Datasets#

Module with dataset and its utilities.

API details#

Basic structures:

TSDataset(df, freq[, df_exog, known_future, ...])

TSDataset is the main class to handle your time series data.

DataFrameFormat(value)

Enum for different kinds of pd.DataFrame which can be used.

HierarchicalStructure(level_structure[, ...])

Represents hierarchical structure of TSDataset.

Utilities for dataset generation:

generate_ar_df(periods[, start_time, ...])

Create DataFrame with AR process data.

generate_const_df(periods[, start_time, ...])

Create DataFrame with const data.

generate_from_patterns_df(periods, ...[, ...])

Create DataFrame from patterns.

generate_hierarchical_df(periods, n_segments)

Create DataFrame with hierarchical structure and AR process data.

generate_periodic_df(periods[, start_time, ...])

Create DataFrame with periodic data.

Utilities for data manipulation:

duplicate_data(df, segments[, format])

Duplicate dataframe for all the segments.

set_columns_wide(df_left, df_right[, ...])

Set columns in a left dataframe with values from the right dataframe.

infer_alignment(df)

Inference alignment of a given dataframe.

apply_alignment(df, alignment[, ...])

Apply given alignment to a dataframe.

make_timestamp_df_from_alignment(alignment)

Create a dataframe with timestamp according to a given alignment.