Improved tasks 2884, 2885, 2886, 2887

src/test/kotlin/g2801_2900/s2884_modify_columns/solution_test.py

@@ -0,0 +1,93 @@
+import pandas as pd
+import unittest
+
+# The function to be tested
+def modifySalaryColumn(employees: pd.DataFrame) -> pd.DataFrame:
+    employees['salary'] = employees['salary'] * 2
+    return employees
+
+# Test class
+class TestDropMissingData(unittest.TestCase):
+
+    def test_modify_salary_column_basic_case(self):
+        # Input DataFrame
+        employees = pd.DataFrame({
+            'name': ['Jack', 'Piper', 'Mia', 'Ulysses'],
+            'salary': [19666, 74754, 62509, 54866]
+        })
+
+        # Expected output DataFrame
+        expected_output = pd.DataFrame({
+            'name': ['Jack', 'Piper', 'Mia', 'Ulysses'],
+            'salary': [39332, 149508, 125018, 109732]
+        })
+
+        # Call the function and assert equality
+        result = modifySalaryColumn(employees)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_modify_salary_column_empty_dataframe(self):
+        # Input: Empty DataFrame
+        employees = pd.DataFrame(columns=['name', 'salary'])
+
+        # Expected output: Empty DataFrame
+        expected_output = pd.DataFrame(columns=['name', 'salary'])
+
+        # Call the function and assert equality
+        result = modifySalaryColumn(employees)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_modify_salary_column_single_row(self):
+        # Input DataFrame with a single row
+        employees = pd.DataFrame({
+            'name': ['Alice'],
+            'salary': [50000]
+        })
+
+        # Expected output DataFrame
+        expected_output = pd.DataFrame({
+            'name': ['Alice'],
+            'salary': [100000]
+        })
+
+        # Call the function and assert equality
+        result = modifySalaryColumn(employees)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_modify_salary_column_zero_salary(self):
+        # Input DataFrame with a zero salary
+        employees = pd.DataFrame({
+            'name': ['Bob'],
+            'salary': [0]
+        })
+
+        # Expected output DataFrame
+        expected_output = pd.DataFrame({
+            'name': ['Bob'],
+            'salary': [0]
+        })
+
+        # Call the function and assert equality
+        result = modifySalaryColumn(employees)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_modify_salary_column_negative_salary(self):
+        # Input DataFrame with a negative salary
+        employees = pd.DataFrame({
+            'name': ['Charlie'],
+            'salary': [-30000]
+        })
+
+        # Expected output DataFrame
+        expected_output = pd.DataFrame({
+            'name': ['Charlie'],
+            'salary': [-60000]
+        })
+
+        # Call the function and assert equality
+        result = modifySalaryColumn(employees)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+# Run the tests
+if __name__ == '__main__':
+    unittest.main()

