PR #150, 151, 152: Radhika

150_group_sold_products_by_date.py

@@ -0,0 +1,13 @@
+# Group the activities DF using 'sell_date'. agg() function is used because we want to apply multiple 
+# functionality to the same grouping. Using agg() we get the total number of unique products sold and also
+# get the names of all those unique products by joining a string of sorted set of product names. 
+# Note: agg() function directly returns a DF, not a series like we get using transform()
+
+import pandas as pd
+
+def categorize_products(activities: pd.DataFrame) -> pd.DataFrame:
+    df = activities.groupby(['sell_date']).agg(
+        num_sold = ('product', 'nunique'), 
+        products = ('product', lambda x: ','.join(sorted(set(x))))
+        ).reset_index()
+    return df

151_daily_leads_and_partners.py

@@ -0,0 +1,11 @@
+# Group the daily_sales DF using both 'date_id' and 'make_name' and return unique lead IDs and unique 
+# partner IDs associated with it.
+
+import pandas as pd
+
+def daily_leads_and_partners(daily_sales: pd.DataFrame) -> pd.DataFrame:
+    df = daily_sales.groupby(['date_id', 'make_name']).agg(
+        unique_leads = ('lead_id', 'nunique'),
+        unique_partners = ('partner_id', 'nunique')
+    ).reset_index()
+    return df

152_actors_and_directors_cooperated.py

@@ -0,0 +1,10 @@
+# Group the DF based on actor and director ID pairs and return the number of times they cooperated. Return
+# the DF where the count is greater than or equal to 3.
+
+import pandas as pd
+
+def actors_and_directors(actor_director: pd.DataFrame) -> pd.DataFrame:
+    df = actor_director.groupby(['actor_id', 'director_id']).agg(
+        count = ('timestamp', 'count')
+    ).reset_index()
+    return df[df['count'] >= 3][['actor_id', 'director_id']]