├── .github
├── ISSUE_TEMPLATE
│ ├── bug_report.md
│ └── feature_request.md
└── workflows
│ └── codeql-analysis.yml
├── CODE_OF_CONDUCT.md
├── CONTRIBUTING.md
├── LICENSE
├── README.md
├── auto_tensorflow
└── tfa.py
├── header.png
├── logo.png
├── pyproject.toml
├── setup.py
└── tutorials
├── TFAuto_|_Classification.ipynb
└── TFAuto_|_Regression.ipynb
/.github/ISSUE_TEMPLATE/bug_report.md:
--------------------------------------------------------------------------------
1 | ---
2 | name: Bug report
3 | about: Create a report to help us improve
4 | title: ''
5 | labels: ''
6 | assignees: ''
7 |
8 | ---
9 |
10 | **Describe the bug**
11 | A clear and concise description of what the bug is.
12 |
13 | **To Reproduce**
14 | Steps to reproduce the behavior:
15 |
16 | **Expected behavior**
17 | A clear and concise description of what you expected to happen.
18 |
19 | **Versions:**
20 | - Auto-Tensorflow:
21 | - Tensorflow:
22 | - Tensorflow-Extended:
23 |
24 | **Additional context**
25 | Add any other context about the problem here.
26 |
--------------------------------------------------------------------------------
/.github/ISSUE_TEMPLATE/feature_request.md:
--------------------------------------------------------------------------------
1 | ---
2 | name: Feature request
3 | about: Suggest an idea for this project
4 | title: ''
5 | labels: ''
6 | assignees: ''
7 |
8 | ---
9 |
10 | **Is your feature request related to a problem? Please describe.**
11 | A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
12 |
13 | **Describe the solution you'd like**
14 | A clear and concise description of what you want to happen.
15 |
16 | **Describe alternatives you've considered**
17 | A clear and concise description of any alternative solutions or features you've considered.
18 |
19 | **Additional context**
20 | Add any other context or screenshots about the feature request here.
21 |
--------------------------------------------------------------------------------
/.github/workflows/codeql-analysis.yml:
--------------------------------------------------------------------------------
1 | # For most projects, this workflow file will not need changing; you simply need
2 | # to commit it to your repository.
3 | #
4 | # You may wish to alter this file to override the set of languages analyzed,
5 | # or to provide custom queries or build logic.
6 | #
7 | # ******** NOTE ********
8 | # We have attempted to detect the languages in your repository. Please check
9 | # the `language` matrix defined below to confirm you have the correct set of
10 | # supported CodeQL languages.
11 | #
12 | name: "AutoQLChecks"
13 |
14 | on:
15 | push:
16 | branches: [ main ]
17 | pull_request:
18 | # The branches below must be a subset of the branches above
19 | branches: [ main ]
20 | schedule:
21 | - cron: '17 22 * * 5'
22 |
23 | jobs:
24 | analyze:
25 | name: Analyze
26 | runs-on: ubuntu-latest
27 | permissions:
28 | actions: read
29 | contents: read
30 | security-events: write
31 |
32 | strategy:
33 | fail-fast: false
34 | matrix:
35 | language: [ 'python' ]
36 | # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python' ]
37 | # Learn more:
38 | # https://docs.github.com/en/free-pro-team@latest/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#changing-the-languages-that-are-analyzed
39 |
40 | steps:
41 | - name: Checkout repository
42 | uses: actions/checkout@v2
43 |
44 | # Initializes the CodeQL tools for scanning.
45 | - name: Initialize CodeQL
46 | uses: github/codeql-action/init@v1
47 | with:
48 | languages: ${{ matrix.language }}
49 | # If you wish to specify custom queries, you can do so here or in a config file.
50 | # By default, queries listed here will override any specified in a config file.
51 | # Prefix the list here with "+" to use these queries and those in the config file.
52 | # queries: ./path/to/local/query, your-org/your-repo/queries@main
53 |
54 | # Autobuild attempts to build any compiled languages (C/C++, C#, or Java).
55 | # If this step fails, then you should remove it and run the build manually (see below)
56 | - name: Autobuild
57 | uses: github/codeql-action/autobuild@v1
58 |
59 | # ℹ️ Command-line programs to run using the OS shell.
60 | # 📚 https://git.io/JvXDl
61 |
62 | # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
63 | # and modify them (or add more) to build your code if your project
64 | # uses a compiled language
65 |
66 | #- run: |
67 | # make bootstrap
68 | # make release
69 |
70 | - name: Perform CodeQL Analysis
71 | uses: github/codeql-action/analyze@v1
72 |
--------------------------------------------------------------------------------
/CODE_OF_CONDUCT.md:
--------------------------------------------------------------------------------
1 | # Contributor Covenant Code of Conduct
2 |
3 | ## Our Pledge
4 |
5 | We as members, contributors, and leaders pledge to make participation in our
6 | community a harassment-free experience for everyone, regardless of age, body
7 | size, visible or invisible disability, ethnicity, sex characteristics, gender
8 | identity and expression, level of experience, education, socio-economic status,
9 | nationality, personal appearance, race, religion, or sexual identity
10 | and orientation.
11 |
12 | We pledge to act and interact in ways that contribute to an open, welcoming,
13 | diverse, inclusive, and healthy community.
14 |
15 | ## Our Standards
16 |
17 | Examples of behavior that contributes to a positive environment for our
18 | community include:
19 |
20 | * Demonstrating empathy and kindness toward other people
21 | * Being respectful of differing opinions, viewpoints, and experiences
22 | * Giving and gracefully accepting constructive feedback
23 | * Accepting responsibility and apologizing to those affected by our mistakes,
24 | and learning from the experience
25 | * Focusing on what is best not just for us as individuals, but for the
26 | overall community
27 |
28 | Examples of unacceptable behavior include:
29 |
30 | * The use of sexualized language or imagery, and sexual attention or
31 | advances of any kind
32 | * Trolling, insulting or derogatory comments, and personal or political attacks
33 | * Public or private harassment
34 | * Publishing others' private information, such as a physical or email
35 | address, without their explicit permission
36 | * Other conduct which could reasonably be considered inappropriate in a
37 | professional setting
38 |
39 | ## Enforcement Responsibilities
40 |
41 | Community leaders are responsible for clarifying and enforcing our standards of
42 | acceptable behavior and will take appropriate and fair corrective action in
43 | response to any behavior that they deem inappropriate, threatening, offensive,
44 | or harmful.
45 |
46 | Community leaders have the right and responsibility to remove, edit, or reject
47 | comments, commits, code, wiki edits, issues, and other contributions that are
48 | not aligned to this Code of Conduct, and will communicate reasons for moderation
49 | decisions when appropriate.
50 |
51 | ## Scope
52 |
53 | This Code of Conduct applies within all community spaces, and also applies when
54 | an individual is officially representing the community in public spaces.
55 | Examples of representing our community include using an official e-mail address,
56 | posting via an official social media account, or acting as an appointed
57 | representative at an online or offline event.
