I Have been trying to use PyCaret library, but when I use the function setup() as shown in my code, it gives me an error of unexpected keyword argument. I have been trying to set argument silent to be True.
from pycaret.clustering import *
s = setup(data, normalize = True, ignore_features = ['CUST_ID'], session_id = 145, silent = True)
I pulled the source code for the function directly from their github repo.
As you can see there is no silent keyword argument for the setup function.
https://github.com/pycaret/pycaret/blob/master/pycaret/clustering/functional.py
def setup(
data: DATAFRAME_LIKE,
ordinal_features: Optional[Dict[str, list]] = None,
numeric_features: Optional[List[str]] = None,
categorical_features: Optional[List[str]] = None,
date_features: Optional[List[str]] = None,
text_features: Optional[List[str]] = None,
ignore_features: Optional[List[str]] = None,
keep_features: Optional[List[str]] = None,
preprocess: bool = True,
imputation_type: Optional[str] = "simple",
numeric_imputation: str = "mean",
categorical_imputation: str = "constant",
text_features_method: str = "tf-idf",
max_encoding_ohe: int = -1,
encoding_method: Optional[Any] = None,
polynomial_features: bool = False,
polynomial_degree: int = 2,
low_variance_threshold: float = 0,
remove_multicollinearity: bool = False,
multicollinearity_threshold: float = 0.9,
bin_numeric_features: Optional[List[str]] = None,
remove_outliers: bool = False,
outliers_method: str = "iforest",
outliers_threshold: float = 0.05,
transformation: bool = False,
transformation_method: str = "yeo-johnson",
normalize: bool = False,
normalize_method: str = "zscore",
pca: bool = False,
pca_method: str = "linear",
pca_components: Union[int, float] = 1.0,
custom_pipeline: Optional[Any] = None,
n_jobs: Optional[int] = -1,
use_gpu: bool = False,
html: bool = True,
session_id: Optional[int] = None,
system_log: Union[bool, str, logging.Logger] = True,
log_experiment: Union[bool, str, BaseLogger, List[Union[str, BaseLogger]]] = False,
experiment_name: Optional[str] = None,
experiment_custom_tags: Optional[Dict[str, Any]] = None,
log_plots: Union[bool, list] = False,
log_profile: bool = False,
log_data: bool = False,
verbose: bool = True,
memory: Union[bool, str, Memory] = True,
profile: bool = False,
profile_kwargs: Dict[str, Any] = None,
):
"""
This function initializes the training environment and creates the transformation
pipeline. Setup function must be called before executing any other function. It
takes one mandatory parameter: ``data``. All the other parameters are optional.
Example
-------
>>> from pycaret.datasets import get_data
>>> jewellery = get_data('jewellery')
>>> from pycaret.clustering import *
>>> exp_name = setup(data = jewellery)
data: dataframe-like
Data set with shape (n_samples, n_features), where n_samples is the
number of samples and n_features is the number of features. If data
is not a pandas dataframe, it's converted to one using default column
names.
ordinal_features: dict, default = None
Categorical features to be encoded ordinally. For example, a categorical
feature with 'low', 'medium', 'high' values where low < medium < high can
be passed as ordinal_features = {'column_name' : ['low', 'medium', 'high']}.
numeric_features: list of str, default = None
If the inferred data types are not correct, the numeric_features param can
be used to define the data types. It takes a list of strings with column
names that are numeric.
categorical_features: list of str, default = None
If the inferred data types are not correct, the categorical_features param
can be used to define the data types. It takes a list of strings with column
names that are categorical.
date_features: list of str, default = None
If the inferred data types are not correct, the date_features param can be
used to overwrite the data types. It takes a list of strings with column
names that are DateTime.
text_features: list of str, default = None
Column names that contain a text corpus. If None, no text features are
selected.
ignore_features: list of str, default = None
ignore_features param can be used to ignore features during preprocessing
and model training. It takes a list of strings with column names that are
to be ignored.
keep_features: list of str, default = None
keep_features param can be used to always keep specific features during
preprocessing, i.e. these features are never dropped by any kind of
feature selection. It takes a list of strings with column names that are
to be kept.
preprocess: bool, default = True
When set to False, no transformations are applied except for train_test_split
and custom transformations passed in ``custom_pipeline`` param. Data must be
ready for modeling (no missing values, no dates, categorical data encoding),
when preprocess is set to False.
imputation_type: str or None, default = 'simple'
The type of imputation to use. Can be either 'simple' or 'iterative'.
