import klib

klib.describe # functions for visualizing datasets
- klib.cat_plot() # returns a visualization of the number and frequency of categorical features
- klib.corr_mat() # returns a color-encoded correlation matrix
- klib.corr_plot() # returns a color-encoded heatmap, ideal for correlations
- klib.dist_plot() # returns a distribution plot for every numeric feature
- klib.missingval_plot() # returns a figure containing information about missing values

klib.clean # functions for cleaning datasets
- klib.clean_column_names() # cleans and standardizes column names, also called inside data_cleaning()
- klib.convert_datatypes() # converts existing to more efficient dtypes, also called inside data_cleaning()
- klib.data_cleaning() # performs datacleaning (drop duplicates & empty rows/columns, adjust dtypes,...) on a dataset
- klib.drop_missing() # drops missing values, also called in data_cleaning()
- klib.mv_col_handling() # drops features with a high ratio of missing values based on their informational content
- klib.pool_duplicate_subsets() # pools a subset of columns based on duplicate values with minimal loss of information

klib.preprocess # functions for data preprocessing (feature selection, scaling, ...)
- klib.train_dev_test_split() # splits a dataset and a label into train, optionally dev and test sets
- klib.feature_selection_pipe() # provides common operations for feature selection
- klib.num_pipe() # provides common operations for preprocessing of numerical data
- klib.cat_pipe() # provides common operations for preprocessing of categorical data
- klib.preprocess.ColumnSelector() # selects numerical or categorical columns, ideal for a Feature Union or Pipeline
- klib.preprocess.PipeInfo() # prints out the shape of the data at the specified step of a Pipeline

klib.missingval_plot(df) # default representation of missing values in a DataFrame, plenty of settings are available

klib.corr_plot(df, split='pos') # displaying only positive correlations, other settings include threshold, cmap...
klib.corr_plot(df, split='neg') # displaying only negative correlations

klib.corr_plot(df, target='wine') # default representation of correlations with the feature column

klib.dist_plot(df) # default representation of a distribution plot, other settings include fill_range, histogram, ...

klib.cat_plot(data, top=4, bottom=4) # representation of the 4 most & least common values in each categorical column