imsciences 0.6.1.2__tar.gz → 0.6.1.4__tar.gz

{imsciences-0.6.1.2 → imsciences-0.6.1.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.6.1.2
+Version: 0.6.1.4
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.6.1.2 → imsciences-0.6.1.4}/imsciences/datafunctions.py

@@ -19,6 +19,7 @@ import requests
 from geopy.geocoders import Nominatim
 import subprocess
 import json
+import xml.etree.ElementTree as ET
 
 class dataprocessing:
     
@@ -1335,9 +1336,9 @@ class datapull:
         print("   - Example: pull_ons_data([{'series_id': 'LMSBSA', 'dataset_id': 'LMS'}], 'mon')")
 
         print("\n4. pull_oecd")
-        print("   - Description: Fetch macroeconomic data from OECD and other sources for a specified country.")
-        print("   - Usage: pull_macro(country='GBR', week_commencing='mon')")
-        print("   - Example: pull_macro('GBR', 'mon')")
+        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("\n5. get_google_mobility_data")
         print("   - Description: Fetch Google Mobility data for the specified country.")
@@ -1353,6 +1354,11 @@ class datapull:
         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("\n8. pull_covid_data")
+        print("   - Description: Get covid pandemic data for the country of interest.")
+        print("   - Usage: pull_covid_data(folder_path, country, week_commencing)")
+        print("   - Example: pull_covid_data('C:/Users/--username--/OneDrive/', 'GB', 'mon')")
     
     ###############################################################  MACRO ##########################################################################
 
@@ -1579,370 +1585,148 @@ class datapull:
         
         return ons_df_final
     
-    def pull_macro(self, country: str = "GBR", week_commencing: str = "mon"):
-        # Change country input to list
-        print("")
-        countries_list = [country]
+    def pull_oecd(self, country: str = "GBR", week_commencing: str = "mon", start_date: str = "1950-01-01") -> pd.DataFrame:
+        """
+        Fetch and process time series data from the OECD API.
 
-        # Check if the data wants to be inputted at any other week commencing date
-        day_dict = {"mon": 0, "tue": 1, "wed": 2, "thur": 3, "fri": 4, "sat": 5, "sun": 6}
+        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".
+            start_date (str): Dataset start date in the format "YYYY-MM-DD"
 