If None, no imputation of missing values is performed.
numeric_imputation: str, default = 'mean'
Missing values in numeric features are imputed with 'mean' value of the feature
in the training dataset. The other available option is 'median' or 'zero'.
categorical_imputation: str, default = 'constant'
Missing values in categorical features are imputed with a constant 'not_available'
value. The other available option is 'mode'.
text_features_method: str, default = "tf-idf"
Method with which to embed the text features in the dataset. Choose
between "bow" (Bag of Words - CountVectorizer) or "tf-idf" (TfidfVectorizer).
Be aware that the sparse matrix output of the transformer is converted
internally to its full array. This can cause memory issues for large
text embeddings.
max_encoding_ohe: int, default = -1
Categorical columns with `max_encoding_ohe` or less unique values are
encoded using OneHotEncoding. If more, the `encoding_method` estimator
is used. Note that columns with exactly two classes are always encoded
ordinally. Set to below 0 to always use OneHotEncoding.
encoding_method: category-encoders estimator, default = None
A `category-encoders` estimator to encode the categorical columns
with more than `max_encoding_ohe` unique values. If None,
`category_encoders.leave_one_out.LeaveOneOutEncoder` is used.
polynomial_features: bool, default = False
When set to True, new features are derived using existing numeric features.
polynomial_degree: int, default = 2
Degree of polynomial features. For example, if an input sample is two dimensional
and of the form [a, b], the polynomial features with degree = 2 are:
[1, a, b, a^2, ab, b^2]. Ignored when ``polynomial_features`` is not True.
low_variance_threshold: float or None, default = 0
Remove features with a training-set variance lower than the provided
threshold. The default is to keep all features with non-zero variance,
i.e. remove the features that have the same value in all samples. If
None, skip this treansformation step.
remove_multicollinearity: bool, default = False
When set to True, features with the inter-correlations higher than the defined
threshold are removed. When two features are highly correlated with each other,
the feature that is less correlated with the target variable is removed. Only
considers numeric features.
multicollinearity_threshold: float, default = 0.9
Threshold for correlated features. Ignored when ``remove_multicollinearity``
is not True.
bin_numeric_features: list of str, default = None
To convert numeric features into categorical, bin_numeric_features parameter can
be used. It takes a list of strings with column names to be discretized. It does
so by using 'sturges' rule to determine the number of clusters and then apply
KMeans algorithm. Original values of the feature are then replaced by the
cluster label.
remove_outliers: bool, default = False
When set to True, outliers from the training data are removed using an
Isolation Forest.
outliers_method: str, default = "iforest"
Method with which to remove outliers. Possible values are:
- 'iforest': Uses sklearn's IsolationForest.
- 'ee': Uses sklearn's EllipticEnvelope.
- 'lof': Uses sklearn's LocalOutlierFactor.
outliers_threshold: float, default = 0.05
The percentage outliers to be removed from the dataset. Ignored
when ``remove_outliers=False``.
transformation: bool, default = False
When set to True, it applies the power transform to make data more Gaussian-like.
Type of transformation is defined by the ``transformation_method`` parameter.
transformation_method: str, default = 'yeo-johnson'
Defines the method for transformation. By default, the transformation method is
set to 'yeo-johnson'. The other available option for transformation is 'quantile'.
Ignored when ``transformation`` is not True.
normalize: bool, default = False
When set to True, it transforms the features by scaling them to a given
range. Type of scaling is defined by the ``normalize_method`` parameter.
normalize_method: str, default = 'zscore'
Defines the method for scaling. By default, normalize method is set to 'zscore'
The standard zscore is calculated as z = (x - u) / s. Ignored when ``normalize``
is not True. The other options are:
- minmax: scales and translates each feature individually such that it is in
the range of 0 - 1.
- maxabs: scales and translates each feature individually such that the
maximal absolute value of each feature will be 1.0. It does not
shift/center the data, and thus does not destroy any sparsity.
- robust: scales and translates each feature according to the Interquartile
range. When the dataset contains outliers, robust scaler often gives
better results.
pca: bool, default = False
When set to True, dimensionality reduction is applied to project the data into
a lower dimensional space using the method defined in ``pca_method`` parameter.
pca_method: str, default = 'linear'
Method with which to apply PCA. Possible values are:
- 'linear': Uses Singular Value Decomposition.
- kernel: Dimensionality reduction through the use of RBF kernel.
