imsciences 0.9.5.8__py3-none-any.whl → 0.9.6.0__py3-none-any.whl

imsciences/mmm.py

@@ -1554,4 +1554,27 @@ class dataprocessing:
             "combined_features": combined_features,
         }
 
-        return output
+        return output
+
+    def quid_pr (self, df):
+        def convert_date(date_str):
+            try:
+                return datetime.strptime(date_str, '%b %d, %Y')
+            except ValueError:
+                return None  # Return None if conversion fails
+        # Apply conversion to create new columns
+        df['Start Date'] = df['Earliest Published'].astype(str).apply(convert_date)
+        df['End Date'] = df['Latest Published'].astype(str).apply(convert_date)
+        df['Days Duration'] = (df['End Date'] - df['Start Date']).dt.days + 1  # Ensure inclusive range
+        df['Count per Day'] = df['Published Count'] / df['Days Duration'] # Calculate count per day
+        df['Social Engagement per Day'] = df['Social Engagement'] / df['Days Duration']
+        df['Week Start'] = df['Start Date'].apply(lambda x: x - timedelta(days=x.weekday()) if pd.notnull(x) else None)
+        count_df = df.groupby('Week Start')['Count per Day'].sum().reset_index()
+        total_engagement_per_company = df.groupby('Company (Primary Mention)')['Social Engagement'].sum().reset_index() # Caluclates Social Engagement across whole period
+        valid_companies = total_engagement_per_company[total_engagement_per_company['Social Engagement'] > 0]['Company (Primary Mention)'] # Filters out Companies with no Social Engagement
+        social_engagement_df = df[df['Company (Primary Mention)'].isin(valid_companies)].groupby(['Week Start', 'Company (Primary Mention)'])[
+        'Social Engagement'
+        ].sum().reset_index()
+        total_social_engagement_df = df.groupby('Week Start')['Social Engagement per Day'].sum().reset_index()
+        
+        return count_df, total_social_engagement_df, social_engagement_df

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",
@@ -1186,6 +1186,9 @@ class datapull:
         # Define CDIDs for sectors and defaults
         sector_cdids = {
             "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"],
         }
 
@@ -1203,7 +1206,7 @@ class datapull:
         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}
+        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]
@@ -1337,7 +1340,7 @@ 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 +1500,9 @@ 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 +1595,9 @@ 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-0.9.5.8.dist-info → imsciences-0.9.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.9.5.8
+Version: 0.9.6.0
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

imsciences-0.9.6.0.dist-info/RECORD

@@ -0,0 +1,11 @@
+imsciences/__init__.py,sha256=_HuYeLbDMTdt7GpKI4r6-d7yRPZgcAQ7yOW0-ydR2Yo,117
+imsciences/geo.py,sha256=eenng7_BP_E2WD5Wt1G_oNxQS8W3t6lycRwJ91ngysY,15808
+imsciences/mmm.py,sha256=qMh0ccOepehfCcux7EeG8cq6piSEoFEz5iiJbDBWOS4,82214
+imsciences/pull.py,sha256=B05cjuWCihFfZp8pyO118QYHJiASsWn94s1o5hd1n1Q,81788
+imsciences/unittesting.py,sha256=U177_Txg0Lqn49zYRu5bl9OVe_X7MkNJ6V_Zd6DHOsU,45656
+imsciences/vis.py,sha256=2izdHQhmWEReerRqIxhY4Ai10VjL7xoUqyWyZC7-2XI,8931
+imsciences-0.9.6.0.dist-info/LICENSE.txt,sha256=lVq2QwcExPX4Kl2DHeEkRrikuItcDB1Pr7yF7FQ8_z8,1108
+imsciences-0.9.6.0.dist-info/METADATA,sha256=Khfs0zUye-2GAdswojmCutDo3JBq2OF0fEjuK0pkBR4,18846
+imsciences-0.9.6.0.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
+imsciences-0.9.6.0.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
+imsciences-0.9.6.0.dist-info/RECORD,,

{imsciences-0.9.5.8.dist-info → imsciences-0.9.6.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (74.1.0)
+Generator: setuptools (75.2.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

dataprocessing/__init__.py

@@ -1 +0,0 @@
-from .datafunctions import hello

dataprocessing/data-processing-functions.py

@@ -1,2 +0,0 @@
-def hello():
-    print("Hello from IMS")

dataprocessing/datafunctions.py

@@ -1,2 +0,0 @@
-def hello():
-    print("Hello from IMS")