-        # Two useful functions for quarterly data
-        # Define a function to get quarterly data
-        def get_quarter(p_date: datetime.date) -> int:
-            return (p_date.month - 1) // 3 + 1
-
-        # Define a function to get the last day of the quarter
-        def get_last_day_of_the_quarter(p_date: datetime.date):
-            quarter = get_quarter(p_date)
-            return datetime(p_date.year + 3 * quarter // 12, 3 * quarter % 12 + 1, 1) + pd.Timedelta(days=-1)
-
-        # For the monthly data
-        data_M, subjects_M, measures_M = cif.createDataFrameFromOECD(countries=countries_list, dsname='MEI',
-                                                                    subject=['LCEAMN01', 'LCEAPR', 'CSCICP03', 'CPALTT01',
-                                                                            'LRHUTTTT', 'LORSGPRT', 'IR3TIB01',
-                                                                            'PRINTO01'],
-                                                                    measure=['IXOBSA', 'IXNSA', 'IXNB', 'STSA', 'ST', 'GPSA', 'GY'],
-                                                                    frequency='M', startDate='2015-01')
-        data_M = data_M.stack(level=[0, -1, -2]).reset_index()
-
-        data_Q, subjects_Q, measures_Q = cif.createDataFrameFromOECD(countries=countries_list, dsname='MEI',
-                                                                    subject=['LCEAMN01', 'LCEAPR', 'CSCICP03', 'CPALTT01',
-                                                                            'LRHUTTTT', 'LORSGPRT', 'IR3TIB01',
-                                                                            'PRINTO01'],
-                                                                    measure=['IXOBSA', 'IXNSA', 'IXNB', 'STSA', 'ST', 'GPSA', 'GY'],
-                                                                    frequency='Q', startDate='2015-01')
-
-        data_Q = data_Q.stack(level=[0, -1, -2]).reset_index()
-
-        # Create a data frame dictionary to store your monthly data frames
-        DataFrameDict_M = {elem: pd.DataFrame() for elem in countries_list}
-        for key in DataFrameDict_M.keys():
-            DataFrameDict_M[key] = data_M[:][data_M.country == key]
-
-        # Create a data frame dictionary to store your quarterly data frames
-        DataFrameDict_Q = {elem: pd.DataFrame() for elem in countries_list}
-        for key in DataFrameDict_Q.keys():
-            DataFrameDict_Q[key] = data_Q[:][data_Q.country == key]
-
-        # Create a monthly list of the dataframes to iterate through
-        countries_df_list_M = []
-        for i in countries_list:
-            df = pd.DataFrame(DataFrameDict_M[i])
-            df.rename(columns={0: 'Values'}, inplace=True)
-            df = pd.pivot_table(data=df, index='time', values='Values', columns=['subject', 'measure'])
-            countries_df_list_M.append(df)
-
-        # Create a quarterly list of the dataframes to iterate through
-        countries_df_list_Q = []
-        for i in countries_list:
-            df = pd.DataFrame(DataFrameDict_Q[i])
-            df.rename(columns={0: 'Values'}, inplace=True)
-            df = pd.pivot_table(data=df, index='time', values='Values', columns=['subject', 'measure'])
-            countries_df_list_Q.append(df)
-
-        combined_countries_df_list = list(zip(countries_df_list_M, countries_df_list_Q))
-
-        # Loop through and create dataframes for every country
-        for index, data in enumerate(combined_countries_df_list):
-            # Find country being extracted
-            country = countries_list[index]
-            print(country)
-
-            # For consumer confidence
-            # For countries with no data
-            if country in ['CAN', 'IND', 'NOR']:
-                Consumer_Confidence_Index_df_M = pd.DataFrame()
-                Consumer_Confidence_Index_df_Q = pd.DataFrame()
-            # For countries with quarterly data
-            elif country in []:
-                Consumer_Confidence_Index_df_Q = data[1]['CSCICP03']['IXNSA']
-                Consumer_Confidence_Index_df_Q.rename('consumer_confidence_index', inplace=True)
-                Consumer_Confidence_Index_df_M = pd.DataFrame()
-            # For countries with monthly data