- incremental: Similar to 'linear', but more efficient for large datasets.
pca_components: int or float, default = 1.0
Number of components to keep. If >1, it selects that number of
components. If <= 1, it selects that fraction of components from
the original features. The value must be smaller than the number
of original features. This parameter is ignored when `pca=False`.
custom_pipeline: list of (str, transformer), dict or Pipeline, default = None
Addidiotnal custom transformers. If passed, they are applied to the
pipeline last, after all the build-in transformers.
n_jobs: int, default = -1
The number of jobs to run in parallel (for functions that supports parallel
processing) -1 means using all processors. To run all functions on single
processor set n_jobs to None.
use_gpu: bool or str, default = False
When set to True, it will use GPU for training with algorithms that support it,
and fall back to CPU if they are unavailable. When set to 'force', it will only
use GPU-enabled algorithms and raise exceptions when they are unavailable. When
False, all algorithms are trained using CPU only.
GPU enabled algorithms:
- None at this moment.
html: bool, default = True
When set to False, prevents runtime display of monitor. This must be set to False
when the environment does not support IPython. For example, command line terminal,
Databricks Notebook, Spyder and other similar IDEs.
session_id: int, default = None
Controls the randomness of experiment. It is equivalent to 'random_state' in
scikit-learn. When None, a pseudo random number is generated. This can be used
for later reproducibility of the entire experiment.
system_log: bool or str or logging.Logger, default = True
Whether to save the system logging file (as logs.log). If the input
is a string, use that as the path to the logging file. If the input
already is a logger object, use that one instead.
log_experiment: bool, default = False
A (list of) PyCaret ``BaseLogger`` or str (one of 'mlflow', 'wandb')
corresponding to a logger to determine which experiment loggers to use.
Setting to True will use just MLFlow.
If ``wandb`` (Weights & Biases) is installed, will also log there.
experiment_name: str, default = None
Name of the experiment for logging. Ignored when ``log_experiment`` is False.
experiment_custom_tags: dict, default = None
Dictionary of tag_name: String -> value: (String, but will be string-ified
if not) passed to the mlflow.set_tags to add new custom tags for the experiment.
log_plots: bool or list, default = False
When set to True, certain plots are logged automatically in the ``MLFlow`` server.
To change the type of plots to be logged, pass a list containing plot IDs. Refer
to documentation of ``plot_model``. Ignored when ``log_experiment`` is False.
log_profile: bool, default = False
When set to True, data profile is logged on the ``MLflow`` server as a html file.
Ignored when ``log_experiment`` is False.
log_data: bool, default = False
When set to True, dataset is logged on the ``MLflow`` server as a csv file.
Ignored when ``log_experiment`` is False.
verbose: bool, default = True
When set to False, Information grid is not printed.
memory: str, bool or Memory, default=True
Used to cache the fitted transformers of the pipeline.
If False: No caching is performed.
If True: A default temp directory is used.
If str: Path to the caching directory.
profile: bool, default = False
When set to True, an interactive EDA report is displayed.
profile_kwargs: dict, default = {} (empty dict)
Dictionary of arguments passed to the ProfileReport method used
to create the EDA report. Ignored if ``profile`` is False.
Returns:
Global variables that can be changed using the ``set_config`` function.
"""
exp = _EXPERIMENT_CLASS()
set_current_experiment(exp)
return exp.setup(
data=data,
ordinal_features=ordinal_features,
numeric_features=numeric_features,
categorical_features=categorical_features,
date_features=date_features,
text_features=text_features,
ignore_features=ignore_features,
keep_features=keep_features,
preprocess=preprocess,
imputation_type=imputation_type,
numeric_imputation=numeric_imputation,
categorical_imputation=categorical_imputation,
text_features_method=text_features_method,
max_encoding_ohe=max_encoding_ohe,
encoding_method=encoding_method,
polynomial_features=polynomial_features,
polynomial_degree=polynomial_degree,
low_variance_threshold=low_variance_threshold,
remove_multicollinearity=remove_multicollinearity,
multicollinearity_threshold=multicollinearity_threshold,
bin_numeric_features=bin_numeric_features,
remove_outliers=remove_outliers,
outliers_method=outliers_method,
outliers_threshold=outliers_threshold,
transformation=transformation,
transformation_method=transformation_method,
normalize=normalize,
normalize_method=normalize_method,
pca=pca,
pca_method=pca_method,
pca_components=pca_components,
custom_pipeline=custom_pipeline,
n_jobs=n_jobs,
use_gpu=use_gpu,
html=html,
session_id=session_id,
system_log=system_log,
log_experiment=log_experiment,
experiment_name=experiment_name,
experiment_custom_tags=experiment_custom_tags,
log_plots=log_plots,
log_profile=log_profile,
log_data=log_data,
verbose=verbose,
memory=memory,
profile=profile,
profile_kwargs=profile_kwargs,
)
The official documentation for the project is at: