020-12-02"] = 0                          
-        df_national_lockdown_2.rename(columns={"covid_uk_national_lockdown_total": "covid_uk_national_lockdown_2"}, inplace=True)
-
-        df_national_lockdown_3.loc[df_national_lockdown_3.index < "2021-01-04"] = 0
-        df_national_lockdown_3.rename(columns={"covid_uk_national_lockdown_total": "covid_uk_national_lockdown_3"}, inplace=True)
-
-        df_final_covid = pd.concat([df_national_lockdown_total, df_national_lockdown_1, df_national_lockdown_2, df_national_lockdown_3], axis=1)
-        df_final_covid.reset_index(inplace=True)
-        df_final_covid.rename(columns={"index": "OBS"}, inplace=True)
-        
         # Create seasonal indicators for the last day and last Friday of the month
-        min_date = '2019-12-29'
-        max_date = datetime.today().strftime('%Y-%m-%d')
-        date_range_seas = pd.date_range(start=min_date, end=max_date)
-        
-        df_seas = pd.DataFrame(date_range_seas, columns=['Date'])
-        df_seas['Last_Day_of_Month'] = df_seas['Date'].apply(lambda x: 1 if x == x.to_period('M').to_timestamp('M') else 0)
+        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')
@@ -2349,21 +2211,12 @@ class datapull:
             last_friday = last_day_of_month - pd.Timedelta(days=days_to_subtract)
             return 1 if date == last_friday else 0
         
-        df_seas['Last_Friday_of_Month'] = df_seas['Date'].apply(is_last_friday)
+        df_combined['seas_last_friday_of_month'] = df_combined["Date"].apply(is_last_friday)
         
-        df_seas['week_start'] = df_seas["Date"].apply(lambda x: x - pd.Timedelta(days=(x.weekday() - day_dict[week_commencing]) % 7))
-        df_seas = df_seas.groupby('week_start').sum(numeric_only=True).reset_index().rename(columns={'week_start': "Date"})
-        df_seas.set_index("Date", inplace=True)
+        # Rename Date to OBS
+        df_combined.rename(columns={"Date": "OBS"}, inplace=True)
         
-        # Combine all dataframes
-        df_combined = df_combined.reset_index().rename(columns={"Date": "OBS"})
-        df_final_combined = pd.merge(df_combined, df_final_covid, how='left', left_on='OBS', right_on='OBS')
-        df_final_combined = pd.merge(df_final_combined, df_seas, how='left', left_on='OBS', right_on='Date')
-
-        # Fill any NaN values with 0
-        df_final_combined.fillna(0, inplace=True)
-        
-        return df_final_combined
+        return df_combined
     
     def pull_weather(self, week_commencing, country) -> pd.DataFrame:
         import pandas as pd
@@ -2966,4 +2819,240 @@ class datapull:
 
         final_weather = ims_proc.rename_cols(merged_df, 'seas_')
 
