Improved tasks 2877-2881

src/test/java/g2801_2900/s2877_create_a_dataframe_from_list/solution_test.py

@@ -0,0 +1,46 @@
+import unittest
+import pandas as pd
+from typing import List
+
+def createDataframe(student_data: List[List[int]]) -> pd.DataFrame:
+    column_name = ['student_id','age']
+    result = pd.DataFrame(student_data, columns=column_name)
+    return result
+
+class TestCreateDataframe(unittest.TestCase):
+
+    def test_valid_data(self):
+        student_data = [[1, 15], [2, 11], [3, 11], [4, 20]]
+        expected_df = pd.DataFrame({
+            'student_id': [1, 2, 3, 4],
+            'age': [15, 11, 11, 20]
+        })
+        result_df = createDataframe(student_data)
+        pd.testing.assert_frame_equal(result_df, expected_df)
+
+    def test_empty_data(self):
+        student_data = []
+        expected_df = pd.DataFrame(columns=['student_id', 'age'])
+        result_df = createDataframe(student_data)
+        pd.testing.assert_frame_equal(result_df, expected_df)
+
+    def test_single_row(self):
+        student_data = [[5, 18]]
+        expected_df = pd.DataFrame({
+            'student_id': [5],
+            'age': [18]
+        })
+        result_df = createDataframe(student_data)
+        pd.testing.assert_frame_equal(result_df, expected_df)
+
+    def test_negative_age(self):
+        student_data = [[6, -10]]
+        expected_df = pd.DataFrame({
+            'student_id': [6],
+            'age': [-10]
+        })
+        result_df = createDataframe(student_data)
+        pd.testing.assert_frame_equal(result_df, expected_df)
+
+if __name__ == '__main__':
+    unittest.main()

src/test/java/g2801_2900/s2878_get_the_size_of_a_dataframe/solution_test.py

@@ -0,0 +1,64 @@
+import unittest
+import pandas as pd
+from typing import List
+
+def getDataframeSize(players: pd.DataFrame) -> List[int]:
+    return [players.shape[0], players.shape[1]]
+
+class TestGetDataframeSize(unittest.TestCase):
+    def test_example_case(self):
+        # Example DataFrame
+        data = {
+            "player_id": [846, 749, 155, 583, 388, 883, 355, 247, 761, 642],
+            "name": ["Mason", "Riley", "Bob", "Isabella", "Zachary", "Ava", "Violet", "Thomas", "Jack", "Charlie"],
+            "age": [21, 30, 28, 32, 24, 23, 18, 27, 33, 36],
+            "position": ["Forward", "Winger", "Striker", "Goalkeeper", "Midfielder", "Defender", "Striker", "Striker", "Midfielder", "Center-back"],
+            "team": ["RealMadrid", "Barcelona", "ManchesterUnited", "Liverpool", "BayernMunich", "Chelsea", "Juventus", "ParisSaint-Germain", "ManchesterCity", "Arsenal"]
+        }
+        players = pd.DataFrame(data)
+
+        # Expected result: 10 rows, 5 columns
+        expected_output = [10, 5]
+        self.assertEqual(getDataframeSize(players), expected_output)
+
+    def test_empty_dataframe(self):
+        # Empty DataFrame
+        players = pd.DataFrame(columns=["player_id", "name", "age", "position", "team"])
+
+        # Expected result: 0 rows, 5 columns
+        expected_output = [0, 5]
+        self.assertEqual(getDataframeSize(players), expected_output)
+
+    def test_single_row(self):
+        # DataFrame with a single row
+        data = {
+            "player_id": [1],
+            "name": ["John"],
+            "age": [25],
+            "position": ["Forward"],
+            "team": ["TestTeam"]
+        }
+        players = pd.DataFrame(data)
+
+        # Expected result: 1 row, 5 columns
+        expected_output = [1, 5]
+        self.assertEqual(getDataframeSize(players), expected_output)
+
+    def test_different_columns(self):
+        # DataFrame with more columns
+        data = {
+            "player_id": [1, 2],
+            "name": ["John", "Doe"],
+            "age": [25, 30],
+            "position": ["Forward", "Midfielder"],
+            "team": ["TestTeam", "AnotherTeam"],
+            "goals": [15, 20]
+        }
+        players = pd.DataFrame(data)
+
+        # Expected result: 2 rows, 6 columns
+        expected_output = [2, 6]
+        self.assertEqual(getDataframeSize(players), expected_output)
+
+if __name__ == "__main__":
+    unittest.main()

