ourownstory/neural_prophet 0.6.0 on GitHub

What's Changed

[major] Nested Additive Model by @karl-richter in #1216
[major] Allow user to set prediction frequency as a dict: {freq: forecast origin} by @judussoari in #1187
[major] lagged regressor with interaction modeling (shared NN) by @karl-richter in #903
[feature] Support for asymmetrical interval in conformal quantile regression by @leoniewgnr in #1215
[minor] Allow lagged regressors with only unique values for global modeling by @judussoari in #1267
[minor] Dependency management with poetry by @noxan in #1202
[minor] Allow lagged regressors with only unique values for global modeling by @judussoari in #1256
[minor] Repeat static trend component n_forecasts times instead of only once by @judussoari in #1254
[minor] add docstring examples by @LeonieFreisinger in #1295
[minor] Address warnings by @leoniewgnr in #1276
[minor] lighten forecaster step 2 - encapsulate _get_maybe_extend_periods and _maybe_extend_df by @LeonieFreisinger in #1278
[minor] Update dependencies to latest versions by @noxan in #1280

[fix] Calculate major frequency percentage properly by @noxan in #1264
[fix] Matplotlib and plotly plot showing aligned by @leoniewgnr in #1266
[fix] Remove regressor config if all regressors are removed due to unique values by @judussoari in #1272
[fix] Unregister plotly resampler directly after usage by @LeonieFreisinger in #1277
[fix] Raise Exception again to avoid UnboundLocalError by @noxan in #1282
[fix] Remove SmoothL1Loss from Tutorial by @judussoari in #1298
[fix] Raise ValueError when df contains not enough rows by @judussoari in #1300

[docs] outdated labels in contributing.md by @leoniewgnr in #1242
[docs] Create new tutorials content by @noxan in #1183
[docs] add note on flexible multiplicativity from prophet by @noxan in #1268
[docs] Add next steps to tutorials by @noxan in #1274
[docs] Improve conformal prediction tutorial by adding marginal before coverage by @noxan in #1284

[refactor] Removed plotting in test_uncertainty.py. by @Kevin-Chen0 in #1246
[refactor] Changed int() to round() for q_hat_idx in uncertainty.py. by @Kevin-Chen0 in #1248
[refactor] Lighten forecaster.py by @LeonieFreisinger in #1255
[refactor] Encapsulate _make_future_dataframe and _check_dataframe by @LeonieFreisinger in #1279
[refactor] Encapsulate _validate_column_name by @LeonieFreisinger in #1289
[refactor] Encapsulate _normalize by @LeonieFreisinger in #1287
[refactor] Encapsulate _handle_missing_data and _handle_missing_data_single_id by @LeonieFreisinger in #1288
[refactor] Encapsulate _prepare_dataframe_to_predict by @LeonieFreisinger in #1290
[refactor] Encapsulate _convert_raw_predictions_to_raw_df by @LeonieFreisinger in #1291
[refactor] Encapsulate _reshape_raw_predictions_to_forecst_df by @LeonieFreisinger in #1293

Full Changelog: 0.5.3...0.6.0