-            else:
-                Consumer_Confidence_Index_df_M = data[0]['CSCICP03']['IXNSA']
-                Consumer_Confidence_Index_df_M.rename('consumer_confidence_index', inplace=True)
-                Consumer_Confidence_Index_df_Q = pd.DataFrame()
-
-            # For consumer prices for COST OF LIVING
-            # For countries with no data
-            if country in []:
-                Consumer_Price_Index_Cost_Of_Living_df_M = pd.DataFrame()
-                Consumer_Price_Index_Cost_Of_Living_df_Q = pd.DataFrame()
-            # For countries with quarterly data
-            elif country in ['AUS', 'NZL']:
-                Consumer_Price_Index_Cost_Of_Living_df_Q = data[1]['CPALTT01']['IXNB']
-                Consumer_Price_Index_Cost_Of_Living_df_Q.rename('consumer_price_index_cost_of_living', inplace=True)
-                Consumer_Price_Index_Cost_Of_Living_df_M = pd.DataFrame()
-            # For countries with monthly data
-            else:
-                Consumer_Price_Index_Cost_Of_Living_df_M = data[0]['CPALTT01']['IXNB']
-                Consumer_Price_Index_Cost_Of_Living_df_M.rename('consumer_price_index_cost_of_living', inplace=True)
-                Consumer_Price_Index_Cost_Of_Living_df_Q = pd.DataFrame()
-
-            # For consumer prices FOR INFLATION
-            # For countries with no data
-            if country in []:
-                Consumer_Price_Index_Inflation_df_M = pd.DataFrame()
-                Consumer_Price_Index_Inflation_df_Q = pd.DataFrame()
-            # For countries with quarterly data
-            elif country in ['AUS', 'NZL']:
-                Consumer_Price_Index_Inflation_df_Q = data[1]['CPALTT01']['GY']
-                Consumer_Price_Index_Inflation_df_Q.rename('consumer_price_index_inflation', inplace=True)
-                Consumer_Price_Index_Inflation_df_M = pd.DataFrame()
-            # For countries with monthly data
-            else:
-                Consumer_Price_Index_Inflation_df_M = data[0]['CPALTT01']['GY']
-                Consumer_Price_Index_Inflation_df_M.rename('consumer_price_index_inflation', inplace=True)
-                Consumer_Price_Index_Inflation_df_Q = pd.DataFrame()
-
-            # For GDP Index Smoothed
-            # For countries with no data
-            if country in ['NLD', 'CHE', 'NZL', 'SWE', 'NOR']:
-                GDP_Index_Smoothed_df_M = pd.DataFrame()
-                GDP_Index_Smoothed_df_Q = pd.DataFrame()
-            # For countries with quarterly data
-            elif country in []:
-                GDP_Index_Smoothed_df_Q = data[1]['LORSGPRT']['STSA']
-                GDP_Index_Smoothed_df_Q.rename('gdp_index_smoothed', inplace=True)
-                GDP_Index_Smoothed_df_M = pd.DataFrame()
-            # For countries with monthly data
-            else:
-                GDP_Index_Smoothed_df_M = data[0]['LORSGPRT']['STSA']
-                GDP_Index_Smoothed_df_M.rename('gdp_index_smoothed', inplace=True)
-                GDP_Index_Smoothed_df_Q = pd.DataFrame()
-
-            # For Harmonised Unemployment Index
-            # For countries with no data
-            if country in ['IND', 'CHE', 'ZAF', 'CHN']:
-                Harmonised_Unemployment_Index_df_M = pd.DataFrame()
-                Harmonised_Unemployment_Index_df_Q = pd.DataFrame()
-            # For countries with quarterly data
-            elif country in ['NZL']:
-                Harmonised_Unemployment_Index_df_Q = data[1]['LRHUTTTT']['STSA']
-                Harmonised_Unemployment_Index_df_Q.rename('harmonised_unemployment_index', inplace=True)
-                Harmonised_Unemployment_Index_df_M = pd.DataFrame()
-            # For countries with monthly data
-            else:
-                Harmonised_Unemployment_Index_df_M = data[0]['LRHUTTTT']['STSA']
-                Harmonised_Unemployment_Index_df_M.rename('harmonised_unemployment_index', inplace=True)
-                Harmonised_Unemployment_Index_df_Q = pd.DataFrame()
-
-            # For hourly earnings index manufacturing
-            # For countries with no data
-            if country in ['IND', 'CHE', 'ZAF', 'CHN']:
-                Hourly_Earnings_Index_Manufacturing_df_M = pd.DataFrame()
-                Hourly_Earnings_Index_Manufacturing_df_Q = pd.DataFrame()
-            # For countries with quarterly data