-        return final_weather
+        return final_weather
+    
+    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, 
+        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').
+
+        Returns:
+            pd.DataFrame: A DataFrame with weekly frequency, containing a 'week_commencing' column 
+                        and all series as renamed columns.
+        """
+        # Define CDIDs for sectors and defaults
+        sector_cdids = {
+            "fast_food": ["L7TD", "L78Q", "DOAD"],
+            "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
+
+        # Combine standard CDIDs and additional CDIDs
+        if cdid_list is None:
+            cdid_list = []
+        cdid_list = list(set(standard_cdids + cdid_list))  # Avoid duplicates
+
+        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:
+            raise ValueError("Invalid week start day. Choose from: " + ", ".join(days_map.keys()))
+        week_start = days_map[week_start_day]
+
+        for cdid in cdid_list:
+            try:
+                # Search for the series
+                search_url = f"{base_search_url}{cdid}"
+                search_response = requests.get(search_url)
+                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}")
+                    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
+                )
+
+                # Fetch the dataset
+                data_url = f"{base_data_url}{latest_uri}"
+                data_response = requests.get(data_url)
+                data_response.raise_for_status()
+                data_json = data_response.json()
+
+                # Detect the frequency and process accordingly
+                if "months" in data_json and data_json["months"]:
+                    frequency_key = "months"
+                elif "quarters" in data_json and data_json["quarters"]:
+                    frequency_key = "quarters"
+                elif "years" in data_json and data_json["years"]:
+                    frequency_key = "years"
+                else:
+                    print(f"Unsupported frequency or no data for CDID: {cdid}")
+                    continue
+
+                # Prepare the DataFrame
+                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")
+
+                df["value"] = pd.to_numeric(df["value"], errors="coerce")
+                df.rename(columns={"value": series_name}, inplace=True)
+
+                # Combine data
+                df = df.loc[:, ["date", series_name]].dropna().reset_index(drop=True)
+                if combined_df.empty:
+                    combined_df = df
+                else:
+                    combined_df = pd.merge(combined_df, df, on="date", how="outer")
+
+            except requests.exceptions.RequestException as e:
+                print(f"Error fetching data for CDID {cdid}: {e}")
+            except (KeyError, ValueError) as e:
+                print(f"Error processing data for CDID {cdid}: {e}")
+
+        if not combined_df.empty:
+            min_date = combined_df["date"].min()
+            max_date = datetime.today()
+            date_range = pd.date_range(start=min_date, end=max_date, freq='D')
+            daily_df = pd.DataFrame(date_range, columns=['date'])
+            daily_df = pd.merge(daily_df, combined_df, on="date", how="left")
+            daily_df = daily_df.ffill()
+
+            # Aggregate to weekly frequency
+            daily_df["week_commencing"] = daily_df["date"] - pd.to_timedelta((daily_df["date"].dt.weekday - week_start) % 7, unit='D')
+            weekly_df = daily_df.groupby("week_commencing").mean(numeric_only=True).reset_index()
+
+            def clean_column_name(name):
+                name = re.sub(r"\(.*?\)", "", name)
+                name = re.split(r":", name)[0]
+                name = re.sub(r"\d+", "", name)
+                name = re.sub(r"\b(annual|rate)\b", "", name, flags=re.IGNORECASE)
+                name = re.sub(r"[^\w\s]", "", name)
+                name = name.replace(" ", "_")
+                name = re.sub(r"_+", "_", name)
+                name = name.rstrip("_")
+                return f"macro_{name.lower()}_uk"
+
+            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 = weekly_df.fillna(0)
+
+            return weekly_df
+        else:
+            print("No data available to process.")
+            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, 
+        aggregates it to weekly averages, and renames variables.
+
+        Parameters:
+            tickers (list): A list of additional stock tickers to fetch (e.g., ['AAPL', 'MSFT']). Defaults to None.
+            week_start_day (str): The day the week starts on (e.g., 'Monday', 'Sunday').
+
+        Returns:
+            pd.DataFrame: A DataFrame with weekly frequency, containing an 'OBS' column 
+                        and aggregated stock data for the specified tickers, with NaN values filled with 0.
+        """
+        # Define default tickers
+        default_tickers = ["^FTSE", "GBPUSD=X", "GBPEUR=X", "^GSPC"]
+
+        # Combine default tickers with additional ones
+        if tickers is None:
+            tickers = []
+        tickers = list(set(default_tickers + tickers))  # Ensure no duplicates
+
+        # Automatically set end_date to today
+        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}
+        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]
+
+        # Fetch data for all tickers without specifying a start date to get all available data
+        data = yf.download(tickers, end=end_date, group_by="ticker", auto_adjust=True)
+        
+        # Process the data
+        combined_df = pd.DataFrame()
+        for ticker in tickers:
+            try:
+                # Extract the ticker's data
+                ticker_data = data[ticker] if len(tickers) > 1 else data
+                ticker_data = ticker_data.reset_index()
+
+                # Ensure necessary columns are present
+                if "Close" not in ticker_data.columns:
+                    raise ValueError(f"Ticker {ticker} does not have 'Close' price data.")
+                
+                # Keep only relevant columns
+                ticker_data = ticker_data[["Date", "Close"]]
+                ticker_data.rename(columns={"Close": ticker}, inplace=True)
+
+                # Merge data
+                if combined_df.empty:
+                    combined_df = ticker_data
+                else:
+                    combined_df = pd.merge(combined_df, ticker_data, on="Date", how="outer")
+
+            except KeyError:
+                print(f"Data for ticker {ticker} not available.")
+            except Exception as e:
+                print(f"Error processing ticker {ticker}: {e}")
+
+        if not combined_df.empty:
+            # Convert to daily frequency
+            combined_df["Date"] = pd.to_datetime(combined_df["Date"])
+            combined_df.set_index("Date", inplace=True)
+
+            # Fill missing dates
+            min_date = combined_df.index.min()
+            max_date = combined_df.index.max()
+            daily_index = pd.date_range(start=min_date, end=max_date, freq='D')
+            combined_df = combined_df.reindex(daily_index)
+            combined_df.index.name = "Date"
+            combined_df = combined_df.ffill()
+
+            # Aggregate to weekly frequency
+            combined_df["OBS"] = combined_df.index - pd.to_timedelta((combined_df.index.weekday - week_start) % 7, unit="D")
+            weekly_df = combined_df.groupby("OBS").mean(numeric_only=True).reset_index()
+
+            # Fill NaN values with 0
+            weekly_df = weekly_df.fillna(0)
+
+            # Clean column names
+            def clean_column_name(name):
+                name = re.sub(r"[^\w\s]", "", name)
+                return f"macro_{name.lower()}"
+
+            weekly_df.columns = [clean_column_name(col) if col != "OBS" else col for col in weekly_df.columns]
+
+            return weekly_df
+
+        else:
+            print("No data available to process.")
+            return pd.DataFrame()

