README.md

metadata

library_name: sklearn
license: mit
tags:
  - sklearn
  - skops
  - tabular-classification
model_format: pickle
model_file: RandomForestClassifier.joblib
widget:
  - structuredData:
      age:
        - 50
        - 31
        - 32
      bd2:
        - 0.627
        - 0.351
        - 0.672
      id:
        - ICU200010
        - ICU200011
        - ICU200012
      insurance:
        - 0
        - 0
        - 1
      m11:
        - 33.6
        - 26.6
        - 23.3
      pl:
        - 148
        - 85
        - 183
      pr:
        - 72
        - 66
        - 64
      prg:
        - 6
        - 1
        - 8
      sepsis:
        - Positive
        - Negative
        - Positive
      sk:
        - 35
        - 29
        - 0
      ts:
        - 0
        - 0
        - 0

Model description

[More Information Needed]

Intended uses & limitations

[More Information Needed]

Training Procedure

[More Information Needed]

Hyperparameters

Click to expand

Hyperparameter	Value
memory
steps	[('preprocessor', ColumnTransformer(transformers=[('numerical_pipeline', Pipeline(steps=[('log_transformations', FunctionTransformer(func=<ufunc 'log1p'>)), ('imputer', SimpleImputer(strategy='median')), ('scaler', RobustScaler())]), ['prg', 'pl', 'pr', 'sk', 'ts', 'm11', 'bd2', 'age']), ('categorical_pipeline', Pipeline(steps=[('as_categorical', FunctionTransformer(func=<function as_... handle_unknown='infrequent_if_exist', sparse_output=False))]), ['insurance']), ('feature_creation_pipeline', Pipeline(steps=[('feature_creation', FunctionTransformer(func=<function feature_creation at 0x000001E7F14514E0>)), ('imputer', SimpleImputer(strategy='most_frequent')), ('encoder', OneHotEncoder(drop='first', handle_unknown='infrequent_if_exist', sparse_output=False))]), ['age'])])), ('feature-selection', SelectKBest(k='all', score_func=<function mutual_info_classif at 0x000001E7EDA4E480>)), ('classifier', RandomForestClassifier(n_jobs=-1, random_state=2024))]
verbose	False
preprocessor	ColumnTransformer(transformers=[('numerical_pipeline', Pipeline(steps=[('log_transformations', FunctionTransformer(func=<ufunc 'log1p'>)), ('imputer', SimpleImputer(strategy='median')), ('scaler', RobustScaler())]), ['prg', 'pl', 'pr', 'sk', 'ts', 'm11', 'bd2', 'age']), ('categorical_pipeline', Pipeline(steps=[('as_categorical', FunctionTransformer(func=<function as_... handle_unknown='infrequent_if_exist', sparse_output=False))]), ['insurance']), ('feature_creation_pipeline', Pipeline(steps=[('feature_creation', FunctionTransformer(func=<function feature_creation at 0x000001E7F14514E0>)), ('imputer', SimpleImputer(strategy='most_frequent')), ('encoder', OneHotEncoder(drop='first', handle_unknown='infrequent_if_exist', sparse_output=False))]), ['age'])])
feature-selection	SelectKBest(k='all', score_func=<function mutual_info_classif at 0x000001E7EDA4E480>)
classifier	RandomForestClassifier(n_jobs=-1, random_state=2024)
preprocessor__force_int_remainder_cols	True
preprocessor__n_jobs
preprocessor__remainder	drop
preprocessor__sparse_threshold	0.3
preprocessor__transformer_weights
preprocessor__transformers	[('numerical_pipeline', Pipeline(steps=[('log_transformations', FunctionTransformer(func=<ufunc 'log1p'>)), ('imputer', SimpleImputer(strategy='median')), ('scaler', RobustScaler())]), ['prg', 'pl', 'pr', 'sk', 'ts', 'm11', 'bd2', 'age']), ('categorical_pipeline', Pipeline(steps=[('as_categorical', FunctionTransformer(func=<function as_category at 0x000001E7F1450680>)), ('imputer', SimpleImputer(strategy='most_frequent')), ('encoder', OneHotEncoder(drop='first', handle_unknown='infrequent_if_exist', sparse_output=False))]), ['insurance']), ('feature_creation_pipeline', Pipeline(steps=[('feature_creation', FunctionTransformer(func=<function feature_creation at 0x000001E7F14514E0>)), ('imputer', SimpleImputer(strategy='most_frequent')), ('encoder', OneHotEncoder(drop='first', handle_unknown='infrequent_if_exist', sparse_output=False))]), ['age'])]
preprocessor__verbose	False
preprocessor__verbose_feature_names_out	True
preprocessor__numerical_pipeline	Pipeline(steps=[('log_transformations', FunctionTransformer(func=<ufunc 'log1p'>)), ('imputer', SimpleImputer(strategy='median')), ('scaler', RobustScaler())])
preprocessor__categorical_pipeline	Pipeline(steps=[('as_categorical', FunctionTransformer(func=<function as_category at 0x000001E7F1450680>)), ('imputer', SimpleImputer(strategy='most_frequent')), ('encoder', OneHotEncoder(drop='first', handle_unknown='infrequent_if_exist', sparse_output=False))])
preprocessor__feature_creation_pipeline	Pipeline(steps=[('feature_creation', FunctionTransformer(func=<function feature_creation at 0x000001E7F14514E0>)), ('imputer', SimpleImputer(strategy='most_frequent')), ('encoder', OneHotEncoder(drop='first', handle_unknown='infrequent_if_exist', sparse_output=False))])
preprocessor__numerical_pipeline__memory
preprocessor__numerical_pipeline__steps	[('log_transformations', FunctionTransformer(func=<ufunc 'log1p'>)), ('imputer', SimpleImputer(strategy='median')), ('scaler', RobustScaler())]
preprocessor__numerical_pipeline__verbose	False
preprocessor__numerical_pipeline__log_transformations	FunctionTransformer(func=<ufunc 'log1p'>)
preprocessor__numerical_pipeline__imputer	SimpleImputer(strategy='median')
preprocessor__numerical_pipeline__scaler	RobustScaler()
preprocessor__numerical_pipeline__log_transformations__accept_sparse	False
preprocessor__numerical_pipeline__log_transformations__check_inverse	True
preprocessor__numerical_pipeline__log_transformations__feature_names_out
preprocessor__numerical_pipeline__log_transformations__func	<ufunc 'log1p'>
preprocessor__numerical_pipeline__log_transformations__inv_kw_args
preprocessor__numerical_pipeline__log_transformations__inverse_func
preprocessor__numerical_pipeline__log_transformations__kw_args
preprocessor__numerical_pipeline__log_transformations__validate	False
preprocessor__numerical_pipeline__imputer__add_indicator	False
preprocessor__numerical_pipeline__imputer__copy	True
preprocessor__numerical_pipeline__imputer__fill_value
preprocessor__numerical_pipeline__imputer__keep_empty_features	False
preprocessor__numerical_pipeline__imputer__missing_values	nan
preprocessor__numerical_pipeline__imputer__strategy	median
preprocessor__numerical_pipeline__scaler__copy	True
preprocessor__numerical_pipeline__scaler__quantile_range	(25.0, 75.0)
preprocessor__numerical_pipeline__scaler__unit_variance	False
preprocessor__numerical_pipeline__scaler__with_centering	True
preprocessor__numerical_pipeline__scaler__with_scaling	True
preprocessor__categorical_pipeline__memory
preprocessor__categorical_pipeline__steps	[('as_categorical', FunctionTransformer(func=<function as_category at 0x000001E7F1450680>)), ('imputer', SimpleImputer(strategy='most_frequent')), ('encoder', OneHotEncoder(drop='first', handle_unknown='infrequent_if_exist', sparse_output=False))]
preprocessor__categorical_pipeline__verbose	False
preprocessor__categorical_pipeline__as_categorical	FunctionTransformer(func=<function as_category at 0x000001E7F1450680>)
preprocessor__categorical_pipeline__imputer	SimpleImputer(strategy='most_frequent')
preprocessor__categorical_pipeline__encoder	OneHotEncoder(drop='first', handle_unknown='infrequent_if_exist', sparse_output=False)
preprocessor__categorical_pipeline__as_categorical__accept_sparse	False
preprocessor__categorical_pipeline__as_categorical__check_inverse	True
preprocessor__categorical_pipeline__as_categorical__feature_names_out
preprocessor__categorical_pipeline__as_categorical__func	<function as_category at 0x000001E7F1450680>
preprocessor__categorical_pipeline__as_categorical__inv_kw_args
preprocessor__categorical_pipeline__as_categorical__inverse_func
preprocessor__categorical_pipeline__as_categorical__kw_args
preprocessor__categorical_pipeline__as_categorical__validate	False
preprocessor__categorical_pipeline__imputer__add_indicator	False
preprocessor__categorical_pipeline__imputer__copy	True
preprocessor__categorical_pipeline__imputer__fill_value
preprocessor__categorical_pipeline__imputer__keep_empty_features	False
preprocessor__categorical_pipeline__imputer__missing_values	nan
preprocessor__categorical_pipeline__imputer__strategy	most_frequent
preprocessor__categorical_pipeline__encoder__categories	auto
preprocessor__categorical_pipeline__encoder__drop	first
preprocessor__categorical_pipeline__encoder__dtype	<class 'numpy.float64'>
preprocessor__categorical_pipeline__encoder__feature_name_combiner	concat
preprocessor__categorical_pipeline__encoder__handle_unknown	infrequent_if_exist
preprocessor__categorical_pipeline__encoder__max_categories
preprocessor__categorical_pipeline__encoder__min_frequency
preprocessor__categorical_pipeline__encoder__sparse_output	False
preprocessor__feature_creation_pipeline__memory
preprocessor__feature_creation_pipeline__steps	[('feature_creation', FunctionTransformer(func=<function feature_creation at 0x000001E7F14514E0>)), ('imputer', SimpleImputer(strategy='most_frequent')), ('encoder', OneHotEncoder(drop='first', handle_unknown='infrequent_if_exist', sparse_output=False))]
preprocessor__feature_creation_pipeline__verbose	False
preprocessor__feature_creation_pipeline__feature_creation	FunctionTransformer(func=<function feature_creation at 0x000001E7F14514E0>)
preprocessor__feature_creation_pipeline__imputer	SimpleImputer(strategy='most_frequent')
preprocessor__feature_creation_pipeline__encoder	OneHotEncoder(drop='first', handle_unknown='infrequent_if_exist', sparse_output=False)
preprocessor__feature_creation_pipeline__feature_creation__accept_sparse	False
preprocessor__feature_creation_pipeline__feature_creation__check_inverse	True
preprocessor__feature_creation_pipeline__feature_creation__feature_names_out
preprocessor__feature_creation_pipeline__feature_creation__func	<function feature_creation at 0x000001E7F14514E0>
preprocessor__feature_creation_pipeline__feature_creation__inv_kw_args
preprocessor__feature_creation_pipeline__feature_creation__inverse_func
preprocessor__feature_creation_pipeline__feature_creation__kw_args
preprocessor__feature_creation_pipeline__feature_creation__validate	False
preprocessor__feature_creation_pipeline__imputer__add_indicator	False
preprocessor__feature_creation_pipeline__imputer__copy	True
preprocessor__feature_creation_pipeline__imputer__fill_value
preprocessor__feature_creation_pipeline__imputer__keep_empty_features	False
preprocessor__feature_creation_pipeline__imputer__missing_values	nan
preprocessor__feature_creation_pipeline__imputer__strategy	most_frequent
preprocessor__feature_creation_pipeline__encoder__categories	auto
preprocessor__feature_creation_pipeline__encoder__drop	first
preprocessor__feature_creation_pipeline__encoder__dtype	<class 'numpy.float64'>
preprocessor__feature_creation_pipeline__encoder__feature_name_combiner	concat
preprocessor__feature_creation_pipeline__encoder__handle_unknown	infrequent_if_exist
preprocessor__feature_creation_pipeline__encoder__max_categories
preprocessor__feature_creation_pipeline__encoder__min_frequency
preprocessor__feature_creation_pipeline__encoder__sparse_output	False
feature-selection__k	all
feature-selection__score_func	<function mutual_info_classif at 0x000001E7EDA4E480>
classifier__bootstrap	True
classifier__ccp_alpha	0.0
classifier__class_weight
classifier__criterion	gini
classifier__max_depth
classifier__max_features	sqrt
classifier__max_leaf_nodes
classifier__max_samples
classifier__min_impurity_decrease	0.0
classifier__min_samples_leaf	1
classifier__min_samples_split	2
classifier__min_weight_fraction_leaf	0.0
classifier__monotonic_cst
classifier__n_estimators	100
classifier__n_jobs	-1
classifier__oob_score	False
classifier__random_state	2024
classifier__verbose	0
classifier__warm_start	False

Model Plot

Pipeline(steps=[('preprocessor',ColumnTransformer(transformers=[('numerical_pipeline',Pipeline(steps=[('log_transformations',FunctionTransformer(func=<ufunc 'log1p'>)),('imputer',SimpleImputer(strategy='median')),('scaler',RobustScaler())]),['prg', 'pl', 'pr', 'sk','ts', 'm11', 'bd2', 'age']),('categorical_pipeline',Pipeline(steps=[('as_categorical',Funct...FunctionTransformer(func=<function feature_creation at 0x000001E7F14514E0>)),('imputer',SimpleImputer(strategy='most_frequent')),('encoder',OneHotEncoder(drop='first',handle_unknown='infrequent_if_exist',sparse_output=False))]),['age'])])),('feature-selection',SelectKBest(k='all',score_func=<function mutual_info_classif at 0x000001E7EDA4E480>)),('classifier',RandomForestClassifier(n_jobs=-1, random_state=2024))])

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

Evaluation Results

[More Information Needed]

How to Get Started with the Model

[More Information Needed]

Model Card Authors

This model card is written by following authors:

[More Information Needed]

Model Card Contact

You can contact the model card authors through following channels: [More Information Needed]

Citation

Below you can find information related to citation.

BibTeX:

[More Information Needed]

citation_bibtex

bibtex @inproceedings{...,year={2024}}

get_started_code

import joblib clf = joblib.load(../models/RandomForestClassifier.joblib)

model_card_authors

Gabriel Okundaye

limitations

This model needs further feature engineering to improve the f1 weighted score. Collaborate on with me here GitHub

model_description

This is a RandomForestClassifier model trained on Sepsis dataset from this kaggle dataset.

roc_auc_curve

feature_importances