-            elif country in ['FRA', 'DEU', 'ESP', 'AUS', 'NZL', 'KOR', 'NOR']:
-                Hourly_Earnings_Index_Manufacturing_df_Q = data[1]['LCEAMN01']['IXOBSA']
-                Hourly_Earnings_Index_Manufacturing_df_Q.rename('hourly_earnings_index_manufacturing', inplace=True)
-                Hourly_Earnings_Index_Manufacturing_df_M = pd.DataFrame()
-            # For countries with monthly data
-            else:
-                Hourly_Earnings_Index_Manufacturing_df_M = data[0]['LCEAMN01']['IXOBSA']
-                Hourly_Earnings_Index_Manufacturing_df_M.rename('hourly_earnings_index_manufacturing', inplace=True)
-                Hourly_Earnings_Index_Manufacturing_df_Q = pd.DataFrame()
-
-            # For Short Term Interest Rate
-            # For countries with no data
-            if country in []:
-                Short_Term_Interest_Rate_df_M = pd.DataFrame()
-                Short_Term_Interest_Rate_df_Q = pd.DataFrame()
-            # For countries with quarterly data
-            elif country in []:
-                Short_Term_Interest_Rate_df_Q = data[1]['IR3TIB01']['ST']
-                Short_Term_Interest_Rate_df_Q.rename('short_term_interest_rate', inplace=True)
-                Short_Term_Interest_Rate_df_M = pd.DataFrame()
-            # For countries with monthly data
-            else:
-                Short_Term_Interest_Rate_df_M = data[0]['IR3TIB01']['ST']
-                Short_Term_Interest_Rate_df_M.rename('short_term_interest_rate', inplace=True)
-                Short_Term_Interest_Rate_df_Q = pd.DataFrame()
-
-            # For Industrial Product Growth on Previous Period
-            # For countries with no data
-            if country in ['ZAF', 'CHN']:
-                Industrial_Product_Growth_on_Previous_Period_df_M = pd.DataFrame()
-                Industrial_Product_Growth_on_Previous_Period_df_Q = pd.DataFrame()
-            # For countries with quarterly data
-            elif country in ['AUS', 'NZL']:
-                Industrial_Product_Growth_on_Previous_Period_df_Q = data[1]['PRINTO01']['GPSA']
-                Industrial_Product_Growth_on_Previous_Period_df_Q.rename('industrial_product_growth_on_previous_period', inplace=True)
-                Industrial_Product_Growth_on_Previous_Period_df_M = pd.DataFrame()
-            # For countries with monthly data
-            else:
-                Industrial_Product_Growth_on_Previous_Period_df_M = data[0]['PRINTO01']['GPSA']
-                Industrial_Product_Growth_on_Previous_Period_df_M.rename('industrial_product_growth_on_previous_period', inplace=True)
-                Industrial_Product_Growth_on_Previous_Period_df_Q = pd.DataFrame()
-
-            # For Industrial Production Index
-            # For countries with no data
-            if country in ['ZAF', 'CHN']:
-                Industrial_Production_Index_df_M = pd.DataFrame()
-                Industrial_Production_Index_df_Q = pd.DataFrame()
-            # For countries with quarterly data
-            elif country in ['AUS', 'NZL']:
-                Industrial_Production_Index_df_Q = data[1]['PRINTO01']['IXOBSA']
-                Industrial_Production_Index_df_Q.rename('industrial_production_index', inplace=True)
-                Industrial_Production_Index_df_M = pd.DataFrame()
-            # For countries with monthly data
-            else:
-                Industrial_Production_Index_df_M = data[0]['PRINTO01']['IXOBSA']
-                Industrial_Production_Index_df_M.rename('industrial_production_index', inplace=True)
-                Industrial_Production_Index_df_Q = pd.DataFrame()
-
-            # Create monthly macroeconomic dataframe
-            all_dfs_list_M = [Consumer_Confidence_Index_df_M,
-                            Consumer_Price_Index_Cost_Of_Living_df_M,
-                            Consumer_Price_Index_Inflation_df_M,
-                            GDP_Index_Smoothed_df_M,
-                            Harmonised_Unemployment_Index_df_M,
-                            Hourly_Earnings_Index_Manufacturing_df_M,
-                            Short_Term_Interest_Rate_df_M,
-                            Industrial_Product_Growth_on_Previous_Period_df_M,
-                            Industrial_Production_Index_df_M]
-
-            # Check if any dataframes are empty and if there are remove them