58 |
59 | ## Enforcement
60 |
61 | Instances of abusive, harassing, or otherwise unacceptable behavior may be
62 | reported to the community leaders responsible for enforcement.
63 | All complaints will be reviewed and investigated promptly and fairly.
64 |
65 | All community leaders are obligated to respect the privacy and security of the
66 | reporter of any incident.
67 |
68 | ## Enforcement Guidelines
69 |
70 | Community leaders will follow these Community Impact Guidelines in determining
71 | the consequences for any action they deem in violation of this Code of Conduct:
72 |
73 | ### 1. Correction
74 |
75 | **Community Impact**: Use of inappropriate language or other behavior deemed
76 | unprofessional or unwelcome in the community.
77 |
78 | **Consequence**: A private, written warning from community leaders, providing
79 | clarity around the nature of the violation and an explanation of why the
80 | behavior was inappropriate. A public apology may be requested.
81 |
82 | ### 2. Warning
83 |
84 | **Community Impact**: A violation through a single incident or series
85 | of actions.
86 |
87 | **Consequence**: A warning with consequences for continued behavior. No
88 | interaction with the people involved, including unsolicited interaction with
89 | those enforcing the Code of Conduct, for a specified period of time. This
90 | includes avoiding interactions in community spaces as well as external channels
91 | like social media. Violating these terms may lead to a temporary or
92 | permanent ban.
93 |
94 | ### 3. Temporary Ban
95 |
96 | **Community Impact**: A serious violation of community standards, including
97 | sustained inappropriate behavior.
98 |
99 | **Consequence**: A temporary ban from any sort of interaction or public
100 | communication with the community for a specified period of time. No public or
101 | private interaction with the people involved, including unsolicited interaction
102 | with those enforcing the Code of Conduct, is allowed during this period.
103 | Violating these terms may lead to a permanent ban.
104 |
105 | ### 4. Permanent Ban
106 |
107 | **Community Impact**: Demonstrating a pattern of violation of community
108 | standards, including sustained inappropriate behavior, harassment of an
109 | individual, or aggression toward or disparagement of classes of individuals.
110 |
111 | **Consequence**: A permanent ban from any sort of public interaction within
112 | the community.
113 |
114 | ## Attribution
115 |
116 | This Code of Conduct is adapted from the [Contributor Covenant][homepage],
117 | version 2.0, available at
118 | https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
119 |
120 | Community Impact Guidelines were inspired by [Mozilla's code of conduct
121 | enforcement ladder](https://github.com/mozilla/diversity).
122 |
123 | [homepage]: https://www.contributor-covenant.org
124 |
125 | For answers to common questions about this code of conduct, see the FAQ at
126 | https://www.contributor-covenant.org/faq. Translations are available at
127 | https://www.contributor-covenant.org/translations.
128 |
--------------------------------------------------------------------------------
/CONTRIBUTING.md:
--------------------------------------------------------------------------------
1 | # How to Contribute
2 |
3 | We'd love to accept your patches and contributions to this project. There are
4 | just a few small guidelines you need to follow.
5 |
6 | ## Contributor License Agreement
7 |
8 | Contributions to this project must be accompanied by a Contributor License
9 | Agreement. You (or your employer) retain the copyright to your contribution;
10 | this simply gives us permission to use and redistribute your contributions as
11 | part of the project.
12 |
13 | ## Code Reviews
14 |
15 | All submissions, including submissions by project members, require review. We
16 | use GitHub pull requests for this purpose. Consult
17 | [GitHub Help](https://help.github.com/articles/about-pull-requests/) for more
18 | information on using pull requests.
19 |
--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
1 |
2 | Apache License
3 | Version 2.0, January 2004
4 | http://www.apache.org/licenses/
5 |
6 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7 |
8 | 1. Definitions.
9 |
10 | "License" shall mean the terms and conditions for use, reproduction,
11 | and distribution as defined by Sections 1 through 9 of this document.
12 |
13 | "Licensor" shall mean the copyright owner or entity authorized by
14 | the copyright owner that is granting the License.
15 |
16 | "Legal Entity" shall mean the union of the acting entity and all
17 | other entities that control, are controlled by, or are under common
18 | control with that entity. For the purposes of this definition,
19 | "control" means (i) the power, direct or indirect, to cause the
20 | direction or management of such entity, whether by contract or
21 | otherwise, or (ii) ownership of fifty percent (50%) or more of the
22 | outstanding shares, or (iii) beneficial ownership of such entity.
23 |
24 | "You" (or "Your") shall mean an individual or Legal Entity
25 | exercising permissions granted by this License.
26 |
27 | "Source" form shall mean the preferred form for making modifications,
28 | including but not limited to software source code, documentation
29 | source, and configuration files.
30 |
31 | "Object" form shall mean any form resulting from mechanical
32 | transformation or translation of a Source form, including but
33 | not limited to compiled object code, generated documentation,
34 | and conversions to other media types.
35 |
36 | "Work" shall mean the work of authorship, whether in Source or
37 | Object form, made available under the License, as indicated by a
38 | copyright notice that is included in or attached to the work
39 | (an example is provided in the Appendix below).
40 |
41 | "Derivative Works" shall mean any work, whether in Source or Object
42 | form, that is based on (or derived from) the Work and for which the
43 | editorial revisions, annotations, elaborations, or other modifications
44 | represent, as a whole, an original work of authorship. For the purposes
45 | of this License, Derivative Works shall not include works that remain
46 | separable from, or merely link (or bind by name) to the interfaces of,
47 | the Work and Derivative Works thereof.
48 |
49 | "Contribution" shall mean any work of authorship, including
50 | the original version of the Work and any modifications or additions
51 | to that Work or Derivative Works thereof, that is intentionally
52 | submitted to Licensor for inclusion in the Work by the copyright owner
53 | or by an individual or Legal Entity authorized to submit on behalf of
54 | the copyright owner. For the purposes of this definition, "submitted"
55 | means any form of electronic, verbal, or written communication sent
56 | to the Licensor or its representatives, including but not limited to
57 | communication on electronic mailing lists, source code control systems,
58 | and issue tracking systems that are managed by, or on behalf of, the
59 | Licensor for the purpose of discussing and improving the Work, but
60 | excluding communication that is conspicuously marked or otherwise
61 | designated in writing by the copyright owner as "Not a Contribution."
62 |
63 | "Contributor" shall mean Licensor and any individual or Legal Entity
64 | on behalf of whom a Contribution has been received by Licensor and
65 | subsequently incorporated within the Work.
66 |
67 | 2. Grant of Copyright License. Subject to the terms and conditions of
68 | this License, each Contributor hereby grants to You a perpetual,
69 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70 | copyright license to reproduce, prepare Derivative Works of,
71 | publicly display, publicly perform, sublicense, and distribute the
72 | Work and such Derivative Works in Source or Object form.
