Initial commit

metagpt/tools/schemas/CatCount.yml

@@ -0,0 +1,25 @@
+type: class
+description: Add value counts of a categorical column as new feature.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, col: ''str'')'
+    parameters: 'Args: col (str): Column for value counts.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/CatCross.yml

@@ -0,0 +1,27 @@
+type: class
+description: Add pairwise crossed features and convert them to numerical features.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, cols: ''list'', max_cat_num: ''int'' = 100)'
+    parameters: 'Args: cols (list): Columns to be pairwise crossed, at least 2 columns.
+      max_cat_num (int, optional): Maximum unique categories per crossed feature.
+      Defaults to 100.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/FillMissingValue.yml

@@ -0,0 +1,30 @@
+type: class
+description: Completing missing values with simple strategies.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, features: ''list'', strategy: "Literal[''mean'', ''median'',
+      ''most_frequent'', ''constant'']" = ''mean'', fill_value=None)'
+    parameters: 'Args: features (list): Columns to be processed. strategy (Literal["mean",
+      "median", "most_frequent", "constant"], optional): The imputation strategy,
+      notice ''mean'' and ''median'' can only be used for numeric features. Defaults
+      to ''mean''. fill_value (int, optional): Fill_value is used to replace all occurrences
+      of missing_values. Defaults to None.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/GPTvGenerator.yml

@@ -0,0 +1,26 @@
+type: class
+description: Class for generating webpage code from a given webpage screenshot. This
+  class provides methods to generate webpages including all code (HTML, CSS, and JavaScript)
+  based on an image. It utilizes a vision model to analyze the layout from an image
+  and generate webpage codes accordingly.
+methods:
+  __init__:
+    type: function
+    description: Initialize GPTvGenerator class with default values from the configuration.
+    signature: (self)
+    parameters: ''
+  generate_webpages:
+    type: async_function
+    description: 'Asynchronously generate webpages including all code (HTML, CSS,
+      and JavaScript) in one go based on the image. '
+    signature: '(self, image_path: str) -> str'
+    parameters: 'Args: image_path (str): The path of the image file. Returns: str:
+      Generated webpages content.'
+  save_webpages:
+    type: function
+    description: 'Save webpages including all code (HTML, CSS, and JavaScript) at
+      once. '
+    signature: '(webpages: str, save_folder_name: str = ''example'') -> pathlib.Path'
+    parameters: 'Args: webpages (str): The generated webpages content. save_folder_name
+      (str, optional): The name of the folder to save the webpages. Defaults to ''example''.
+      Returns: Path: The path of the saved webpages.'

metagpt/tools/schemas/GeneralSelection.yml

@@ -0,0 +1,25 @@
+type: class
+description: Drop all nan feats and feats with only one unique value.
+methods:
+  __init__:
+    type: function
+    description: Initialize self. See help(type(self)) for accurate signature.
+    signature: '(self, label_col: ''str'')'
+    parameters: ''
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/GroupStat.yml

@@ -0,0 +1,28 @@
+type: class
+description: Aggregate specified column in a DataFrame grouped by another column,
+  adding new features named '<agg_col>_<agg_func>_by_<group_col>'.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, group_col: ''str'', agg_col: ''str'', agg_funcs: ''list'')'
+    parameters: 'Args: group_col (str): Column used for grouping. agg_col (str): Column
+      on which aggregation is performed. agg_funcs (list): List of aggregation functions
+      to apply, such as [''mean'', ''std'']. Each function must be supported by pandas.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/KFoldTargetMeanEncoder.yml

@@ -0,0 +1,29 @@
+type: class
+description: Add a new feature to the DataFrame by k-fold mean encoding of a categorical
+  column using the label column.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, col: ''str'', label: ''str'', n_splits: ''int'' = 5, random_state:
+      ''int'' = 2021)'
+    parameters: 'Args: col (str): Column to be k-fold mean encoded. label (str): Predicted
+      label column. n_splits (int, optional): Number of splits for K-fold. Defaults
+      to 5. random_state (int, optional): Random seed. Defaults to 2021.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/LabelEncode.yml

@@ -0,0 +1,25 @@
+type: class
+description: Apply label encoding to specified categorical columns in-place.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, features: ''list'')'
+    parameters: 'Args: features (list): Categorical columns to be label encoded.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/MaxAbsScale.yml

@@ -0,0 +1,25 @@
+type: class
+description: Scale each feature by its maximum absolute value.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, features: ''list'')'
+    parameters: 'Args: features (list): Columns to be processed.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/MinMaxScale.yml

@@ -0,0 +1,25 @@
+type: class
+description: Transform features by scaling each feature to a range, which is (0, 1).
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, features: ''list'')'
+    parameters: 'Args: features (list): Columns to be processed.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/OneHotEncode.yml

@@ -0,0 +1,26 @@
+type: class
+description: Apply one-hot encoding to specified categorical columns, the original
+  columns will be dropped.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, features: ''list'')'
+    parameters: 'Args: features (list): Columns to be processed.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/OrdinalEncode.yml

@@ -0,0 +1,25 @@
+type: class
+description: Encode categorical features as ordinal integers.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, features: ''list'')'
+    parameters: 'Args: features (list): Columns to be processed.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/PolynomialExpansion.yml

@@ -0,0 +1,28 @@
+type: class
+description: Add polynomial and interaction features from selected numeric columns
+  to input DataFrame.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, cols: ''list'', label_col: ''str'', degree: ''int'' = 2)'
+    parameters: 'Args: cols (list): Columns for polynomial expansion. label_col (str):
+      Label column name. degree (int, optional): The degree of the polynomial features.
+      Defaults to 2.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/RobustScale.yml