-            all_dfs_list_M = [df for df in all_dfs_list_M if not df.empty]
-            cif_Macroeconomic_df_M = pd.concat(all_dfs_list_M, axis=1)
-
-            # Create quarterly macroeconomic dataframe
-            all_dfs_list_Q = [Consumer_Confidence_Index_df_Q,
-                            Consumer_Price_Index_Cost_Of_Living_df_Q,
-                            Consumer_Price_Index_Inflation_df_Q,
-                            GDP_Index_Smoothed_df_Q,
-                            Harmonised_Unemployment_Index_df_Q,
-                            Hourly_Earnings_Index_Manufacturing_df_Q,
-                            Short_Term_Interest_Rate_df_Q,
-                            Industrial_Product_Growth_on_Previous_Period_df_Q,
-                            Industrial_Production_Index_df_Q]
-
-            # Check if any dataframes are empty and if there are remove them
-            all_dfs_list_Q = [df for df in all_dfs_list_Q if not df.empty]
-            if all_dfs_list_Q != []:
-                macroeconomic_monthly_df_Q = pd.concat(all_dfs_list_Q, axis=1)
-            else:
-                macroeconomic_monthly_df_Q = pd.DataFrame()
-
-            # For USD GBP Exchange Rate
-            # If it's the UK add this series else don't
-            if countries_list[index] == 'GBR':
-                USD_GBP_Exchange_Rate_df = pd.read_csv(
-                    'https://stats.oecd.org/SDMX-JSON/data/MEI_FIN/CCUS.' + countries_list[index] + '.M/OECD?contentType=csv')
-                USD_GBP_Exchange_Rate_df.head()
-                USD_GBP_Exchange_Rate_df_pivot = pd.pivot_table(USD_GBP_Exchange_Rate_df, values='Value', index='TIME',
-                                                                columns='Subject')
-                USD_GBP_Exchange_Rate_df_pivot_final = USD_GBP_Exchange_Rate_df_pivot.loc["2015-01":]
-                USD_GBP_Exchange_Rate_df_pivot_final.rename(
-                    columns={'Currency exchange rates, monthly average': 'usd_gbp_exchange_rate'}, inplace=True)
-
-                # Create final monthly dataframe
-                macroeconomic_monthly_df_M = pd.concat([cif_Macroeconomic_df_M, USD_GBP_Exchange_Rate_df_pivot_final], axis=1)
-            else:
-                # Create final monthly dataframe
-                macroeconomic_monthly_df_M = cif_Macroeconomic_df_M
-
-            # Create the final W/C Sunday dataframe
-            # For monthly data
-            macroeconomic_monthly_df_M['Date'] = macroeconomic_monthly_df_M.index
-            df_M = macroeconomic_monthly_df_M.set_index(pd.to_datetime(macroeconomic_monthly_df_M['Date'])).drop(columns='Date')
-            df_M.fillna(method="ffill", inplace=True)
-            df_M.reset_index(inplace=True)
-
-            daily_records = []
-            # Iterate over each row in the DataFrame
-            for _, row in df_M.iterrows():
-                # Calculate the number of days in the month
-                num_days = calendar.monthrange(row["Date"].year, row["Date"].month)[1]
-                # Create a new record for each day of the month
-                for day in range(1, num_days + 1):
-                    daily_row = row.copy()
-                    daily_row["Date"] = row["Date"].replace(day=day)
-                    daily_records.append(daily_row)
-
-            # Convert the list of daily records into a DataFrame
-            daily_df = pd.DataFrame(daily_records)
-
-            # Extend dataframe to include the current data if needed
-            datelist = pd.date_range(daily_df["Date"].iloc[-1] + pd.Timedelta(days=1), datetime.today()).tolist()
-            extended_data = np.repeat([list(daily_df.iloc[-1, 1:].values)], len(datelist), axis=0)
-            q = pd.Series(datelist, name="Date")
-            s = pd.DataFrame(extended_data, columns=list(df_M.columns[1:]))
-            extended_daily_df = pd.concat([q, s], axis=1)
-            extended_daily_df = pd.concat([daily_df, extended_daily_df], ignore_index=False)
-
-            # Create a week commencing column
-            extended_daily_df["Date"] = pd.to_datetime(extended_daily_df["Date"], format='%d %b %Y')
-            extended_daily_df['week_start'] = extended_daily_df["Date"].apply(
-                lambda x: x - pd.Timedelta(days=(x.weekday() - day_dict[week_commencing]) % 7))