src/test/kotlin/g2801_2900/s2885_rename_columns/solution_test.py

@@ -0,0 +1,88 @@
+import pandas as pd
+import unittest
+
+# The function to be tested
+def renameColumns(students: pd.DataFrame) -> pd.DataFrame:
+    students.rename(columns={'id': 'student_id', 'first': 'first_name', 'last': 'last_name', 'age': 'age_in_years'}, inplace=True)
+    return students
+
+# Test class
+class TestRenameColumns(unittest.TestCase):
+
+    def test_rename_columns_basic_case(self):
+        # Input DataFrame
+        students = pd.DataFrame({
+            'id': [1, 2, 3, 4, 5],
+            'first': ['Mason', 'Ava', 'Taylor', 'Georgia', 'Thomas'],
+            'last': ['King', 'Wright', 'Hall', 'Thompson', 'Moore'],
+            'age': [6, 7, 16, 18, 10]
+        })
+
+        # Expected output DataFrame
+        expected_output = pd.DataFrame({
+            'student_id': [1, 2, 3, 4, 5],
+            'first_name': ['Mason', 'Ava', 'Taylor', 'Georgia', 'Thomas'],
+            'last_name': ['King', 'Wright', 'Hall', 'Thompson', 'Moore'],
+            'age_in_years': [6, 7, 16, 18, 10]
+        })
+
+        # Call the function and assert equality
+        result = renameColumns(students)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_rename_columns_empty_dataframe(self):
+        # Input: Empty DataFrame with the correct column names
+        students = pd.DataFrame(columns=['id', 'first', 'last', 'age'])
+
+        # Expected output: Empty DataFrame with renamed columns
+        expected_output = pd.DataFrame(columns=['student_id', 'first_name', 'last_name', 'age_in_years'])
+
+        # Call the function and assert equality
+        result = renameColumns(students)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_rename_columns_single_row(self):
+        # Input DataFrame with a single row
+        students = pd.DataFrame({
+            'id': [10],
+            'first': ['Emma'],
+            'last': ['Johnson'],
+            'age': [15]
+        })
+
+        # Expected output DataFrame
+        expected_output = pd.DataFrame({
+            'student_id': [10],
+            'first_name': ['Emma'],
+            'last_name': ['Johnson'],
+            'age_in_years': [15]
+        })
+
+        # Call the function and assert equality
+        result = renameColumns(students)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_rename_columns_with_different_ages(self):
+        # Input DataFrame with various ages
+        students = pd.DataFrame({
+            'id': [101, 102],
+            'first': ['Liam', 'Olivia'],
+            'last': ['Brown', 'Davis'],
+            'age': [21, 30]
+        })
+
+        # Expected output DataFrame
+        expected_output = pd.DataFrame({
+            'student_id': [101, 102],
+            'first_name': ['Liam', 'Olivia'],
+            'last_name': ['Brown', 'Davis'],
+            'age_in_years': [21, 30]
+        })
+
+        # Call the function and assert equality
+        result = renameColumns(students)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+# Run the tests
+if __name__ == '__main__':
+    unittest.main()

src/test/kotlin/g2801_2900/s2886_change_data_type/solution_test.py

@@ -0,0 +1,114 @@
+import pandas as pd
+import unittest
+
+# The function to be tested
+def changeDatatype(students: pd.DataFrame) -> pd.DataFrame:
+    students['grade'] = students['grade'].astype('int64')
+    return students
+
+# Test class
+class TestChangeDatatype(unittest.TestCase):
+
+    def test_change_datatype_basic_case(self):
+        # Input DataFrame
+        students = pd.DataFrame({
+            'student_id': [1, 2],
+            'name': ['Ava', 'Kate'],
+            'age': [6, 15],
+            'grade': [73.0, 87.0]
+        })
+
+        # Expected output DataFrame with grade explicitly set as int64
+        expected_output = pd.DataFrame({
+            'student_id': [1, 2],
+            'name': ['Ava', 'Kate'],
+            'age': [6, 15],
+            'grade': [73, 87]
+        })
+        expected_output['grade'] = expected_output['grade'].astype('int64')
+
+        # Call the function and assert equality
+        result = changeDatatype(students)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_change_datatype_empty_dataframe(self):
+        # Input: Empty DataFrame with the correct columns
+        students = pd.DataFrame(columns=['student_id', 'name', 'age', 'grade'])
+
+        # Expected output: Empty DataFrame with the same columns and grade set to Int64 dtype
+        expected_output = pd.DataFrame(columns=['student_id', 'name', 'age', 'grade'])
+        expected_output['grade'] = expected_output['grade'].astype('int64')
+
+        # Call the function and assert equality
+        result = changeDatatype(students)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_change_datatype_with_negative_grades(self):
+        # Input DataFrame with negative grades
+        students = pd.DataFrame({
+            'student_id': [3, 4],
+            'name': ['Liam', 'Olivia'],
+            'age': [12, 10],
+            'grade': [-45.0, -88.0]
+        })
+
+        # Expected output DataFrame with grades as integers
+        expected_output = pd.DataFrame({
+            'student_id': [3, 4],
+            'name': ['Liam', 'Olivia'],
+            'age': [12, 10],
+            'grade': [-45, -88]
+        })
+        expected_output['grade'] = expected_output['grade'].astype('int64')
+
+        # Call the function and assert equality
+        result = changeDatatype(students)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_change_datatype_with_decimal_grades(self):
+        # Input DataFrame with decimal grades that will truncate
+        students = pd.DataFrame({
+            'student_id': [5, 6],
+            'name': ['Ella', 'Noah'],
+            'age': [14, 17],
+            'grade': [95.6, 78.9]
+        })
+
+        # Expected output DataFrame with truncated grades as integers
+        expected_output = pd.DataFrame({
+            'student_id': [5, 6],
+            'name': ['Ella', 'Noah'],
+            'age': [14, 17],
+            'grade': [95, 78]
+        })
+        expected_output['grade'] = expected_output['grade'].astype('int64')
+
+        # Call the function and assert equality
+        result = changeDatatype(students)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_change_datatype_single_row(self):
+        # Input DataFrame with a single row
+        students = pd.DataFrame({
+            'student_id': [7],
+            'name': ['James'],
+            'age': [11],
+            'grade': [80.0]
+        })
+
+        # Expected output DataFrame
+        expected_output = pd.DataFrame({
+            'student_id': [7],
+            'name': ['James'],
+            'age': [11],
+            'grade': [80]
+        })
+        expected_output['grade'] = expected_output['grade'].astype('int64')
+
+        # Call the function and assert equality
+        result = changeDatatype(students)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+# Run the tests
+if __name__ == '__main__':
+    unittest.main()

