ovo.app.components.descriptor_correlation

Module Contents

Functions

correlation_clustermap

Displays a clustermap of the correlation matrix with options to select which descriptors to include.

cluster_correlation_matrix

Clusters the correlation matrix using hierarchical clustering and returns a reordered DataFrame.

correlation_explorer

Explores the correlation of a selected descriptor with other descriptors.

correlation_scatterplot_interactive

correlation_scatterplot

Displays scatterplots for the correlation between selected descriptors.

r2_score_pandas

API

ovo.app.components.descriptor_correlation.correlation_clustermap(correlation_df: pandas.DataFrame, correlation_label: str)

Displays a clustermap of the correlation matrix with options to select which descriptors to include.

Args: correlation_df (pd.DataFrame): A DataFrame containing the correlation matrix of descriptors. The columns should be ovo descriptor keys, index should be user uploaded endpoint columns, and the values should be correlation coefficients. correlation_label: The name of the correlation metric to display in the plot legend

ovo.app.components.descriptor_correlation.cluster_correlation_matrix(correlation_df: pandas.DataFrame) pandas.DataFrame

Clusters the correlation matrix using hierarchical clustering and returns a reordered DataFrame.

ovo.app.components.descriptor_correlation.correlation_explorer(correlation_df: pandas.DataFrame, df_combined: pandas.DataFrame, correlation_label: str, top_n: int = 10)

Explores the correlation of a selected descriptor with other descriptors.

Args: correlation_df (pd.DataFrame): A DataFrame containing the correlation matrix of descriptors. The columns should be ovo descriptor keys, index should be user uploaded descriptor keys, and the values should be correlation coefficients. df_combined: A DataFrame containing the combined data of uploaded and computed descriptors, indexed by design_id. correlation_label: The name of the correlation metric to display in the plot legend top_n (int): The number of top positively and negatively correlated descriptors to display.

ovo.app.components.descriptor_correlation.correlation_scatterplot_interactive(combined_df: pandas.DataFrame, corr_df: pandas.DataFrame, correlation_label: str)
ovo.app.components.descriptor_correlation.correlation_scatterplot(combined_df: pandas.DataFrame, corr_df: pandas.DataFrame, correlation_label: str, x_descriptor: str, y_descriptor: str, key_suffix: str = '')

Displays scatterplots for the correlation between selected descriptors.

Args: combined_df (pd.DataFrame): A DataFrame containing the combined data of uploaded and computed descriptors. corr_df (pd.DataFrame): A DataFrame containing the correlation matrix of descriptors. correlation_label: The name of the correlation metric to display in the plot legend x_descriptor (str): The ovo descriptor key to use for the X axis. y_descriptor (str): The user descriptor key to use for the Y axis.

ovo.app.components.descriptor_correlation.r2_score_pandas(y_true: pandas.Series, y_pred: pandas.Series) float