-            extended_daily_df.drop("Date", axis=1, inplace=True)
-            extended_daily_df.rename(columns={'week_start': "Date"}, inplace=True)
-
-            # Take a weekly average
-            macroeconomic_weekly_df_M = extended_daily_df.groupby('Date').mean()
-
-            # For quarterly data
-            # If there are quarterly datasets
-            if all_dfs_list_Q != []:
-                macroeconomic_monthly_df_Q['Date'] = macroeconomic_monthly_df_Q.index
-                df_Q = macroeconomic_monthly_df_Q.set_index(pd.to_datetime(macroeconomic_monthly_df_Q['Date'])).drop(
-                    columns='Date')
-                df_Q.fillna(method="ffill", inplace=True)
-                df_Q.reset_index(inplace=True)
-
-                daily_records = []
-                for _, row in df_Q.iterrows():
-                    year = row["Date"].year
-                    month = row["Date"].month
-                    day = row["Date"].day
-                    last_date = get_last_day_of_the_quarter(datetime(year, month, day).date())
-                    all_days = pd.date_range(row["Date"], last_date, freq="D")
-
-                    # Create a new record for each day of the quarter
-                    for day in all_days:
-                        daily_row = row.copy()
-                        daily_row["Date"] = row["Date"].replace(day=day.day, month=day.month)
-                        daily_records.append(daily_row)
-
-                # Convert the list of daily records into a DataFrame
-                daily_df = pd.DataFrame(daily_records)
-
-                # Extend dataframe to include data up to today
-                datelist = pd.date_range(daily_df["Date"].iloc[-1] + pd.Timedelta(days=1), datetime.today()).tolist()
-                extended_data = np.repeat([list(daily_df.iloc[-1, 1:].values)], len(datelist), axis=0)
-                q = pd.Series(datelist, name="Date")
-                s = pd.DataFrame(extended_data, columns=list(df_Q.columns[1:]))
-                extended_daily_df = pd.concat([q, s], axis=1)
-                extended_daily_df = pd.concat([daily_df, extended_daily_df], ignore_index=False)
-
-                # Create a week commencing column
-                extended_daily_df["Date"] = pd.to_datetime(extended_daily_df["Date"], format='%d %b %Y')
-                extended_daily_df['week_start'] = extended_daily_df["Date"].apply(
-                    lambda x: x - pd.Timedelta(days=(x.weekday() - day_dict[week_commencing]) % 7))
-                extended_daily_df.drop("Date", axis=1, inplace=True)
-                extended_daily_df.rename(columns={'week_start': "Date"}, inplace=True)
-
-                # Take a weekly average
-                macroeconomic_weekly_df_Q = extended_daily_df.groupby('Date').mean()
-
-            # Merge the two datasets together
-            if all_dfs_list_Q != []:
-                macroeconomic_weekly_df = macroeconomic_weekly_df_M.merge(macroeconomic_weekly_df_Q, left_index=True,
-                                                                        right_index=True)
-            # If there are no quarterly datasets
+        Returns:
+            pd.DataFrame: A DataFrame with weekly aggregated OECD 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=start_date, end=datetime.today(), freq='D')
+
+        url_details = [
+            ["BCICP",    "SDD.STES,DSD_STES@DF_CLI,",                       ".....",              "macro_business_confidence_index"],
+            ["CCICP",    "SDD.STES,DSD_STES@DF_CLI,",                       ".....",              "macro_consumer_confidence_index"],
+            ["N.CPI",    "SDD.TPS,DSD_PRICES@DF_PRICES_ALL,",               "PA._T.N.GY",         "macro_cpi_total"],        
+            ["N.CPI",    "SDD.TPS,DSD_PRICES@DF_PRICES_ALL,",               "PA.CP041T043.N.GY",  "macro_cpi_housing"],
+            ["N.CPI",    "SDD.TPS,DSD_PRICES@DF_PRICES_ALL,",               "PA.CP01.N.GY",       "macro_cpi_food"],
+            ["N.CPI",    "SDD.TPS,DSD_PRICES@DF_PRICES_ALL,",               "PA.CP045_0722.N.GY", "macro_cpi_energy"],
+            ["UNE_LF_M", "SDD.TPS,DSD_LFS@DF_IALFS_UNE_M,",                 "._Z.Y._T.Y_GE15.",   "macro_unemployment_rate"],
+            ["EAR",      "SDD.TPS,DSD_EAR@DF_HOU_EAR,",                     ".Y..S1D",            "macro_private_hourly_earnings"],
