palma.preprocessing package

Submodules

palma.preprocessing.na_encoder module

class palma.preprocessing.na_encoder.NA_encoder(numerical_strategy='mean', categorical_strategy='<NULL>')

Bases: object

Encodes missing values for both numerical and categorical features.

Several strategies are possible in each case.

Parameters:

numerical_strategystr or float or int. default = “mean”

The strategy to encode NA for numerical features. Available strategies = “mean”, “median”, “most_frequent” or a float/int value

categorical_strategystr, default = ‘<NULL>’

The strategy to encode NA for categorical features. Available strategies = a string or “most_frequent”

Methods

fit(df_train[, y_train])	Fits NA Encoder.
fit_transform(df_train[, y_train])	Fits NA Encoder and transforms the dataset.
get_params([deep])	Get parameters of a NA_encoder object.
set_params(**params)	Set parameters for a NA_encoder object.
transform(df)	Transform the dataset.

fit(df_train, y_train=None)

Fits NA Encoder.

Parameters:

df_trainpandas dataframe of shape = (n_train, n_features)

The train dataset with numerical and categorical features.

y_trainpandas series of shape = (n_train, ), default = None

The target for classification or regression tasks.

Returns:

object

self

fit_transform(df_train, y_train=None)

Fits NA Encoder and transforms the dataset.

Parameters:

df_trainpandas.Dataframe of shape = (n_train, n_features)

The train dataset with numerical and categorical features.

y_trainpandas.Series of shape = (n_train, ), default = None

The target for classification or regression tasks.

Returns:

pandas.Dataframe of shape = (n_train, n_features)

The train dataset with no missing values.

get_params(deep=True)

Get parameters of a NA_encoder object.

set_params(**params)

Set parameters for a NA_encoder object.

Set numerical strategy and categorical strategy.

Parameters:

numerical_strategystr or float or int. default = “mean”

The strategy to encode NA for numerical features.

categorical_strategystr, default = ‘<NULL>’

The strategy to encode NA for categorical features.

transform(df)

Transform the dataset.

Parameters:

dfpandas.Dataframe of shape = (n, n_features)

The dataset with numerical and categorical features.

Returns:

pandas.Dataframe of shape = (n, n_features)

The dataset with no missing values.

palma.preprocessing.pca module

class palma.preprocessing.pca.PCA(data: DataFrame, prefix_name='pc')

Bases: object

Attributes:

nb_component

Methods

get_correlation
get_individual_contributions
get_variables_contributions
plot_circle_corr
plot_correlation_matrix
plot_cumulated_variance
plot_eigen_values
plot_factorial_plan
plot_var_cp
plot_variance_bar
set_nb_components
transform

get_correlation(n_components=None) → DataFrame

get_individual_contributions(n_components=None) → DataFrame

get_variables_contributions(n_components=None) → DataFrame

property nb_component

plot_circle_corr() → None

plot_correlation_matrix() → None

plot_cumulated_variance(color='tab:blue') → None

plot_eigen_values() → None

plot_factorial_plan(X: DataFrame, x_axis='pc1', y_axis='pc2', c=None, cmap=None) → None

plot_var_cp(X: DataFrame, n_col=3, figsize=(10, 10), x_axis='pc1', y_axis='pc2') → None

plot_variance_bar(separator=0.5) → None

set_nb_components(n=None, variance_threshold: float = None, **kwargs)

transform(X: DataFrame) → DataFrame

Module contents