src/test/java/g2801_2900/s2879_display_the_first_three_rows/solution_test.py

@@ -0,0 +1,69 @@
+import unittest
+import pandas as pd
+
+def selectFirstRows(zs: pd.DataFrame) -> pd.DataFrame:
+    return zs.head(3)
+
+class TestSelectFirstRows(unittest.TestCase):
+    def test_example_case(self):
+        # Example DataFrame
+        data = {
+            "employee_id": [3, 90, 9, 60, 49, 43],
+            "name": ["Bob", "Alice", "Tatiana", "Annabelle", "Jonathan", "Khaled"],
+            "department": ["Operations", "Sales", "Engineering", "InformationTechnology", "HumanResources", "Administration"],
+            "salary": [48675, 11096, 33805, 37678, 23793, 40454]
+        }
+        employees = pd.DataFrame(data)
+
+        # Expected DataFrame with the first 3 rows
+        expected_data = {
+            "employee_id": [3, 90, 9],
+            "name": ["Bob", "Alice", "Tatiana"],
+            "department": ["Operations", "Sales", "Engineering"],
+            "salary": [48675, 11096, 33805]
+        }
+        expected_output = pd.DataFrame(expected_data)
+
+        pd.testing.assert_frame_equal(selectFirstRows(employees), expected_output)
+
+    def test_less_than_three_rows(self):
+        # DataFrame with less than 3 rows
+        data = {
+            "employee_id": [1, 2],
+            "name": ["John", "Doe"],
+            "department": ["HR", "IT"],
+            "salary": [50000, 60000]
+        }
+        employees = pd.DataFrame(data)
+
+        # Expected DataFrame (same as input since there are fewer than 3 rows)
+        expected_output = employees.copy()
+
+        pd.testing.assert_frame_equal(selectFirstRows(employees), expected_output)
+
+    def test_empty_dataframe(self):
+        # Empty DataFrame
+        employees = pd.DataFrame(columns=["employee_id", "name", "department", "salary"])
+
+        # Expected result: Empty DataFrame with same columns
+        expected_output = employees.copy()
+
+        pd.testing.assert_frame_equal(selectFirstRows(employees), expected_output)
+
+    def test_exactly_three_rows(self):
+        # DataFrame with exactly 3 rows
+        data = {
+            "employee_id": [10, 20, 30],
+            "name": ["Eve", "Mark", "Lily"],
+            "department": ["Finance", "Operations", "Engineering"],
+            "salary": [70000, 65000, 72000]
+        }
+        employees = pd.DataFrame(data)
+
+        # Expected DataFrame (same as input since there are exactly 3 rows)
+        expected_output = employees.copy()
+
+        pd.testing.assert_frame_equal(selectFirstRows(employees), expected_output)
+
+if __name__ == "__main__":
+    unittest.main()

src/test/java/g2801_2900/s2880_select_data/solution_test.py

@@ -0,0 +1,68 @@
+import unittest
+import pandas as pd
+
+def selectData(students: pd.DataFrame) -> pd.DataFrame:
+    return students[students.student_id == 101][['name', 'age']]
+
+class TestSelectData(unittest.TestCase):
+    def test_example_case(self):
+        # Example DataFrame
+        data = {
+            "student_id": [101, 53, 128, 3],
+            "name": ["Ulysses", "William", "Henry", "Henry"],
+            "age": [13, 10, 6, 11]
+        }
+        students = pd.DataFrame(data)
+
+        # Expected output DataFrame with explicit data types
+        expected_data = {
+            "name": pd.Series(["Ulysses"], dtype="object"),
+            "age": pd.Series([13], dtype="int64")
+        }
+        expected_output = pd.DataFrame(expected_data)
+
+        pd.testing.assert_frame_equal(selectData(students), expected_output, check_dtype=False)
+
+    def test_no_matching_id(self):
+        # DataFrame with no matching student_id = 101
+        data = {
+            "student_id": [102, 53, 128, 3],
+            "name": ["John", "William", "Henry", "Doe"],
+            "age": [12, 10, 6, 11]
+        }
+        students = pd.DataFrame(data)
+
+        # Expected output: Empty DataFrame with columns ['name', 'age']
+        expected_output = pd.DataFrame(columns=['name', 'age'])
+
+        pd.testing.assert_frame_equal(selectData(students), expected_output, check_dtype=False)
+
+    def test_multiple_students_with_101(self):
+        # DataFrame with multiple students having student_id = 101
+        data = {
+            "student_id": [101, 101, 128],
+            "name": ["Alice", "Bob", "Charlie"],
+            "age": [20, 21, 22]
+        }
+        students = pd.DataFrame(data)
+
+        # Expected output: DataFrame with both rows where student_id = 101
+        expected_data = {
+            "name": ["Alice", "Bob"],
+            "age": [20, 21]
+        }
+        expected_output = pd.DataFrame(expected_data)
+
+        pd.testing.assert_frame_equal(selectData(students), expected_output, check_dtype=False)
+
+    def test_empty_dataframe(self):
+        # Empty DataFrame with the same structure
+        students = pd.DataFrame(columns=["student_id", "name", "age"])
+
+        # Expected output: Empty DataFrame with columns ['name', 'age']
+        expected_output = pd.DataFrame(columns=['name', 'age'])
+
+        pd.testing.assert_frame_equal(selectData(students), expected_output, check_dtype=False)
+
+if __name__ == "__main__":
+    unittest.main()

src/test/java/g2801_2900/s2881_create_a_new_column/solution_test.py

@@ -0,0 +1,32 @@
+import unittest
+import pandas as pd
+
+def createBonusColumn(employees: pd.DataFrame) -> pd.DataFrame:
+    employees["bonus"] = employees["salary"] * 2
+    return employees
+
+class TestCreateBonusColumn(unittest.TestCase):
+    def test_create_bonus_column(self):
+        # Example DataFrame as input
+        data = {
+            "name": ["Piper", "Grace", "Georgia", "Willow", "Finn", "Thomas"],
+            "salary": [4548, 28150, 1103, 6593, 74576, 24433]
+        }
+        employees = pd.DataFrame(data)
+
+        # Expected output DataFrame
+        expected_data = {
+            "name": ["Piper", "Grace", "Georgia", "Willow", "Finn", "Thomas"],
+            "salary": [4548, 28150, 1103, 6593, 74576, 24433],
+            "bonus": [9096, 56300, 2206, 13186, 149152, 48866]
+        }
+        expected_output = pd.DataFrame(expected_data)
+
+        # Test the function
+        result = createBonusColumn(employees)
+
+        # Use pandas testing utilities to compare DataFrames
+        pd.testing.assert_frame_equal(result, expected_output)
+
+if __name__ == '__main__':
+    unittest.main()