+            ["RHP",      "ECO.MPD,DSD_AN_HOUSE_PRICES@DF_HOUSE_PRICES,1.0", "",                   "macro_real_house_prices"],
+            ["PRVM",     "SDD.STES,DSD_KEI@DF_KEI,4.0",                     "IX.C..",             "macro_manufacturing_production_volume"],
+            ["TOVM",     "SDD.STES,DSD_KEI@DF_KEI,4.0",                     "IX...",              "macro_retail_trade_volume"],
+            ["IRSTCI",   "SDD.STES,DSD_KEI@DF_KEI,4.0",                     "PA...",              "macro_interbank_rate"],
+            ["IRLT",     "SDD.STES,DSD_KEI@DF_KEI,4.0",                     "PA...",              "macro_long_term_interest_rate"],
+            ["B1GQ",     "SDD.NAD,DSD_NAMAIN1@DF_QNA,1.1",                  "._Z....GY.T0102",    "macro_gdp_growth_yoy"]
+        ]
+
+        # Create empty final dataframe
+        oecd_df_final = pd.DataFrame()
+
+        daily_df = pd.DataFrame({'OBS': date_range})
+        value_columns = []
+
+        # Iterate for each variable of interest
+        for series_details in url_details:
+            series = series_details[0]
+            dataset_id = series_details[1]
+            filter = series_details[2]
+            col_name = series_details[3]
+
+            # check if request was successful and determine the most granular data available
+            for freq in ['M', 'Q', 'A']:
+                
+                if series in ["UNE_LF_M", "EAR"]:
+                    data_url = f"https://sdmx.oecd.org/public/rest/data/OECD.{dataset_id}/{country}.{series}.{filter}.{freq}?startPeriod=1950-01"
+                elif series in ["B1GQ"]:
+                    data_url = f"https://sdmx.oecd.org/public/rest/data/OECD.{dataset_id}/{freq}..{country}...{series}.{filter}?startPeriod=1950-01"
+                else:
+                    data_url = f"https://sdmx.oecd.org/public/rest/data/OECD.{dataset_id}/{country}.{freq}.{series}.{filter}?startPeriod=1950-01"
+
+                # Make the request to the OECD 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} with frequency '{freq}' for {country}: {data_response.status_code} {data_response.text}")
+                    url_test = False
+                    continue
+                else:
+                    url_test = True
+                    break
+            
+            # get data for the next variable if url doesn't exist
+            if url_test == False:
+                continue
+
+            root = ET.fromstring(data_response.content)
+
+            # Define namespaces if necessary (the namespace is included in the tags)
+            namespaces = {'generic': 'http://www.sdmx.org/resources/sdmxml/schemas/v2_1/data/generic'}
+
+            # Lists to store the data
+            dates = []
+            values = []
+
+            # Iterate over all <Obs> elements and extract date and value
+            for obs in root.findall('.//generic:Obs', namespaces):        
+
+                # Extracting the time period (date)
+                time_period = obs.find('.//generic:ObsDimension', namespaces).get('value')
+                
+                # Extracting the observation value
+                value = obs.find('.//generic:ObsValue', namespaces).get('value')
+                
+                # Storing the data
+                if time_period and value:
+                    dates.append(time_period)
+                    values.append(float(value))  # Convert value to float
+
+            # Add variable names that were found to a list
+            value_columns.append(col_name)
+
+            # Creating a DataFrame
+            data = pd.DataFrame({'OBS': dates, col_name: values})
+
+            # Convert date strings into datetime format
+            if freq == 'Q':
+                data['OBS'] = data['OBS'].apply(parse_quarter)
             else:
-                macroeconomic_weekly_df = macroeconomic_weekly_df_M
+                # Display the DataFrame
+                data['OBS'] = data['OBS'].apply(lambda x: datetime.strptime(x, '%Y-%m'))
+
+            # Sort data by chronological order
+            data.sort_values(by='OBS', inplace=True)
+
+            # Merge the data based on the observation date
+            daily_df = pd.merge_asof(daily_df, data[['OBS', col_name]], on='OBS', direction='backward')
 