@@ -0,0 +1,26 @@
+type: class
+description: Apply the RobustScaler to scale features using statistics that are robust
+  to outliers.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, features: ''list'')'
+    parameters: 'Args: features (list): Columns to be processed.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/SDEngine.yml

@@ -0,0 +1,42 @@
+type: class
+description: Generate image using stable diffusion model. This class provides methods
+  to interact with a stable diffusion service to generate images based on text inputs.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize the SDEngine instance with configuration. '
+    signature: (self, sd_url='')
+    parameters: 'Args: sd_url (str, optional): URL of the stable diffusion service.
+      Defaults to "".'
+  construct_payload:
+    type: function
+    description: 'Modify and set the API parameters for image generation. '
+    signature: (self, prompt, negtive_prompt='(easynegative:0.8),black, dark,Low resolution',
+      width=512, height=512, sd_model='galaxytimemachinesGTM_photoV20')
+    parameters: 'Args: prompt (str): Text input for image generation. negtive_prompt
+      (str, optional): Text input for negative prompts. Defaults to None. width (int,
+      optional): Width of the generated image in pixels. Defaults to 512. height (int,
+      optional): Height of the generated image in pixels. Defaults to 512. sd_model
+      (str, optional): The model to use for image generation. Defaults to "galaxytimemachinesGTM_photoV20".
+      Returns: dict: Updated parameters for the stable diffusion API.'
+  run_t2i:
+    type: async_function
+    description: 'Run the stable diffusion API for multiple prompts asynchronously. '
+    signature: '(self, payloads: ''list'')'
+    parameters: 'Args: payloads (list): list of payload, each payload is a dictionary
+      of input parameters for the stable diffusion API.'
+  save:
+    type: function
+    description: 'Save generated images to the output directory. '
+    signature: (self, imgs, save_name='')
+    parameters: 'Args: imgs (str): Generated images. save_name (str, optional): Output
+      image name. Default is empty.'
+  simple_run_t2i:
+    type: function
+    description: 'Run the stable diffusion API for multiple prompts, calling the stable
+      diffusion API to generate images. '
+    signature: '(self, payload: ''dict'', auto_save: ''bool'' = True)'
+    parameters: 'Args: payload (dict): Dictionary of input parameters for the stable
+      diffusion API. auto_save (bool, optional): Save generated images automatically.
+      Defaults to True. Returns: list: The generated images as a result of the API
+      call.'

metagpt/tools/schemas/SplitBins.yml

@@ -0,0 +1,28 @@
+type: class
+description: Inplace binning of continuous data into intervals, returning integer-encoded
+  bin identifiers directly.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, cols: ''list'', strategy: ''str'' = ''quantile'')'
+    parameters: 'Args: cols (list): Columns to be binned inplace. strategy (str, optional):
+      Strategy used to define the widths of the bins. Enum: [''quantile'', ''uniform'',
+      ''kmeans'']. Defaults to ''quantile''.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/StandardScale.yml

@@ -0,0 +1,25 @@
+type: class
+description: Standardize features by removing the mean and scaling to unit variance.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, features: ''list'')'
+    parameters: 'Args: features (list): Columns to be processed.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/TargetMeanEncoder.yml

@@ -0,0 +1,27 @@
+type: class
+description: Encode a categorical column by the mean of the label column, and adds
+  the result as a new feature.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, col: ''str'', label: ''str'')'
+    parameters: 'Args: col (str): Column to be mean encoded. label (str): Predicted
+      label column.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/VarianceBasedSelection.yml

@@ -0,0 +1,26 @@
+type: class
+description: Select features based on variance and remove features with low variance.
+methods:
+  __init__:
+    type: function
+    description: 'Initialize self. '
+    signature: '(self, label_col: ''str'', threshold: ''float'' = 0)'
+    parameters: 'Args: label_col (str): Label column name. threshold (float, optional):
+      Threshold for variance. Defaults to 0.'
+  fit:
+    type: function
+    description: 'Fit a model to be used in subsequent transform. '
+    signature: '(self, df: ''pd.DataFrame'')'
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame.'
+  fit_transform:
+    type: function
+    description: 'Fit and transform the input DataFrame. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'
+  transform:
+    type: function
+    description: 'Transform the input DataFrame with the fitted model. '
+    signature: '(self, df: ''pd.DataFrame'') -> ''pd.DataFrame'''
+    parameters: 'Args: df (pd.DataFrame): The input DataFrame. Returns: pd.DataFrame:
+      The transformed DataFrame.'

metagpt/tools/schemas/email_login_imap.yml

@@ -0,0 +1,9 @@
+type: function
+description: 'Use imap_tools package to log in to your email (the email that supports
+  IMAP protocol) to verify and return the account object. '
+signature: (email_address, email_password)
+parameters: 'Args: email_address (str): Email address that needs to be logged in and
+  linked. email_password (str): Password for the email address that needs to be logged
+  in and linked. Returns: object: The imap_tools''s MailBox object returned after
+  successfully connecting to the mailbox through imap_tools, including various information
+  about this account (email, etc.), or None if login fails.'

metagpt/tools/schemas/scrape_web_playwright.yml

@@ -0,0 +1,7 @@
+type: async_function
+description: 'Asynchronously Scrape and save the HTML structure and inner text content
+  of a web page using Playwright. '
+signature: (url)
+parameters: 'Args: url (str): The main URL to fetch inner text from. Returns: dict:
+  The inner text content and html structure of the web page, keys are ''inner_text'',
+  ''html''.'