├── .github └── workflows │ ├── deploy.yaml │ └── test.yaml ├── .gitignore ├── LICENSE ├── MANIFEST.in ├── README.md ├── nbs ├── 00_core.ipynb ├── _quarto.yml ├── index.ipynb ├── nbdev.yml ├── sidebar.yml └── styles.css ├── settings.ini ├── setup.py └── ts2ml ├── __init__.py ├── _modidx.py └── core.py /.github/workflows/deploy.yaml: -------------------------------------------------------------------------------- 1 | name: Deploy to GitHub Pages 2 | 3 | permissions: 4 | contents: write 5 | pages: write 6 | 7 | on: 8 | push: 9 | branches: [ "main", "master" ] 10 | workflow_dispatch: 11 | jobs: 12 | deploy: 13 | runs-on: ubuntu-latest 14 | steps: [uses: fastai/workflows/quarto-ghp@master] 15 | -------------------------------------------------------------------------------- /.github/workflows/test.yaml: -------------------------------------------------------------------------------- 1 | name: CI 2 | on: [workflow_dispatch, pull_request, push] 3 | 4 | jobs: 5 | test: 6 | runs-on: ubuntu-latest 7 | steps: [uses: fastai/workflows/nbdev-ci@master] 8 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | _docs/ 2 | _proc/ 3 | 4 | *.bak 5 | .gitattributes 6 | .last_checked 7 | .gitconfig 8 | *.bak 9 | *.log 10 | *~ 11 | ~* 12 | _tmp* 13 | tmp* 14 | tags 15 | *.pkg 16 | 17 | # Byte-compiled / optimized / DLL files 18 | __pycache__/ 19 | *.py[cod] 20 | *$py.class 21 | 22 | # C extensions 23 | *.so 24 | 25 | # Distribution / packaging 26 | .Python 27 | env/ 28 | build/ 29 | develop-eggs/ 30 | dist/ 31 | downloads/ 32 | eggs/ 33 | .eggs/ 34 | lib/ 35 | lib64/ 36 | parts/ 37 | sdist/ 38 | var/ 39 | wheels/ 40 | *.egg-info/ 41 | .installed.cfg 42 | *.egg 43 | 44 | # PyInstaller 45 | # Usually these files are written by a python script from a template 46 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 47 | *.manifest 48 | *.spec 49 | 50 | # Installer logs 51 | pip-log.txt 52 | pip-delete-this-directory.txt 53 | 54 | # Unit test / coverage reports 55 | htmlcov/ 56 | .tox/ 57 | .coverage 58 | .coverage.* 59 | .cache 60 | nosetests.xml 61 | coverage.xml 62 | *.cover 63 | .hypothesis/ 64 | 65 | # Translations 66 | *.mo 67 | *.pot 68 | 69 | # Django stuff: 70 | *.log 71 | local_settings.py 72 | 73 | # Flask stuff: 74 | instance/ 75 | .webassets-cache 76 | 77 | # Scrapy stuff: 78 | .scrapy 79 | 80 | # Sphinx documentation 81 | docs/_build/ 82 | 83 | # PyBuilder 84 | target/ 85 | 86 | # Jupyter Notebook 87 | .ipynb_checkpoints 88 | 89 | # pyenv 90 | .python-version 91 | 92 | # celery beat schedule file 93 | celerybeat-schedule 94 | 95 | # SageMath parsed files 96 | *.sage.py 97 | 98 | # dotenv 99 | .env 100 | 101 | # virtualenv 102 | .venv 103 | venv/ 104 | ENV/ 105 | 106 | # Spyder project settings 107 | .spyderproject 108 | .spyproject 109 | 110 | # Rope project settings 111 | .ropeproject 112 | 113 | # mkdocs documentation 114 | /site 115 | 116 | # mypy 117 | .mypy_cache/ 118 | 119 | .vscode 120 | *.swp 121 | 122 | # osx generated files 123 | .DS_Store 124 | .DS_Store? 125 | .Trashes 126 | ehthumbs.db 127 | Thumbs.db 128 | .idea 129 | 130 | # pytest 131 | .pytest_cache 132 | 133 | # tools/trust-doc-nbs 134 | docs_src/.last_checked 135 | 136 | # symlinks to fastai 137 | docs_src/fastai 138 | tools/fastai 139 | 140 | # link checker 141 | checklink/cookies.txt 142 | 143 | # .gitconfig is now autogenerated 144 | .gitconfig 145 | 146 | # Quarto installer 147 | .deb 148 | .pkg 149 | 150 | # Quarto 151 | .quarto 152 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright 2022, fastai 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- 1 | include settings.ini 2 | include LICENSE 3 | include CONTRIBUTING.md 4 | include README.md 5 | recursive-exclude * __pycache__ 6 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # ts2ml 2 | 3 | 4 | 5 | ## Install 6 | 7 | ``` sh 8 | pip install ts2ml 9 | ``` 10 | 11 | ## How to use 12 | 13 | ``` python 14 | import pandas as pd 15 | from ts2ml.core import add_missing_slots 16 | from ts2ml.core import transform_ts_data_into_features_and_target 17 | ``` 18 | 19 | ``` python 20 | df = pd.DataFrame({ 21 | 'pickup_hour': ['2022-01-01 00:00:00', '2022-01-01 01:00:00', '2022-01-01 03:00:00', '2022-01-01 01:00:00', '2022-01-01 02:00:00', '2022-01-01 05:00:00'], 22 | 'pickup_location_id': [1, 1, 1, 2, 2, 2], 23 | 'rides': [2, 3, 1, 1, 2, 1] 24 | }) 25 | df 26 | ``` 27 | 28 |
29 | 40 | 41 | | | pickup_hour | pickup_location_id | rides | 42 | |-----|---------------------|--------------------|-------| 43 | | 0 | 2022-01-01 00:00:00 | 1 | 2 | 44 | | 1 | 2022-01-01 01:00:00 | 1 | 3 | 45 | | 2 | 2022-01-01 03:00:00 | 1 | 1 | 46 | | 3 | 2022-01-01 01:00:00 | 2 | 1 | 47 | | 4 | 2022-01-01 02:00:00 | 2 | 2 | 48 | | 5 | 2022-01-01 05:00:00 | 2 | 1 | 49 | 50 |
51 | 52 | Let’s fill the missing slots with zeros 53 | 54 | ``` python 55 | df = add_missing_slots(df, datetime_col='pickup_hour', entity_col='pickup_location_id', value_col='rides', freq='H') 56 | df 57 | ``` 58 | 59 | 100%|██████████| 2/2 [00:00<00:00, 907.86it/s] 60 | 61 |
62 | 73 | 74 | | | pickup_hour | pickup_location_id | rides | 75 | |-----|---------------------|--------------------|-------| 76 | | 0 | 2022-01-01 00:00:00 | 1 | 2 | 77 | | 1 | 2022-01-01 01:00:00 | 1 | 3 | 78 | | 2 | 2022-01-01 02:00:00 | 1 | 0 | 79 | | 3 | 2022-01-01 03:00:00 | 1 | 1 | 80 | | 4 | 2022-01-01 04:00:00 | 1 | 0 | 81 | | 5 | 2022-01-01 05:00:00 | 1 | 0 | 82 | | 6 | 2022-01-01 00:00:00 | 2 | 0 | 83 | | 7 | 2022-01-01 01:00:00 | 2 | 1 | 84 | | 8 | 2022-01-01 02:00:00 | 2 | 2 | 85 | | 9 | 2022-01-01 03:00:00 | 2 | 0 | 86 | | 10 | 2022-01-01 04:00:00 | 2 | 0 | 87 | | 11 | 2022-01-01 05:00:00 | 2 | 1 | 88 | 89 |
90 | 91 | Now, let’s build features and targets to predict the number of rides for 92 | the next hour for each location_id, by using the historical number of 93 | rides for the last 3 hours 94 | 95 | ``` python 96 | features, targets = transform_ts_data_into_features_and_target( 97 | df, 98 | n_features=3, 99 | datetime_col='pickup_hour', 100 | entity_col='pickup_location_id', 101 | value_col='rides', 102 | n_targets=1, 103 | step_size=1, 104 | step_name='hour' 105 | ) 106 | ``` 107 | 108 | 100%|██████████| 2/2 [00:00<00:00, 597.86it/s] 109 | 110 | ``` python 111 | features 112 | ``` 113 | 114 |
115 | 126 | 127 | | | rides_previous_3_hour | rides_previous_2_hour | rides_previous_1_hour | pickup_hour | pickup_location_id | 128 | |-----|-----------------------|-----------------------|-----------------------|---------------------|--------------------| 129 | | 0 | 2.0 | 3.0 | 0.0 | 2022-01-01 03:00:00 | 1 | 130 | | 1 | 3.0 | 0.0 | 1.0 | 2022-01-01 04:00:00 | 1 | 131 | | 2 | 0.0 | 1.0 | 2.0 | 2022-01-01 03:00:00 | 2 | 132 | | 3 | 1.0 | 2.0 | 0.0 | 2022-01-01 04:00:00 | 2 | 133 | 134 |
135 | 136 | ``` python 137 | targets 138 | ``` 139 | 140 |
141 | 152 | 153 | | | target_rides_next_hour | 154 | |-----|------------------------| 155 | | 0 | 1.0 | 156 | | 1 | 0.0 | 157 | | 2 | 0.0 | 158 | | 3 | 0.0 | 159 | 160 |
161 | 162 | ``` python 163 | Xy_df = pd.concat([features, targets], axis=1) 164 | Xy_df 165 | ``` 166 | 167 |
168 | 179 | 180 | | | rides_previous_3_hour | rides_previous_2_hour | rides_previous_1_hour | pickup_hour | pickup_location_id | target_rides_next_hour | 181 | |-----|-----------------------|-----------------------|-----------------------|---------------------|--------------------|------------------------| 182 | | 0 | 2.0 | 3.0 | 0.0 | 2022-01-01 03:00:00 | 1 | 1.0 | 183 | | 1 | 3.0 | 0.0 | 1.0 | 2022-01-01 04:00:00 | 1 | 0.0 | 184 | | 2 | 0.0 | 1.0 | 2.0 | 2022-01-01 03:00:00 | 2 | 0.0 | 185 | | 3 | 1.0 | 2.0 | 0.0 | 2022-01-01 04:00:00 | 2 | 0.0 | 186 | 187 |
188 | 189 | # Another Example 190 | 191 | Montly spaced time series 192 | 193 | ``` python 194 | import pandas as pd 195 | import numpy as np 196 | 197 | # Generate timestamp index with monthly frequency 198 | date_rng = pd.date_range(start='1/1/2020', end='12/1/2022', freq='MS') 199 | 200 | # Create list of city codes 201 | cities = ['FOR', 'SP', 'RJ'] 202 | 203 | # Create dataframe with random sales data for each city on each month 204 | df = pd.DataFrame({ 205 | 'date': date_rng, 206 | 'city': np.repeat(cities, len(date_rng)//len(cities)), 207 | 'sales': np.random.randint(1000, 5000, size=len(date_rng)) 208 | }) 209 | df 210 | ``` 211 | 212 |
213 | 224 | 225 | | | date | city | sales | 226 | |-----|------------|------|-------| 227 | | 0 | 2020-01-01 | FOR | 4944 | 228 | | 1 | 2020-02-01 | FOR | 3435 | 229 | | 2 | 2020-03-01 | FOR | 4543 | 230 | | 3 | 2020-04-01 | FOR | 3879 | 231 | | 4 | 2020-05-01 | FOR | 2601 | 232 | | 5 | 2020-06-01 | FOR | 2922 | 233 | | 6 | 2020-07-01 | FOR | 4542 | 234 | | 7 | 2020-08-01 | FOR | 1338 | 235 | | 8 | 2020-09-01 | FOR | 2938 | 236 | | 9 | 2020-10-01 | FOR | 2695 | 237 | | 10 | 2020-11-01 | FOR | 4065 | 238 | | 11 | 2020-12-01 | FOR | 3864 | 239 | | 12 | 2021-01-01 | SP | 2652 | 240 | | 13 | 2021-02-01 | SP | 2137 | 241 | | 14 | 2021-03-01 | SP | 2663 | 242 | | 15 | 2021-04-01 | SP | 1168 | 243 | | 16 | 2021-05-01 | SP | 4523 | 244 | | 17 | 2021-06-01 | SP | 4135 | 245 | | 18 | 2021-07-01 | SP | 3566 | 246 | | 19 | 2021-08-01 | SP | 2121 | 247 | | 20 | 2021-09-01 | SP | 1070 | 248 | | 21 | 2021-10-01 | SP | 1624 | 249 | | 22 | 2021-11-01 | SP | 3034 | 250 | | 23 | 2021-12-01 | SP | 4063 | 251 | | 24 | 2022-01-01 | RJ | 2297 | 252 | | 25 | 2022-02-01 | RJ | 3430 | 253 | | 26 | 2022-03-01 | RJ | 2903 | 254 | | 27 | 2022-04-01 | RJ | 4197 | 255 | | 28 | 2022-05-01 | RJ | 4141 | 256 | | 29 | 2022-06-01 | RJ | 2899 | 257 | | 30 | 2022-07-01 | RJ | 4529 | 258 | | 31 | 2022-08-01 | RJ | 3612 | 259 | | 32 | 2022-09-01 | RJ | 1856 | 260 | | 33 | 2022-10-01 | RJ | 4804 | 261 | | 34 | 2022-11-01 | RJ | 1764 | 262 | | 35 | 2022-12-01 | RJ | 4425 | 263 | 264 |
265 | 266 | FOR city only have data for 2020 year, RJ only for 2022 and SP only for 267 | 2021. Let’s also simulate more missing slots between the years. 268 | 269 | ``` python 270 | # Generate random indices to drop 271 | drop_indices = np.random.choice(df.index, size=int(len(df)*0.2), replace=False) 272 | 273 | # Drop selected rows from dataframe 274 | df = df.drop(drop_indices) 275 | df.reset_index(drop=True, inplace=True) 276 | df 277 | ``` 278 | 279 |
280 | 291 | 292 | | | date | city | sales | 293 | |-----|------------|------|-------| 294 | | 0 | 2020-01-01 | FOR | 4944 | 295 | | 1 | 2020-02-01 | FOR | 3435 | 296 | | 2 | 2020-03-01 | FOR | 4543 | 297 | | 3 | 2020-04-01 | FOR | 3879 | 298 | | 4 | 2020-05-01 | FOR | 2601 | 299 | | 5 | 2020-06-01 | FOR | 2922 | 300 | | 6 | 2020-07-01 | FOR | 4542 | 301 | | 7 | 2020-08-01 | FOR | 1338 | 302 | | 8 | 2020-09-01 | FOR | 2938 | 303 | | 9 | 2020-11-01 | FOR | 4065 | 304 | | 10 | 2020-12-01 | FOR | 3864 | 305 | | 11 | 2021-01-01 | SP | 2652 | 306 | | 12 | 2021-02-01 | SP | 2137 | 307 | | 13 | 2021-03-01 | SP | 2663 | 308 | | 14 | 2021-07-01 | SP | 3566 | 309 | | 15 | 2021-08-01 | SP | 2121 | 310 | | 16 | 2021-10-01 | SP | 1624 | 311 | | 17 | 2021-11-01 | SP | 3034 | 312 | | 18 | 2021-12-01 | SP | 4063 | 313 | | 19 | 2022-01-01 | RJ | 2297 | 314 | | 20 | 2022-02-01 | RJ | 3430 | 315 | | 21 | 2022-03-01 | RJ | 2903 | 316 | | 22 | 2022-04-01 | RJ | 4197 | 317 | | 23 | 2022-05-01 | RJ | 4141 | 318 | | 24 | 2022-06-01 | RJ | 2899 | 319 | | 25 | 2022-09-01 | RJ | 1856 | 320 | | 26 | 2022-10-01 | RJ | 4804 | 321 | | 27 | 2022-11-01 | RJ | 1764 | 322 | | 28 | 2022-12-01 | RJ | 4425 | 323 | 324 |
325 | 326 | Now lets fill the missing slots with zero values. The function will 327 | complete the missing slots with zeros: 328 | 329 | ``` python 330 | df_full = add_missing_slots(df, datetime_col='date', entity_col='city', value_col='sales', freq='MS') 331 | df_full 332 | ``` 333 | 334 | 100%|██████████| 3/3 [00:00<00:00, 843.70it/s] 335 | 336 |
337 | 348 | 349 | | | date | city | sales | 350 | |-----|------------|------|-------| 351 | | 0 | 2020-01-01 | FOR | 4944 | 352 | | 1 | 2020-02-01 | FOR | 3435 | 353 | | 2 | 2020-03-01 | FOR | 4543 | 354 | | 3 | 2020-04-01 | FOR | 3879 | 355 | | 4 | 2020-05-01 | FOR | 2601 | 356 | | ... | ... | ... | ... | 357 | | 103 | 2022-08-01 | RJ | 0 | 358 | | 104 | 2022-09-01 | RJ | 1856 | 359 | | 105 | 2022-10-01 | RJ | 4804 | 360 | | 106 | 2022-11-01 | RJ | 1764 | 361 | | 107 | 2022-12-01 | RJ | 4425 | 362 | 363 |

108 rows × 3 columns

364 |