src/test/kotlin/g2801_2900/s2887_fill_missing_data/solution_test.py

@@ -0,0 +1,92 @@
+import pandas as pd
+import unittest
+
+# The updated function to be tested
+def fillMissingValues(products: pd.DataFrame) -> pd.DataFrame:
+    products['quantity'].fillna(0, inplace=True)
+    products['quantity'] = products['quantity'].astype(int)  # Ensure the quantity is of type int
+    return products
+
+# Test class
+class TestFillMissingValues(unittest.TestCase):
+
+    def test_fill_missing_values_basic_case(self):
+        # Input DataFrame with missing values in quantity
+        products = pd.DataFrame({
+            'name': ['Wristwatch', 'WirelessEarbuds', 'GolfClubs', 'Printer'],
+            'quantity': [None, None, 779, 849],
+            'price': [135, 821, 9319, 3051]
+        })
+
+        # Expected output DataFrame
+        expected_output = pd.DataFrame({
+            'name': ['Wristwatch', 'WirelessEarbuds', 'GolfClubs', 'Printer'],
+            'quantity': [0, 0, 779, 849],
+            'price': [135, 821, 9319, 3051]
+        })
+
+        # Call the function and assert equality
+        result = fillMissingValues(products)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_fill_missing_values_no_missing(self):
+        # Input DataFrame with no missing values
+        products = pd.DataFrame({
+            'name': ['Laptop', 'Mouse', 'Keyboard'],
+            'quantity': [10, 5, 0],
+            'price': [1000, 50, 30]
+        })
+
+        # Expected output should be the same as input
+        expected_output = products.copy()
+
+        # Call the function and assert equality
+        result = fillMissingValues(products)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_fill_missing_values_empty_dataframe(self):
+        # Input: Empty DataFrame
+        products = pd.DataFrame(columns=['name', 'quantity', 'price'])
+
+        # Expected output: Empty DataFrame with specified dtypes
+        expected_output = pd.DataFrame(columns=['name', 'quantity', 'price'], dtype='object')
+        expected_output['quantity'] = expected_output['quantity'].astype('int64')
+
+        # Call the function and assert equality
+        result = fillMissingValues(products)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_fill_missing_values_empty_dataframe(self):
+        # Input: Empty DataFrame
+        products = pd.DataFrame(columns=['name', 'quantity', 'price'])
+
+        # Expected output: Empty DataFrame
+        expected_output = pd.DataFrame(columns=['name', 'quantity', 'price'])
+        expected_output['quantity'] = expected_output['quantity'].astype('int64')
+
+        # Call the function and assert equality
+        result = fillMissingValues(products)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+    def test_fill_missing_values_all_none(self):
+        # Input DataFrame with all None in quantity
+        products = pd.DataFrame({
+            'name': ['Item1', 'Item2', 'Item3'],
+            'quantity': [None, None, None],
+            'price': [100, 200, 300]
+        })
+
+        # Expected output DataFrame with quantity filled with 0
+        expected_output = pd.DataFrame({
+            'name': ['Item1', 'Item2', 'Item3'],
+            'quantity': [0, 0, 0],
+            'price': [100, 200, 300]
+        })
+
+        # Call the function and assert equality
+        result = fillMissingValues(products)
+        pd.testing.assert_frame_equal(result, expected_output)
+
+# Run the tests
+if __name__ == '__main__':
+    unittest.main()