feat(pandas): add problem 1581

Author: IndexSeek

README.md

@@ -18,7 +18,7 @@ Fiddling around with DataFusion, pandas, and PyArrow.
 |----------:|:------|:-----------|:-------:|:----------:|:------:|
 | 1378 | [Replace Employee ID With The Unique Identifier](https://leetcode.com/problems/replace-employee-id-with-the-unique-identifier) | Easy | ✅ | ❌ | ✅ |
 | 1068 | [Product Sales Analysis I](https://leetcode.com/problems/product-sales-analysis-i) | Easy | ✅ | ❌ | ✅ |
-| 1581 | [Customer Who Visited but Did Not Make Any Transactions](https://leetcode.com/problems/customer-who-visited-but-did-not-make-any-transactions) | Easy | ✅ | ❌ | ❌ |
+| 1581 | [Customer Who Visited but Did Not Make Any Transactions](https://leetcode.com/problems/customer-who-visited-but-did-not-make-any-transactions) | Easy | ✅ | ❌ | ✅ |
 | 197  | [Rising Temperature](https://leetcode.com/problems/rising-temperature) | Easy | ✅ | ❌ | ❌ |
 | 1661 | [Average Time of Process per Machine](https://leetcode.com/problems/average-time-of-process-per-machine) | Easy | ✅ | ❌ | ❌ |
 | 577  | [Employee Bonus](https://leetcode.com/problems/employee-bonus) | Easy | ✅ | ❌ | ❌ |

problems/pandas.py

@@ -199,6 +199,32 @@ def problem_1378(employees: pd.DataFrame, employee_uni: pd.DataFrame) -> pd.Data
     return employees.merge(employee_uni, how="left", on="id")[["unique_id", "name"]]
 
 
+def problem_1581(visits: pd.DataFrame, transactions: pd.DataFrame) -> pd.DataFrame:
+    """Find users who visited without transactions and count their visit frequency.
+
+    Return the result table sorted in any order.
+
+    Parameters
+    ----------
+    visits : pd.DataFrame
+        Table containing information about the customers who visited the mall.
+    transactions : pd.DataFrame
+        Table containing information about the transactions made during the visit_id.
+
+    Returns
+    -------
+    pd.DataFrame
+
+    """
+    joined = visits.merge(transactions, how="left")
+    return (
+        joined.loc[joined["transaction_id"].isnull(), ["visit_id", "customer_id"]]
+        .groupby("customer_id", as_index=False)
+        .count()
+        .rename(columns={"visit_id": "count_no_trans"})
+    )
+
+
 def problem_1683(tweets: pd.DataFrame) -> pd.DataFrame:
     """Find the IDs of the invalid tweets.
 

tests/test_pandas.py

@@ -2,6 +2,7 @@
 
 import pandas as pd
 import pytest
+from pandas.testing import assert_frame_equal
 
 from problems.pandas import (
     problem_176,
@@ -12,6 +13,7 @@
     problem_1148,
     problem_1321,
     problem_1378,
+    problem_1581,
     problem_1683,
     problem_1757,
 )
@@ -425,6 +427,41 @@ def test_problem_1378(input_data_1, input_data_2, expected_data):
     assert result.equals(expected_table)
 
 
+@pytest.mark.parametrize(
+    "input_data_1, input_data_2, expected_data",
+    [
+        pytest.param(
+            {
+                "visit_id": [1, 2, 5, 5, 5, 4, 6, 7, 8],
+                "customer_id": [23, 9, 54, 54, 54, 30, 96, 54, 54],
+            },
+            {
+                "visit_id": [1, 2, 5],
+                "transaction_id": [12, 13, 9],
+                "amount": [910, 970, 200],
+            },
+            {"customer_id": [30, 96, 54], "count_no_trans": [1, 1, 2]},
+            id="happy_path",
+        ),
+        pytest.param(
+            {"visit_id": [10, 11], "customer_id": [100, 101]},
+            {"visit_id": [1, 2], "transaction_id": [12, 13], "amount": [910, 970]},
+            {"customer_id": [100, 101], "count_no_trans": [1, 1]},
+            id="no_matching_visit_id",
+        ),
+    ],
+)
+def test_problem_1581(input_data_1, input_data_2, expected_data):
+    table_1 = pd.DataFrame(input_data_1)
+    table_2 = pd.DataFrame(input_data_2)
+    expected_table = (
+        pd.DataFrame(expected_data).sort_values(by="customer_id").reset_index(drop=True)
+    )
+    result = problem_1581(table_1, table_2).sort_values(by="customer_id")
+
+    assert_frame_equal(result, expected_table, check_dtype=False, check_index_type=True)
+
+
 @pytest.mark.parametrize(
     "input_data, expected_data",
     [