365 | 366 | Let’s build a dataset for training a machine learning model to predict 367 | the sales for the next 3 months, for each city, based on historical data 368 | of sales for the previous 6 months. 369 | 370 | ``` python 371 | features, targets = transform_ts_data_into_features_and_target( 372 | df_full, 373 | n_features=3, 374 | datetime_col='date', 375 | entity_col='city', 376 | value_col='sales', 377 | n_targets=1, 378 | step_size=1, 379 | step_name='month' 380 | ) 381 | ``` 382 | 383 | 100%|██████████| 3/3 [00:00<00:00, 205.58it/s] 384 | 385 | ``` python 386 | pd.concat([features, targets], axis=1) 387 | ``` 388 | 389 |
390 | 401 | 402 | | | sales_previous_3_month | sales_previous_2_month | sales_previous_1_month | date | city | target_sales_next_month | 403 | |-----|------------------------|------------------------|------------------------|------------|------|-------------------------| 404 | | 0 | 4944.0 | 3435.0 | 4543.0 | 2020-04-01 | FOR | 3879.0 | 405 | | 1 | 3435.0 | 4543.0 | 3879.0 | 2020-05-01 | FOR | 2601.0 | 406 | | 2 | 4543.0 | 3879.0 | 2601.0 | 2020-06-01 | FOR | 2922.0 | 407 | | 3 | 3879.0 | 2601.0 | 2922.0 | 2020-07-01 | FOR | 4542.0 | 408 | | 4 | 2601.0 | 2922.0 | 4542.0 | 2020-08-01 | FOR | 1338.0 | 409 | | ... | ... | ... | ... | ... | ... | ... | 410 | | 91 | 4197.0 | 4141.0 | 2899.0 | 2022-07-01 | RJ | 0.0 | 411 | | 92 | 4141.0 | 2899.0 | 0.0 | 2022-08-01 | RJ | 0.0 | 412 | | 93 | 2899.0 | 0.0 | 0.0 | 2022-09-01 | RJ | 1856.0 | 413 | | 94 | 0.0 | 0.0 | 1856.0 | 2022-10-01 | RJ | 4804.0 | 414 | | 95 | 0.0 | 1856.0 | 4804.0 | 2022-11-01 | RJ | 1764.0 | 415 | 416 |

96 rows × 6 columns

417 |
418 | 419 | # Embedding on Sklearn Pipelines 420 | 421 | ``` python 422 | from sklearn.pipeline import make_pipeline 423 | from sklearn.preprocessing import FunctionTransformer 424 | ``` 425 | 426 | ``` python 427 | add_missing_slots_transformer = FunctionTransformer( 428 | add_missing_slots, 429 | kw_args={ 430 | 'datetime_col': 'date', 431 | 'entity_col': 'city', 432 | 'value_col': 'sales', 433 | 'freq': 'MS' 434 | } 435 | ) 436 | 437 | transform_ts_data_into_features_and_target_transformer = FunctionTransformer( 438 | transform_ts_data_into_features_and_target, 439 | kw_args={ 440 | 'n_features': 3, 441 | 'datetime_col': 'date', 442 | 'entity_col': 'city', 443 | 'value_col': 'sales', 444 | 'n_targets': 1, 445 | 'step_size': 1, 446 | 'step_name': 'month', 447 | 'concat_Xy': True 448 | } 449 | ) 450 | ``` 451 | 452 | ``` python 453 | ts_data_to_features_and_target_pipeline = make_pipeline( 454 | add_missing_slots_transformer, 455 | transform_ts_data_into_features_and_target_transformer 456 | ) 457 | ts_data_to_features_and_target_pipeline 458 | ``` 459 | 460 | 
Pipeline(steps=[('functiontransformer-1',
461 |                  FunctionTransformer(func=<function add_missing_slots at 0x11f8f49d0>,
462 |                                      kw_args={'datetime_col': 'date',
463 |                                               'entity_col': 'city',
464 |                                               'freq': 'MS',
465 |                                               'value_col': 'sales'})),
466 |                 ('functiontransformer-2',
467 |                  FunctionTransformer(func=<function transform_ts_data_into_features_and_target at 0x11f925ca0>,
468 |                                      kw_args={'concat_Xy': True,
469 |                                               'datetime_col': 'date',
470 |                                               'entity_col': 'city',
471 |                                               'n_features': 3, 'n_targets': 1,
472 |                                               'step_name': 'month',
473 |                                               'step_size': 1,
474 |                                               'value_col': 'sales'}))])
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
495 | 496 | ``` python 497 | Xy_df = ts_data_to_features_and_target_pipeline.fit_transform(df) 498 | Xy_df 499 | ``` 500 | 501 | 100%|██████████| 3/3 [00:00<00:00, 715.47it/s] 502 | 100%|██████████| 3/3 [00:00<00:00, 184.12it/s] 503 | 504 |
505 | 516 | 517 | | | sales_previous_3_month | sales_previous_2_month | sales_previous_1_month | date | city | target_sales_next_month | 518 | |-----|------------------------|------------------------|------------------------|------------|------|-------------------------| 519 | | 0 | 4944.0 | 3435.0 | 4543.0 | 2020-04-01 | FOR | 3879.0 | 520 | | 1 | 3435.0 | 4543.0 | 3879.0 | 2020-05-01 | FOR | 2601.0 | 521 | | 2 | 4543.0 | 3879.0 | 2601.0 | 2020-06-01 | FOR | 2922.0 | 522 | | 3 | 3879.0 | 2601.0 | 2922.0 | 2020-07-01 | FOR | 4542.0 | 523 | | 4 | 2601.0 | 2922.0 | 4542.0 | 2020-08-01 | FOR | 1338.0 | 524 | | ... | ... | ... | ... | ... | ... | ... | 525 | | 91 | 4197.0 | 4141.0 | 2899.0 | 2022-07-01 | RJ | 0.0 | 526 | | 92 | 4141.0 | 2899.0 | 0.0 | 2022-08-01 | RJ | 0.0 | 527 | | 93 | 2899.0 | 0.0 | 0.0 | 2022-09-01 | RJ | 1856.0 | 528 | | 94 | 0.0 | 0.0 | 1856.0 | 2022-10-01 | RJ | 4804.0 | 529 | | 95 | 0.0 | 1856.0 | 4804.0 | 2022-11-01 | RJ | 1764.0 | 530 | 531 |

96 rows × 6 columns

532 |
533 | -------------------------------------------------------------------------------- /nbs/00_core.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "attachments": {}, 5 | "cell_type": "markdown", 6 | "metadata": {}, 7 | "source": [ 8 | "# core\n", 9 | "\n", 10 | "> Core functions" 11 | ] 12 | }, 13 | { 14 | "cell_type": "code", 15 | "execution_count": null, 16 | "metadata": {}, 17 | "outputs": [], 18 | "source": [ 19 | "#| default_exp core" 20 | ] 21 | }, 22 | { 23 | "cell_type": "code", 24 | "execution_count": null, 25 | "metadata": {}, 26 | "outputs": [], 27 | "source": [ 28 | "#| hide\n", 29 | "from nbdev.showdoc import *" 30 | ] 31 | }, 32 | { 33 | "cell_type": "code", 34 | "execution_count": null, 35 | "metadata": {}, 36 | "outputs": [], 37 | "source": [ 38 | "#| export\n", 39 | "import numpy as np\n", 40 | "import pandas as pd\n", 41 | "from tqdm import tqdm\n", 42 | "from typing import List" 43 | ] 44 | }, 45 | { 46 | "cell_type": "code", 47 | "execution_count": null, 48 | "metadata": {}, 49 | "outputs": [], 50 | "source": [ 51 | "#| export\n", 52 | "def add_missing_slots(\n", 53 | " df: pd.DataFrame, # input dataframe with datetime, entity and value columns - time series format\n", 54 | " datetime_col: str, # name of the datetime column\n", 55 | " entity_col: str, # name of the entity column. If a time series is associated to a location, this column will be 'location_id'\n", 56 | " value_col: str, # name of the value column\n", 57 | " freq: str='H', # frequency of the time series. Default is hourly\n", 58 | " fill_value: int = 0 # value to use to fill missing slots\n", 59 | ") -> pd.DataFrame:\n", 60 | " \"\"\"\n", 61 | " Add missing slots to a time series dataframe.\n", 62 | " This function is useful to fill missing slots in a time series dataframe.\n", 63 | " For example, if a time series is associated to a location, this function will add missing slots for each location.\n", 64 | " Missing slots are filled with the value specified in the 'fill_value' parameter.\n", 65 | " By default, the frequency of the time series is hourly.\n", 66 | " \"\"\"\n", 67 | "\n", 68 | " entity_ids = df[entity_col].unique()\n", 69 | " all_hours = pd.date_range(start=df[datetime_col].min(), end=df[datetime_col].max(), freq=freq)\n", 70 | "\n", 71 | " output = pd.DataFrame()\n", 72 | "\n", 73 | " for entity_id in tqdm(entity_ids):\n", 74 | "\n", 75 | " # keep only rides for this 'location_id'\n", 76 | " df_entity_id = df.loc[df[entity_col] == entity_id, [datetime_col, value_col]]\n", 77 | "\n", 78 | " # quick way to add missing dates with 0 in a Series\n", 79 | " # taken from https://stackoverflow.com/a/19324591\n", 80 | " df_entity_id.set_index(datetime_col, inplace=True)\n", 81 | " df_entity_id.index = pd.DatetimeIndex(df_entity_id.index)\n", 82 | " df_entity_id = df_entity_id.reindex(all_hours, fill_value=0)\n", 83 | "\n", 84 | " # add back 'location_id' column\n", 85 | " df_entity_id[entity_col] = entity_id\n", 86 | "\n", 87 | " output = pd.concat([output, df_entity_id])\n", 88 | "\n", 89 | " # move the purchase_day from index to column\n", 90 | " output = output.reset_index().rename(columns={'index': datetime_col})\n", 91 | " output = output[[datetime_col, entity_col, value_col]].copy()\n", 92 | "\n", 93 | " return output" 94 | ] 95 | }, 96 | { 97 | "cell_type": "code", 98 | "execution_count": null, 99 | "metadata": {}, 100 | "outputs": [ 101 | { 102 | "data": { 103 | "text/html": [ 104 | "
\n", 105 | "\n", 118 | "\n", 119 | " \n", 120 | " \n", 121 | " \n", 122 | " \n", 123 | " \n", 124 | " \n", 125 | " \n", 126 | " \n", 127 | " \n", 128 | " \n", 129 | " \n", 130 | " \n", 131 | " \n", 132 | " \n", 133 | " \n", 134 | " \n", 135 | " \n", 136 | " \n", 137 | " \n", 138 | " \n", 139 | " \n", 140 | " \n", 141 | " \n", 142 | " \n", 143 | " \n", 144 | " \n", 145 | " \n", 146 | " \n", 147 | " \n", 148 | " \n", 149 | " \n", 150 | " \n", 151 | " \n", 152 | " \n", 153 | " \n", 154 | " \n", 155 | " \n", 156 | " \n", 157 | " \n", 158 | " \n", 159 | " \n", 160 | " \n", 161 | " \n", 162 | " \n", 163 | " \n", 164 | " \n", 165 | "
pickup_hourpickup_location_idrides
02022-01-01 00:00:0012
12022-01-01 01:00:0013
22022-01-01 03:00:0011
32022-01-01 01:00:0021
42022-01-01 02:00:0022
52022-01-01 05:00:0021
\n", 166 | "
" 167 | ], 168 | "text/plain": [ 169 | " pickup_hour pickup_location_id rides\n", 170 | "0 2022-01-01 00:00:00 1 2\n", 171 | "1 2022-01-01 01:00:00 1 3\n", 172 | "2 2022-01-01 03:00:00 1 1\n", 173 | "3 2022-01-01 01:00:00 2 1\n", 174 | "4 2022-01-01 02:00:00 2 2\n", 175 | "5 2022-01-01 05:00:00 2 1" 176 | ] 177 | }, 178 | "execution_count": null, 179 | "metadata": {}, 180 | "output_type": "execute_result" 181 | } 182 | ], 183 | "source": [ 184 | "df = pd.DataFrame({\n", 185 | " 'pickup_hour': ['2022-01-01 00:00:00', '2022-01-01 01:00:00', '2022-01-01 03:00:00', '2022-01-01 01:00:00', '2022-01-01 02:00:00', '2022-01-01 05:00:00'],\n", 186 | " 'pickup_location_id': [1, 1, 1, 2, 2, 2],\n", 187 | " 'rides': [2, 3, 1, 1, 2, 1]\n", 188 | "})\n", 189 | "df" 190 | ] 191 | }, 192 | { 193 | "cell_type": "code", 194 | "execution_count": null, 195 | "metadata": {}, 196 | "outputs": [ 197 | { 198 | "name": "stderr", 199 | "output_type": "stream", 200 | "text": [ 201 | "100%|██████████| 2/2 [00:00<00:00, 448.83it/s]\n" 202 | ] 203 | }, 204 | { 205 | "data": { 206 | "text/html": [ 207 | "
\n", 208 | "\n", 221 | "\n", 222 | " \n", 223 | " \n", 224 | " \n", 225 | " \n", 226 | " \n", 227 | " \n", 228 | " \n", 229 | " \n", 230 | " \n", 231 | " \n", 232 | " \n", 233 | " \n", 234 | " \n", 235 | " \n", 236 | " \n", 237 | " \n", 238 | " \n", 239 | " \n", 240 | " \n", 241 | " \n", 242 | " \n", 243 | " \n", 244 | " \n", 245 | " \n", 246 | " \n", 247 | " \n", 248 | " \n", 249 | " \n", 250 | " \n", 251 | " \n", 252 | " \n", 253 | " \n", 254 | " \n", 255 | " \n", 256 | " \n", 257 | " \n", 258 | " \n", 259 | " \n", 260 | " \n", 261 | " \n", 262 | " \n", 263 | " \n", 264 | " \n", 265 | " \n", 266 | " \n", 267 | " \n", 268 | " \n", 269 | " \n", 270 | " \n", 271 | " \n", 272 | " \n", 273 | " \n", 274 | " \n", 275 | " \n", 276 | " \n", 277 | " \n", 278 | " \n", 279 | " \n", 280 | " \n", 281 | " \n", 282 | " \n", 283 | " \n", 284 | " \n", 285 | " \n", 286 | " \n", 287 | " \n", 288 | " \n", 289 | " \n", 290 | " \n", 291 | " \n", 292 | " \n", 293 | " \n", 294 | " \n", 295 | " \n", 296 | " \n", 297 | " \n", 298 | " \n", 299 | " \n", 300 | " \n", 301 | " \n", 302 | " \n", 303 | " \n", 304 | "
pickup_hourpickup_location_idrides
02022-01-01 00:00:0012
12022-01-01 01:00:0013
22022-01-01 02:00:0010
32022-01-01 03:00:0011
42022-01-01 04:00:0010
52022-01-01 05:00:0010
62022-01-01 00:00:0020
72022-01-01 01:00:0021
82022-01-01 02:00:0022
92022-01-01 03:00:0020
102022-01-01 04:00:0020
112022-01-01 05:00:0021
\n", 305 | "
