apunkt/MetaGPT
1
0
Fork 0
mirror of https://github.com/FoundationAgents/MetaGPT.git synced 2026-04-26 17:26:22 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

add ut to check code saving

Browse source
This commit is contained in:
yzlin 2024-02-06 23:57:39 +08:00
parent ee4aba206e
commit ea6c440294
2 changed files with 10 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

6
tests/data/rsp_cache.json
View file

@ -389,5 +389,11 @@
"reflection": "The implementation failed the test case where the input array is [1, 5, 2, 3, 4]. The issue arises because the code does not handle the sorting of elements with the same number of ones in their binary representation correctly. According to the context, for similar number of ones, the elements should be sorted based on their decimal value in ascending order. However, the output [1, 2, 4, 3, 5] shows that 3 and 4 are not in the correct order, indicating that the sorting by decimal value is not functioning as intended. To fix this issue, we should ensure that the sorting is stable, so that when two elements have the same number of ones, they maintain their relative order if their decimal values are already in ascending order.",
"improved_impl": "def sort_array(arr):\n # Helper function to count the number of ones in the binary representation\n def count_ones(n):\n return bin(n).count('1')\n \n # Sort the array using a custom key function\n # The key function returns a tuple (number of ones, value) for each element\n # This ensures that if two elements have the same number of ones, they are sorted by their value\n # We use a stable sorting algorithm to maintain the relative order of elements with the same number of ones\n sorted_arr = sorted(arr, key=lambda x: (count_ones(x), x), reverse=True)\n sorted_arr = sorted(sorted_arr, key=count_ones)\n \n return sorted_arr\n"
},
"[{\"role\": \"system\", \"content\": \"You are Code Interpreter, a world-class programmer that can complete any goal by executing code. Strictly follow the plan and generate code step by step. Each step of the code will be executed on the user's machine, and the user will provide the code execution results to you.**Notice: The code for the next step depends on the code for the previous step. Must reuse variables in the lastest other code directly, dont creat it again, it is very import for you. Use !pip install in a standalone block to install missing packages.Usually the libraries you need are already installed.Dont check if packages already imported.**\"}, {\"role\": \"user\", \"content\": \"\\n## User Requirement\\nRun data analysis on sklearn Iris dataset, include a plot\\n## Context\\n\\n## Current Plan\\n[\\n {\\n \\\"task_id\\\": \\\"1\\\",\\n \\\"dependent_task_ids\\\": [],\\n \\\"instruction\\\": \\\"Load the sklearn Iris dataset.\\\",\\n \\\"task_type\\\": \\\"other\\\",\\n \\\"code\\\": \\\"from sklearn.datasets import load_iris\\\\niris_data = load_iris()\\\",\\n \\\"result\\\": \\\"a successful run\\\",\\n \\\"is_success\\\": true,\\n \\\"is_finished\\\": true\\n },\\n {\\n \\\"task_id\\\": \\\"2\\\",\\n \\\"dependent_task_ids\\\": [\\n \\\"1\\\"\\n ],\\n \\\"instruction\\\": \\\"Perform exploratory data analysis on the Iris dataset.\\\",\\n \\\"task_type\\\": \\\"eda\\\",\\n \\\"code\\\": \\\"\\\",\\n \\\"result\\\": \\\"\\\",\\n \\\"is_success\\\": false,\\n \\\"is_finished\\\": false\\n },\\n {\\n \\\"task_id\\\": \\\"3\\\",\\n \\\"dependent_task_ids\\\": [\\n \\\"2\\\"\\n ],\\n \\\"instruction\\\": \\\"Create a plot visualizing the Iris dataset.\\\",\\n \\\"task_type\\\": \\\"other\\\",\\n \\\"code\\\": \\\"\\\",\\n \\\"result\\\": \\\"\\\",\\n \\\"is_success\\\": false,\\n \\\"is_finished\\\": false\\n }\\n]\\n## Current Task\\n{\\\"task_id\\\":\\\"2\\\",\\\"dependent_task_ids\\\":[\\\"1\\\"],\\\"instruction\\\":\\\"Perform exploratory data analysis on the Iris dataset.\\\",\\\"task_type\\\":\\\"eda\\\",\\\"code\\\":\\\"\\\",\\\"result\\\":\\\"\\\",\\\"is_success\\\":false,\\\"is_finished\\\":false}\\n\"}, {\"role\": \"user\", \"content\": \"\\n# Instruction\\nWrite complete code for 'Current Task'. And avoid duplicating code from finished tasks, such as repeated import of packages, reading data, etc.\\nSpecifically, \\n\\n# Capabilities\\n- You can utilize pre-defined tools in any code lines from 'Available Tools' in the form of Python Class.\\n- You can freely combine the use of any other public packages, like sklearn, numpy, pandas, etc..\\n\\n# Available Tools (can be empty):\\nEach Class tool is described in JSON format. When you call a tool, import the tool first.\\n{}\\n\\n# Constraints:\\n- Ensure the output new code is executable in the same Jupyter notebook with previous tasks code have been executed.\\n- Always prioritize using pre-defined tools for the same functionality.\\n\"}]": {
"code": "import pandas as pd\n\n# Convert the Iris dataset to a DataFrame for easier manipulation\niris_df = pd.DataFrame(data=iris_data.data, columns=iris_data.feature_names)\niris_df['target'] = iris_data.target\niris_df['target_names'] = iris_df['target'].apply(lambda x: iris_data.target_names[x])\n\n# Display basic information about the dataset\niris_df.info()\n\n# Display statistical summary of the dataset\niris_df.describe()\n\n# Display the first few rows of the dataset\ndisplay(iris_df.head())"
},
"[{\"role\": \"system\", \"content\": \"You are Code Interpreter, a world-class programmer that can complete any goal by executing code. Strictly follow the plan and generate code step by step. Each step of the code will be executed on the user's machine, and the user will provide the code execution results to you.**Notice: The code for the next step depends on the code for the previous step. Must reuse variables in the lastest other code directly, dont creat it again, it is very import for you. Use !pip install in a standalone block to install missing packages.Usually the libraries you need are already installed.Dont check if packages already imported.**\"}, {\"role\": \"user\", \"content\": \"\\n## User Requirement\\nRun data analysis on sklearn Iris dataset, include a plot\\n## Context\\n\\n## Current Plan\\n[\\n {\\n \\\"task_id\\\": \\\"1\\\",\\n \\\"dependent_task_ids\\\": [],\\n \\\"instruction\\\": \\\"Load the sklearn Iris dataset.\\\",\\n \\\"task_type\\\": \\\"other\\\",\\n \\\"code\\\": \\\"from sklearn.datasets import load_iris\\\\niris_data = load_iris()\\\",\\n \\\"result\\\": \\\"a successful run\\\",\\n \\\"is_success\\\": true,\\n \\\"is_finished\\\": true\\n },\\n {\\n \\\"task_id\\\": \\\"2\\\",\\n \\\"dependent_task_ids\\\": [\\n \\\"1\\\"\\n ],\\n \\\"instruction\\\": \\\"Perform exploratory data analysis on the Iris dataset.\\\",\\n \\\"task_type\\\": \\\"eda\\\",\\n \\\"code\\\": \\\"import pandas as pd\\\\n\\\\n# Convert the Iris dataset to a DataFrame for easier manipulation\\\\niris_df = pd.DataFrame(data=iris_data.data, columns=iris_data.feature_names)\\\\niris_df['target'] = iris_data.target\\\\niris_df['target_names'] = iris_df['target'].apply(lambda x: iris_data.target_names[x])\\\\n\\\\n# Display basic information about the dataset\\\\niris_df.info()\\\\n\\\\n# Display statistical summary of the dataset\\\\niris_df.describe()\\\\n\\\\n# Display the first few rows of the dataset\\\\ndisplay(iris_df.head())\\\",\\n \\\"result\\\": \\\"a successful run\\\",\\n \\\"is_success\\\": true,\\n \\\"is_finished\\\": true\\n },\\n {\\n \\\"task_id\\\": \\\"3\\\",\\n \\\"dependent_task_ids\\\": [\\n \\\"2\\\"\\n ],\\n \\\"instruction\\\": \\\"Create a plot visualizing the Iris dataset.\\\",\\n \\\"task_type\\\": \\\"other\\\",\\n \\\"code\\\": \\\"\\\",\\n \\\"result\\\": \\\"\\\",\\n \\\"is_success\\\": false,\\n \\\"is_finished\\\": false\\n }\\n]\\n## Current Task\\n{\\\"task_id\\\":\\\"3\\\",\\\"dependent_task_ids\\\":[\\\"2\\\"],\\\"instruction\\\":\\\"Create a plot visualizing the Iris dataset.\\\",\\\"task_type\\\":\\\"other\\\",\\\"code\\\":\\\"\\\",\\\"result\\\":\\\"\\\",\\\"is_success\\\":false,\\\"is_finished\\\":false}\\n\"}, {\"role\": \"user\", \"content\": \"\\n# Instruction\\nWrite complete code for 'Current Task'. And avoid duplicating code from finished tasks, such as repeated import of packages, reading data, etc.\\nSpecifically, \\n\\n# Capabilities\\n- You can utilize pre-defined tools in any code lines from 'Available Tools' in the form of Python Class.\\n- You can freely combine the use of any other public packages, like sklearn, numpy, pandas, etc..\\n\\n# Available Tools (can be empty):\\nEach Class tool is described in JSON format. When you call a tool, import the tool first.\\n{}\\n\\n# Constraints:\\n- Ensure the output new code is executable in the same Jupyter notebook with previous tasks code have been executed.\\n- Always prioritize using pre-defined tools for the same functionality.\\n\"}]": {
"code": "import matplotlib.pyplot as plt\nimport seaborn as sns\n\n# Set the style of seaborn\nsns.set_style('whitegrid')\n\n# Pairplot to visualize the relationships between features\nsns.pairplot(iris_df, hue='target_names', markers='+')\nplt.show()"
},
"\n## context\n\n\n-----\n\n## format example\n[CONTENT]\n{\n \"invoice\": \"False\"\n}\n[/CONTENT]\n\n## nodes: \"<node>: <type> # <instruction>\"\n- invoice: <class 'bool'> # if it's a invoice file, return True else False\n\n\n## constraint\nLanguage: Please use the same language as Human INPUT.\nFormat: output wrapped inside [CONTENT][/CONTENT] like format example, nothing else.\n\n## action\nFollow instructions of nodes, generate output and make sure it follows the format example.\n": "[CONTENT]\n{\n \"invoice\": \"True\"\n}\n[/CONTENT]"
}