73 |
74 | 3. Grant of Patent License. Subject to the terms and conditions of
75 | this License, each Contributor hereby grants to You a perpetual,
76 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77 | (except as stated in this section) patent license to make, have made,
78 | use, offer to sell, sell, import, and otherwise transfer the Work,
79 | where such license applies only to those patent claims licensable
80 | by such Contributor that are necessarily infringed by their
81 | Contribution(s) alone or by combination of their Contribution(s)
82 | with the Work to which such Contribution(s) was submitted. If You
83 | institute patent litigation against any entity (including a
84 | cross-claim or counterclaim in a lawsuit) alleging that the Work
85 | or a Contribution incorporated within the Work constitutes direct
86 | or contributory patent infringement, then any patent licenses
87 | granted to You under this License for that Work shall terminate
88 | as of the date such litigation is filed.
89 |
90 | 4. Redistribution. You may reproduce and distribute copies of the
91 | Work or Derivative Works thereof in any medium, with or without
92 | modifications, and in Source or Object form, provided that You
93 | meet the following conditions:
94 |
95 | (a) You must give any other recipients of the Work or
96 | Derivative Works a copy of this License; and
97 |
98 | (b) You must cause any modified files to carry prominent notices
99 | stating that You changed the files; and
100 |
101 | (c) You must retain, in the Source form of any Derivative Works
102 | that You distribute, all copyright, patent, trademark, and
103 | attribution notices from the Source form of the Work,
104 | excluding those notices that do not pertain to any part of
105 | the Derivative Works; and
106 |
107 | (d) If the Work includes a "NOTICE" text file as part of its
108 | distribution, then any Derivative Works that You distribute must
109 | include a readable copy of the attribution notices contained
110 | within such NOTICE file, excluding those notices that do not
111 | pertain to any part of the Derivative Works, in at least one
112 | of the following places: within a NOTICE text file distributed
113 | as part of the Derivative Works; within the Source form or
114 | documentation, if provided along with the Derivative Works; or,
115 | within a display generated by the Derivative Works, if and
116 | wherever such third-party notices normally appear. The contents
117 | of the NOTICE file are for informational purposes only and
118 | do not modify the License. You may add Your own attribution
119 | notices within Derivative Works that You distribute, alongside
120 | or as an addendum to the NOTICE text from the Work, provided
121 | that such additional attribution notices cannot be construed
122 | as modifying the License.
123 |
124 | You may add Your own copyright statement to Your modifications and
125 | may provide additional or different license terms and conditions
126 | for use, reproduction, or distribution of Your modifications, or
127 | for any such Derivative Works as a whole, provided Your use,
128 | reproduction, and distribution of the Work otherwise complies with
129 | the conditions stated in this License.
130 |
131 | 5. Submission of Contributions. Unless You explicitly state otherwise,
132 | any Contribution intentionally submitted for inclusion in the Work
133 | by You to the Licensor shall be under the terms and conditions of
134 | this License, without any additional terms or conditions.
135 | Notwithstanding the above, nothing herein shall supersede or modify
136 | the terms of any separate license agreement you may have executed
137 | with Licensor regarding such Contributions.
138 |
139 | 6. Trademarks. This License does not grant permission to use the trade
140 | names, trademarks, service marks, or product names of the Licensor,
141 | except as required for reasonable and customary use in describing the
142 | origin of the Work and reproducing the content of the NOTICE file.
143 |
144 | 7. Disclaimer of Warranty. Unless required by applicable law or
145 | agreed to in writing, Licensor provides the Work (and each
146 | Contributor provides its Contributions) on an "AS IS" BASIS,
147 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148 | implied, including, without limitation, any warranties or conditions
149 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150 | PARTICULAR PURPOSE. You are solely responsible for determining the
151 | appropriateness of using or redistributing the Work and assume any
152 | risks associated with Your exercise of permissions under this License.
153 |
154 | 8. Limitation of Liability. In no event and under no legal theory,
155 | whether in tort (including negligence), contract, or otherwise,
156 | unless required by applicable law (such as deliberate and grossly
157 | negligent acts) or agreed to in writing, shall any Contributor be
158 | liable to You for damages, including any direct, indirect, special,
159 | incidental, or consequential damages of any character arising as a
160 | result of this License or out of the use or inability to use the
161 | Work (including but not limited to damages for loss of goodwill,
162 | work stoppage, computer failure or malfunction, or any and all
163 | other commercial damages or losses), even if such Contributor
164 | has been advised of the possibility of such damages.
165 |
166 | 9. Accepting Warranty or Additional Liability. While redistributing
167 | the Work or Derivative Works thereof, You may choose to offer,
168 | and charge a fee for, acceptance of support, warranty, indemnity,
169 | or other liability obligations and/or rights consistent with this
170 | License. However, in accepting such obligations, You may act only
171 | on Your own behalf and on Your sole responsibility, not on behalf
172 | of any other Contributor, and only if You agree to indemnify,
173 | defend, and hold each Contributor harmless for any liability
174 | incurred by, or claims asserted against, such Contributor by reason
175 | of your accepting any such warranty or additional liability.
176 |
177 | END OF TERMS AND CONDITIONS
178 |
179 | APPENDIX: How to apply the Apache License to your work.
180 |
181 | To apply the Apache License to your work, attach the following
182 | boilerplate notice, with the fields enclosed by brackets "[]"
183 | replaced with your own identifying information. (Don't include
184 | the brackets!) The text should be enclosed in the appropriate
185 | comment syntax for the file format. We also recommend that a
186 | file or class name and description of purpose be included on the
187 | same "printed page" as the copyright notice for easier
188 | identification within third-party archives.
189 |
190 | Copyright [yyyy] [name of copyright owner]
191 |
192 | Licensed under the Apache License, Version 2.0 (the "License");
193 | you may not use this file except in compliance with the License.
194 | You may obtain a copy of the License at
195 |
196 | http://www.apache.org/licenses/LICENSE-2.0
197 |
198 | Unless required by applicable law or agreed to in writing, software
199 | distributed under the License is distributed on an "AS IS" BASIS,
200 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201 | See the License for the specific language governing permissions and
202 | limitations under the License.
203 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 |
2 |
3 | [](https://pepy.tech/project/auto-tensorflow)
4 | [](https://pypi.org/project/auto-tensorflow/)
5 | 
6 | 
7 | 
8 |
9 | ### **Auto Tensorflow - Mission:**
10 | **Build Low Code Automated Tensorflow, What-IF explainable models in just 3 lines of code.**
11 |
12 | To make Deep Learning on Tensorflow absolutely easy for the masses with its low code framework and also increase trust on ML models through What-IF model explainability.
13 |
14 | ### **Under the hood:**
15 | Built on top of the powerful **Tensorflow** ecosystem tools like **TFX** , **TF APIs** and **What-IF Tool** , the library automatically does all the heavy lifting internally like EDA, schema discovery, feature engineering, HPT, model search etc. This empowers developers to focus only on building end user applications quickly without any knowledge of Tensorflow, ML or debugging. Built for handling large volume of data / BigData - using only TF scalable components. Moreover the models trained with auto-tensorflow can directly be deployed on any cloud like GCP / AWS / Azure.
16 |
17 |
18 |
19 | ### **Official Launch**: https://youtu.be/sil-RbuckG0
20 |
21 | ### **Features:**
22 | 1. Build Classification / Regression models on CSV data
23 | 2. Automated Schema Inference
24 | 3. Automated Feature Engineering
25 | - Discretization
26 | - Scaling
27 | - Normalization
28 | - Text Embedding
29 | - Category encoding
30 | 5. Automated Model build for mixed data types( Continuous, Categorical and Free Text )
31 | 6. Automated Hyper-parameter tuning
32 | 7. Automated GPU Distributed training
33 | 8. Automated UI based What-IF analysis( Fairness, Feature Partial dependencies, What-IF )
34 | 9. Control over complexity of model
35 | 10. No dependency over Pandas / SKLearn
36 | 11. Can handle dataset of any size - including multiple CSV files
37 |
38 | ### **Tutorials**:
39 | 1. [](https://colab.research.google.com/github/rafiqhasan/auto-tensorflow/blob/main/tutorials/TFAuto_%7C_Classification.ipynb) - Auto Classification on CSV data
40 | 2. [](https://colab.research.google.com/github/rafiqhasan/auto-tensorflow/blob/main/tutorials/TFAuto_%7C_Regression.ipynb) - Auto Regression on CSV data
41 |
42 | ### **Setup:**
43 | 1. Install library
44 | - PIP(Recommended): ```pip install auto-tensorflow```
45 | - Nightly: ```pip install git+https://github.com/rafiqhasan/auto-tensorflow.git```
46 | 2. Works best on UNIX/Linux/Debian/Google Colab/MacOS
47 |
48 | ### **Usage:**
49 | 1. Initialize TFAuto Engine
50 | ```
51 | from auto_tensorflow.tfa import TFAuto
52 | tfa = TFAuto(train_data_path='/content/train_data/', test_data_path='/content/test_data/', path_root='/content/tfauto')
53 | ```
54 |
55 | 2. Step 1 - Automated EDA and Schema discovery
56 | ```
57 | tfa.step_data_explore(viz=True) ##Viz=False for no visualization
58 | ```
59 |
60 | 3. Step 2 - Automated ML model build and train
61 | ```
62 | tfa.step_model_build(label_column = 'price', model_type='REGRESSION', model_complexity=1)
63 | ```
64 |
65 | 4. Step 3 - Automated What-IF Tool launch
66 | ```
67 | tfa.step_model_whatif()
68 | ```
69 |
70 | ### **API Arguments:**
71 | - Method **TFAuto**
72 | - ```train_data_path```: Path where training data is stored
73 | - ```test_data_path```: Path where Test / Eval data is stored
74 | - ```path_root```: Directory for running TFAuto( Directory should NOT exist )
75 |
76 | - Method **step_data_explore**
77 | - ```viz```: Is data visualization required ? - True or False( Default )
78 |
79 | - Method **step_model_build**
80 | - `label_column`: The feature to be used as Label
81 | - `model_type`: Either of 'REGRESSION'( Default ), 'CLASSIFICATION'
82 | - `model_complexity`:
83 | - `0` : Model with default hyper-parameters
84 | - `1` (Default): Model with automated hyper-parameter tuning
85 | - `2` : Complexity 1 + Advanced fine-tuning of Text layers
86 |
87 | ### **Current limitations:**
88 | There are a few limitations in the initial release but we are working day and night to resolve these and **add them as future features**.
89 | 1. Doesn't support Image / Audio data
90 |
91 | ### **Future roadmap:**
92 | 1. Add support for Timeseries / Audio / Image data
93 | 2. Add feature to download full pipeline model Python code for advanced tweaking
94 |
95 | ### **Release History:**
96 | **1.3.4** - 09/12/2022 - [Release Notes](https://github.com/rafiqhasan/auto-tensorflow/releases/tag/1.3.4)
97 |
98 | **1.3.3** - 09/12/2022 - [Release Notes](https://github.com/rafiqhasan/auto-tensorflow/releases/tag/1.3.3)
99 |
100 | **1.3.2** - 27/11/2021 - [Release Notes](https://github.com/rafiqhasan/auto-tensorflow/releases/tag/1.3.2)
101 |
102 | **1.3.1** - 18/11/2021 - [Release Notes](https://github.com/rafiqhasan/auto-tensorflow/releases/tag/1.3.1)
103 |
104 | **1.2.0** - 24/07/2021 - [Release Notes](https://github.com/rafiqhasan/auto-tensorflow/releases/tag/1.2.0)
105 |
106 | **1.1.1** - 14/07/2021 - [Release Notes](https://github.com/rafiqhasan/auto-tensorflow/releases/tag/1.1.1)
107 |
108 | **1.0.1** - 07/07/2021 - [Release Notes](https://github.com/rafiqhasan/auto-tensorflow/releases/tag/1.0.1)
109 |
--------------------------------------------------------------------------------
/auto_tensorflow/tfa.py:
--------------------------------------------------------------------------------
1 | ##Owner: Hasan Rafiq
2 | ##URL: https://www.linkedin.com/in/sam04/
3 | import os
4 | import tempfile
5 | import re
6 | import json
7 | import urllib
8 |
9 | import absl
10 | import tensorflow as tf
11 | import tensorflow.keras as keras
12 | import tensorflow_text
13 | import tfx
14 | import tensorflow_hub as hub
15 | import keras_tuner as kt
16 | # import tensorflow_model_analysis as tfma
17 | import witwidget
18 | import tensorflow_data_validation as tfdv
19 | tf.get_logger().propagate = False
20 |
21 | from tfx.components import CsvExampleGen
22 | from typing import Dict, List, Text
23 | from tfx.components import Evaluator, ExampleValidator, Pusher, SchemaGen, Trainer, StatisticsGen, Transform
24 | from tfx.orchestration import metadata, pipeline
25 | from tfx.orchestration.experimental.interactive.interactive_context import InteractiveContext
26 | from tfx.proto import pusher_pb2, trainer_pb2, example_gen_pb2
27 | from tfx.v1 import proto
28 | from tfx.orchestration.local.local_dag_runner import LocalDagRunner
29 | from ml_metadata.proto import metadata_store_pb2
30 | from tfx.orchestration.portable.mlmd import execution_lib
31 | from tensorflow_metadata.proto.v0 import anomalies_pb2
32 | from tensorflow_data_validation.utils import io_util, display_util
33 | from google.protobuf.json_format import MessageToDict
34 | from witwidget.notebook.visualization import WitConfigBuilder
35 | from witwidget.notebook.visualization import WitWidget
36 |
37 | class TFAutoUtils():
38 | def __init__(self, data_path, path_root='/tfx'):
39 | ##Define all constants
40 | self._tfx_root = os.path.join(os.getcwd(), path_root)
41 | self._pipeline_root = os.path.join(self._tfx_root, 'pipelines'); # Join ~/tfx/pipelines/
42 | self._metadata_db_root = os.path.join(self._tfx_root, 'metadata.db'); # Join ~/tfx/metadata.db
43 | self._metadata = os.path.join(self._tfx_root, 'metadata'); # Join ~/tfx/metadata
44 | self._log_root = os.path.join(self._tfx_root, 'logs');
45 | self._model_root = os.path.join(self._tfx_root, 'model');
46 | self._data_path = data_path
47 |
48 | def check_directories(self):
49 | if os.path.exists(self._tfx_root):
50 | raise Exception("Root Directory: {} already exists. Please make sure directory doesn't exist!".format(self._tfx_root))
51 |
52 | def create_directories(self):
53 | self.check_directories()
54 |
55 | directories = [self._tfx_root, self._pipeline_root, self._metadata,
56 | self._log_root, self._model_root]
57 | [ print("Creating {}".format(d)) for d in directories ]
58 | [ os.mkdir(d) for d in directories ]
59 |
60 | def load_anomalies_binary(self, input_path: Text) -> anomalies_pb2.Anomalies:
61 | """Loads the Anomalies proto stored in text format in the input path.
62 | Args:
63 | input_path: File path from which to load the Anomalies proto.
64 | Returns:
65 | An Anomalies protocol buffer.
66 | """
67 | anomalies_proto = anomalies_pb2.Anomalies()
68 |
69 | anomalies_proto.ParseFromString(io_util.read_file_to_string(
70 | input_path, binary_mode=True))
71 |
72 | return anomalies_proto
73 |
74 | def _get_latest_execution(self, metadata, pipeline_name, component_id):
75 | """Gets the execution objects for the latest run of the pipeline."""
76 | node_context = metadata.store.get_context_by_type_and_name(
77 | 'node', f'{pipeline_name}.{component_id}')
78 | executions = metadata.store.get_executions_by_context(node_context.id)
79 | # Pick the latest one.
80 | return max(executions, key=lambda e: e.last_update_time_since_epoch)
81 |
82 | #Get all running artifact details from MLMD
83 | def _get_artifacts_for_component_id(self, metadata, execution):
84 | return execution_lib.get_artifacts_dict(metadata, execution.id,
85 | [metadata_store_pb2.Event.OUTPUT])
86 |
87 | #Get all running artifact directories from MLMD for later uses
88 | def get_artifacts_directories(self, component_name='StatisticsGen'):
89 | metadata_connection_config = metadata.sqlite_metadata_connection_config(self._metadata_db_root)
90 |
91 | with metadata.Metadata(metadata_connection_config) as metadata_handler:
92 | execution = self._get_latest_execution(metadata_handler, 'data_pipeline', component_name)
93 | output_directory = self._get_artifacts_for_component_id(metadata_handler, execution)
94 |
95 | return output_directory
96 |
97 | class TFAutoData():
98 | def __init__(self):
99 | ##Define all constants
100 | self.features_list = [] #Features used for training
101 | self._train_data_path = '' #Training data path
102 | self.schema = '' #Schema details of data
103 | self.stats_train = '' #Statistics of Train data
104 | self.stats_eval = '' #Statistics of Eval data
105 | self.anom_train = ''
106 | self.anom_eval = ''
107 | self.file_headers = [] #Headers of CSV train file
108 | self._len_train = 0 #Training data size
109 | self._run = False #Run flag
110 |
111 | def collect_feature_details(self, schema):
112 | features_list = []
113 | features_dict = display_util.get_schema_dataframe(schema)[0].to_dict('index')
114 | features_stats = MessageToDict(self.stats_train)
115 | self._len_train = features_stats['datasets'][0]['numExamples']
116 |
117 | for f_ in features_dict.keys():
118 | features_dict[f_]['feature'] = re.sub( r"\'", "", f_)
119 | #Feature has a domain( categorical feature )
120 | if features_dict[f_]['Domain'] != '-':
121 | features_dict[f_]['categorical_values'] = [ v for v in tfdv.get_domain(schema, features_dict[f_]['feature']).value ]
122 | features_dict[f_]['num_categorical_values'] = len(tfdv.get_domain(schema, features_dict[f_]['feature']).value)
123 |
124 | #Handle for free Text( If ratio of unique values with rows > 0.2 )
125 | if int(features_dict[f_]['num_categorical_values']) / int(self._len_train) > 0.2:
126 | features_dict[f_]['Type'] = 'STRING'
127 | features_dict[f_]['categorical_values'] = ""
128 | features_dict[f_]['num_categorical_values'] = 0
129 | else:
130 | features_dict[f_]['Type'] = 'CATEGORICAL'
131 |
132 | #Min/Max for numerical features
133 | #Count of unique values
134 | for feat in features_stats['datasets'][0]['features']:
135 | curr_feat = feat['path']['step'][0]
136 | if curr_feat == features_dict[f_]['feature'] and features_dict[f_]['Type'] in ['INT','FLOAT']:
137 | features_dict[f_]['min'] = feat['numStats'].get('min', 0.0)
138 | features_dict[f_]['max'] = feat['numStats'].get('max', 0.0)
139 | features_dict[f_]['mean'] = feat['numStats'].get('mean', 0.0)
140 | features_dict[f_]['std_dev'] = feat['numStats'].get('stdDev', 1)
141 | elif curr_feat == features_dict[f_]['feature'] and features_dict[f_]['Type'] == 'CATEGORICAL':
142 | features_dict[f_]['categorical_values_count'] = {}
143 | features_dict[f_]['categorical_values_count_total'] = 0
144 | #For each categorical value store counts
145 | for categ in features_dict[f_]['categorical_values']:
146 | categ_found = 0
147 | for topvals in feat['stringStats']['topValues']:
148 | if categ == topvals['value']:
149 | categ_found = 1
150 | features_dict[f_]['categorical_values_count'][topvals.get('value', "NA")] = topvals.get('frequency', 0)
151 | features_dict[f_]['categorical_values_count_total'] += topvals.get('frequency', 0)
152 | break
153 | #If value count for this category not present
154 | if categ_found == 0:
155 | features_dict[f_]['categorical_values_count'][categ] = 1
156 | features_dict[f_]['categorical_values_count_total'] += 1
157 |
158 | features_list.append(features_dict[f_])
159 | self.features_list = features_list
160 | return self.features_list
161 |
162 | def get_columns_from_file_header(self, path, num_cols):
163 | record_defaults=[]
164 | #Create dataset input functions
165 | if os.path.isdir(path):
166 | path = path + "*"
167 | elif os.path.isfile(path):
168 | path = path
169 |
170 | for _ in range(num_cols):
171 | record_defaults.append('')
172 |
173 | # Create list of files that match pattern
174 | file_list = tf.io.gfile.glob(path)
175 |
176 | # Create dataset from file list
177 | dataset = tf.data.experimental.CsvDataset(file_list, header=False, record_defaults=record_defaults, use_quote_delim=False)
178 |
179 | for example in dataset.take(1):
180 | return ([e.numpy().decode('utf-8') for e in example])
181 |
182 | def run_initial(self, _train_data_path, _test_data_path, _tfx_root, _metadata_db_root, tfautils, viz=False):
183 | """Run all data steps in pipeline and generate visuals"""
184 | input = proto.Input(splits=[
185 | example_gen_pb2.Input.Split(name='train', pattern=os.path.join(_train_data_path, "*")),
186 | example_gen_pb2.Input.Split(name='eval', pattern=os.path.join(_test_data_path, "*"))
187 | ])
188 | self.example_gen = CsvExampleGen(input_base="/", input_config=input)
189 |
190 | self.statistics_gen = StatisticsGen(examples=self.example_gen.outputs['examples'])
191 |
192 | self.infer_schema = SchemaGen(
193 | statistics=self.statistics_gen.outputs['statistics'], infer_feature_shape=False)
194 |
195 | self.validate_stats = ExampleValidator(
196 | statistics=self.statistics_gen.outputs['statistics'],
197 | schema=self.infer_schema.outputs['schema'])
198 |
199 | #Create pipeline
200 | self.pipeline = pipeline.Pipeline(
201 | pipeline_name= 'data_pipeline',
202 | pipeline_root= _tfx_root,
203 | components=[
204 | self.example_gen, self.statistics_gen, self.infer_schema, self.validate_stats
205 | ],
206 | metadata_connection_config = metadata.sqlite_metadata_connection_config(_metadata_db_root),
207 | enable_cache=True,
208 | beam_pipeline_args=['--direct_num_workers=%d' % 0, '--direct_running_mode=multi_threading'],
209 | )
210 |
211 | #Run data pipeline
212 | print("Data: Pipeline execution started...")
213 | LocalDagRunner().run(self.pipeline)
214 | self._run = True
215 |
216 | #Get directories after run
217 | dir_stats = tfautils.get_artifacts_directories('StatisticsGen')
218 | dir_anom = tfautils.get_artifacts_directories('ExampleValidator')
219 | dir_schema = tfautils.get_artifacts_directories('SchemaGen')
220 |
221 | #Get statistics
222 | stats_url_train = str(dir_stats['statistics'][0].uri) + "/Split-train/FeatureStats.pb"
223 | self.stats_train = tfdv.load_stats_binary(stats_url_train)
224 | stats_url_eval = str(dir_stats['statistics'][0].uri) + "/Split-eval/FeatureStats.pb"
225 | self.stats_eval = tfdv.load_stats_binary(stats_url_eval)
226 |
227 | #Get data anomalies
228 | anom_url_train = str(dir_anom['anomalies'][0].uri) + "/Split-train/SchemaDiff.pb"
229 | self.anom_train = tfautils.load_anomalies_binary(anom_url_train)
230 | anom_url_eval = str(dir_anom['anomalies'][0].uri) + "/Split-eval/SchemaDiff.pb"
231 | self.anom_eval = tfautils.load_anomalies_binary(anom_url_eval)
232 |
233 | #Get Schema and Features details, generate config JSON
234 | schema_url = str(dir_schema['schema'][0].uri) + "/schema.pbtxt"
235 | self.schema = tfdv.load_schema_text(schema_url)
236 | self.features_list = self.collect_feature_details(self.schema)
237 |
238 | #Get columns from training file
239 | self.file_headers = self.get_columns_from_file_header(_train_data_path, len(self.features_list))
240 |
241 | # Visualize results using TFDV
242 | if viz==True:
243 | #Show Schema Gen
244 | print("\n### Generating schema visuals")
245 | tfdv.display_schema(self.schema)
246 |
247 | #Show Train Vs Eval Schema Stats
248 | print("\n### Generating Comparative Statistics Visuals...")
249 | tfdv.visualize_statistics(lhs_statistics=self.stats_eval, rhs_statistics=self.stats_train,
250 | lhs_name='EVAL_DATASET', rhs_name='TRAIN_DATASET')
251 |
252 | #Show Eval Anomalies
253 | print("\n### Generating Test Data Anomaly Visuals...")
254 | tfdv.display_anomalies(self.anom_eval)
255 |
256 | return self.pipeline
257 |
258 | class TextEncoder(tf.keras.Model):
259 | def __init__(self, strategy, trainable=False):
260 | self.strategy = strategy
261 | with self.strategy.scope():
262 | super(TextEncoder, self).__init__()
263 | self.encoder = hub.KerasLayer("https://tfhub.dev/google/tf2-preview/nnlm-en-dim50/1", trainable=trainable)
264 |
265 | def __call__(self, inp):
266 | with self.strategy.scope():
267 | #Encode text
268 | embedding = self.encoder(inp)
269 |
270 | return embedding
271 |
272 | class TFAutoModel():
273 | def __init__(self, _tfx_root, train_data_path, test_data_path):
274 | ##Define all constants
275 | self._tfx_root = _tfx_root
276 | self._config_json = ''
277 | self._pipeline_root = os.path.join(self._tfx_root, 'pipelines'); # Join ~/tfx/pipelines/
278 | self._log_root = os.path.join(self._tfx_root, 'logs');
279 | self._model_root = os.path.join(self._tfx_root, 'model');
280 | self._label = '' #Label
281 | self._label_vocab = []
282 | self._features = [] #List of features to be used for modeling
283 | self._class_weights = {} #Class weights
284 | self._train_data_path = train_data_path #Training data
285 | self._test_data_path = test_data_path #Test data
286 | self._model_type = ''
287 | self._model_complexity = 1
288 | self._defaults = []
289 | self._run = False #Run flag
290 | self.hpt_config = {
291 | 0:{
292 | 'deep_neurons':{
293 | 'min':64,
294 | 'max':64
295 | },
296 | 'wide_neurons':{
297 | 'min':64,
298 | 'max':64
299 | },
300 | 'prefinal_dense': {
301 | 'min':32,
302 | 'max':32
303 | },
304 | 'learning_rate':{
305 | 'min':0.01,
306 | 'max':0.01
307 | },
308 | 'bins':{
309 | 'min':10,
310 | 'max':10
311 | },
312 | 'l1_regularization':{
313 | 'min':0.0001,
314 | 'max':0.0001
315 | },
316 | },
317 | 1:{
318 | 'deep_neurons':{
319 | 'min':8,
320 | 'max':1024
321 | },
322 | 'wide_neurons':{
323 | 'min':32,
324 | 'max':2048
325 | },
326 | 'prefinal_dense': {
327 | 'min':8,
328 | 'max':512
329 | },
330 | 'learning_rate':{
331 | 'min':0.0005,
332 | 'max':0.1
333 | },
334 | 'bins':{
335 | 'min':4,
336 | 'max':40
337 | },
338 | 'l1_regularization':{
339 | 'min':0.00001,
340 | 'max':0.0001
341 | },
342 | },
343 | }
344 | self.hpt_config[2] = self.hpt_config[1]
345 |
346 | ##GPU Strategy
347 | self.strategy = tf.distribute.MirroredStrategy()
348 |
349 | def load_config_json(self):
350 | with open(os.path.join(self._tfx_root, 'config.json')) as f:
351 | self._config_json = json.load(f)
352 |
353 | #Create list of features
354 | for feats in self._config_json['data_schema']:
355 | #Don't include ignored features
356 | if feats['feature'] in self._config_json['ignore_features'] or feats['feature'] == self._label:
357 | continue
358 | else:
359 | self._features.append(feats['feature'])
360 |
361 | def make_input_fn(self, filename, mode, vnum_epochs = None, batch_size = 512):
362 | CSV_COLUMNS = [ feats['feature'] for feats in self._config_json['data_schema'] ]
363 | LABEL_COLUMN = self._label
364 |
365 | # Set default values for required only CSV columns + LABEL
366 | # This has to be in sequence of CSV columns 0 to N
367 | DEFAULTS = []
368 | for f_ in self._config_json['file_headers']:
369 | for feats in self._config_json['data_schema']:
370 | if feats['feature'] != f_:
371 | continue
372 |
373 | #Logic for default values
374 | if feats['Type'] in [ 'CATEGORICAL', 'STRING', 'BYTES' ]:
375 | DEFAULTS.append([''])
376 | elif feats['Type'] == 'FLOAT':
377 | DEFAULTS.append([tf.cast(0, tf.float32)])
378 | elif feats['Type'] == 'INT':
379 | DEFAULTS.append([tf.cast(0, tf.int64)])
380 |
381 | # print("Default for {} is {}".format(f_, DEFAULTS[-1]))
382 |
383 | break
384 |
385 | self._defaults = DEFAULTS
386 |
387 | ###############################
388 | ##Feature engineering functions
389 | def feature_engg_features(features):
390 | #Apply data type conversions
391 | for feats in self._config_json['data_schema']:
392 | if feats['feature'] == self._label or not feats['feature'] in self._features:
393 | continue
394 |
395 | #Convert dtype of all tensors as per requested schema
396 | if feats['Type'] in [ 'CATEGORICAL', 'STRING', 'BYTES' ] and features[feats['feature']].dtype != tf.string:
397 | features[feats['feature']] = tf.strings.as_string(features[feats['feature']])
398 | elif feats['Type'] == 'FLOAT' and features[feats['feature']].dtype != tf.float32:
399 | #Needs special handling for strings
400 | if features[feats['feature']].dtype != tf.string:
401 | features[feats['feature']] = tf.cast(features[feats['feature']], dtype=tf.float32)
402 | elif feats['Type'] == 'INT' and features[feats['feature']].dtype != tf.int64:
403 | #Needs special handling for strings
404 | if features[feats['feature']].dtype != tf.string:
405 | features[feats['feature']] = tf.cast(features[feats['feature']], dtype=tf.int64)
406 |
407 | return(features)
408 |
409 | #Convert string labels 0 to N
410 | def string_labels_to_num(v_feats, v_label):
411 | pass_label = v_label
412 | for ix, cat_vals in enumerate(v_feats['categorical_values']):
413 | search_string = str(cat_vals) + "$"
414 | pass_label = tf.strings.regex_replace(pass_label, search_string, tf.strings.as_string(ix))
415 |
416 | pass_label = tf.strings.to_number(pass_label, out_type=tf.dtypes.int32)
417 | return pass_label
418 |
419 | #To be called from TF
420 | def feature_engg(features, label):
421 | #Add new features
422 | features = feature_engg_features(features)
423 |
424 | #Replace string label with 0 to N for classification case
425 | if self._model_type == 'CLASSIFICATION':
426 | for feats in self._config_json['data_schema']:
427 | if feats['feature'] == self._label:
428 | break
429 |
430 | #Replace categorical values with 0 to N
431 | if feats['Type'] == 'CATEGORICAL' and feats['feature'] == self._label:
432 | self._label_vocab = feats['categorical_values']
433 | label = string_labels_to_num(feats, label)
434 |
435 | return(features, label)
436 |
437 | def _input_fn(v_test=False):
438 | # Create list of files that match pattern
439 | file_list = tf.io.gfile.glob(filename)
440 |
441 | if mode == tf.estimator.ModeKeys.TRAIN:
442 | num_epochs = vnum_epochs # indefinitely
443 | else:
444 | num_epochs = 1 # end-of-input after this
445 |
446 | # Create dataset from file list
447 | dataset = tf.data.experimental.make_csv_dataset(file_list,
448 | batch_size=batch_size,
449 | column_names=self._config_json['file_headers'],
450 | column_defaults=DEFAULTS,
451 | label_name=LABEL_COLUMN,
452 | num_epochs = num_epochs,
453 | num_parallel_reads=30)
454 |
455 | dataset = dataset.prefetch(buffer_size = batch_size)
456 |
457 | #Feature engineering
458 | dataset = dataset.map(feature_engg)
459 |
460 | if mode == tf.estimator.ModeKeys.TRAIN:
461 | num_epochs = vnum_epochs # indefinitely
462 | dataset = dataset.shuffle(buffer_size = batch_size)
463 | else:
464 | num_epochs = 1 # end-of-input after this
465 |
466 | dataset = dataset.repeat(num_epochs)
467 |
468 | #Begins - Uncomment for testing only -----------------------------------------------------<
469 | if v_test == True:
470 | print(next(dataset.__iter__()))
471 |
472 | #End - Uncomment for testing only -----------------------------------------------------<
473 | return dataset
474 | return _input_fn
475 |
476 | # def make_input_fn_gz(self, dir_uri, mode, vnum_epochs = None, batch_size = 512):
477 | # def decode_tfr(serialized_example):
478 | # schema = {}
479 | # features = {}
480 | # for feats in self._config_json['data_schema']:
481 | # #1. Create GZIP TFR parser schema
482 | # # if feats['Type'] == 'CATEGORICAL':
483 | # # schema[feats['feature']] = tf.io.FixedLenFeature([], tf.string, default_value="")
484 | # # elif feats['Type'] == 'FLOAT':
485 | # # schema[feats['feature']] = tf.io.FixedLenFeature([], tf.float32, default_value=0.0 )
486 | # # elif feats['Type'] == 'INT':
487 | # # schema[feats['feature']] = tf.io.FixedLenFeature([], tf.int64, default_value=0)
488 |
489 | # if feats['Type'] == 'CATEGORICAL':
490 | # schema[feats['feature']] = tf.io.VarLenFeature(tf.string)
491 | # elif feats['Type'] == 'FLOAT':
492 | # schema[feats['feature']] = tf.io.VarLenFeature(tf.float32)
493 | # elif feats['Type'] == 'INT':
494 | # schema[feats['feature']] = tf.io.VarLenFeature(tf.int64)
495 |
496 | # # 1. define a parser
497 | # features = tf.io.parse_example(
498 | # serialized_example,
499 | # # Defaults are not specified since both keys are required.