" 306 | ], 307 | "text/plain": [ 308 | " pickup_hour pickup_location_id rides\n", 309 | "0 2022-01-01 00:00:00 1 2\n", 310 | "1 2022-01-01 01:00:00 1 3\n", 311 | "2 2022-01-01 02:00:00 1 0\n", 312 | "3 2022-01-01 03:00:00 1 1\n", 313 | "4 2022-01-01 04:00:00 1 0\n", 314 | "5 2022-01-01 05:00:00 1 0\n", 315 | "6 2022-01-01 00:00:00 2 0\n", 316 | "7 2022-01-01 01:00:00 2 1\n", 317 | "8 2022-01-01 02:00:00 2 2\n", 318 | "9 2022-01-01 03:00:00 2 0\n", 319 | "10 2022-01-01 04:00:00 2 0\n", 320 | "11 2022-01-01 05:00:00 2 1" 321 | ] 322 | }, 323 | "execution_count": null, 324 | "metadata": {}, 325 | "output_type": "execute_result" 326 | } 327 | ], 328 | "source": [ 329 | "add_missing_slots(df, datetime_col='pickup_hour', entity_col='pickup_location_id', value_col='rides', freq='H')" 330 | ] 331 | }, 332 | { 333 | "cell_type": "code", 334 | "execution_count": null, 335 | "metadata": {}, 336 | "outputs": [], 337 | "source": [ 338 | "#| export\n", 339 | "def get_cutoff_indices_features_and_target(\n", 340 | " ts_data: pd.DataFrame, # Time Series DataFrame\n", 341 | " datetime_col: str, # Name of the datetime column\n", 342 | " n_features: int, # Number of features to use for the prediction\n", 343 | " n_targets: int=1, # Number of target values to predict\n", 344 | " step_size: int=1, # Step size to use to slide the Time Series DataFrame\n", 345 | ") -> List[tuple]:\n", 346 | " \"\"\"Function to get the indices for the cutoffs of a Time Series DataFrame.\n", 347 | " The Time Series DataFrame should be orderded by time.\"\"\"\n", 348 | "\n", 349 | " # check if it is ordered\n", 350 | " if not ts_data[datetime_col].is_monotonic_increasing:\n", 351 | " raise ValueError(\"The DataFrame should be ordered by time.\")\n", 352 | " \n", 353 | " # check if the index is ordered\n", 354 | " if not ts_data.index.is_monotonic_increasing:\n", 355 | " raise ValueError(\"The index should be ordered by time.\")\n", 356 | " \n", 357 | " # check if the step_size is valid\n", 358 | " if step_size < 1:\n", 359 | " raise ValueError(\"The step_size should be >= 1.\")\n", 360 | " \n", 361 | " # check if the number of features is valid\n", 362 | " if n_features < 1:\n", 363 | " raise ValueError(\"The number of features should be >= 1.\")\n", 364 | " \n", 365 | " # check if the number of target values is valid\n", 366 | " if n_targets < 1:\n", 367 | " raise ValueError(\"The number of target values should be >= 1.\")\n", 368 | " \n", 369 | " # check if the number of features and target values is valid\n", 370 | " if n_features + n_targets > len(ts_data):\n", 371 | " raise ValueError(\"The number of features + target values should be <= the length of the time series.\")\n", 372 | " \n", 373 | " # below we compute the indices for the cutoffs\n", 374 | " stop_position = len(ts_data) - 1\n", 375 | "\n", 376 | " # Start the first sub-sequence at index position 0\n", 377 | " subseq_first_idx = 0\n", 378 | " subseq_mid_idx = n_features\n", 379 | " subseq_last_idx = n_features + n_targets\n", 380 | " indices = []\n", 381 | "\n", 382 | " while subseq_last_idx <= stop_position:\n", 383 | " indices.append((subseq_first_idx, subseq_mid_idx, subseq_last_idx))\n", 384 | "\n", 385 | " subseq_first_idx += step_size\n", 386 | " subseq_mid_idx += step_size\n", 387 | " subseq_last_idx += step_size\n", 388 | "\n", 389 | " return indices" 390 | ] 391 | }, 392 | { 393 | "cell_type": "code", 394 | "execution_count": null, 395 | "metadata": {}, 396 | "outputs": [ 397 | { 398 | "data": { 399 | "text/html": [ 400 | "
\n", 401 | "\n", 414 | "\n", 415 | " \n", 416 | " \n", 417 | " \n", 418 | " \n", 419 | " \n", 420 | " \n", 421 | " \n", 422 | " \n", 423 | " \n", 424 | " \n", 425 | " \n", 426 | " \n", 427 | " \n", 428 | " \n", 429 | " \n", 430 | " \n", 431 | " \n", 432 | " \n", 433 | " \n", 434 | " \n", 435 | " \n", 436 | " \n", 437 | " \n", 438 | " \n", 439 | " \n", 440 | " \n", 441 | " \n", 442 | " \n", 443 | " \n", 444 | " \n", 445 | " \n", 446 | " \n", 447 | " \n", 448 | " \n", 449 | " \n", 450 | " \n", 451 | " \n", 452 | " \n", 453 | " \n", 454 | " \n", 455 | " \n", 456 | " \n", 457 | " \n", 458 | " \n", 459 | " \n", 460 | " \n", 461 | " \n", 462 | " \n", 463 | " \n", 464 | " \n", 465 | " \n", 466 | " \n", 467 | " \n", 468 | " \n", 469 | " \n", 470 | " \n", 471 | " \n", 472 | " \n", 473 | " \n", 474 | "
pickup_hourrides
02022-01-01 01:00:002
12022-01-01 00:00:003
22022-01-01 03:00:001
32022-01-01 04:00:001
42022-01-01 02:00:002
52022-01-01 05:00:001
62022-01-01 09:00:001
72022-01-01 06:00:002
82022-01-01 07:00:001
92022-01-01 08:00:001
\n", 475 | "
" 476 | ], 477 | "text/plain": [ 478 | " pickup_hour rides\n", 479 | "0 2022-01-01 01:00:00 2\n", 480 | "1 2022-01-01 00:00:00 3\n", 481 | "2 2022-01-01 03:00:00 1\n", 482 | "3 2022-01-01 04:00:00 1\n", 483 | "4 2022-01-01 02:00:00 2\n", 484 | "5 2022-01-01 05:00:00 1\n", 485 | "6 2022-01-01 09:00:00 1\n", 486 | "7 2022-01-01 06:00:00 2\n", 487 | "8 2022-01-01 07:00:00 1\n", 488 | "9 2022-01-01 08:00:00 1" 489 | ] 490 | }, 491 | "execution_count": null, 492 | "metadata": {}, 493 | "output_type": "execute_result" 494 | } 495 | ], 496 | "source": [ 497 | "# build a time series dataframe with 10 hours of data in random order\n", 498 | "ts_data = pd.DataFrame({\n", 499 | " 'pickup_hour': ['2022-01-01 01:00:00', '2022-01-01 00:00:00', '2022-01-01 03:00:00', '2022-01-01 04:00:00', '2022-01-01 02:00:00', '2022-01-01 05:00:00', '2022-01-01 09:00:00', '2022-01-01 06:00:00', '2022-01-01 07:00:00', '2022-01-01 08:00:00'],\n", 500 | " 'rides': [2, 3, 1, 1, 2, 1, 1, 2, 1, 1]\n", 501 | "})\n", 502 | "ts_data" 503 | ] 504 | }, 505 | { 506 | "cell_type": "code", 507 | "execution_count": null, 508 | "metadata": {}, 509 | "outputs": [ 510 | { 511 | "data": { 512 | "text/plain": [ 513 | "[(0, 3, 5), (1, 4, 6), (2, 5, 7), (3, 6, 8), (4, 7, 9)]" 514 | ] 515 | }, 516 | "execution_count": null, 517 | "metadata": {}, 518 | "output_type": "execute_result" 519 | } 520 | ], 521 | "source": [ 522 | "# the time series should be ordered by time, otherwise it will not work and throw a ValueError\n", 523 | "ts_data.sort_values(by='pickup_hour', inplace=True, ignore_index=True)\n", 524 | "cutoff_idxs = get_cutoff_indices_features_and_target(ts_data, datetime_col='pickup_hour', n_features=3, n_targets=2, step_size=1)\n", 525 | "cutoff_idxs" 526 | ] 527 | }, 528 | { 529 | "cell_type": "code", 530 | "execution_count": null, 531 | "metadata": {}, 532 | "outputs": [], 533 | "source": [ 534 | "assert cutoff_idxs == [(0, 3, 5), (1, 4, 6), (2, 5, 7), (3, 6, 8), (4, 7, 9)]" 535 | ] 536 | }, 537 | { 538 | "cell_type": "code", 539 | "execution_count": null, 540 | "metadata": {}, 541 | "outputs": [], 542 | "source": [ 543 | "#| export\n", 544 | "def transform_ts_data_into_features_and_target(\n", 545 | " ts_data: pd.DataFrame, # Time Series DataFrame\n", 546 | " n_features: int, # Number of features to use for the prediction\n", 547 | " datetime_col: str, # Name of the datetime column\n", 548 | " entity_col: str, # Name of the entity column, e.g. location_id\n", 549 | " value_col: str, # Name of the value column\n", 550 | " n_targets: int=1, # Number of target values to predict\n", 551 | " step_size: int=1, # Step size to use to slide the Time Series DataFrame\n", 552 | " step_name: str=None, # Name of the step column\n", 553 | " concat_Xy: bool=False # Whether to concat X and y on the same dataframe or not\n", 554 | ") -> pd.DataFrame:\n", 555 | " \"\"\"\n", 556 | " Slices and transposes data from time-series format into a (features, target)\n", 557 | " format that we can use to train Supervised ML models.\n", 558 | " \"\"\"\n", 559 | "\n", 560 | " entity_ids = ts_data[entity_col].unique()\n", 561 | " features = pd.DataFrame()\n", 562 | " targets = pd.DataFrame()\n", 563 | " \n", 564 | " for entity_id in tqdm(entity_ids):\n", 565 | " \n", 566 | " # keep only ts data for this `location_id`\n", 567 | " ts_data_one_location = ts_data.loc[\n", 568 | " ts_data[entity_col] == entity_id, \n", 569 | " [datetime_col, value_col]\n", 570 | " ]\n", 571 | "\n", 572 | " # pre-compute cutoff indices to split dataframe rows\n", 573 | " indices = get_cutoff_indices_features_and_target(\n", 574 | " ts_data=ts_data_one_location,\n", 575 | " datetime_col=datetime_col,\n", 576 | " n_features=n_features,\n", 577 | " n_targets=n_targets,\n", 578 | " step_size=step_size\n", 579 | " )\n", 580 | "\n", 581 | " # slice and transpose data into numpy arrays for features and targets\n", 582 | " time_values = []\n", 583 | " n_examples = len(indices)\n", 584 | " x = np.ndarray(shape=(n_examples, n_features), dtype=np.float32)\n", 585 | " if n_targets == 1:\n", 586 | " y = np.ndarray(shape=(n_examples), dtype=np.float32)\n", 587 | " for i, idx in enumerate(indices):\n", 588 | " x[i, :] = ts_data_one_location.iloc[idx[0]:idx[1]][value_col].values\n", 589 | " y[i] = ts_data_one_location.iloc[idx[1]:idx[2]][value_col].values\n", 590 | " time_values.append(ts_data_one_location.iloc[idx[1]][datetime_col])\n", 591 | " else:\n", 592 | " y = np.ndarray(shape=(n_examples, n_targets), dtype=np.float32)\n", 593 | " for i, idx in enumerate(indices):\n", 594 | " x[i, :] = ts_data_one_location.iloc[idx[0]:idx[1]][value_col].values\n", 595 | " y[i, :] = ts_data_one_location.iloc[idx[1]:idx[2]][value_col].values\n", 596 | " time_values.append(ts_data_one_location.iloc[idx[1]][datetime_col])\n", 597 | "\n", 598 | " # numpy -> pandas\n", 599 | " if step_name is None:\n", 600 | " features_one_location = pd.DataFrame(\n", 601 | " x,\n", 602 | " columns=[f'{value_col}_previous_{i+1}' for i in reversed(range(n_features))]\n", 603 | " )\n", 604 | " features_one_location[datetime_col] = time_values\n", 605 | " features_one_location[entity_col] = entity_id\n", 606 | "\n", 607 | " # numpy -> pandas\n", 608 | " if n_targets == 1:\n", 609 | " targets_one_location = pd.DataFrame(y, columns=[f'target_{value_col}_next'])\n", 610 | " else:\n", 611 | " targets_one_location = pd.DataFrame(\n", 612 | " y,\n", 613 | " columns=[f'target_{value_col}_next_{i+1}' for i in range(n_targets)]\n", 614 | " )\n", 615 | " else:\n", 616 | " features_one_location = pd.DataFrame(\n", 617 | " x,\n", 618 | " columns=[f'{value_col}_previous_{i+1}_{step_name}' for i in reversed(range(n_features))]\n", 619 | " )\n", 620 | " features_one_location[datetime_col] = time_values\n", 621 | " features_one_location[entity_col] = entity_id\n", 622 | "\n", 623 | " # numpy -> pandas\n", 624 | " if n_targets == 1:\n", 625 | " targets_one_location = pd.DataFrame(y, columns=[f'target_{value_col}_next_{step_name}'])\n", 626 | " else:\n", 627 | " targets_one_location = pd.DataFrame(\n", 628 | " y,\n", 629 | " columns=[f'target_{value_col}_next_{i+1}_{step_name}' for i in range(n_targets)]\n", 630 | " )\n", 631 | " \n", 632 | " # concatenate results\n", 633 | " features = pd.concat([features, features_one_location])\n", 634 | " targets = pd.concat([targets, targets_one_location])\n", 635 | "\n", 636 | " features.reset_index(inplace=True, drop=True)\n", 637 | " targets.reset_index(inplace=True, drop=True)\n", 638 | "\n", 639 | " if concat_Xy:\n", 640 | " return pd.concat([features, targets], axis=1)\n", 641 | " else:\n", 642 | " return features, targets" 643 | ] 644 | }, 645 | { 646 | "cell_type": "code", 647 | "execution_count": null, 648 | "metadata": {}, 649 | "outputs": [ 650 | { 651 | "data": { 652 | "text/html": [ 653 | "
\n", 654 | "\n", 667 | "\n", 668 | " \n", 669 | " \n", 670 | " \n", 671 | " \n", 672 | " \n", 673 | " \n", 674 | " \n", 675 | " \n", 676 | " \n", 677 | " \n", 678 | " \n", 679 | " \n", 680 | " \n", 681 | " \n", 682 | " \n", 683 | " \n", 684 | " \n", 685 | " \n", 686 | " \n", 687 | " \n", 688 | " \n", 689 | " \n", 690 | " \n", 691 | " \n", 692 | " \n", 693 | " \n", 694 | " \n", 695 | " \n", 696 | " \n", 697 | " \n", 698 | " \n", 699 | " \n", 700 | " \n", 701 | " \n", 702 | " \n", 703 | " \n", 704 | " \n", 705 | " \n", 706 | " \n", 707 | " \n", 708 | " \n", 709 | " \n", 710 | " \n", 711 | " \n", 712 | " \n", 713 | " \n", 714 | " \n", 715 | " \n", 716 | " \n", 717 | " \n", 718 | " \n", 719 | " \n", 720 | " \n", 721 | " \n", 722 | " \n", 723 | " \n", 724 | " \n", 725 | " \n", 726 | " \n", 727 | " \n", 728 | " \n", 729 | " \n", 730 | " \n", 731 | " \n", 732 | " \n", 733 | " \n", 734 | " \n", 735 | " \n", 736 | " \n", 737 | " \n", 738 | "
pickup_hourlocation_idrides
02022-01-01 01:00:0012
12022-01-01 00:00:0013
22022-01-01 03:00:0011
32022-01-01 04:00:0011
42022-01-01 02:00:0012
52022-01-01 05:00:0011
62022-01-01 09:00:0021
72022-01-01 06:00:0022
82022-01-01 07:00:0021
92022-01-01 08:00:0021
\n", 739 | "
" 740 | ], 741 | "text/plain": [ 742 | " pickup_hour location_id rides\n", 743 | "0 2022-01-01 01:00:00 1 2\n", 744 | "1 2022-01-01 00:00:00 1 3\n", 745 | "2 2022-01-01 03:00:00 1 1\n", 746 | "3 2022-01-01 04:00:00 1 1\n", 747 | "4 2022-01-01 02:00:00 1 2\n", 748 | "5 2022-01-01 05:00:00 1 1\n", 749 | "6 2022-01-01 09:00:00 2 1\n", 750 | "7 2022-01-01 06:00:00 2 2\n", 751 | "8 2022-01-01 07:00:00 2 1\n", 752 | "9 2022-01-01 08:00:00 2 1" 753 | ] 754 | }, 755 | "execution_count": null, 756 | "metadata": {}, 757 | "output_type": "execute_result" 758 | } 759 | ], 760 | "source": [ 761 | "# build a time series dataframe with 10 hours of data in random order and a location id column with 1 and 2\n", 762 | "ts_data = pd.DataFrame({\n", 763 | " 'pickup_hour': ['2022-01-01 01:00:00', '2022-01-01 00:00:00', '2022-01-01 03:00:00', '2022-01-01 04:00:00', '2022-01-01 02:00:00', '2022-01-01 05:00:00', '2022-01-01 09:00:00', '2022-01-01 06:00:00', '2022-01-01 07:00:00', '2022-01-01 08:00:00'],\n", 764 | " 'location_id': [1, 1, 1, 1, 1, 1, 2, 2, 2, 2],\n", 765 | " 'rides': [2, 3, 1, 1, 2, 1, 1, 2, 1, 1]\n", 766 | "})\n", 767 | "ts_data" 768 | ] 769 | }, 770 | { 771 | "cell_type": "code", 772 | "execution_count": null, 773 | "metadata": {}, 774 | "outputs": [ 775 | { 776 | "name": "stderr", 777 | "output_type": "stream", 778 | "text": [ 779 | "100%|██████████| 2/2 [00:00<00:00, 708.92it/s]\n" 780 | ] 781 | }, 782 | { 783 | "data": { 784 | "text/html": [ 785 | "
\n", 786 | "\n", 799 | "\n", 800 | " \n", 801 | " \n", 802 | " \n", 803 | " \n", 804 | " \n", 805 | " \n", 806 | " \n", 807 | " \n", 808 | " \n", 809 | " \n", 810 | " \n", 811 | " \n", 812 | " \n", 813 | " \n", 814 | " \n", 815 | " \n", 816 | " \n", 817 | " \n", 818 | " \n", 819 | " \n", 820 | " \n", 821 | " \n", 822 | " \n", 823 | " \n", 824 | " \n", 825 | " \n", 826 | " \n", 827 | " \n", 828 | " \n", 829 | " \n", 830 | " \n", 831 | " \n", 832 | " \n", 833 | " \n", 834 | " \n", 835 | " \n", 836 | " \n", 837 | " \n", 838 | " \n", 839 | " \n", 840 | " \n", 841 | " \n", 842 | " \n", 843 | " \n", 844 | " \n", 845 | " \n", 846 | " \n", 847 | " \n", 848 | " \n", 849 | " \n", 850 | " \n", 851 | " \n", 852 | " \n", 853 | " \n", 854 | " \n", 855 | " \n", 856 | " \n", 857 | " \n", 858 | " \n", 859 | " \n", 860 | " \n", 861 | " \n", 862 | " \n", 863 | " \n", 864 | " \n", 865 | " \n", 866 | " \n", 867 | " \n", 868 | " \n", 869 | " \n", 870 | " \n", 871 | " \n", 872 | " \n", 873 | " \n", 874 | " \n", 875 | " \n", 876 | " \n", 877 | " \n", 878 | " \n", 879 | " \n", 880 | " \n", 881 | " \n", 882 | " \n", 883 | " \n", 884 | " \n", 885 | " \n", 886 | " \n", 887 | " \n", 888 | " \n", 889 | " \n", 890 | " \n", 891 | " \n", 892 | " \n", 893 | " \n", 894 | " \n", 895 | " \n", 896 | " \n", 897 | " \n", 898 | " \n", 899 | " \n", 900 | " \n", 901 | " \n", 902 | " \n", 903 | " \n", 904 | " \n", 905 | " \n", 906 | " \n", 907 | " \n", 908 | " \n", 909 | " \n", 910 | " \n", 911 | " \n", 912 | " \n", 913 | " \n", 914 | " \n", 915 | " \n", 916 | " \n", 917 | " \n", 918 | " \n", 919 | " \n", 920 | " \n", 921 | " \n", 922 | " \n", 923 | " \n", 924 | " \n", 925 | " \n", 926 | " \n", 927 | " \n", 928 | " \n", 929 | " \n", 930 | "
pickup_hourlocation_idrides
02022-01-01 00:00:0013
12022-01-01 01:00:0012
22022-01-01 02:00:0012
32022-01-01 03:00:0011
42022-01-01 04:00:0011
52022-01-01 05:00:0011
62022-01-01 06:00:0010
72022-01-01 07:00:0010
82022-01-01 08:00:0010
92022-01-01 09:00:0010
102022-01-01 00:00:0020
112022-01-01 01:00:0020
122022-01-01 02:00:0020
132022-01-01 03:00:0020
142022-01-01 04:00:0020
152022-01-01 05:00:0020
162022-01-01 06:00:0022
172022-01-01 07:00:0021
182022-01-01 08:00:0021
192022-01-01 09:00:0021
\n", 931 | "
" 932 | ], 933 | "text/plain": [ 934 | " pickup_hour location_id rides\n", 935 | "0 2022-01-01 00:00:00 1 3\n", 936 | "1 2022-01-01 01:00:00 1 2\n", 937 | "2 2022-01-01 02:00:00 1 2\n", 938 | "3 2022-01-01 03:00:00 1 1\n", 939 | "4 2022-01-01 04:00:00 1 1\n", 940 | "5 2022-01-01 05:00:00 1 1\n", 941 | "6 2022-01-01 06:00:00 1 0\n", 942 | "7 2022-01-01 07:00:00 1 0\n", 943 | "8 2022-01-01 08:00:00 1 0\n", 944 | "9 2022-01-01 09:00:00 1 0\n", 945 | "10 2022-01-01 00:00:00 2 0\n", 946 | "11 2022-01-01 01:00:00 2 0\n", 947 | "12 2022-01-01 02:00:00 2 0\n", 948 | "13 2022-01-01 03:00:00 2 0\n", 949 | "14 2022-01-01 04:00:00 2 0\n", 950 | "15 2022-01-01 05:00:00 2 0\n", 951 | "16 2022-01-01 06:00:00 2 2\n", 952 | "17 2022-01-01 07:00:00 2 1\n", 953 | "18 2022-01-01 08:00:00 2 1\n", 954 | "19 2022-01-01 09:00:00 2 1" 955 | ] 956 | }, 957 | "execution_count": null, 958 | "metadata": {}, 959 | "output_type": "execute_result" 960 | } 961 | ], 962 | "source": [ 963 | "ts_data = add_missing_slots(ts_data, datetime_col='pickup_hour', entity_col='location_id', value_col='rides', freq='1H')\n", 964 | "ts_data" 965 | ] 966 | }, 967 | { 968 | "cell_type": "code", 969 | "execution_count": null, 970 | "metadata": {}, 971 | "outputs": [ 972 | { 973 | "name": "stderr", 974 | "output_type": "stream", 975 | "text": [ 976 | "100%|██████████| 2/2 [00:00<00:00, 371.60it/s]\n" 977 | ] 978 | } 979 | ], 980 | "source": [ 981 | "features, targets = transform_ts_data_into_features_and_target(\n", 982 | " ts_data=ts_data,\n", 983 | " n_features=3,\n", 984 | " datetime_col='pickup_hour',\n", 985 | " entity_col='location_id',\n", 986 | " value_col='rides',\n", 987 | " n_targets=2,\n", 988 | " step_size=1\n", 989 | ")" 990 | ] 991 | }, 992 | { 993 | "cell_type": "code", 994 | "execution_count": null, 995 | "metadata": {}, 996 | "outputs": [ 997 | { 998 | "data": { 999 | "text/html": [ 1000 | "
\n", 1001 | "\n", 1014 | "\n", 1015 | " \n", 1016 | " \n", 1017 | " \n", 1018 | " \n", 1019 | " \n", 1020 | " \n", 1021 | " \n", 1022 | " \n", 1023 | " \n", 1024 | " \n", 1025 | " \n", 1026 | " \n", 1027 | " \n", 1028 | " \n", 1029 | " \n", 1030 | " \n", 1031 | " \n", 1032 | " \n", 1033 | " \n", 1034 | " \n", 1035 | " \n", 1036 | " \n", 1037 | " \n", 1038 | " \n", 1039 | " \n", 1040 | " \n", 1041 | " \n", 1042 | " \n", 1043 | " \n", 1044 | " \n", 1045 | " \n", 1046 | " \n", 1047 | " \n", 1048 | " \n", 1049 | " \n", 1050 | " \n", 1051 | " \n", 1052 | " \n", 1053 | " \n", 1054 | " \n", 1055 | " \n", 1056 | " \n", 1057 | " \n", 1058 | " \n", 1059 | " \n", 1060 | " \n", 1061 | " \n", 1062 | " \n", 1063 | " \n", 1064 | " \n", 1065 | " \n", 1066 | " \n", 1067 | " \n", 1068 | " \n", 1069 | " \n", 1070 | " \n", 1071 | " \n", 1072 | " \n", 1073 | " \n", 1074 | " \n", 1075 | " \n", 1076 | " \n", 1077 | " \n", 1078 | " \n", 1079 | " \n", 1080 | " \n", 1081 | " \n", 1082 | " \n", 1083 | " \n", 1084 | " \n", 1085 | " \n", 1086 | " \n", 1087 | " \n", 1088 | " \n", 1089 | " \n", 1090 | " \n", 1091 | " \n", 1092 | " \n", 1093 | " \n", 1094 | " \n", 1095 | " \n", 1096 | " \n", 1097 | " \n", 1098 | " \n", 1099 | " \n", 1100 | " \n", 1101 | " \n", 1102 | " \n", 1103 | " \n", 1104 | " \n", 1105 | " \n", 1106 | " \n", 1107 | "
rides_previous_3rides_previous_2rides_previous_1pickup_hourlocation_id
03.02.02.02022-01-01 03:00:001
12.02.01.02022-01-01 04:00:001
22.01.01.02022-01-01 05:00:001
31.01.01.02022-01-01 06:00:001
41.01.00.02022-01-01 07:00:001
50.00.00.02022-01-01 03:00:002
60.00.00.02022-01-01 04:00:002
70.00.00.02022-01-01 05:00:002
80.00.00.02022-01-01 06:00:002
90.00.02.02022-01-01 07:00:002
\n", 1108 | "
" 1109 | ], 1110 | "text/plain": [ 1111 | " rides_previous_3 rides_previous_2 rides_previous_1 pickup_hour \\\n", 1112 | "0 3.0 2.0 2.0 2022-01-01 03:00:00 \n", 1113 | "1 2.0 2.0 1.0 2022-01-01 04:00:00 \n", 1114 | "2 2.0 1.0 1.0 2022-01-01 05:00:00 \n", 1115 | "3 1.0 1.0 1.0 2022-01-01 06:00:00 \n", 1116 | "4 1.0 1.0 0.0 2022-01-01 07:00:00 \n", 1117 | "5 0.0 0.0 0.0 2022-01-01 03:00:00 \n", 1118 | "6 0.0 0.0 0.0 2022-01-01 04:00:00 \n", 1119 | "7 0.0 0.0 0.0 2022-01-01 05:00:00 \n", 1120 | "8 0.0 0.0 0.0 2022-01-01 06:00:00 \n", 1121 | "9 0.0 0.0 2.0 2022-01-01 07:00:00 \n", 1122 | "\n", 1123 | " location_id \n", 1124 | "0 1 \n", 1125 | "1 1 \n", 1126 | "2 1 \n", 1127 | "3 1 \n", 1128 | "4 1 \n", 1129 | "5 2 \n", 1130 | "6 2 \n", 1131 | "7 2 \n", 1132 | "8 2 \n", 1133 | "9 2 " 1134 | ] 1135 | }, 1136 | "execution_count": null, 1137 | "metadata": {}, 1138 | "output_type": "execute_result" 1139 | } 1140 | ], 1141 | "source": [ 1142 | "features" 1143 | ] 1144 | }, 1145 | { 1146 | "cell_type": "code", 1147 | "execution_count": null, 1148 | "metadata": {}, 1149 | "outputs": [ 1150 | { 1151 | "data": { 1152 | "text/html": [ 1153 | "
\n", 1154 | "\n", 1167 | "\n", 1168 | " \n", 1169 | " \n", 1170 | " \n", 1171 | " \n", 1172 | " \n", 1173 | " \n", 1174 | " \n", 1175 | " \n", 1176 | " \n", 1177 | " \n", 1178 | " \n", 1179 | " \n", 1180 | " \n", 1181 | " \n", 1182 | " \n", 1183 | " \n", 1184 | " \n", 1185 | " \n", 1186 | " \n", 1187 | " \n", 1188 | " \n", 1189 | " \n", 1190 | " \n", 1191 | " \n", 1192 | " \n", 1193 | " \n", 1194 | " \n", 1195 | " \n", 1196 | " \n", 1197 | " \n", 1198 | " \n", 1199 | " \n", 1200 | " \n", 1201 | " \n", 1202 | " \n", 1203 | " \n", 1204 | " \n", 1205 | " \n", 1206 | " \n", 1207 | " \n", 1208 | " \n", 1209 | " \n", 1210 | " \n", 1211 | " \n", 1212 | " \n", 1213 | " \n", 1214 | " \n", 1215 | " \n", 1216 | " \n", 1217 | " \n", 1218 | " \n", 1219 | " \n", 1220 | " \n", 1221 | " \n", 1222 | " \n", 1223 | " \n", 1224 | " \n", 1225 | " \n", 1226 | " \n", 1227 | "
target_rides_next_1target_rides_next_2
01.01.0
11.01.0
21.00.0
30.00.0
40.00.0
50.00.0
60.00.0
70.02.0
82.01.0
91.01.0
\n", 1228 | "
" 1229 | ], 1230 | "text/plain": [ 1231 | " target_rides_next_1 target_rides_next_2\n", 1232 | "0 1.0 1.0\n", 1233 | "1 1.0 1.0\n", 1234 | "2 1.0 0.0\n", 1235 | "3 0.0 0.0\n", 1236 | "4 0.0 0.0\n", 1237 | "5 0.0 0.0\n", 1238 | "6 0.0 0.0\n", 1239 | "7 0.0 2.0\n", 1240 | "8 2.0 1.0\n", 1241 | "9 1.0 1.0" 1242 | ] 1243 | }, 1244 | "execution_count": null, 1245 | "metadata": {}, 1246 | "output_type": "execute_result" 1247 | } 1248 | ], 1249 | "source": [ 1250 | "targets" 1251 | ] 1252 | }, 1253 | { 1254 | "cell_type": "code", 1255 | "execution_count": null, 1256 | "metadata": {}, 1257 | "outputs": [ 1258 | { 1259 | "data": { 1260 | "text/html": [ 1261 | "
\n", 1262 | "\n", 1275 | "\n", 1276 | " \n", 1277 | " \n", 1278 | " \n", 1279 | " \n", 1280 | " \n", 1281 | " \n", 1282 | " \n", 1283 | " \n", 1284 | " \n", 1285 | " \n", 1286 | " \n", 1287 | " \n", 1288 | " \n", 1289 | " \n", 1290 | " \n", 1291 | " \n", 1292 | " \n", 1293 | " \n", 1294 | " \n", 1295 | " \n", 1296 | " \n", 1297 | " \n", 1298 | " \n", 1299 | " \n", 1300 | " \n", 1301 | " \n", 1302 | " \n", 1303 | " \n", 1304 | " \n", 1305 | " \n", 1306 | " \n", 1307 | " \n", 1308 | " \n", 1309 | " \n", 1310 | " \n", 1311 | " \n", 1312 | " \n", 1313 | " \n", 1314 | " \n", 1315 | " \n", 1316 | " \n", 1317 | " \n", 1318 | " \n", 1319 | " \n", 1320 | " \n", 1321 | " \n", 1322 | " \n", 1323 | " \n", 1324 | " \n", 1325 | " \n", 1326 | " \n", 1327 | " \n", 1328 | " \n", 1329 | " \n", 1330 | " \n", 1331 | " \n", 1332 | " \n", 1333 | " \n", 1334 | " \n", 1335 | " \n", 1336 | " \n", 1337 | " \n", 1338 | " \n", 1339 | " \n", 1340 | " \n", 1341 | " \n", 1342 | " \n", 1343 | " \n", 1344 | " \n", 1345 | " \n", 1346 | " \n", 1347 | " \n", 1348 | " \n", 1349 | " \n", 1350 | " \n", 1351 | " \n", 1352 | " \n", 1353 | " \n", 1354 | " \n", 1355 | " \n", 1356 | " \n", 1357 | " \n", 1358 | " \n", 1359 | " \n", 1360 | " \n", 1361 | " \n", 1362 | " \n", 1363 | " \n", 1364 | " \n", 1365 | " \n", 1366 | " \n", 1367 | " \n", 1368 | " \n", 1369 | " \n", 1370 | " \n", 1371 | " \n", 1372 | " \n", 1373 | " \n", 1374 | " \n", 1375 | " \n", 1376 | " \n", 1377 | " \n", 1378 | " \n", 1379 | " \n", 1380 | " \n", 1381 | " \n", 1382 | " \n", 1383 | " \n", 1384 | " \n", 1385 | " \n", 1386 | " \n", 1387 | " \n", 1388 | " \n", 1389 | " \n", 1390 | "
rides_previous_3rides_previous_2rides_previous_1pickup_hourlocation_idtarget_rides_next_1target_rides_next_2
03.02.02.02022-01-01 03:00:0011.01.0
12.02.01.02022-01-01 04:00:0011.01.0
22.01.01.02022-01-01 05:00:0011.00.0
31.01.01.02022-01-01 06:00:0010.00.0
41.01.00.02022-01-01 07:00:0010.00.0
50.00.00.02022-01-01 03:00:0020.00.0
60.00.00.02022-01-01 04:00:0020.00.0
70.00.00.02022-01-01 05:00:0020.02.0
80.00.00.02022-01-01 06:00:0022.01.0
90.00.02.02022-01-01 07:00:0021.01.0
\n", 1391 | "
" 1392 | ], 1393 | "text/plain": [ 1394 | " rides_previous_3 rides_previous_2 rides_previous_1 pickup_hour \\\n", 1395 | "0 3.0 2.0 2.0 2022-01-01 03:00:00 \n", 1396 | "1 2.0 2.0 1.0 2022-01-01 04:00:00 \n", 1397 | "2 2.0 1.0 1.0 2022-01-01 05:00:00 \n", 1398 | "3 1.0 1.0 1.0 2022-01-01 06:00:00 \n", 1399 | "4 1.0 1.0 0.0 2022-01-01 07:00:00 \n", 1400 | "5 0.0 0.0 0.0 2022-01-01 03:00:00 \n", 1401 | "6 0.0 0.0 0.0 2022-01-01 04:00:00 \n", 1402 | "7 0.0 0.0 0.0 2022-01-01 05:00:00 \n", 1403 | "8 0.0 0.0 0.0 2022-01-01 06:00:00 \n", 1404 | "9 0.0 0.0 2.0 2022-01-01 07:00:00 \n", 1405 | "\n", 1406 | " location_id target_rides_next_1 target_rides_next_2 \n", 1407 | "0 1 1.0 1.0 \n", 1408 | "1 1 1.0 1.0 \n", 1409 | "2 1 1.0 0.0 \n", 1410 | "3 1 0.0 0.0 \n", 1411 | "4 1 0.0 0.0 \n", 1412 | "5 2 0.0 0.0 \n", 1413 | "6 2 0.0 0.0 \n", 1414 | "7 2 0.0 2.0 \n", 1415 | "8 2 2.0 1.0 \n", 1416 | "9 2 1.0 1.0 " 1417 | ] 1418 | }, 1419 | "execution_count": null, 1420 | "metadata": {}, 1421 | "output_type": "execute_result" 1422 | } 1423 | ], 1424 | "source": [ 1425 | "pd.concat([features, targets], axis=1)" 1426 | ] 1427 | }, 1428 | { 1429 | "attachments": {}, 1430 | "cell_type": "markdown", 1431 | "metadata": {}, 1432 | "source": [ 1433 | "This dataset could be use to predict the rides for the next 2 hours, for each location_id, by using historical rides from the previous 3 hours." 1434 | ] 1435 | }, 1436 | { 1437 | "cell_type": "code", 1438 | "execution_count": null, 1439 | "metadata": {}, 1440 | "outputs": [], 1441 | "source": [ 1442 | "#| hide\n", 1443 | "import nbdev; nbdev.nbdev_export()" 1444 | ] 1445 | } 1446 | ], 1447 | "metadata": { 1448 | "kernelspec": { 1449 | "display_name": "python3", 1450 | "language": "python", 1451 | "name": "python3" 1452 | } 1453 | }, 1454 | "nbformat": 4, 1455 | "nbformat_minor": 4 1456 | } 1457 | -------------------------------------------------------------------------------- /nbs/_quarto.yml: -------------------------------------------------------------------------------- 1 | project: 2 | type: website 3 | 4 | format: 5 | html: 6 | theme: cosmo 7 | css: styles.css 8 | toc: true 9 | 10 | website: 11 | twitter-card: true 12 | open-graph: true 13 | repo-actions: [issue] 14 | navbar: 15 | background: primary 16 | search: true 17 | sidebar: 18 | style: floating 19 | 20 | metadata-files: [nbdev.yml, sidebar.yml] -------------------------------------------------------------------------------- /nbs/index.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "attachments": {}, 5 | "cell_type": "markdown", 6 | "metadata": {}, 7 | "source": [ 8 | "# ts2ml\n", 9 | "\n", 10 | "> Tools to Transform a Time Series into Features and Target Dataset" 11 | ] 12 | }, 13 | { 14 | "attachments": {}, 15 | "cell_type": "markdown", 16 | "metadata": {}, 17 | "source": [ 18 | "## Install" 19 | ] 20 | }, 21 | { 22 | "attachments": {}, 23 | "cell_type": "markdown", 24 | "metadata": {}, 25 | "source": [ 26 | "```sh\n", 27 | "pip install ts2ml\n", 28 | "```" 29 | ] 30 | }, 31 | { 32 | "attachments": {}, 33 | "cell_type": "markdown", 34 | "metadata": {}, 35 | "source": [ 36 | "## How to use" 37 | ] 38 | }, 39 | { 40 | "cell_type": "code", 41 | "execution_count": null, 42 | "metadata": {}, 43 | "outputs": [], 44 | "source": [ 45 | "import pandas as pd\n", 46 | "from ts2ml.core import add_missing_slots\n", 47 | "from ts2ml.core import transform_ts_data_into_features_and_target" 48 | ] 49 | }, 50 | { 51 | "cell_type": "code", 52 | "execution_count": null, 53 | "metadata": {}, 54 | "outputs": [ 55 | { 56 | "data": { 57 | "text/html": [ 58 | "
\n", 59 | "\n", 72 | "\n", 73 | " \n", 74 | " \n", 75 | " \n", 76 | " \n", 77 | " \n", 78 | " \n", 79 | " \n", 80 | " \n", 81 | " \n", 82 | " \n", 83 | " \n", 84 | " \n", 85 | " \n", 86 | " \n", 87 | " \n", 88 | " \n", 89 | " \n", 90 | " \n", 91 | " \n", 92 | " \n", 93 | " \n", 94 | " \n", 95 | " \n", 96 | " \n", 97 | " \n", 98 | " \n", 99 | " \n", 100 | " \n", 101 | " \n", 102 | " \n", 103 | " \n", 104 | " \n", 105 | " \n", 106 | " \n", 107 | " \n", 108 | " \n", 109 | " \n", 110 | " \n", 111 | " \n", 112 | " \n", 113 | " \n", 114 | " \n", 115 | " \n", 116 | " \n", 117 | " \n", 118 | " \n", 119 | "
pickup_hourpickup_location_idrides
02022-01-01 00:00:0012
12022-01-01 01:00:0013
22022-01-01 03:00:0011
32022-01-01 01:00:0021
42022-01-01 02:00:0022
52022-01-01 05:00:0021
\n", 120 | "
" 121 | ], 122 | "text/plain": [ 123 | " pickup_hour pickup_location_id rides\n", 124 | "0 2022-01-01 00:00:00 1 2\n", 125 | "1 2022-01-01 01:00:00 1 3\n", 126 | "2 2022-01-01 03:00:00 1 1\n", 127 | "3 2022-01-01 01:00:00 2 1\n", 128 | "4 2022-01-01 02:00:00 2 2\n", 129 | "5 2022-01-01 05:00:00 2 1" 130 | ] 131 | }, 132 | "execution_count": null, 133 | "metadata": {}, 134 | "output_type": "execute_result" 135 | } 136 | ], 137 | "source": [ 138 | "df = pd.DataFrame({\n", 139 | " 'pickup_hour': ['2022-01-01 00:00:00', '2022-01-01 01:00:00', '2022-01-01 03:00:00', '2022-01-01 01:00:00', '2022-01-01 02:00:00', '2022-01-01 05:00:00'],\n", 140 | " 'pickup_location_id': [1, 1, 1, 2, 2, 2],\n", 141 | " 'rides': [2, 3, 1, 1, 2, 1]\n", 142 | "})\n", 143 | "df" 144 | ] 145 | }, 146 | { 147 | "attachments": {}, 148 | "cell_type": "markdown", 149 | "metadata": {}, 150 | "source": [ 151 | "Let's fill the missing slots with zeros" 152 | ] 153 | }, 154 | { 155 | "cell_type": "code", 156 | "execution_count": null, 157 | "metadata": {}, 158 | "outputs": [ 159 | { 160 | "name": "stderr", 161 | "output_type": "stream", 162 | "text": [ 163 | "100%|██████████| 2/2 [00:00<00:00, 907.86it/s]\n" 164 | ] 165 | }, 166 | { 167 | "data": { 168 | "text/html": [ 169 | "
\n", 170 | "\n", 183 | "\n", 184 | " \n", 185 | " \n", 186 | " \n", 187 | " \n", 188 | " \n", 189 | " \n", 190 | " \n", 191 | " \n", 192 | " \n", 193 | " \n", 194 | " \n", 195 | " \n", 196 | " \n", 197 | " \n", 198 | " \n", 199 | " \n", 200 | " \n", 201 | " \n", 202 | " \n", 203 | " \n", 204 | " \n", 205 | " \n", 206 | " \n", 207 | " \n", 208 | " \n", 209 | " \n", 210 | " \n", 211 | " \n", 212 | " \n", 213 | " \n", 214 | " \n", 215 | " \n", 216 | " \n", 217 | " \n", 218 | " \n", 219 | " \n", 220 | " \n", 221 | " \n", 222 | " \n", 223 | " \n", 224 | " \n", 225 | " \n", 226 | " \n", 227 | " \n", 228 | " \n", 229 | " \n", 230 | " \n", 231 | " \n", 232 | " \n", 233 | " \n", 234 | " \n", 235 | " \n", 236 | " \n", 237 | " \n", 238 | " \n", 239 | " \n", 240 | " \n", 241 | " \n", 242 | " \n", 243 | " \n", 244 | " \n", 245 | " \n", 246 | " \n", 247 | " \n", 248 | " \n", 249 | " \n", 250 | " \n", 251 | " \n", 252 | " \n", 253 | " \n", 254 | " \n", 255 | " \n", 256 | " \n", 257 | " \n", 258 | " \n", 259 | " \n", 260 | " \n", 261 | " \n", 262 | " \n", 263 | " \n", 264 | " \n", 265 | " \n", 266 | "
pickup_hourpickup_location_idrides
02022-01-01 00:00:0012
12022-01-01 01:00:0013
22022-01-01 02:00:0010
32022-01-01 03:00:0011
42022-01-01 04:00:0010
52022-01-01 05:00:0010
62022-01-01 00:00:0020
72022-01-01 01:00:0021
82022-01-01 02:00:0022
92022-01-01 03:00:0020
102022-01-01 04:00:0020
112022-01-01 05:00:0021
\n", 267 | "
" 268 | ], 269 | "text/plain": [ 270 | " pickup_hour pickup_location_id rides\n", 271 | "0 2022-01-01 00:00:00 1 2\n", 272 | "1 2022-01-01 01:00:00 1 3\n", 273 | "2 2022-01-01 02:00:00 1 0\n", 274 | "3 2022-01-01 03:00:00 1 1\n", 275 | "4 2022-01-01 04:00:00 1 0\n", 276 | "5 2022-01-01 05:00:00 1 0\n", 277 | "6 2022-01-01 00:00:00 2 0\n", 278 | "7 2022-01-01 01:00:00 2 1\n", 279 | "8 2022-01-01 02:00:00 2 2\n", 280 | "9 2022-01-01 03:00:00 2 0\n", 281 | "10 2022-01-01 04:00:00 2 0\n", 282 | "11 2022-01-01 05:00:00 2 1" 283 | ] 284 | }, 285 | "execution_count": null, 286 | "metadata": {}, 287 | "output_type": "execute_result" 288 | } 289 | ], 290 | "source": [ 291 | "df = add_missing_slots(df, datetime_col='pickup_hour', entity_col='pickup_location_id', value_col='rides', freq='H')\n", 292 | "df" 293 | ] 294 | }, 295 | { 296 | "attachments": {}, 297 | "cell_type": "markdown", 298 | "metadata": {}, 299 | "source": [ 300 | "Now, let's build features and targets to predict the number of rides for the next hour for each location_id, by using the historical number of rides for the last 3 hours" 301 | ] 302 | }, 303 | { 304 | "cell_type": "code", 305 | "execution_count": null, 306 | "metadata": {}, 307 | "outputs": [ 308 | { 309 | "name": "stderr", 310 | "output_type": "stream", 311 | "text": [ 312 | "100%|██████████| 2/2 [00:00<00:00, 597.86it/s]\n" 313 | ] 314 | } 315 | ], 316 | "source": [ 317 | "features, targets = transform_ts_data_into_features_and_target(\n", 318 | " df,\n", 319 | " n_features=3,\n", 320 | " datetime_col='pickup_hour', \n", 321 | " entity_col='pickup_location_id', \n", 322 | " value_col='rides',\n", 323 | " n_targets=1,\n", 324 | " step_size=1,\n", 325 | " step_name='hour'\n", 326 | ")" 327 | ] 328 | }, 329 | { 330 | "cell_type": "code", 331 | "execution_count": null, 332 | "metadata": {}, 333 | "outputs": [ 334 | { 335 | "data": { 336 | "text/html": [ 337 | "
\n", 338 | "\n", 351 | "\n", 352 | " \n", 353 | " \n", 354 | " \n", 355 | " \n", 356 | " \n", 357 | " \n", 358 | " \n", 359 | " \n", 360 | " \n", 361 | " \n", 362 | " \n", 363 | " \n", 364 | " \n", 365 | " \n", 366 | " \n", 367 | " \n", 368 | " \n", 369 | " \n", 370 | " \n", 371 | " \n", 372 | " \n", 373 | " \n", 374 | " \n", 375 | " \n", 376 | " \n", 377 | " \n", 378 | " \n", 379 | " \n", 380 | " \n", 381 | " \n", 382 | " \n", 383 | " \n", 384 | " \n", 385 | " \n", 386 | " \n", 387 | " \n", 388 | " \n", 389 | " \n", 390 | " \n", 391 | " \n", 392 | " \n", 393 | " \n", 394 | " \n", 395 | " \n", 396 | "
rides_previous_3_hourrides_previous_2_hourrides_previous_1_hourpickup_hourpickup_location_id
02.03.00.02022-01-01 03:00:001
13.00.01.02022-01-01 04:00:001
20.01.02.02022-01-01 03:00:002
31.02.00.02022-01-01 04:00:002
\n", 397 | "
" 398 | ], 399 | "text/plain": [ 400 | " rides_previous_3_hour rides_previous_2_hour rides_previous_1_hour \\\n", 401 | "0 2.0 3.0 0.0 \n", 402 | "1 3.0 0.0 1.0 \n", 403 | "2 0.0 1.0 2.0 \n", 404 | "3 1.0 2.0 0.0 \n", 405 | "\n", 406 | " pickup_hour pickup_location_id \n", 407 | "0 2022-01-01 03:00:00 1 \n", 408 | "1 2022-01-01 04:00:00 1 \n", 409 | "2 2022-01-01 03:00:00 2 \n", 410 | "3 2022-01-01 04:00:00 2 " 411 | ] 412 | }, 413 | "execution_count": null, 414 | "metadata": {}, 415 | "output_type": "execute_result" 416 | } 417 | ], 418 | "source": [ 419 | "features" 420 | ] 421 | }, 422 | { 423 | "cell_type": "code", 424 | "execution_count": null, 425 | "metadata": {}, 426 | "outputs": [ 427 | { 428 | "data": { 429 | "text/html": [ 430 | "
\n", 431 | "\n", 444 | "\n", 445 | " \n", 446 | " \n", 447 | " \n", 448 | " \n", 449 | " \n", 450 | " \n", 451 | " \n", 452 | " \n", 453 | " \n", 454 | " \n", 455 | " \n", 456 | " \n", 457 | " \n", 458 | " \n", 459 | " \n", 460 | " \n", 461 | " \n", 462 | " \n", 463 | " \n", 464 | " \n", 465 | " \n", 466 | " \n", 467 | " \n", 468 | " \n", 469 | "
target_rides_next_hour
01.0
10.0
20.0
30.0
\n", 470 | "
" 471 | ], 472 | "text/plain": [ 473 | " target_rides_next_hour\n", 474 | "0 1.0\n", 475 | "1 0.0\n", 476 | "2 0.0\n", 477 | "3 0.0" 478 | ] 479 | }, 480 | "execution_count": null, 481 | "metadata": {}, 482 | "output_type": "execute_result" 483 | } 484 | ], 485 | "source": [ 486 | "targets" 487 | ] 488 | }, 489 | { 490 | "cell_type": "code", 491 | "execution_count": null, 492 | "metadata": {}, 493 | "outputs": [ 494 | { 495 | "data": { 496 | "text/html": [ 497 | "
\n", 498 | "\n", 511 | "\n", 512 | " \n", 513 | " \n", 514 | " \n", 515 | " \n", 516 | " \n", 517 | " \n", 518 | " \n", 519 | " \n", 520 | " \n", 521 | " \n", 522 | " \n", 523 | " \n", 524 | " \n", 525 | " \n", 526 | " \n", 527 | " \n", 528 | " \n", 529 | " \n", 530 | " \n", 531 | " \n", 532 | " \n", 533 | " \n", 534 | " \n", 535 | " \n", 536 | " \n", 537 | " \n", 538 | " \n", 539 | " \n", 540 | " \n", 541 | " \n", 542 | " \n", 543 | " \n", 544 | " \n", 545 | " \n", 546 | " \n", 547 | " \n", 548 | " \n", 549 | " \n", 550 | " \n", 551 | " \n", 552 | " \n", 553 | " \n", 554 | " \n", 555 | " \n", 556 | " \n", 557 | " \n", 558 | " \n", 559 | " \n", 560 | " \n", 561 | "
rides_previous_3_hourrides_previous_2_hourrides_previous_1_hourpickup_hourpickup_location_idtarget_rides_next_hour
02.03.00.02022-01-01 03:00:0011.0
13.00.01.02022-01-01 04:00:0010.0
20.01.02.02022-01-01 03:00:0020.0
31.02.00.02022-01-01 04:00:0020.0
\n", 562 | "
" 563 | ], 564 | "text/plain": [ 565 | " rides_previous_3_hour rides_previous_2_hour rides_previous_1_hour \\\n", 566 | "0 2.0 3.0 0.0 \n", 567 | "1 3.0 0.0 1.0 \n", 568 | "2 0.0 1.0 2.0 \n", 569 | "3 1.0 2.0 0.0 \n", 570 | "\n", 571 | " pickup_hour pickup_location_id target_rides_next_hour \n", 572 | "0 2022-01-01 03:00:00 1 1.0 \n", 573 | "1 2022-01-01 04:00:00 1 0.0 \n", 574 | "2 2022-01-01 03:00:00 2 0.0 \n", 575 | "3 2022-01-01 04:00:00 2 0.0 " 576 | ] 577 | }, 578 | "execution_count": null, 579 | "metadata": {}, 580 | "output_type": "execute_result" 581 | } 582 | ], 583 | "source": [ 584 | "Xy_df = pd.concat([features, targets], axis=1)\n", 585 | "Xy_df" 586 | ] 587 | }, 588 | { 589 | "attachments": {}, 590 | "cell_type": "markdown", 591 | "metadata": {}, 592 | "source": [ 593 | "# Another Example\n", 594 | "Montly spaced time series" 595 | ] 596 | }, 597 | { 598 | "cell_type": "code", 599 | "execution_count": null, 600 | "metadata": {}, 601 | "outputs": [ 602 | { 603 | "data": { 604 | "text/html": [ 605 | "
\n", 606 | "\n", 619 | "\n", 620 | " \n", 621 | " \n", 622 | " \n", 623 | " \n", 624 | " \n", 625 | " \n", 626 | " \n", 627 | " \n", 628 | " \n", 629 | " \n", 630 | " \n", 631 | " \n", 632 | " \n", 633 | " \n", 634 | " \n", 635 | " \n", 636 | " \n", 637 | " \n", 638 | " \n", 639 | " \n", 640 | " \n", 641 | " \n", 642 | " \n", 643 | " \n", 644 | " \n", 645 | " \n", 646 | " \n", 647 | " \n", 648 | " \n", 649 | " \n", 650 | " \n", 651 | " \n", 652 | " \n", 653 | " \n", 654 | " \n", 655 | " \n", 656 | " \n", 657 | " \n", 658 | " \n", 659 | " \n", 660 | " \n", 661 | " \n", 662 | " \n", 663 | " \n", 664 | " \n", 665 | " \n", 666 | " \n", 667 | " \n", 668 | " \n", 669 | " \n", 670 | " \n", 671 | " \n", 672 | " \n", 673 | " \n", 674 | " \n", 675 | " \n", 676 | " \n", 677 | " \n", 678 | " \n", 679 | " \n", 680 | " \n", 681 | " \n", 682 | " \n", 683 | " \n", 684 | " \n", 685 | " \n", 686 | " \n", 687 | " \n", 688 | " \n", 689 | " \n", 690 | " \n", 691 | " \n", 692 | " \n", 693 | " \n", 694 | " \n", 695 | " \n", 696 | " \n", 697 | " \n", 698 | " \n", 699 | " \n", 700 | " \n", 701 | " \n", 702 | " \n", 703 | " \n", 704 | " \n", 705 | " \n", 706 | " \n", 707 | " \n", 708 | " \n", 709 | " \n", 710 | " \n", 711 | " \n", 712 | " \n", 713 | " \n", 714 | " \n", 715 | " \n", 716 | " \n", 717 | " \n", 718 | " \n", 719 | " \n", 720 | " \n", 721 | " \n", 722 | " \n", 723 | " \n", 724 | " \n", 725 | " \n", 726 | " \n", 727 | " \n", 728 | " \n", 729 | " \n", 730 | " \n", 731 | " \n", 732 | " \n", 733 | " \n", 734 | " \n", 735 | " \n", 736 | " \n", 737 | " \n", 738 | " \n", 739 | " \n", 740 | " \n", 741 | " \n", 742 | " \n", 743 | " \n", 744 | " \n", 745 | " \n", 746 | " \n", 747 | " \n", 748 | " \n", 749 | " \n", 750 | " \n", 751 | " \n", 752 | " \n", 753 | " \n", 754 | " \n", 755 | " \n", 756 | " \n", 757 | " \n", 758 | " \n", 759 | " \n", 760 | " \n", 761 | " \n", 762 | " \n", 763 | " \n", 764 | " \n", 765 | " \n", 766 | " \n", 767 | " \n", 768 | " \n", 769 | " \n", 770 | " \n", 771 | " \n", 772 | " \n", 773 | " \n", 774 | " \n", 775 | " \n", 776 | " \n", 777 | " \n", 778 | " \n", 779 | " \n", 780 | " \n", 781 | " \n", 782 | " \n", 783 | " \n", 784 | " \n", 785 | " \n", 786 | " \n", 787 | " \n", 788 | " \n", 789 | " \n", 790 | " \n", 791 | " \n", 792 | " \n", 793 | " \n", 794 | " \n", 795 | " \n", 796 | " \n", 797 | " \n", 798 | " \n", 799 | " \n", 800 | " \n", 801 | " \n", 802 | " \n", 803 | " \n", 804 | " \n", 805 | " \n", 806 | " \n", 807 | " \n", 808 | " \n", 809 | " \n", 810 | " \n", 811 | " \n", 812 | " \n", 813 | " \n", 814 | " \n", 815 | " \n", 816 | " \n", 817 | " \n", 818 | " \n", 819 | " \n", 820 | " \n", 821 | " \n", 822 | " \n", 823 | " \n", 824 | " \n", 825 | " \n", 826 | " \n", 827 | " \n", 828 | " \n", 829 | " \n", 830 | " \n", 831 | " \n", 832 | " \n", 833 | " \n", 834 | " \n", 835 | " \n", 836 | " \n", 837 | " \n", 838 | " \n", 839 | " \n", 840 | " \n", 841 | " \n", 842 | " \n", 843 | " \n", 844 | " \n", 845 | " \n", 846 | "
datecitysales
02020-01-01FOR4944
12020-02-01FOR3435
22020-03-01FOR4543
32020-04-01FOR3879
42020-05-01FOR2601
52020-06-01FOR2922
62020-07-01FOR4542
72020-08-01FOR1338
82020-09-01FOR2938
92020-10-01FOR2695
102020-11-01FOR4065
112020-12-01FOR3864
122021-01-01SP2652
132021-02-01SP2137
142021-03-01SP2663
152021-04-01SP1168
162021-05-01SP4523
172021-06-01SP4135
182021-07-01SP3566
192021-08-01SP2121
202021-09-01SP1070
212021-10-01SP1624
222021-11-01SP3034
232021-12-01SP4063
242022-01-01RJ2297
252022-02-01RJ3430
262022-03-01RJ2903
272022-04-01RJ4197
282022-05-01RJ4141
292022-06-01RJ2899
302022-07-01RJ4529
312022-08-01RJ3612
322022-09-01RJ1856
332022-10-01RJ4804
342022-11-01RJ1764
352022-12-01RJ4425
\n", 847 | "
" 848 | ], 849 | "text/plain": [ 850 | " date city sales\n", 851 | "0 2020-01-01 FOR 4944\n", 852 | "1 2020-02-01 FOR 3435\n", 853 | "2 2020-03-01 FOR 4543\n", 854 | "3 2020-04-01 FOR 3879\n", 855 | "4 2020-05-01 FOR 2601\n", 856 | "5 2020-06-01 FOR 2922\n", 857 | "6 2020-07-01 FOR 4542\n", 858 | "7 2020-08-01 FOR 1338\n", 859 | "8 2020-09-01 FOR 2938\n", 860 | "9 2020-10-01 FOR 2695\n", 861 | "10 2020-11-01 FOR 4065\n", 862 | "11 2020-12-01 FOR 3864\n", 863 | "12 2021-01-01 SP 2652\n", 864 | "13 2021-02-01 SP 2137\n", 865 | "14 2021-03-01 SP 2663\n", 866 | "15 2021-04-01 SP 1168\n", 867 | "16 2021-05-01 SP 4523\n", 868 | "17 2021-06-01 SP 4135\n", 869 | "18 2021-07-01 SP 3566\n", 870 | "19 2021-08-01 SP 2121\n", 871 | "20 2021-09-01 SP 1070\n", 872 | "21 2021-10-01 SP 1624\n", 873 | "22 2021-11-01 SP 3034\n", 874 | "23 2021-12-01 SP 4063\n", 875 | "24 2022-01-01 RJ 2297\n", 876 | "25 2022-02-01 RJ 3430\n", 877 | "26 2022-03-01 RJ 2903\n", 878 | "27 2022-04-01 RJ 4197\n", 879 | "28 2022-05-01 RJ 4141\n", 880 | "29 2022-06-01 RJ 2899\n", 881 | "30 2022-07-01 RJ 4529\n", 882 | "31 2022-08-01 RJ 3612\n", 883 | "32 2022-09-01 RJ 1856\n", 884 | "33 2022-10-01 RJ 4804\n", 885 | "34 2022-11-01 RJ 1764\n", 886 | "35 2022-12-01 RJ 4425" 887 | ] 888 | }, 889 | "execution_count": null, 890 | "metadata": {}, 891 | "output_type": "execute_result" 892 | } 893 | ], 894 | "source": [ 895 | "import pandas as pd\n", 896 | "import numpy as np\n", 897 | "\n", 898 | "# Generate timestamp index with monthly frequency\n", 899 | "date_rng = pd.date_range(start='1/1/2020', end='12/1/2022', freq='MS')\n", 900 | "\n", 901 | "# Create list of city codes\n", 902 | "cities = ['FOR', 'SP', 'RJ']\n", 903 | "\n", 904 | "# Create dataframe with random sales data for each city on each month\n", 905 | "df = pd.DataFrame({\n", 906 | " 'date': date_rng,\n", 907 | " 'city': np.repeat(cities, len(date_rng)//len(cities)),\n", 908 | " 'sales': np.random.randint(1000, 5000, size=len(date_rng))\n", 909 | "})\n", 910 | "df" 911 | ] 912 | }, 913 | { 914 | "attachments": {}, 915 | "cell_type": "markdown", 916 | "metadata": {}, 917 | "source": [ 918 | "FOR city only have data for 2020 year, RJ only for 2022 and SP only for 2021. Let's also simulate more missing slots between the years." 919 | ] 920 | }, 921 | { 922 | "cell_type": "code", 923 | "execution_count": null, 924 | "metadata": {}, 925 | "outputs": [ 926 | { 927 | "data": { 928 | "text/html": [ 929 | "
\n", 930 | "\n", 943 | "\n", 944 | " \n", 945 | " \n", 946 | " \n", 947 | " \n", 948 | " \n", 949 | " \n", 950 | " \n", 951 | " \n", 952 | " \n", 953 | " \n", 954 | " \n", 955 | " \n", 956 | " \n", 957 | " \n", 958 | " \n", 959 | " \n", 960 | " \n", 961 | " \n", 962 | " \n", 963 | " \n", 964 | " \n", 965 | " \n", 966 | " \n", 967 | " \n", 968 | " \n", 969 | " \n", 970 | " \n", 971 | " \n", 972 | " \n", 973 | " \n", 974 | " \n", 975 | " \n", 976 | " \n", 977 | " \n", 978 | " \n", 979 | " \n", 980 | " \n", 981 | " \n", 982 | " \n", 983 | " \n", 984 | " \n", 985 | " \n", 986 | " \n", 987 | " \n", 988 | " \n", 989 | " \n", 990 | " \n", 991 | " \n", 992 | " \n", 993 | " \n", 994 | " \n", 995 | " \n", 996 | " \n", 997 | " \n", 998 | " \n", 999 | " \n", 1000 | " \n", 1001 | " \n", 1002 | " \n", 1003 | " \n", 1004 | " \n", 1005 | " \n", 1006 | " \n", 1007 | " \n", 1008 | " \n", 1009 | " \n", 1010 | " \n", 1011 | " \n", 1012 | " \n", 1013 | " \n", 1014 | " \n", 1015 | " \n", 1016 | " \n", 1017 | " \n", 1018 | " \n", 1019 | " \n", 1020 | " \n", 1021 | " \n", 1022 | " \n", 1023 | " \n", 1024 | " \n", 1025 | " \n", 1026 | " \n", 1027 | " \n", 1028 | " \n", 1029 | " \n", 1030 | " \n", 1031 | " \n", 1032 | " \n", 1033 | " \n", 1034 | " \n", 1035 | " \n", 1036 | " \n", 1037 | " \n", 1038 | " \n", 1039 | " \n", 1040 | " \n", 1041 | " \n", 1042 | " \n", 1043 | " \n", 1044 | " \n", 1045 | " \n", 1046 | " \n", 1047 | " \n", 1048 | " \n", 1049 | " \n", 1050 | " \n", 1051 | " \n", 1052 | " \n", 1053 | " \n", 1054 | " \n", 1055 | " \n", 1056 | " \n", 1057 | " \n", 1058 | " \n", 1059 | " \n", 1060 | " \n", 1061 | " \n", 1062 | " \n", 1063 | " \n", 1064 | " \n", 1065 | " \n", 1066 | " \n", 1067 | " \n", 1068 | " \n", 1069 | " \n", 1070 | " \n", 1071 | " \n", 1072 | " \n", 1073 | " \n", 1074 | " \n", 1075 | " \n", 1076 | " \n", 1077 | " \n", 1078 | " \n", 1079 | " \n", 1080 | " \n", 1081 | " \n", 1082 | " \n", 1083 | " \n", 1084 | " \n", 1085 | " \n", 1086 | " \n", 1087 | " \n", 1088 | " \n", 1089 | " \n", 1090 | " \n", 1091 | " \n", 1092 | " \n", 1093 | " \n", 1094 | " \n", 1095 | " \n", 1096 | " \n", 1097 | " \n", 1098 | " \n", 1099 | " \n", 1100 | " \n", 1101 | " \n", 1102 | " \n", 1103 | " \n", 1104 | " \n", 1105 | " \n", 1106 | " \n", 1107 | " \n", 1108 | " \n", 1109 | " \n", 1110 | " \n", 1111 | " \n", 1112 | " \n", 1113 | " \n", 1114 | " \n", 1115 | " \n", 1116 | " \n", 1117 | " \n", 1118 | " \n", 1119 | " \n", 1120 | " \n", 1121 | " \n", 1122 | " \n", 1123 | " \n", 1124 | " \n", 1125 | " \n", 1126 | " \n", 1127 | " \n", 1128 | "
datecitysales
02020-01-01FOR4944
12020-02-01FOR3435
22020-03-01FOR4543
32020-04-01FOR3879
42020-05-01FOR2601
52020-06-01FOR2922
62020-07-01FOR4542
72020-08-01FOR1338
82020-09-01FOR2938
92020-11-01FOR4065
102020-12-01FOR3864
112021-01-01SP2652
122021-02-01SP2137
132021-03-01SP2663
142021-07-01SP3566
152021-08-01SP2121
162021-10-01SP1624
172021-11-01SP3034
182021-12-01SP4063
192022-01-01RJ2297
202022-02-01RJ3430
212022-03-01RJ2903
222022-04-01RJ4197
232022-05-01RJ4141
242022-06-01RJ2899
252022-09-01RJ1856
262022-10-01RJ4804
272022-11-01RJ1764
282022-12-01RJ4425
\n", 1129 | "
" 1130 | ], 1131 | "text/plain": [ 1132 | " date city sales\n", 1133 | "0 2020-01-01 FOR 4944\n", 1134 | "1 2020-02-01 FOR 3435\n", 1135 | "2 2020-03-01 FOR 4543\n", 1136 | "3 2020-04-01 FOR 3879\n", 1137 | "4 2020-05-01 FOR 2601\n", 1138 | "5 2020-06-01 FOR 2922\n", 1139 | "6 2020-07-01 FOR 4542\n", 1140 | "7 2020-08-01 FOR 1338\n", 1141 | "8 2020-09-01 FOR 2938\n", 1142 | "9 2020-11-01 FOR 4065\n", 1143 | "10 2020-12-01 FOR 3864\n", 1144 | "11 2021-01-01 SP 2652\n", 1145 | "12 2021-02-01 SP 2137\n", 1146 | "13 2021-03-01 SP 2663\n", 1147 | "14 2021-07-01 SP 3566\n", 1148 | "15 2021-08-01 SP 2121\n", 1149 | "16 2021-10-01 SP 1624\n", 1150 | "17 2021-11-01 SP 3034\n", 1151 | "18 2021-12-01 SP 4063\n", 1152 | "19 2022-01-01 RJ 2297\n", 1153 | "20 2022-02-01 RJ 3430\n", 1154 | "21 2022-03-01 RJ 2903\n", 1155 | "22 2022-04-01 RJ 4197\n", 1156 | "23 2022-05-01 RJ 4141\n", 1157 | "24 2022-06-01 RJ 2899\n", 1158 | "25 2022-09-01 RJ 1856\n", 1159 | "26 2022-10-01 RJ 4804\n", 1160 | "27 2022-11-01 RJ 1764\n", 1161 | "28 2022-12-01 RJ 4425" 1162 | ] 1163 | }, 1164 | "execution_count": null, 1165 | "metadata": {}, 1166 | "output_type": "execute_result" 1167 | } 1168 | ], 1169 | "source": [ 1170 | "# Generate random indices to drop\n", 1171 | "drop_indices = np.random.choice(df.index, size=int(len(df)*0.2), replace=False)\n", 1172 | "\n", 1173 | "# Drop selected rows from dataframe\n", 1174 | "df = df.drop(drop_indices)\n", 1175 | "df.reset_index(drop=True, inplace=True)\n", 1176 | "df" 1177 | ] 1178 | }, 1179 | { 1180 | "attachments": {}, 1181 | "cell_type": "markdown", 1182 | "metadata": {}, 1183 | "source": [ 1184 | "Now lets fill the missing slots with zero values. The function will complete the missing slots with zeros:" 1185 | ] 1186 | }, 1187 | { 1188 | "cell_type": "code", 1189 | "execution_count": null, 1190 | "metadata": {}, 1191 | "outputs": [ 1192 | { 1193 | "name": "stderr", 1194 | "output_type": "stream", 1195 | "text": [ 1196 | "100%|██████████| 3/3 [00:00<00:00, 843.70it/s]\n" 1197 | ] 1198 | }, 1199 | { 1200 | "data": { 1201 | "text/html": [ 1202 | "
\n", 1203 | "\n", 1216 | "\n", 1217 | " \n", 1218 | " \n", 1219 | " \n", 1220 | " \n", 1221 | " \n", 1222 | " \n", 1223 | " \n", 1224 | " \n", 1225 | " \n", 1226 | " \n", 1227 | " \n", 1228 | " \n", 1229 | " \n", 1230 | " \n", 1231 | " \n", 1232 | " \n", 1233 | " \n", 1234 | " \n", 1235 | " \n", 1236 | " \n", 1237 | " \n", 1238 | " \n", 1239 | " \n", 1240 | " \n", 1241 | " \n", 1242 | " \n", 1243 | " \n", 1244 | " \n", 1245 | " \n", 1246 | " \n", 1247 | " \n", 1248 | " \n", 1249 | " \n", 1250 | " \n", 1251 | " \n", 1252 | " \n", 1253 | " \n", 1254 | " \n", 1255 | " \n", 1256 | " \n", 1257 | " \n", 1258 | " \n", 1259 | " \n", 1260 | " \n", 1261 | " \n", 1262 | " \n", 1263 | " \n", 1264 | " \n", 1265 | " \n", 1266 | " \n", 1267 | " \n", 1268 | " \n", 1269 | " \n", 1270 | " \n", 1271 | " \n", 1272 | " \n", 1273 | " \n", 1274 | " \n", 1275 | " \n", 1276 | " \n", 1277 | " \n", 1278 | " \n", 1279 | " \n", 1280 | " \n", 1281 | " \n", 1282 | " \n", 1283 | " \n", 1284 | " \n", 1285 | " \n", 1286 | " \n", 1287 | " \n", 1288 | " \n", 1289 | " \n", 1290 | " \n", 1291 | " \n", 1292 | " \n", 1293 | "
datecitysales
02020-01-01FOR4944
12020-02-01FOR3435
22020-03-01FOR4543
32020-04-01FOR3879
42020-05-01FOR2601
............
1032022-08-01RJ0
1042022-09-01RJ1856
1052022-10-01RJ4804
1062022-11-01RJ1764
1072022-12-01RJ4425
\n", 1294 | "

108 rows × 3 columns

\n", 1295 | "
" 1296 | ], 1297 | "text/plain": [ 1298 | " date city sales\n", 1299 | "0 2020-01-01 FOR 4944\n", 1300 | "1 2020-02-01 FOR 3435\n", 1301 | "2 2020-03-01 FOR 4543\n", 1302 | "3 2020-04-01 FOR 3879\n", 1303 | "4 2020-05-01 FOR 2601\n", 1304 | ".. ... ... ...\n", 1305 | "103 2022-08-01 RJ 0\n", 1306 | "104 2022-09-01 RJ 1856\n", 1307 | "105 2022-10-01 RJ 4804\n", 1308 | "106 2022-11-01 RJ 1764\n", 1309 | "107 2022-12-01 RJ 4425\n", 1310 | "\n", 1311 | "[108 rows x 3 columns]" 1312 | ] 1313 | }, 1314 | "execution_count": null, 1315 | "metadata": {}, 1316 | "output_type": "execute_result" 1317 | } 1318 | ], 1319 | "source": [ 1320 | "df_full = add_missing_slots(df, datetime_col='date', entity_col='city', value_col='sales', freq='MS')\n", 1321 | "df_full" 1322 | ] 1323 | }, 1324 | { 1325 | "attachments": {}, 1326 | "cell_type": "markdown", 1327 | "metadata": {}, 1328 | "source": [ 1329 | "Let's build a dataset for training a machine learning model to predict the sales for the next 3 months, for each city, based on historical data of sales for the previous 6 months." 1330 | ] 1331 | }, 1332 | { 1333 | "cell_type": "code", 1334 | "execution_count": null, 1335 | "metadata": {}, 1336 | "outputs": [ 1337 | { 1338 | "name": "stderr", 1339 | "output_type": "stream", 1340 | "text": [ 1341 | "100%|██████████| 3/3 [00:00<00:00, 205.58it/s]\n" 1342 | ] 1343 | } 1344 | ], 1345 | "source": [ 1346 | "features, targets = transform_ts_data_into_features_and_target(\n", 1347 | " df_full,\n", 1348 | " n_features=3,\n", 1349 | " datetime_col='date',\n", 1350 | " entity_col='city',\n", 1351 | " value_col='sales',\n", 1352 | " n_targets=1,\n", 1353 | " step_size=1,\n", 1354 | " step_name='month'\n", 1355 | ")" 1356 | ] 1357 | }, 1358 | { 1359 | "cell_type": "code", 1360 | "execution_count": null, 1361 | "metadata": {}, 1362 | "outputs": [ 1363 | { 1364 | "data": { 1365 | "text/html": [ 1366 | "
\n", 1367 | "\n", 1380 | "\n", 1381 | " \n", 1382 | " \n", 1383 | " \n", 1384 | " \n", 1385 | " \n", 1386 | " \n", 1387 | " \n", 1388 | " \n", 1389 | " \n", 1390 | " \n", 1391 | " \n", 1392 | " \n", 1393 | " \n", 1394 | " \n", 1395 | " \n", 1396 | " \n", 1397 | " \n", 1398 | " \n", 1399 | " \n", 1400 | " \n", 1401 | " \n", 1402 | " \n", 1403 | " \n", 1404 | " \n", 1405 | " \n", 1406 | " \n", 1407 | " \n", 1408 | " \n", 1409 | " \n", 1410 | " \n", 1411 | " \n", 1412 | " \n", 1413 | " \n", 1414 | " \n", 1415 | " \n", 1416 | " \n", 1417 | " \n", 1418 | " \n", 1419 | " \n", 1420 | " \n", 1421 | " \n", 1422 | " \n", 1423 | " \n", 1424 | " \n", 1425 | " \n", 1426 | " \n", 1427 | " \n", 1428 | " \n", 1429 | " \n", 1430 | " \n", 1431 | " \n", 1432 | " \n", 1433 | " \n", 1434 | " \n", 1435 | " \n", 1436 | " \n", 1437 | " \n", 1438 | " \n", 1439 | " \n", 1440 | " \n", 1441 | " \n", 1442 | " \n", 1443 | " \n", 1444 | " \n", 1445 | " \n", 1446 | " \n", 1447 | " \n", 1448 | " \n", 1449 | " \n", 1450 | " \n", 1451 | " \n", 1452 | " \n", 1453 | " \n", 1454 | " \n", 1455 | " \n", 1456 | " \n", 1457 | " \n", 1458 | " \n", 1459 | " \n", 1460 | " \n", 1461 | " \n", 1462 | " \n", 1463 | " \n", 1464 | " \n", 1465 | " \n", 1466 | " \n", 1467 | " \n", 1468 | " \n", 1469 | " \n", 1470 | " \n", 1471 | " \n", 1472 | " \n", 1473 | " \n", 1474 | " \n", 1475 | " \n", 1476 | " \n", 1477 | " \n", 1478 | " \n", 1479 | " \n", 1480 | " \n", 1481 | " \n", 1482 | " \n", 1483 | " \n", 1484 | " \n", 1485 | " \n", 1486 | " \n", 1487 | " \n", 1488 | " \n", 1489 | " \n", 1490 | " \n", 1491 | " \n", 1492 | " \n", 1493 | "
sales_previous_3_monthsales_previous_2_monthsales_previous_1_monthdatecitytarget_sales_next_month
04944.03435.04543.02020-04-01FOR3879.0
13435.04543.03879.02020-05-01FOR2601.0
24543.03879.02601.02020-06-01FOR2922.0
33879.02601.02922.02020-07-01FOR4542.0
42601.02922.04542.02020-08-01FOR1338.0
.....................
914197.04141.02899.02022-07-01RJ0.0
924141.02899.00.02022-08-01RJ0.0
932899.00.00.02022-09-01RJ1856.0
940.00.01856.02022-10-01RJ4804.0
950.01856.04804.02022-11-01RJ1764.0
\n", 1494 | "

96 rows × 6 columns

\n", 1495 | "
" 1496 | ], 1497 | "text/plain": [ 1498 | " sales_previous_3_month sales_previous_2_month sales_previous_1_month \\\n", 1499 | "0 4944.0 3435.0 4543.0 \n", 1500 | "1 3435.0 4543.0 3879.0 \n", 1501 | "2 4543.0 3879.0 2601.0 \n", 1502 | "3 3879.0 2601.0 2922.0 \n", 1503 | "4 2601.0 2922.0 4542.0 \n", 1504 | ".. ... ... ... \n", 1505 | "91 4197.0 4141.0 2899.0 \n", 1506 | "92 4141.0 2899.0 0.0 \n", 1507 | "93 2899.0 0.0 0.0 \n", 1508 | "94 0.0 0.0 1856.0 \n", 1509 | "95 0.0 1856.0 4804.0 \n", 1510 | "\n", 1511 | " date city target_sales_next_month \n", 1512 | "0 2020-04-01 FOR 3879.0 \n", 1513 | "1 2020-05-01 FOR 2601.0 \n", 1514 | "2 2020-06-01 FOR 2922.0 \n", 1515 | "3 2020-07-01 FOR 4542.0 \n", 1516 | "4 2020-08-01 FOR 1338.0 \n", 1517 | ".. ... ... ... \n", 1518 | "91 2022-07-01 RJ 0.0 \n", 1519 | "92 2022-08-01 RJ 0.0 \n", 1520 | "93 2022-09-01 RJ 1856.0 \n", 1521 | "94 2022-10-01 RJ 4804.0 \n", 1522 | "95 2022-11-01 RJ 1764.0 \n", 1523 | "\n", 1524 | "[96 rows x 6 columns]" 1525 | ] 1526 | }, 1527 | "execution_count": null, 1528 | "metadata": {}, 1529 | "output_type": "execute_result" 1530 | } 1531 | ], 1532 | "source": [ 1533 | "pd.concat([features, targets], axis=1)" 1534 | ] 1535 | }, 1536 | { 1537 | "attachments": {}, 1538 | "cell_type": "markdown", 1539 | "metadata": {}, 1540 | "source": [ 1541 | "# Embedding on Sklearn Pipelines" 1542 | ] 1543 | }, 1544 | { 1545 | "cell_type": "code", 1546 | "execution_count": null, 1547 | "metadata": {}, 1548 | "outputs": [], 1549 | "source": [ 1550 | "from sklearn.pipeline import make_pipeline\n", 1551 | "from sklearn.preprocessing import FunctionTransformer" 1552 | ] 1553 | }, 1554 | { 1555 | "cell_type": "code", 1556 | "execution_count": null, 1557 | "metadata": {}, 1558 | "outputs": [], 1559 | "source": [ 1560 | "add_missing_slots_transformer = FunctionTransformer(\n", 1561 | " add_missing_slots, \n", 1562 | " kw_args={\n", 1563 | " 'datetime_col': 'date', \n", 1564 | " 'entity_col': 'city', \n", 1565 | " 'value_col': 'sales', \n", 1566 | " 'freq': 'MS'\n", 1567 | " }\n", 1568 | ")\n", 1569 | "\n", 1570 | "transform_ts_data_into_features_and_target_transformer = FunctionTransformer(\n", 1571 | " transform_ts_data_into_features_and_target, \n", 1572 | " kw_args={\n", 1573 | " 'n_features': 3, \n", 1574 | " 'datetime_col': 'date', \n", 1575 | " 'entity_col': 'city', \n", 1576 | " 'value_col': 'sales', \n", 1577 | " 'n_targets': 1, \n", 1578 | " 'step_size': 1, \n", 1579 | " 'step_name': 'month',\n", 1580 | " 'concat_Xy': True\n", 1581 | " }\n", 1582 | ")" 1583 | ] 1584 | }, 1585 | { 1586 | "cell_type": "code", 1587 | "execution_count": null, 1588 | "metadata": {}, 1589 | "outputs": [ 1590 | { 1591 | "data": { 1592 | "text/html": [ 1593 | "
Pipeline(steps=[('functiontransformer-1',\n",
1594 |        "                 FunctionTransformer(func=<function add_missing_slots at 0x11f8f49d0>,\n",
1595 |        "                                     kw_args={'datetime_col': 'date',\n",
1596 |        "                                              'entity_col': 'city',\n",
1597 |        "                                              'freq': 'MS',\n",
1598 |        "                                              'value_col': 'sales'})),\n",
1599 |        "                ('functiontransformer-2',\n",
1600 |        "                 FunctionTransformer(func=<function transform_ts_data_into_features_and_target at 0x11f925ca0>,\n",
1601 |        "                                     kw_args={'concat_Xy': True,\n",
1602 |        "                                              'datetime_col': 'date',\n",
1603 |        "                                              'entity_col': 'city',\n",
1604 |        "                                              'n_features': 3, 'n_targets': 1,\n",
1605 |        "                                              'step_name': 'month',\n",
1606 |        "                                              'step_size': 1,\n",
1607 |        "                                              'value_col': 'sales'}))])
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" 1628 | ], 1629 | "text/plain": [ 1630 | "Pipeline(steps=[('functiontransformer-1',\n", 1631 | " FunctionTransformer(func=,\n", 1632 | " kw_args={'datetime_col': 'date',\n", 1633 | " 'entity_col': 'city',\n", 1634 | " 'freq': 'MS',\n", 1635 | " 'value_col': 'sales'})),\n", 1636 | " ('functiontransformer-2',\n", 1637 | " FunctionTransformer(func=,\n", 1638 | " kw_args={'concat_Xy': True,\n", 1639 | " 'datetime_col': 'date',\n", 1640 | " 'entity_col': 'city',\n", 1641 | " 'n_features': 3, 'n_targets': 1,\n", 1642 | " 'step_name': 'month',\n", 1643 | " 'step_size': 1,\n", 1644 | " 'value_col': 'sales'}))])" 1645 | ] 1646 | }, 1647 | "execution_count": null, 1648 | "metadata": {}, 1649 | "output_type": "execute_result" 1650 | } 1651 | ], 1652 | "source": [ 1653 | "ts_data_to_features_and_target_pipeline = make_pipeline(\n", 1654 | " add_missing_slots_transformer,\n", 1655 | " transform_ts_data_into_features_and_target_transformer\n", 1656 | ")\n", 1657 | "ts_data_to_features_and_target_pipeline" 1658 | ] 1659 | }, 1660 | { 1661 | "cell_type": "code", 1662 | "execution_count": null, 1663 | "metadata": {}, 1664 | "outputs": [ 1665 | { 1666 | "name": "stderr", 1667 | "output_type": "stream", 1668 | "text": [ 1669 | "100%|██████████| 3/3 [00:00<00:00, 715.47it/s]\n", 1670 | "100%|██████████| 3/3 [00:00<00:00, 184.12it/s]\n" 1671 | ] 1672 | }, 1673 | { 1674 | "data": { 1675 | "text/html": [ 1676 | "
\n", 1677 | "\n", 1690 | "\n", 1691 | " \n", 1692 | " \n", 1693 | " \n", 1694 | " \n", 1695 | " \n", 1696 | " \n", 1697 | " \n", 1698 | " \n", 1699 | " \n", 1700 | " \n", 1701 | " \n", 1702 | " \n", 1703 | " \n", 1704 | " \n", 1705 | " \n", 1706 | " \n", 1707 | " \n", 1708 | " \n", 1709 | " \n", 1710 | " \n", 1711 | " \n", 1712 | " \n", 1713 | " \n", 1714 | " \n", 1715 | " \n", 1716 | " \n", 1717 | " \n", 1718 | " \n", 1719 | " \n", 1720 | " \n", 1721 | " \n", 1722 | " \n", 1723 | " \n", 1724 | " \n", 1725 | " \n", 1726 | " \n", 1727 | " \n", 1728 | " \n", 1729 | " \n", 1730 | " \n", 1731 | " \n", 1732 | " \n", 1733 | " \n", 1734 | " \n", 1735 | " \n", 1736 | " \n", 1737 | " \n", 1738 | " \n", 1739 | " \n", 1740 | " \n", 1741 | " \n", 1742 | " \n", 1743 | " \n", 1744 | " \n", 1745 | " \n", 1746 | " \n", 1747 | " \n", 1748 | " \n", 1749 | " \n", 1750 | " \n", 1751 | " \n", 1752 | " \n", 1753 | " \n", 1754 | " \n", 1755 | " \n", 1756 | " \n", 1757 | " \n", 1758 | " \n", 1759 | " \n", 1760 | " \n", 1761 | " \n", 1762 | " \n", 1763 | " \n", 1764 | " \n", 1765 | " \n", 1766 | " \n", 1767 | " \n", 1768 | " \n", 1769 | " \n", 1770 | " \n", 1771 | " \n", 1772 | " \n", 1773 | " \n", 1774 | " \n", 1775 | " \n", 1776 | " \n", 1777 | " \n", 1778 | " \n", 1779 | " \n", 1780 | " \n", 1781 | " \n", 1782 | " \n", 1783 | " \n", 1784 | " \n", 1785 | " \n", 1786 | " \n", 1787 | " \n", 1788 | " \n", 1789 | " \n", 1790 | " \n", 1791 | " \n", 1792 | " \n", 1793 | " \n", 1794 | " \n", 1795 | " \n", 1796 | " \n", 1797 | " \n", 1798 | " \n", 1799 | " \n", 1800 | " \n", 1801 | " \n", 1802 | " \n", 1803 | "
sales_previous_3_monthsales_previous_2_monthsales_previous_1_monthdatecitytarget_sales_next_month
04944.03435.04543.02020-04-01FOR3879.0
13435.04543.03879.02020-05-01FOR2601.0
24543.03879.02601.02020-06-01FOR2922.0
33879.02601.02922.02020-07-01FOR4542.0
42601.02922.04542.02020-08-01FOR1338.0
.....................
914197.04141.02899.02022-07-01RJ0.0
924141.02899.00.02022-08-01RJ0.0
932899.00.00.02022-09-01RJ1856.0
940.00.01856.02022-10-01RJ4804.0
950.01856.04804.02022-11-01RJ1764.0
\n", 1804 | "

96 rows × 6 columns

\n", 1805 | "
" 1806 | ], 1807 | "text/plain": [ 1808 | " sales_previous_3_month sales_previous_2_month sales_previous_1_month \\\n", 1809 | "0 4944.0 3435.0 4543.0 \n", 1810 | "1 3435.0 4543.0 3879.0 \n", 1811 | "2 4543.0 3879.0 2601.0 \n", 1812 | "3 3879.0 2601.0 2922.0 \n", 1813 | "4 2601.0 2922.0 4542.0 \n", 1814 | ".. ... ... ... \n", 1815 | "91 4197.0 4141.0 2899.0 \n", 1816 | "92 4141.0 2899.0 0.0 \n", 1817 | "93 2899.0 0.0 0.0 \n", 1818 | "94 0.0 0.0 1856.0 \n", 1819 | "95 0.0 1856.0 4804.0 \n", 1820 | "\n", 1821 | " date city target_sales_next_month \n", 1822 | "0 2020-04-01 FOR 3879.0 \n", 1823 | "1 2020-05-01 FOR 2601.0 \n", 1824 | "2 2020-06-01 FOR 2922.0 \n", 1825 | "3 2020-07-01 FOR 4542.0 \n", 1826 | "4 2020-08-01 FOR 1338.0 \n", 1827 | ".. ... ... ... \n", 1828 | "91 2022-07-01 RJ 0.0 \n", 1829 | "92 2022-08-01 RJ 0.0 \n", 1830 | "93 2022-09-01 RJ 1856.0 \n", 1831 | "94 2022-10-01 RJ 4804.0 \n", 1832 | "95 2022-11-01 RJ 1764.0 \n", 1833 | "\n", 1834 | "[96 rows x 6 columns]" 1835 | ] 1836 | }, 1837 | "execution_count": null, 1838 | "metadata": {}, 1839 | "output_type": "execute_result" 1840 | } 1841 | ], 1842 | "source": [ 1843 | "Xy_df = ts_data_to_features_and_target_pipeline.fit_transform(df)\n", 1844 | "Xy_df" 1845 | ] 1846 | }, 1847 | { 1848 | "cell_type": "code", 1849 | "execution_count": null, 1850 | "metadata": {}, 1851 | "outputs": [], 1852 | "source": [] 1853 | } 1854 | ], 1855 | "metadata": { 1856 | "kernelspec": { 1857 | "display_name": "python3", 1858 | "language": "python", 1859 | "name": "python3" 1860 | } 1861 | }, 1862 | "nbformat": 4, 1863 | "nbformat_minor": 4 1864 | } 1865 | -------------------------------------------------------------------------------- /nbs/nbdev.yml: -------------------------------------------------------------------------------- 1 | project: 2 | output-dir: _docs 3 | 4 | website: 5 | title: "ts2ml" 6 | site-url: "https://joaopcnogueira.github.io/ts2ml" 7 | description: "Tools to Transform a Time Series into Features and Target a.k.a Supervised Learning" 8 | repo-branch: main 9 | repo-url: "https://github.com/joaopcnogueira/ts2ml" 10 | -------------------------------------------------------------------------------- /nbs/sidebar.yml: -------------------------------------------------------------------------------- 1 | website: 2 | sidebar: 3 | contents: 4 | - index.ipynb 5 | - 00_core.ipynb 6 | -------------------------------------------------------------------------------- /nbs/styles.css: -------------------------------------------------------------------------------- 1 | .cell { 2 | margin-bottom: 1rem; 3 | } 4 | 5 | .cell > .sourceCode { 6 | margin-bottom: 0; 7 | } 8 | 9 | .cell-output > pre { 10 | margin-bottom: 0; 11 | } 12 | 13 | .cell-output > pre, .cell-output > .sourceCode > pre, .cell-output-stdout > pre { 14 | margin-left: 0.8rem; 15 | margin-top: 0; 16 | background: none; 17 | border-left: 2px solid lightsalmon; 18 | border-top-left-radius: 0; 19 | border-top-right-radius: 0; 20 | } 21 | 22 | .cell-output > .sourceCode { 23 | border: none; 24 | } 25 | 26 | .cell-output > .sourceCode { 27 | background: none; 28 | margin-top: 0; 29 | } 30 | 31 | div.description { 32 | padding-left: 2px; 33 | padding-top: 5px; 34 | font-style: italic; 35 | font-size: 135%; 36 | opacity: 70%; 37 | } 38 | -------------------------------------------------------------------------------- /settings.ini: -------------------------------------------------------------------------------- 1 | [DEFAULT] 2 | repo = ts2ml 3 | lib_name = ts2ml 4 | version = 1.0.1 5 | min_python = 3.7 6 | license = apache2 7 | black_formatting = False 8 | doc_path = _docs 9 | lib_path = ts2ml 10 | nbs_path = nbs 11 | recursive = True 12 | tst_flags = notest 13 | put_version_in_init = True 14 | branch = main 15 | custom_sidebar = False 16 | doc_host = https://joaopcnogueira.github.io 17 | doc_baseurl = /ts2ml 18 | git_url = https://github.com/joaopcnogueira/ts2ml 19 | title = ts2ml 20 | audience = Developers 21 | author = João Nogueira 22 | author_email = joaopcnogueira@gmail.com 23 | copyright = 2023 onwards, João Nogueira 24 | description = Tools to Transform a Time Series into Features and Target a.k.a Supervised Learning 25 | keywords = nbdev jupyter notebook python 26 | language = English 27 | status = 3 28 | user = joaopcnogueira 29 | requirements = fastcore pandas numpy tqdm scikit-learn 30 | dev_requirements = jupyter 31 | readme_nb = index.ipynb 32 | allowed_metadata_keys = 33 | allowed_cell_metadata_keys = 34 | jupyter_hooks = True 35 | clean_ids = True 36 | clear_all = False 37 | 38 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | from pkg_resources import parse_version 2 | from configparser import ConfigParser 3 | import setuptools, shlex 4 | assert parse_version(setuptools.__version__)>=parse_version('36.2') 5 | 6 | # note: all settings are in settings.ini; edit there, not here 7 | config = ConfigParser(delimiters=['=']) 8 | config.read('settings.ini', encoding='utf-8') 9 | cfg = config['DEFAULT'] 10 | 11 | cfg_keys = 'version description keywords author author_email'.split() 12 | expected = cfg_keys + "lib_name user branch license status min_python audience language".split() 13 | for o in expected: assert o in cfg, "missing expected setting: {}".format(o) 14 | setup_cfg = {o:cfg[o] for o in cfg_keys} 15 | 16 | licenses = { 17 | 'apache2': ('Apache Software License 2.0','OSI Approved :: Apache Software License'), 18 | 'mit': ('MIT License', 'OSI Approved :: MIT License'), 19 | 'gpl2': ('GNU General Public License v2', 'OSI Approved :: GNU General Public License v2 (GPLv2)'), 20 | 'gpl3': ('GNU General Public License v3', 'OSI Approved :: GNU General Public License v3 (GPLv3)'), 21 | 'bsd3': ('BSD License', 'OSI Approved :: BSD License'), 22 | } 23 | statuses = [ '1 - Planning', '2 - Pre-Alpha', '3 - Alpha', 24 | '4 - Beta', '5 - Production/Stable', '6 - Mature', '7 - Inactive' ] 25 | py_versions = '3.6 3.7 3.8 3.9 3.10'.split() 26 | 27 | requirements = shlex.split(cfg.get('requirements', '')) 28 | if cfg.get('pip_requirements'): requirements += shlex.split(cfg.get('pip_requirements', '')) 29 | min_python = cfg['min_python'] 30 | lic = licenses.get(cfg['license'].lower(), (cfg['license'], None)) 31 | dev_requirements = (cfg.get('dev_requirements') or '').split() 32 | 33 | setuptools.setup( 34 | name = cfg['lib_name'], 35 | license = lic[0], 36 | classifiers = [ 37 | 'Development Status :: ' + statuses[int(cfg['status'])], 38 | 'Intended Audience :: ' + cfg['audience'].title(), 39 | 'Natural Language :: ' + cfg['language'].title(), 40 | ] + ['Programming Language :: Python :: '+o for o in py_versions[py_versions.index(min_python):]] + (['License :: ' + lic[1] ] if lic[1] else []), 41 | url = cfg['git_url'], 42 | packages = setuptools.find_packages(), 43 | include_package_data = True, 44 | install_requires = requirements, 45 | extras_require={ 'dev': dev_requirements }, 46 | dependency_links = cfg.get('dep_links','').split(), 47 | python_requires = '>=' + cfg['min_python'], 48 | long_description = open('README.md', encoding='utf-8').read(), 49 | long_description_content_type = 'text/markdown', 50 | zip_safe = False, 51 | entry_points = { 52 | 'console_scripts': cfg.get('console_scripts','').split(), 53 | 'nbdev': [f'{cfg.get("lib_path")}={cfg.get("lib_path")}._modidx:d'] 54 | }, 55 | **setup_cfg) 56 | 57 | 58 | -------------------------------------------------------------------------------- /ts2ml/__init__.py: -------------------------------------------------------------------------------- 1 | __version__ = "1.0.1" 2 | -------------------------------------------------------------------------------- /ts2ml/_modidx.py: -------------------------------------------------------------------------------- 1 | # Autogenerated by nbdev 2 | 3 | d = { 'settings': { 'branch': 'main', 4 | 'doc_baseurl': '/ts2ml', 5 | 'doc_host': 'https://joaopcnogueira.github.io', 6 | 'git_url': 'https://github.com/joaopcnogueira/ts2ml', 7 | 'lib_path': 'ts2ml'}, 8 | 'syms': { 'ts2ml.core': { 'ts2ml.core.add_missing_slots': ('core.html#add_missing_slots', 'ts2ml/core.py'), 9 | 'ts2ml.core.get_cutoff_indices_features_and_target': ( 'core.html#get_cutoff_indices_features_and_target', 10 | 'ts2ml/core.py'), 11 | 'ts2ml.core.transform_ts_data_into_features_and_target': ( 'core.html#transform_ts_data_into_features_and_target', 12 | 'ts2ml/core.py')}}} 13 | -------------------------------------------------------------------------------- /ts2ml/core.py: -------------------------------------------------------------------------------- 1 | # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/00_core.ipynb. 2 | 3 | # %% auto 0 4 | __all__ = ['add_missing_slots', 'get_cutoff_indices_features_and_target', 'transform_ts_data_into_features_and_target'] 5 | 6 | # %% ../nbs/00_core.ipynb 3 7 | import numpy as np 8 | import pandas as pd 9 | from tqdm import tqdm 10 | from typing import List 11 | 12 | # %% ../nbs/00_core.ipynb 4 13 | def add_missing_slots( 14 | df: pd.DataFrame, # input dataframe with datetime, entity and value columns - time series format 15 | datetime_col: str, # name of the datetime column 16 | entity_col: str, # name of the entity column. If a time series is associated to a location, this column will be 'location_id' 17 | value_col: str, # name of the value column 18 | freq: str='H', # frequency of the time series. Default is hourly 19 | fill_value: int = 0 # value to use to fill missing slots 20 | ) -> pd.DataFrame: 21 | """ 22 | Add missing slots to a time series dataframe. 23 | This function is useful to fill missing slots in a time series dataframe. 24 | For example, if a time series is associated to a location, this function will add missing slots for each location. 25 | Missing slots are filled with the value specified in the 'fill_value' parameter. 26 | By default, the frequency of the time series is hourly. 27 | """ 28 | 29 | entity_ids = df[entity_col].unique() 30 | all_hours = pd.date_range(start=df[datetime_col].min(), end=df[datetime_col].max(), freq=freq) 31 | 32 | output = pd.DataFrame() 33 | 34 | for entity_id in tqdm(entity_ids): 35 | 36 | # keep only rides for this 'location_id' 37 | df_entity_id = df.loc[df[entity_col] == entity_id, [datetime_col, value_col]] 38 | 39 | # quick way to add missing dates with 0 in a Series 40 | # taken from https://stackoverflow.com/a/19324591 41 | df_entity_id.set_index(datetime_col, inplace=True) 42 | df_entity_id.index = pd.DatetimeIndex(df_entity_id.index) 43 | df_entity_id = df_entity_id.reindex(all_hours, fill_value=0) 44 | 45 | # add back 'location_id' column 46 | df_entity_id[entity_col] = entity_id 47 | 48 | output = pd.concat([output, df_entity_id]) 49 | 50 | # move the purchase_day from index to column 51 | output = output.reset_index().rename(columns={'index': datetime_col}) 52 | output = output[[datetime_col, entity_col, value_col]].copy() 53 | 54 | return output 55 | 56 | # %% ../nbs/00_core.ipynb 7 57 | def get_cutoff_indices_features_and_target( 58 | ts_data: pd.DataFrame, # Time Series DataFrame 59 | datetime_col: str, # Name of the datetime column 60 | n_features: int, # Number of features to use for the prediction 61 | n_targets: int=1, # Number of target values to predict 62 | step_size: int=1, # Step size to use to slide the Time Series DataFrame 63 | ) -> List[tuple]: 64 | """Function to get the indices for the cutoffs of a Time Series DataFrame. 65 | The Time Series DataFrame should be orderded by time.""" 66 | 67 | # check if it is ordered 68 | if not ts_data[datetime_col].is_monotonic_increasing: 69 | raise ValueError("The DataFrame should be ordered by time.") 70 | 71 | # check if the index is ordered 72 | if not ts_data.index.is_monotonic_increasing: 73 | raise ValueError("The index should be ordered by time.") 74 | 75 | # check if the step_size is valid 76 | if step_size < 1: 77 | raise ValueError("The step_size should be >= 1.") 78 | 79 | # check if the number of features is valid 80 | if n_features < 1: 81 | raise ValueError("The number of features should be >= 1.") 82 | 83 | # check if the number of target values is valid 84 | if n_targets < 1: 85 | raise ValueError("The number of target values should be >= 1.") 86 | 87 | # check if the number of features and target values is valid 88 | if n_features + n_targets > len(ts_data): 89 | raise ValueError("The number of features + target values should be <= the length of the time series.") 90 | 91 | # below we compute the indices for the cutoffs 92 | stop_position = len(ts_data) - 1 93 | 94 | # Start the first sub-sequence at index position 0 95 | subseq_first_idx = 0 96 | subseq_mid_idx = n_features 97 | subseq_last_idx = n_features + n_targets 98 | indices = [] 99 | 100 | while subseq_last_idx <= stop_position: 101 | indices.append((subseq_first_idx, subseq_mid_idx, subseq_last_idx)) 102 | 103 | subseq_first_idx += step_size 104 | subseq_mid_idx += step_size 105 | subseq_last_idx += step_size 106 | 107 | return indices 108 | 109 | # %% ../nbs/00_core.ipynb 11 110 | def transform_ts_data_into_features_and_target( 111 | ts_data: pd.DataFrame, # Time Series DataFrame 112 | n_features: int, # Number of features to use for the prediction 113 | datetime_col: str, # Name of the datetime column 114 | entity_col: str, # Name of the entity column, e.g. location_id 115 | value_col: str, # Name of the value column 116 | n_targets: int=1, # Number of target values to predict 117 | step_size: int=1, # Step size to use to slide the Time Series DataFrame 118 | step_name: str=None, # Name of the step column 119 | concat_Xy: bool=False # Whether to concat X and y on the same dataframe or not 120 | ) -> pd.DataFrame: 121 | """ 122 | Slices and transposes data from time-series format into a (features, target) 123 | format that we can use to train Supervised ML models. 124 | """ 125 | 126 | entity_ids = ts_data[entity_col].unique() 127 | features = pd.DataFrame() 128 | targets = pd.DataFrame() 129 | 130 | for entity_id in tqdm(entity_ids): 131 | 132 | # keep only ts data for this `location_id` 133 | ts_data_one_location = ts_data.loc[ 134 | ts_data[entity_col] == entity_id, 135 | [datetime_col, value_col] 136 | ] 137 | 138 | # pre-compute cutoff indices to split dataframe rows 139 | indices = get_cutoff_indices_features_and_target( 140 | ts_data=ts_data_one_location, 141 | datetime_col=datetime_col, 142 | n_features=n_features, 143 | n_targets=n_targets, 144 | step_size=step_size 145 | ) 146 | 147 | # slice and transpose data into numpy arrays for features and targets 148 | time_values = [] 149 | n_examples = len(indices) 150 | x = np.ndarray(shape=(n_examples, n_features), dtype=np.float32) 151 | if n_targets == 1: 152 | y = np.ndarray(shape=(n_examples), dtype=np.float32) 153 | for i, idx in enumerate(indices): 154 | x[i, :] = ts_data_one_location.iloc[idx[0]:idx[1]][value_col].values 155 | y[i] = ts_data_one_location.iloc[idx[1]:idx[2]][value_col].values 156 | time_values.append(ts_data_one_location.iloc[idx[1]][datetime_col]) 157 | else: 158 | y = np.ndarray(shape=(n_examples, n_targets), dtype=np.float32) 159 | for i, idx in enumerate(indices): 160 | x[i, :] = ts_data_one_location.iloc[idx[0]:idx[1]][value_col].values 161 | y[i, :] = ts_data_one_location.iloc[idx[1]:idx[2]][value_col].values 162 | time_values.append(ts_data_one_location.iloc[idx[1]][datetime_col]) 163 | 164 | # numpy -> pandas 165 | if step_name is None: 166 | features_one_location = pd.DataFrame( 167 | x, 168 | columns=[f'{value_col}_previous_{i+1}' for i in reversed(range(n_features))] 169 | ) 170 | features_one_location[datetime_col] = time_values 171 | features_one_location[entity_col] = entity_id 172 | 173 | # numpy -> pandas 174 | if n_targets == 1: 175 | targets_one_location = pd.DataFrame(y, columns=[f'target_{value_col}_next']) 176 | else: 177 | targets_one_location = pd.DataFrame( 178 | y, 179 | columns=[f'target_{value_col}_next_{i+1}' for i in range(n_targets)] 180 | ) 181 | else: 182 | features_one_location = pd.DataFrame( 183 | x, 184 | columns=[f'{value_col}_previous_{i+1}_{step_name}' for i in reversed(range(n_features))] 185 | ) 186 | features_one_location[datetime_col] = time_values 187 | features_one_location[entity_col] = entity_id 188 | 189 | # numpy -> pandas 190 | if n_targets == 1: 191 | targets_one_location = pd.DataFrame(y, columns=[f'target_{value_col}_next_{step_name}']) 192 | else: 193 | targets_one_location = pd.DataFrame( 194 | y, 195 | columns=[f'target_{value_col}_next_{i+1}_{step_name}' for i in range(n_targets)] 196 | ) 197 | 198 | # concatenate results 199 | features = pd.concat([features, features_one_location]) 200 | targets = pd.concat([targets, targets_one_location]) 201 | 202 | features.reset_index(inplace=True, drop=True) 203 | targets.reset_index(inplace=True, drop=True) 204 | 205 | if concat_Xy: 206 | return pd.concat([features, targets], axis=1) 207 | else: 208 | return features, targets 209 | --------------------------------------------------------------------------------