Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 393353c

Browse files
authored
Improved tasks 2882, 2883
1 parent 54b28d4 commit 393353c

File tree

2 files changed

+166
-0
lines changed

2 files changed

+166
-0
lines changed
Lines changed: 72 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,72 @@
1+
import unittest
2+
import pandas as pd
3+
from pandas.testing import assert_frame_equal
4+
5+
def dropDuplicateEmails(customers: pd.DataFrame) -> pd.DataFrame:
6+
customers.drop_duplicates(subset='email', keep='first', inplace=True)
7+
return customers
8+
9+
class TestDropDuplicateEmails(unittest.TestCase):
10+
11+
def test_no_duplicates(self):
12+
data = {
13+
'customer_id': [1, 2, 3],
14+
'name': ['Ella', 'David', 'Zachary'],
15+
'email': ['emily@example.com', 'michael@example.com', 'sarah@example.com']
16+
}
17+
customers = pd.DataFrame(data)
18+
expected = pd.DataFrame(data)
19+
20+
result = dropDuplicateEmails(customers).reset_index(drop=True)
21+
expected = expected.reset_index(drop=True)
22+
23+
assert_frame_equal(result, expected)
24+
25+
def test_with_duplicates(self):
26+
data = {
27+
'customer_id': [1, 2, 3, 4, 5, 6],
28+
'name': ['Ella', 'David', 'Zachary', 'Alice', 'Finn', 'Violet'],
29+
'email': [
30+
'emily@example.com', 'michael@example.com', 'sarah@example.com',
31+
'john@example.com', 'john@example.com', 'alice@example.com'
32+
]
33+
}
34+
customers = pd.DataFrame(data)
35+
36+
expected_data = {
37+
'customer_id': [1, 2, 3, 4, 6],
38+
'name': ['Ella', 'David', 'Zachary', 'Alice', 'Violet'],
39+
'email': ['emily@example.com', 'michael@example.com', 'sarah@example.com', 'john@example.com', 'alice@example.com']
40+
}
41+
expected = pd.DataFrame(expected_data)
42+
43+
result = dropDuplicateEmails(customers).reset_index(drop=True)
44+
expected = expected.reset_index(drop=True)
45+
46+
assert_frame_equal(result, expected)
47+
48+
def test_empty_dataframe(self):
49+
customers = pd.DataFrame(columns=['customer_id', 'name', 'email'])
50+
expected = customers.copy()
51+
52+
result = dropDuplicateEmails(customers).reset_index(drop=True)
53+
expected = expected.reset_index(drop=True)
54+
55+
assert_frame_equal(result, expected)
56+
57+
def test_single_row(self):
58+
data = {
59+
'customer_id': [1],
60+
'name': ['Ella'],
61+
'email': ['emily@example.com']
62+
}
63+
customers = pd.DataFrame(data)
64+
expected = pd.DataFrame(data)
65+
66+
result = dropDuplicateEmails(customers).reset_index(drop=True)
67+
expected = expected.reset_index(drop=True)
68+
69+
assert_frame_equal(result, expected)
70+
71+
if __name__ == '__main__':
72+
unittest.main()
Lines changed: 94 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,94 @@
1+
import unittest
2+
import pandas as pd
3+
from pandas.testing import assert_frame_equal
4+
5+
def dropMissingData(students: pd.DataFrame) -> pd.DataFrame:
6+
r = pd.DataFrame(students)
7+
r.dropna(subset='name', inplace=True)
8+
return r
9+
10+
class TestDropMissingData(unittest.TestCase):
11+
12+
def test_no_missing_data(self):
13+
# Input DataFrame with no missing values in the 'name' column
14+
data = {
15+
'student_id': [32, 779, 849],
16+
'name': ['Piper', 'Georgia', 'Willow'],
17+
'age': [5, 20, 14]
18+
}
19+
students = pd.DataFrame(data)
20+
expected = pd.DataFrame(data)
21+
22+
result = dropMissingData(students).reset_index(drop=True)
23+
expected = expected.reset_index(drop=True)
24+
25+
assert_frame_equal(result, expected)
26+
27+
def test_with_missing_data(self):
28+
# Input DataFrame with missing values in the 'name' column
29+
data = {
30+
'student_id': [32, 217, 779, 849],
31+
'name': ['Piper', None, 'Georgia', 'Willow'],
32+
'age': [5, 19, 20, 14]
33+
}
34+
students = pd.DataFrame(data)
35+
36+
# Expected output after removing rows with missing 'name'
37+
expected_data = {
38+
'student_id': [32, 779, 849],
39+
'name': ['Piper', 'Georgia', 'Willow'],
40+
'age': [5, 20, 14]
41+
}
42+
expected = pd.DataFrame(expected_data)
43+
44+
result = dropMissingData(students).reset_index(drop=True)
45+
expected = expected.reset_index(drop=True)
46+
47+
assert_frame_equal(result, expected)
48+
49+
def test_empty_dataframe(self):
50+
# Input: Empty DataFrame
51+
students = pd.DataFrame(columns=['student_id', 'name', 'age'])
52+
expected = students.copy()
53+
54+
result = dropMissingData(students).reset_index(drop=True)
55+
expected = expected.reset_index(drop=True)
56+
57+
assert_frame_equal(result, expected)
58+
59+
def test_all_missing_data(self):
60+
# Input DataFrame where all 'name' values are missing
61+
data = {
62+
'student_id': [217, 301],
63+
'name': [None, None],
64+
'age': [19, 21]
65+
}
66+
students = pd.DataFrame(data)
67+
68+
# Expected: empty DataFrame since all 'name' values are missing
69+
expected = pd.DataFrame(columns=['student_id', 'name', 'age'])
70+
71+
result = dropMissingData(students).reset_index(drop=True)
72+
expected = expected.reset_index(drop=True)
73+
74+
assert_frame_equal(result, expected, check_dtype=False)
75+
76+
def test_single_row_with_missing_name(self):
77+
# Input DataFrame with a single row and missing 'name'
78+
data = {
79+
'student_id': [217],
80+
'name': [None],
81+
'age': [19]
82+
}
83+
students = pd.DataFrame(data)
84+
85+
# Expected: empty DataFrame since the single row has missing 'name'
86+
expected = pd.DataFrame(columns=['student_id', 'name', 'age'])
87+
88+
result = dropMissingData(students).reset_index(drop=True)
89+
expected = expected.reset_index(drop=True)
90+
91+
assert_frame_equal(result, expected, check_dtype=False)
92+
93+
if __name__ == '__main__':
94+
unittest.main()

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /