tabular-playground / README.md
freddyaboulton's picture
Upload README.md
d430187
metadata
library_name: sklearn
tags:
  - sklearn
  - skops
  - tabular-classification
widget:
  structuredData:
    attribute_0:
      - material_7
      - material_7
      - material_7
    attribute_1:
      - material_8
      - material_8
      - material_6
    attribute_2:
      - 5
      - 5
      - 6
    attribute_3:
      - 8
      - 8
      - 9
    loading:
      - 154.02
      - 108.73
      - 99.84
    measurement_0:
      - 14
      - 4
      - 6
    measurement_1:
      - 6
      - 7
      - 7
    measurement_10:
      - 16.637
      - 16.207
      - 17.17
    measurement_11:
      - 20.719
      - 20.058
      - 20.858
    measurement_12:
      - 12.824
      - 11.898
      - 10.968
    measurement_13:
      - 16.067
      - 13.871
      - 16.448
    measurement_14:
      - 15.181
      - 14.266
      - 15.6
    measurement_15:
      - 18.546
      - 15.734
      - 14.637
    measurement_16:
      - 19.402
      - 16.886
      - 13.86
    measurement_17:
      - 643.086
      - 642.533
      - 673.545
    measurement_2:
      - 6
      - 9
      - 6
    measurement_3:
      - 19.532
      - 18.128
      - NaN
    measurement_4:
      - 11.017
      - 11.866
      - 10.064
    measurement_5:
      - 15.639
      - 17.891
      - 16.287
    measurement_6:
      - 16.709
      - 20.302
      - 17.445
    measurement_7:
      - 10.057
      - NaN
      - 12.117
    measurement_8:
      - 20.201
      - 18.148
      - 20.659
    measurement_9:
      - 11.106
      - 10.221
      - 11.999
    product_code:
      - C
      - C
      - E

Model description

This is a DecisionTreeClassifier model built for Kaggle Tabular Playground Series August 2022, trained on supersoaker production failures dataset.

Intended uses & limitations

This model is not ready to be used in production.

Training Procedure

Hyperparameters

The model is trained with below hyperparameters.

Click to expand
Hyperparameter Value
memory
steps [('transformation', ColumnTransformer(transformers=[('loading_missing_value_imputer',
                             SimpleImputer(), ['loading']),
                            ('numerical_missing_value_imputer',
                             SimpleImputer(),
                             ['loading', 'measurement_3', 'measurement_4',
                              'measurement_5', 'measurement_6',
                              'measurement_7', 'measurement_8',
                              'measurement_9', 'measurement_10',
                              'measurement_11', 'measurement_12',
                              'measurement_13', 'measurement_14',
                              'measurement_15', 'measurement_16',
                              'measurement_17']),
                            ('attribute_0_encoder', OneHotEncoder(),
                             ['attribute_0']),
                            ('attribute_1_encoder', OneHotEncoder(),
                             ['attribute_1']),
                            ('product_code_encoder', OneHotEncoder(),
                             ['product_code'])])), ('model', DecisionTreeClassifier(max_depth=4))]                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |

| verbose | False | | transformation | ColumnTransformer(transformers=[('loading_missing_value_imputer', SimpleImputer(), ['loading']), ('numerical_missing_value_imputer', SimpleImputer(), ['loading', 'measurement_3', 'measurement_4', 'measurement_5', 'measurement_6', 'measurement_7', 'measurement_8', 'measurement_9', 'measurement_10', 'measurement_11', 'measurement_12', 'measurement_13', 'measurement_14', 'measurement_15', 'measurement_16', 'measurement_17']), ('attribute_0_encoder', OneHotEncoder(), ['attribute_0']), ('attribute_1_encoder', OneHotEncoder(), ['attribute_1']), ('product_code_encoder', OneHotEncoder(), ['product_code'])]) | | model | DecisionTreeClassifier(max_depth=4) | | transformation__n_jobs | | | transformation__remainder | drop | | transformation__sparse_threshold | 0.3 | | transformation__transformer_weights | | | transformation__transformers | [('loading_missing_value_imputer', SimpleImputer(), ['loading']), ('numerical_missing_value_imputer', SimpleImputer(), ['loading', 'measurement_3', 'measurement_4', 'measurement_5', 'measurement_6', 'measurement_7', 'measurement_8', 'measurement_9', 'measurement_10', 'measurement_11', 'measurement_12', 'measurement_13', 'measurement_14', 'measurement_15', 'measurement_16', 'measurement_17']), ('attribute_0_encoder', OneHotEncoder(), ['attribute_0']), ('attribute_1_encoder', OneHotEncoder(), ['attribute_1']), ('product_code_encoder', OneHotEncoder(), ['product_code'])] | | transformation__verbose | False | | transformation__verbose_feature_names_out | True | | transformation__loading_missing_value_imputer | SimpleImputer() | | transformation__numerical_missing_value_imputer | SimpleImputer() | | transformation__attribute_0_encoder | OneHotEncoder() | | transformation__attribute_1_encoder | OneHotEncoder() | | transformation__product_code_encoder | OneHotEncoder() | | transformation__loading_missing_value_imputer__add_indicator | False | | transformation__loading_missing_value_imputer__copy | True | | transformation__loading_missing_value_imputer__fill_value | | | transformation__loading_missing_value_imputer__missing_values | nan | | transformation__loading_missing_value_imputer__strategy | mean | | transformation__loading_missing_value_imputer__verbose | 0 | | transformation__numerical_missing_value_imputer__add_indicator | False | | transformation__numerical_missing_value_imputer__copy | True | | transformation__numerical_missing_value_imputer__fill_value | | | transformation__numerical_missing_value_imputer__missing_values | nan | | transformation__numerical_missing_value_imputer__strategy | mean | | transformation__numerical_missing_value_imputer__verbose | 0 | | transformation__attribute_0_encoder__categories | auto | | transformation__attribute_0_encoder__drop | | | transformation__attribute_0_encoder__dtype | <class 'numpy.float64'> | | transformation__attribute_0_encoder__handle_unknown | error | | transformation__attribute_0_encoder__sparse | True | | transformation__attribute_1_encoder__categories | auto | | transformation__attribute_1_encoder__drop | | | transformation__attribute_1_encoder__dtype | <class 'numpy.float64'> | | transformation__attribute_1_encoder__handle_unknown | error | | transformation__attribute_1_encoder__sparse | True | | transformation__product_code_encoder__categories | auto | | transformation__product_code_encoder__drop | | | transformation__product_code_encoder__dtype | <class 'numpy.float64'> | | transformation__product_code_encoder__handle_unknown | error | | transformation__product_code_encoder__sparse | True | | model__ccp_alpha | 0.0 | | model__class_weight | | | model__criterion | gini | | model__max_depth | 4 | | model__max_features | | | model__max_leaf_nodes | | | model__min_impurity_decrease | 0.0 | | model__min_samples_leaf | 1 | | model__min_samples_split | 2 | | model__min_weight_fraction_leaf | 0.0 | | model__random_state | | | model__splitter | best |

Model Plot

The model plot is below.

Pipeline(steps=[('transformation',ColumnTransformer(transformers=[('loading_missing_value_imputer',SimpleImputer(),['loading']),('numerical_missing_value_imputer',SimpleImputer(),['loading', 'measurement_3','measurement_4','measurement_5','measurement_6','measurement_7','measurement_8','measurement_9','measurement_10','measurement_11','measurement_12','measurement_13','measurement_14','measurement_15','measurement_16','measurement_17']),('attribute_0_encoder',OneHotEncoder(),['attribute_0']),('attribute_1_encoder',OneHotEncoder(),['attribute_1']),('product_code_encoder',OneHotEncoder(),['product_code'])])),('model', DecisionTreeClassifier(max_depth=4))])
Please rerun this cell to show the HTML repr or trust the notebook.

Evaluation Results

You can find the details about evaluation process and the evaluation results.

Metric Value
accuracy 0.7888
f1 score 0.7888

How to Get Started with the Model

Use the code below to get started with the model.

Click to expand
import pickle 
with open(decision-tree-playground-kaggle/model.pkl, 'rb') as file: 
    clf = pickle.load(file)

Model Card Authors

This model card is written by following authors:

huggingface

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]

Tree Plot Tree Plot

Confusion Matrix Confusion Matrix