From 07771a769955f900b305334920d2ef5c70eae5bc Mon Sep 17 00:00:00 2001
From: lidanyang <lidanyang@fuzhi.ai>
Date: Tue, 12 Dec 2023 10:56:51 +0800
Subject: [PATCH] add ml Class tool schema

---
 .../functions/schemas/data_preprocess.yml     | 306 +++++++++++++
 .../functions/schemas/feature_engineering.yml | 429 ++++++++++++++++++
 2 files changed, 735 insertions(+)
 create mode 100644 metagpt/tools/functions/schemas/data_preprocess.yml
 create mode 100644 metagpt/tools/functions/schemas/feature_engineering.yml

diff --git a/metagpt/tools/functions/schemas/data_preprocess.yml b/metagpt/tools/functions/schemas/data_preprocess.yml
new file mode 100644
index 000000000..95b0124cc
--- /dev/null
+++ b/metagpt/tools/functions/schemas/data_preprocess.yml
@@ -0,0 +1,306 @@
+FillMissingValue:
+  type: class
+  description: "Completing missing values with simple strategies"
+  methods:
+    __init__:
+      description: "Initialize self."
+      parameters:
+        properties:
+          features:
+            type: list
+            description: "columns to be processed"
+          strategy:
+            type: str
+            description: "the imputation strategy"
+            default: mean
+            enum:
+              - mean
+              - median
+              - most_frequent
+              - constant
+          fill_value:
+            type: int
+            description: "fill_value is used to replace all occurrences of missing_values"
+            default: null
+        required:
+          - features
+    fit:
+      description: "Fit the FillMissingValue model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+    transform:
+      description: "Transform the input DataFrame with the fitted model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+    fit_transform:
+      description: "Fit and transform the input DataFrame."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+
+MinMaxScale:
+  type: class
+  description: "Transform features by scaling each feature to a range, witch is (0, 1)"
+  methods:
+    __init__:
+      description: "Initialize self."
+      parameters:
+        properties:
+          features:
+            type: list
+            description: "columns to be processed"
+        required:
+          - features
+    fit:
+      description: "Fit the MinMaxScale model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+    transform:
+      description: "Transform the input DataFrame with the fitted model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+    fit_transform:
+      description: "Fit and transform the input DataFrame."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+
+StandardScale:
+  type: class
+  description: "Standardize features by removing the mean and scaling to unit variance"
+  methods:
+    __init__:
+      description: "Initialize self."
+      parameters:
+        properties:
+          features:
+            type: list
+            description: "columns to be processed"
+        required:
+          - features
+    fit:
+      description: "Fit the StandardScale model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+    transform:
+      description: "Transform the input DataFrame with the fitted model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+    fit_transform:
+      description: "Fit and transform the input DataFrame."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+
+MaxAbsScale:
+  type: class
+  description: "cale each feature by its maximum absolute value"
+  methods:
+    __init__:
+      description: "Initialize self."
+      parameters:
+        properties:
+          features:
+            type: list
+            description: "columns to be processed"
+        required:
+          - features
+    fit:
+      description: "Fit the MaxAbsScale model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+    transform:
+      description: "Transform the input DataFrame with the fitted model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+    fit_transform:
+      description: "Fit and transform the input DataFrame."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+
+LabelEncode:
+  type: class
+  description: "Apply label encoding to specified categorical columns in-place."
+  methods:
+    __init__:
+      description: "Initialize self."
+      parameters:
+        properties:
+          features:
+            type: list
+            description: "Categorical columns to be label encoded"
+        required:
+          - features
+    fit:
+      description: "Fit the LabelEncode model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+    transform:
+      description: "Transform the input DataFrame with the fitted model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+    fit_transform:
+      description: "Fit and transform the input DataFrame."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+
+OneHotEncode:
+  type: class
+  description: "Apply one-hot encoding to specified categorical columns, the original columns will be dropped."
+  methods:
+    __init__:
+      description: "Initialize self."
+      parameters:
+        properties:
+          features:
+            type: list
+            description: "Categorical columns to be one-hot encoded and dropped"
+        required:
+          - features
+    fit:
+      description: "Fit the OneHotEncoding model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+    transform:
+      description: "Transform the input DataFrame with the fitted model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+    fit_transform:
+      description: "Fit and transform the input DataFrame."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
\ No newline at end of file
diff --git a/metagpt/tools/functions/schemas/feature_engineering.yml b/metagpt/tools/functions/schemas/feature_engineering.yml
new file mode 100644
index 000000000..2cc4ec2fa
--- /dev/null
+++ b/metagpt/tools/functions/schemas/feature_engineering.yml
@@ -0,0 +1,429 @@
+PolynomialExpansion:
+  type: class
+  description: "Add polynomial and interaction features from selected numeric columns, excluding the bias column."
+  methods:
+    __init__:
+      description: "Initialize self."
+      parameters:
+        properties:
+          cols:
+            type: list
+            description: "Columns for polynomial expansion."
