Improved tasks 2882, 2883

Author: javadev

src/test/java/g2801_2900/s2882_drop_duplicate_rows/solution_test.py

@@ -0,0 +1,72 @@
+import unittest
+import pandas as pd
+from pandas.testing import assert_frame_equal
+
+def dropDuplicateEmails(customers: pd.DataFrame) -> pd.DataFrame:
+    customers.drop_duplicates(subset='email', keep='first', inplace=True)
+    return customers
+
+class TestDropDuplicateEmails(unittest.TestCase):
+
+    def test_no_duplicates(self):
+        data = {
+            'customer_id': [1, 2, 3],
+            'name': ['Ella', 'David', 'Zachary'],
+            'email': ['emily@example.com', 'michael@example.com', 'sarah@example.com']
+        }
+        customers = pd.DataFrame(data)
+        expected = pd.DataFrame(data)
+
+        result = dropDuplicateEmails(customers).reset_index(drop=True)
+        expected = expected.reset_index(drop=True)
+
+        assert_frame_equal(result, expected)
+
+    def test_with_duplicates(self):
+        data = {
+            'customer_id': [1, 2, 3, 4, 5, 6],
+            'name': ['Ella', 'David', 'Zachary', 'Alice', 'Finn', 'Violet'],
+            'email': [
+                'emily@example.com', 'michael@example.com', 'sarah@example.com',
+                'john@example.com', 'john@example.com', 'alice@example.com'
+            ]
+        }
+        customers = pd.DataFrame(data)
+
+        expected_data = {
+            'customer_id': [1, 2, 3, 4, 6],
+            'name': ['Ella', 'David', 'Zachary', 'Alice', 'Violet'],
+            'email': ['emily@example.com', 'michael@example.com', 'sarah@example.com', 'john@example.com', 'alice@example.com']
+        }
+        expected = pd.DataFrame(expected_data)
+
+        result = dropDuplicateEmails(customers).reset_index(drop=True)
+        expected = expected.reset_index(drop=True)
+
+        assert_frame_equal(result, expected)
+
+    def test_empty_dataframe(self):
+        customers = pd.DataFrame(columns=['customer_id', 'name', 'email'])
+        expected = customers.copy()
+
+        result = dropDuplicateEmails(customers).reset_index(drop=True)
+        expected = expected.reset_index(drop=True)
+
+        assert_frame_equal(result, expected)
+
+    def test_single_row(self):
+        data = {
+            'customer_id': [1],
+            'name': ['Ella'],
+            'email': ['emily@example.com']
+        }
+        customers = pd.DataFrame(data)
+        expected = pd.DataFrame(data)
+
+        result = dropDuplicateEmails(customers).reset_index(drop=True)
+        expected = expected.reset_index(drop=True)
+
+        assert_frame_equal(result, expected)
+
+if __name__ == '__main__':
+    unittest.main()

src/test/java/g2801_2900/s2883_drop_missing_data/solution_test.py

@@ -0,0 +1,94 @@
+import unittest
+import pandas as pd
+from pandas.testing import assert_frame_equal
+
+def dropMissingData(students: pd.DataFrame) -> pd.DataFrame:
+   r = pd.DataFrame(students)
+   r.dropna(subset='name', inplace=True)
+   return r
+
+class TestDropMissingData(unittest.TestCase):
+
+    def test_no_missing_data(self):
+        # Input DataFrame with no missing values in the 'name' column
+        data = {
+            'student_id': [32, 779, 849],
+            'name': ['Piper', 'Georgia', 'Willow'],
+            'age': [5, 20, 14]
+        }
+        students = pd.DataFrame(data)
+        expected = pd.DataFrame(data)
+
+        result = dropMissingData(students).reset_index(drop=True)
+        expected = expected.reset_index(drop=True)
+
+        assert_frame_equal(result, expected)
+
+    def test_with_missing_data(self):
+        # Input DataFrame with missing values in the 'name' column
+        data = {
+            'student_id': [32, 217, 779, 849],
+            'name': ['Piper', None, 'Georgia', 'Willow'],
+            'age': [5, 19, 20, 14]
+        }
+        students = pd.DataFrame(data)
+        
+        # Expected output after removing rows with missing 'name'
+        expected_data = {
+            'student_id': [32, 779, 849],
+            'name': ['Piper', 'Georgia', 'Willow'],
+            'age': [5, 20, 14]
+        }
+        expected = pd.DataFrame(expected_data)
+
+        result = dropMissingData(students).reset_index(drop=True)
+        expected = expected.reset_index(drop=True)
+
+        assert_frame_equal(result, expected)
+
+    def test_empty_dataframe(self):
+        # Input: Empty DataFrame
+        students = pd.DataFrame(columns=['student_id', 'name', 'age'])
+        expected = students.copy()
+
+        result = dropMissingData(students).reset_index(drop=True)
+        expected = expected.reset_index(drop=True)
+
+        assert_frame_equal(result, expected)
+
+    def test_all_missing_data(self):
+        # Input DataFrame where all 'name' values are missing
+        data = {
+            'student_id': [217, 301],
+            'name': [None, None],
+            'age': [19, 21]
+        }
+        students = pd.DataFrame(data)
+        
+        # Expected: empty DataFrame since all 'name' values are missing
+        expected = pd.DataFrame(columns=['student_id', 'name', 'age'])
+
+        result = dropMissingData(students).reset_index(drop=True)
+        expected = expected.reset_index(drop=True)
+
+        assert_frame_equal(result, expected, check_dtype=False)
+
+    def test_single_row_with_missing_name(self):
+        # Input DataFrame with a single row and missing 'name'
+        data = {
+            'student_id': [217],
+            'name': [None],
+            'age': [19]
+        }
+        students = pd.DataFrame(data)
+        
+        # Expected: empty DataFrame since the single row has missing 'name'
+        expected = pd.DataFrame(columns=['student_id', 'name', 'age'])
+
+        result = dropMissingData(students).reset_index(drop=True)
+        expected = expected.reset_index(drop=True)
+
+        assert_frame_equal(result, expected, check_dtype=False)
+
+if __name__ == '__main__':
+    unittest.main()