{imsciences-0.6.3.2.dist-info → imsciences-0.8.dist-info}/METADATA

@@ -1,10 +1,9 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.6.3.2
+Version: 0.8
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com
-License: MIT
 Keywords: python,data processing,apis
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
@@ -20,14 +19,34 @@ Requires-Dist: fredapi
 Requires-Dist: requests-cache
 Requires-Dist: geopy
 Requires-Dist: bs4
+Requires-Dist: yfinance
+Requires-Dist: holidays
 
 # IMS Package Documentation
 
-The IMS package is a python library for processing incoming data into a format that can be used for specifically for econometrics projects that use weekly timeseries data. IMS processing offers a variety of functions to manipulate and analyze data efficiently. Here are the functionalities provided by the package:
+The **IMSciences package** is a Python library designed to process incoming data into a format tailored for econometrics projects, particularly those utilising weekly time series data. This package offers a suite of functions for efficient data manipulation and analysis.
+
+---
+
+## Key Features
+- Seamless data processing for econometrics workflows.
+- Aggregation, filtering, and transformation of time series data.
+- Integration with external data sources like FRED, Bank of England, ONS and OECD.
+
+---
+
+## Table of Contents
+
+1. [Data Processing](#data-processing)
+2. [Data Pulling](#data-pulling)
+3. [Installation](#installation)
+4. [Useage](#useage)
+5. [License](#license)
+
+---
 
 ## Data Processing
 
-# Function Descriptions and Usage Examples
 
 ## 1. `get_wd_levels`
 - **Description**: Get the working directory with the option of moving up parents.
@@ -333,51 +352,82 @@ The IMS package is a python library for processing incoming data into a format t
 
 ## Data Pulling
 
-## 1. `pull_fred_data`
+## 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'])`
+- **Usage**: pull_fred_data(week_commencing, series_id_list)
+- **Example**: pull_fred_data('mon', ['GPDIC1', 'Y057RX1Q020SBEA', 'GCEC1', 'ND000333Q', 'Y006RX1Q020SBEA'])
 
 ---
 
-## 2. `pull_boe_data`
+## 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_ons_data`
-- **Description**: Fetch and process time series data from the ONS API.
-- **Usage**: `pull_ons_data(series_list, week_commencing)`
-- **Example**: `pull_ons_data([{'series_id': 'LMSBSA', 'dataset_id': 'LMS'}], 'mon')`
+- **Usage**: pull_boe_data(week_commencing)
+- **Example**: pull_boe_data('mon')
 