+          degree:
+            type: int
+            description: "The degree of the polynomial features."
+            default: 2
+        required:
+          - cols
+    fit:
+      description: "Fit the PolynomialExpansion model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+    transform:
+      description: "Transform the input DataFrame with the fitted model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+    fit_transform:
+      description: "Fit and transform the input DataFrame."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+
+CatCount:
+  type: class
+  description: "Add value counts of categorical columns as new features."
+  methods:
+    __init__:
+      description: "Initialize self."
+      parameters:
+        properties:
+          cols:
+            type: list
+            description: "Columns for value counts."
+        required:
+          - cols
+    fit:
+      description: "Fit the CatCount model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+    transform:
+      description: "Transform the input DataFrame with the fitted model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+    fit_transform:
+      description: "Fit and transform the input DataFrame."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+
+TargetMeanEncoder:
+  type: class
+  description: "Encodes a categorical column by the mean of the label column, and adds the result as a new feature."
+  methods:
+    __init__:
+      description: "Initialize self."
+      parameters:
+        properties:
+          col:
+            type: str
+            description: "Column to be mean encoded."
+          label:
+            type: str
+            description: "Predicted label column."
+        required:
+          - col
+          - label
+    fit:
+      description: "Fit the TargetMeanEncoder model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+    transform:
+      description: "Transform the input DataFrame with the fitted model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+    fit_transform:
+      description: "Fit and transform the input DataFrame."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+
+KFoldTargetMeanEncoder:
+  type: class
+  description: "Adds a new feature to the DataFrame by k-fold mean encoding of a categorical column using the label column."
+  methods:
+    __init__:
+      description: "Initialize self."
+      parameters:
+        properties:
+          col:
+            type: str
+            description: "Column to be k-fold mean encoded."
+          label:
+            type: str
+            description: "Predicted label column."
+          n_splits:
+            type: int
+            description: "Number of splits for K-fold."
+            default: 5
+          random_state:
+            type: int
+            description: "Random seed."
+            default: 2021
+        required:
+          - col
+          - label
+    fit:
+      description: "Fit the KFoldTargetMeanEncoder model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+    transform:
+      description: "Transform the input DataFrame with the fitted model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+    fit_transform:
+      description: "Fit and transform the input DataFrame."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+
+CatCross:
+  type: class
+  description: "Add pairwise crossed features and convert them to numerical features."
+  methods:
+    __init__:
+      description: "Initialize self."
+      parameters:
+        properties:
+          cols:
+            type: list
+            description: "Columns to be pairwise crossed."
+          max_cat_num:
+            type: int
+            description: "Maximum unique categories per crossed feature."
+            default: 100
+      required:
+        - cols
+    fit:
+      description: "Fit the CatCross model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+    transform:
+      description: "Transform the input DataFrame with the fitted model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+    fit_transform:
+      description: "Fit and transform the input DataFrame."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+
+GroupStat:
+  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__:
+      description: "Initialize self."
+      parameters:
+        properties:
+          group_col:
+            type: str
+            description: "Column used for grouping."
+          agg_col:
+            type: str
+            description: "Column on which aggregation is performed."
+          agg_funcs:
+            type: list
+            description: >-
+              List of aggregation functions to apply, such as ['mean', 'std'].
+              Each function must be supported by pandas.
+        required:
+          - group_col
+          - agg_col
+          - agg_funcs
+    fit:
+      description: "Fit the GroupStat model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+    transform:
+      description: "Transform the input DataFrame with the fitted model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+    fit_transform:
+      description: "Fit and transform the input DataFrame."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+
+SplitBins:
+  type: class
+  description: "Bin continuous data into intervals and return the bin identifier encoded as an integer value"
+  methods:
+    __init__:
+      description: "Initialize self."
+      parameters:
+        properties:
+          cols:
+            type: list
+            description: "Columns to be binned."
+          strategy:
+            type: str
+            description: "Strategy used to define the widths of the bins."
+            default: quantile
+        required:
+          - cols
+    fit:
+      description: "Fit the SplitBins model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+    transform:
+      description: "Transform the input DataFrame with the fitted model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+    fit_transform:
+      description: "Fit and transform the input DataFrame."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+
+GeneralSelection:
+  type: class
+  description: "Drop all nan feats and feats with only one unique value."
+  methods:
+    __init__:
+      description: "Initialize self."
+      parameters:
+        properties:
+          label_col:
+            type: str
+            description: "Label column name."
+        required:
+          - label_col
+    fit:
+      description: "Fit the GeneralSelection model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+    transform:
+      description: "Transform the input DataFrame with the fitted model."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
+    fit_transform:
+      description: "Fit and transform the input DataFrame."
+      parameters:
+        properties:
+          df:
+            type: DataFrame
+            description: "The input DataFrame."
+        required:
+          - df
+      returns:
+        df:
+          type: DataFrame
+          description: "The transformed DataFrame."
\ No newline at end of file