-            # Change datetime format
-            macroeconomic_weekly_df.index = macroeconomic_weekly_df.index.strftime('%d/%m/%Y')
 
-        macroeconomic_weekly_df.reset_index()
-        macroeconomic_weekly_df.reset_index(drop=False, inplace=True)
-        macroeconomic_weekly_df.rename(columns={'Date': 'OBS'}, inplace=True)
+        # 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
+        country_df = ims_proc.aggregate_daily_to_wc_wide(df=daily_df, 
+                                                        date_column="OBS", 
+                                                        group_columns=[], 
+                                                        sum_columns=value_columns,
+                                                        wc=week_commencing,
+                                                        aggregation="average")
+        
+        oecd_df_final = pd.concat([oecd_df_final, country_df], axis=0, ignore_index=True)
 
-        return macroeconomic_weekly_df
+        return oecd_df_final
     
     def get_google_mobility_data(self, country: str, wc: str) -> pd.DataFrame:
         """
@@ -2709,4 +2493,37 @@ class datapull:
 
         final_weather = ims_proc.rename_cols(merged_df, 'seas_')
 
-        return final_weather
+        return final_weather
+    
+    def pull_covid_data(self, folder_path: str, country: str = "GB", week_commencing: str = "mon") -> pd.DataFrame:
+        """
+        Get covid pandemic data for the country of interest.
+
+        Args:
+            folder_path (str): A string containing the local location of the OneDrive folder.
+                                Example: "C:/Users/-- username --/OneDrive - im-sciences.com"
+                                The file location within the MasterDrive of the worldwide covid data is: 
+                                MasterDrive/Central Database/Covid/oxford-government-response.csv
+            country (str): A string containing the country of interest (E.g: "GB", "FR")
+            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 containing seasonality and public holiday dummies for the country of interest.
+                            The 'OBS' column contains the week commencing dates.
+        """
+
+        df = pd.read_csv(f'{folder_path}/MasterDrive/Central Database/Covid/oxford-government-response.csv')
+
+        country_df = df[df['location_key']==country]
+        country_df.rename(columns={'date': 'OBS'}, inplace=True)
+        country_df.drop('location_key', axis=1, inplace=True)
+
+        agg_df = ims_proc.aggregate_daily_to_wc_wide(country_df, 'OBS', [], country_df.columns.to_list(), week_commencing, 'average')
+
+        covid_df = ims_proc.rename_cols(agg_df, 'covid_')
+
+        covid_df['OBS'] = covid_df['OBS'].apply(lambda x: x[0].date())
+
+        return covid_df
+    

{imsciences-0.6.1.2 → imsciences-0.6.1.4}/imsciences.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.6.1.2
+Version: 0.6.1.4
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.6.1.2 → imsciences-0.6.1.4}/setup.py

@@ -8,7 +8,7 @@ def read_md(file_name):
             return f.read()
     return ''
 
-VERSION = '0.6.1.2'
+VERSION = '0.6.1.4'
 DESCRIPTION = 'IMS Data Processing Package'
 LONG_DESCRIPTION = read_md('README.md')  # Reading from README.md