 ---
 
-## 4. `pull_oecd`
+## 3. pull_oecd
 - **Description**: Fetch macroeconomic data from OECD for a specified country.
-- **Usage**: `pull_oecd(country='GBR', week_commencing='mon', start_date='1950-01-01')`
-- **Example**: `pull_oecd('GBR', 'mon', '1950-01-01')`
+- **Usage**: pull_oecd(country='GBR', week_commencing='mon', start_date='2020-01-01')
+- **Example**: pull_oecd('GBR', 'mon', '2000-01-01')
 
 ---
 
-## 5. `get_google_mobility_data`
+## 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')`
+- **Usage**: get_google_mobility_data(country, wc)
+- **Example**: get_google_mobility_data('United Kingdom', 'mon')
 
 ---
 
-## 6. `pull_combined_dummies`
+## 5. pull_seasonality
 - **Description**: Generate combined dummy variables for seasonality, trends, and COVID lockdowns.
-- **Usage**: `pull_combined_dummies(week_commencing)`
-- **Example**: `pull_combined_dummies('mon')`
+- **Usage**: pull_seasonality(week_commencing, start_date, countries)
+- **Example**: pull_seasonality('mon', '2020-01-01', ['US', 'GB'])
 
 ---
 
-## 7. `pull_weather`
+## 6. pull_weather
 - **Description**: Fetch and process historical weather data for the specified country.
-- **Usage**: `pull_weather(week_commencing, country)`
-- **Example**: `pull_weather('mon', 'GBR')`
+- **Usage**: pull_weather(week_commencing, country)
+- **Example**: pull_weather('mon', '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')
+
+## Installation
+
+Install the IMS package via pip:
+
+```bash
+pip install ims-package
+```
+
+---
+
+## Useage 
+
+```bash
+from imsciences import * 
+ims = dataprocessing()
+ims_pull = datapull()
+```
+
+---
+
+## License
+
+This project is licensed under the MIT License.
 
 ---

{imsciences-0.6.3.2.dist-info → imsciences-0.8.dist-info}/RECORD

@@ -1,17 +1,17 @@
 dataprocessing/__init__.py,sha256=quSwsLs6IuLoA5Rzi0ZD40xZaQudwDteF7_ai9JfTPk,32
 dataprocessing/data-processing-functions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nFydwGkvzHXf2f1Y,41
 dataprocessing/datafunctions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nFydwGkvzHXf2f1Y,41
-imsciences/__init__.py,sha256=0IwH7R_2N8vimJJo2DLzIG1hq9ddn8gB6ijlLrQemZs,122
+imsciences/__init__.py,sha256=7CfK2dMjPnBBw6I4st-20MdMlLjZULviFVXF2eMD9NI,80
 imsciences/datafunctions-IMS-24Ltp-3.py,sha256=3Snv-0iE_03StmyjtT-riOU9f4v8TaJWLoyZLJp6l8Y,141406
-imsciences/datafunctions.py,sha256=lvvodU8dZ9IN_GS7FYMuft9ZsQkD2BMIGQxLiN8GY7c,151557
+imsciences/datafunctions.py,sha256=KbZuvjJF-1gydPsb2qFlvpbVLwuG6y-lhLKt-wZ5JDI,156389
 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-0.6.3.2.dist-info/METADATA,sha256=k22-OJm6rdvDU7mubqDGW1K9Z-inek4VCQ4HdAw51cA,16981
-imsciences-0.6.3.2.dist-info/PKG-INFO-IMS-24Ltp-3,sha256=yqZbigwHjnYoqyI81PGz_AeofRFfOrwH_Vyawyef-mg,854
-imsciences-0.6.3.2.dist-info/WHEEL,sha256=ixB2d4u7mugx_bCBycvM9OzZ5yD7NmPXFRtKlORZS2Y,91
-imsciences-0.6.3.2.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
-imsciences-0.6.3.2.dist-info/RECORD,,
+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,,