mirror of
https://gitee.com/coder-xiaomo/leetcode-problemset
synced 2025-01-10 18:48:13 +08:00
55 lines
6.8 KiB
JSON
55 lines
6.8 KiB
JSON
{
|
||
"data": {
|
||
"question": {
|
||
"questionId": "3071",
|
||
"questionFrontendId": "2882",
|
||
"categoryTitle": "pandas",
|
||
"boundTopicId": 2467488,
|
||
"title": "Drop Duplicate Rows",
|
||
"titleSlug": "drop-duplicate-rows",
|
||
"content": "<pre>\nDataFrame customers\n+-------------+--------+\n| Column Name | Type |\n+-------------+--------+\n| customer_id | int |\n| name | object |\n| email | object |\n+-------------+--------+\n</pre>\n\n<p>There are some duplicate rows in the DataFrame based on the <code>email</code> column.</p>\n\n<p>Write a solution to remove these duplicate rows and keep only the <strong>first</strong> occurrence.</p>\n\n<p>The result format is in the following example.</p>\n\n<p> </p>\n<pre>\n<strong class=\"example\">Example 1:</strong>\n<strong>Input:</strong>\n+-------------+---------+---------------------+\n| customer_id | name | email |\n+-------------+---------+---------------------+\n| 1 | Ella | emily@example.com |\n| 2 | David | michael@example.com |\n| 3 | Zachary | sarah@example.com |\n| 4 | Alice | john@example.com |\n| 5 | Finn | john@example.com |\n| 6 | Violet | alice@example.com |\n+-------------+---------+---------------------+\n<strong>Output: </strong> \n+-------------+---------+---------------------+\n| customer_id | name | email |\n+-------------+---------+---------------------+\n| 1 | Ella | emily@example.com |\n| 2 | David | michael@example.com |\n| 3 | Zachary | sarah@example.com |\n| 4 | Alice | john@example.com |\n| 6 | Violet | alice@example.com |\n+-------------+---------+---------------------+\n<strong>Explanation:</strong>\nAlic (customer_id = 4) and Finn (customer_id = 5) both use john@example.com, so only the first occurrence of this email is retained.\n</pre>\n",
|
||
"translatedTitle": "删去重复的行",
|
||
"translatedContent": "<pre>\nDataFrame customers\n+-------------+--------+\n| Column Name | Type |\n+-------------+--------+\n| customer_id | int |\n| name | object |\n| email | object |\n+-------------+--------+\n</pre>\n\n<p>在 DataFrame 中基于 <code>email</code> 列存在一些重复行。</p>\n\n<p>编写一个解决方案，删除这些重复行，仅保留第一次出现的行。</p>\n\n<p>返回结果格式如下例所示。</p>\n\n<p> </p>\n\n<p><strong>示例 1:</strong></p>\n\n<pre>\n<b>输入：</b>\n+-------------+---------+---------------------+\n| customer_id | name | email |\n+-------------+---------+---------------------+\n| 1 | Ella | emily@example.com |\n| 2 | David | michael@example.com |\n| 3 | Zachary | sarah@example.com |\n| 4 | Alice | john@example.com |\n| 5 | Finn | john@example.com |\n| 6 | Violet | alice@example.com |\n+-------------+---------+---------------------+\n<b>输出：</b>\n+-------------+---------+---------------------+\n| customer_id | name | email |\n+-------------+---------+---------------------+\n| 1 | Ella | emily@example.com |\n| 2 | David | michael@example.com |\n| 3 | Zachary | sarah@example.com |\n| 4 | Alice | john@example.com |\n| 6 | Violet | alice@example.com |\n+-------------+---------+---------------------+\n<b>解释：</b>\nAlice (customer_id = 4) 和 Finn (customer_id = 5) 都使用 john@example.com，因此只保留该邮箱地址的第一次出现。\n</pre>\n",
|
||
"isPaidOnly": false,
|
||
"difficulty": "Easy",
|
||
"likes": 1,
|
||
"dislikes": 0,
|
||
"isLiked": null,
|
||
"similarQuestions": "[]",
|
||
"contributors": [],
|
||
"langToValidPlayground": "{\"cpp\": false, \"java\": false, \"python\": false, \"python3\": false, \"mysql\": false, \"mssql\": false, \"oraclesql\": false, \"c\": false, \"csharp\": false, \"javascript\": false, \"typescript\": false, \"bash\": false, \"php\": false, \"swift\": false, \"kotlin\": false, \"dart\": false, \"golang\": false, \"ruby\": false, \"scala\": false, \"html\": false, \"pythonml\": false, \"rust\": false, \"racket\": false, \"erlang\": false, \"elixir\": false, \"pythondata\": false, \"react\": false, \"vanillajs\": false, \"postgresql\": false}",
|
||
"topicTags": [],
|
||
"companyTagStats": null,
|
||
"codeSnippets": [
|
||
{
|
||
"lang": "Pandas",
|
||
"langSlug": "pythondata",
|
||
"code": "import pandas as pd\n\ndef dropDuplicateEmails(customers: pd.DataFrame) -> pd.DataFrame:\n ",
|
||
"__typename": "CodeSnippetNode"
|
||
}
|
||
],
|
||
"stats": "{\"totalAccepted\": \"1.5K\", \"totalSubmission\": \"1.9K\", \"totalAcceptedRaw\": 1536, \"totalSubmissionRaw\": 1925, \"acRate\": \"79.8%\"}",
|
||
"hints": [
|
||
"Consider using a build-in function in pandas library to remove the duplicate rows based on specified data."
|
||
],
|
||
"solution": null,
|
||
"status": null,
|
||
"sampleTestCase": "{\"headers\":{\"customers\":[\"customer_id\",\"name\",\"email\"]},\"rows\":{\"customers\":[[1,\"Ella\",\"emily@example.com\"],[2,\"David\",\"michael@example.com\"],[3,\"Zachary\",\"sarah@example.com\"],[4,\"Alice\",\"john@example.com\"],[5,\"Finn\",\"john@example.com\"],[6,\"Violet\",\"alice@example.com\"]]}}",
|
||
"metaData": "{\n \"pythondata\": [\n \"customers = pd.DataFrame([], columns=['customer_id', 'name', 'email']).astype({'customer_id':'Int64', 'name':'object', 'email':'object'})\"\n ],\n \"database\": true,\n \"name\": \"dropDuplicateEmails\",\n \"languages\": [\n \"pythondata\"\n ]\n}",
|
||
"judgerAvailable": true,
|
||
"judgeType": "large",
|
||
"mysqlSchemas": [],
|
||
"enableRunCode": true,
|
||
"envInfo": "{\"pythondata\":[\"Pandas\",\"<p>Python 3.10 with Pandas 2.0.2 and NumPy 1.25.0<\\/p>\"]}",
|
||
"book": null,
|
||
"isSubscribed": false,
|
||
"isDailyQuestion": false,
|
||
"dailyRecordStatus": null,
|
||
"editorType": "CKEDITOR",
|
||
"ugcQuestionId": null,
|
||
"style": "LEETCODE",
|
||
"exampleTestcases": "{\"headers\":{\"customers\":[\"customer_id\",\"name\",\"email\"]},\"rows\":{\"customers\":[[1,\"Ella\",\"emily@example.com\"],[2,\"David\",\"michael@example.com\"],[3,\"Zachary\",\"sarah@example.com\"],[4,\"Alice\",\"john@example.com\"],[5,\"Finn\",\"john@example.com\"],[6,\"Violet\",\"alice@example.com\"]]}}",
|
||
"__typename": "QuestionNode"
|
||
}
|
||
}
|
||
} |