Pandas10: Problem Solutions_RN32MAY2025DS

ActorsAndDirectorsWhoCooperatedAtLeastThreeTimes.py

@@ -0,0 +1,29 @@
+# Method 1
+import pandas as pd
+
+def actors_and_directors(actor_director: pd.DataFrame) -> pd.DataFrame:
+    act_dict = {}
+    for i in range(len(actor_director)):
+        a = actor_director['actor_id'][i]
+        d = actor_director['director_id'][i]
+
+        if (a,d) in act_dict:
+            act_dict[(a,d)] += 1
+        else:
+            act_dict[(a,d)] = 1
+
+    result = []
+    for k,v in act_dict.items():
+        if v >= 3:
+            result.append([k[0],k[1]])
+
+    return pd.DataFrame(result, columns = ['actor_id','director_id'])
+
+
+# Method 2
+import pandas as pd
+
+def actors_and_directors(actor_director: pd.DataFrame) -> pd.DataFrame:
+    df = actor_director.groupby(['actor_id','director_id']).size().reset_index(name = 'cnt')
+
+    return df[df['cnt'] >= 3][['actor_id','director_id']]

DailyLeadsAndPartners.py

@@ -0,0 +1,42 @@
+# Method 1
+import pandas as pd
+
+def daily_leads_and_partners(daily_sales: pd.DataFrame) -> pd.DataFrame:
+    ds_dict = {}
+    for i in range(len(daily_sales)):
+        d = daily_sales['date_id'][i]
+        m = daily_sales['make_name'][i]
+        l = daily_sales['lead_id'][i]
+        p = daily_sales['partner_id'][i]
+
+        if (d,m) not in ds_dict:
+            ds_dict[(d,m)] = [set(),set()]
+        ds_dict[(d,m)][0].add(l)
+        ds_dict[(d,m)][1].add(p)
+
+    result = []
+    for k,v in ds_dict.items():
+        result.append([k[0], k[1], len(v[0]), len(v[1])])
+
+    return pd.DataFrame(result, columns = ['date_id','make_name','unique_leads','unique_partners'])
+
+
+# Method 2
+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
+
+
+# Method 3
+import pandas as pd
+
+def daily_leads_and_partners(daily_sales: pd.DataFrame) -> pd.DataFrame:
+    df = daily_sales.groupby(['date_id','make_name']).nunique().reset_index()
+
+    return df.rename(columns = {'lead_id':'unique_leads','partner_id':'unique_partners'})

GroupSoldProductsByTheDate.py

@@ -0,0 +1,31 @@
+# Method 1
+import pandas as pd
+
+def categorize_products(activities: pd.DataFrame) -> pd.DataFrame:
+    adict = {}
+    for i in range(len(activities)):
+        s = activities['sell_date'][i]
+        p = activities['product'][i]
+
+        if s not in adict:
+            adict[s] = set()
+        adict[s].add(p)
+
+    result = []
+    for k,v in adict.items():
+        result.append([k, len(v), ','.join(sorted(v))])
+
+    return pd.DataFrame(result, columns = ['sell_date','num_sold','products']).sort_values('sell_date')
+
+
+# Method 2
+import pandas as pd
+
+def categorize_products(activities: pd.DataFrame) -> pd.DataFrame:
+    # df = activities.groupby('sell_date').nunique().reset_index()
+    df = activities.groupby('sell_date').agg(
+            num_sold = ('product','nunique'),
+            products = ('product', lambda x : ','.join(sorted(x.drop_duplicates()))) # or you can also take set(x) which gives distinct values
+            ).reset_index()
+
+    return df