500 | # features=schema)
501 |
502 | # return features, features[self._label]
503 |
504 | # def _input_fn(v_test=False):
505 | # # Get the list of files in this directory (all compressed TFRecord files)
506 | # tfrecord_filenames = tf.io.gfile.glob(dir_uri)
507 |
508 | # # Create a `TFRecordDataset` to read these files
509 | # dataset = tf.data.TFRecordDataset(tfrecord_filenames, compression_type="GZIP")
510 |
511 | # if mode == tf.estimator.ModeKeys.TRAIN:
512 | # num_epochs = vnum_epochs # indefinitely
513 | # else:
514 | # num_epochs = 1 # end-of-input after this
515 |
516 | # dataset = dataset.batch(batch_size)
517 | # dataset = dataset.prefetch(buffer_size = batch_size)
518 |
519 | # #Convert TFRecord data to dict
520 | # dataset = dataset.map(decode_tfr)
521 |
522 | # #Feature engineering
523 | # # dataset = dataset.map(feature_engg)
524 |
525 | # if mode == tf.estimator.ModeKeys.TRAIN:
526 | # num_epochs = vnum_epochs # indefinitely
527 | # dataset = dataset.shuffle(buffer_size = batch_size)
528 | # else:
529 | # num_epochs = 1 # end-of-input after this
530 |
531 | # dataset = dataset.repeat(num_epochs)
532 |
533 | # #Begins - Uncomment for testing only -----------------------------------------------------<
534 | # if v_test == True:
535 | # print(next(dataset.__iter__()))
536 |
537 | # #End - Uncomment for testing only -----------------------------------------------------<
538 | # return dataset
539 | # return _input_fn
540 |
541 | def create_feature_cols(self):
542 | #Keras format features
543 | feats_dict = {}
544 | keras_dict_input = {}
545 | for feats in self._config_json['data_schema']:
546 | #Only include features
547 | if feats['feature'] not in self._features:
548 | continue
549 |
550 | #Create feature columns list
551 | if feats['Type'] in [ 'CATEGORICAL', 'STRING', 'BYTES' ]:
552 | feats_dict[feats['feature']] = tf.keras.Input(name=feats['feature'], shape=(1,), dtype=tf.string)
553 | elif feats['Type'] == 'FLOAT':
554 | feats_dict[feats['feature']] = tf.keras.Input(name=feats['feature'], shape=(1,), dtype=tf.float32)
555 | elif feats['Type'] == 'INT':
556 | feats_dict[feats['feature']] = tf.keras.Input(name=feats['feature'], shape=(1,), dtype=tf.int32)
557 |
558 | for k_ in feats_dict.keys():
559 | keras_dict_input[k_] = feats_dict[k_]
560 |
561 | self._feature_cols = {'K' : keras_dict_input}
562 | return self._feature_cols
563 |
564 | def create_keras_model_classification(self, hp):
565 | with self.strategy.scope():
566 | # params = self.params_default
567 | feature_cols = self._feature_cols
568 |
569 | #Number of classes
570 | for feats in self._config_json['data_schema']:
571 | #Only include label
572 | if feats['feature'] == self._label:
573 | if feats['Type'] != 'CATEGORICAL':
574 | num_classes = int(feats['max'] + 1)
575 | break
576 | else:
577 | num_classes = len(feats['categorical_values'])
578 | break
579 |
580 | #Calculate class weights
581 | for feats in self._config_json['data_schema']:
582 | #Only include label
583 | if feats['feature'] == self._label:
584 | if feats.get('categorical_values', 'NA') != 'NA':
585 | #In case of categorical labels
586 | for ix, class_ in enumerate(feats['categorical_values']):
587 | self._class_weights[ix] = (1 / feats['categorical_values_count'][class_]) * (feats['categorical_values_count_total'])/2.0
588 | else:
589 | #In case of numerical labels
590 | for class_ in range(num_classes):
591 | self._class_weights[class_] = 1
592 |
593 | METRICS = [
594 | # tf.keras.metrics.AUC(multi_label=True, num_labels=num_classes),
595 | 'sparse_categorical_accuracy'
596 | ]
597 |
598 | #Input layers
599 | input_feats = []
600 | for inp in feature_cols['K'].keys():
601 | input_feats.append(feature_cols['K'][inp])
602 |
603 | ##Input processing
604 | ##https://keras.io/examples/structured_data/structured_data_classification_from_scratch/
605 | ##https://github.com/tensorflow/community/blob/master/rfcs/20191212-keras-categorical-inputs.md
606 |
607 | ##Automated feature handling
608 | #Handle categorical attributes( One-hot encoding )
609 | feat_cat = []
610 | for feats in self._config_json['data_schema']:
611 | if feats['feature'] in self._features and feats['Type'] == 'CATEGORICAL':
612 | feat_cat.append('')
613 | cat_len = feats['num_categorical_values']
614 | cat = tf.keras.layers.experimental.preprocessing.StringLookup(vocabulary=feats['categorical_values'], mask_token=None, oov_token = '~UNK~')(feature_cols['K'][feats['feature']])
615 | feat_cat[-1] = tf.keras.layers.experimental.preprocessing.CategoryEncoding(num_tokens = cat_len + 1)(cat)
616 |
617 | #Handle numerical attributes
618 | feat_numeric = []
619 | for feats in self._config_json['data_schema']:
620 | if feats['feature'] in self._features and feats['Type'] not in [ 'CATEGORICAL', 'STRING', 'BYTES' ]:
621 | feat_numeric.append('')
622 |
623 | #Apply normalization
624 | if feats['std_dev'] != 0:
625 | feat_numeric[-1] = ( tf.cast(feature_cols['K'][feats['feature']], tf.float32) - feats['mean'] ) / feats['std_dev']
626 | else:
627 | feat_numeric[-1] = tf.cast(feature_cols['K'][feats['feature']], tf.float32)
628 |
629 | #More feature engineering( Squaring )
630 | feat_numeric.append('')
631 | feat_numeric[-1] = tf.math.pow(feat_numeric[-2], 2)
632 |
633 | #Apply min-max scaling
634 | if feats['max'] - feats['min'] != 0:
635 | feat_numeric.append('')
636 | feat_numeric[-1] = ( tf.cast(feature_cols['K'][feats['feature']], tf.float32) - feats['min'] ) / ( feats['max'] - feats['min'] )
637 |
638 | ##SPECIAL HANDLING CONVERT NUMERIC TO CATEG
639 | #Bucketization( 2 to 40 )
640 | feat_cat.append('')
641 | no_of_bins = hp.Int('bins_' + feats['feature'], min_value=self.hpt_config[self._model_complexity]['bins']['min'],
642 | max_value=self.hpt_config[self._model_complexity]['bins']['max'])
643 | bins = tf.linspace(feats['min'], feats['max'], no_of_bins)
644 | layer_discretization = tf.keras.layers.Discretization(bin_boundaries=bins)(feature_cols['K'][feats['feature']])
645 | feat_cat[-1] = tf.keras.layers.experimental.preprocessing.CategoryEncoding(num_tokens = no_of_bins + 2)(layer_discretization)
646 |
647 | #Handle Text attributes
648 | feat_text = []
649 | if self._model_complexity < 2:
650 | #Without fine-tuning
651 | text_emb = TextEncoder(self.strategy)
652 | else:
653 | #With fine-tuning
654 | text_emb = TextEncoder(self.strategy, trainable=True)
655 |
656 | for feats in self._config_json['data_schema']:
657 | if feats['Type'] in ['STRING', 'BYTES']:
658 | feat_text.append('')
659 |
660 | #Apply Text Encoding from TFHub
661 | feat_text[-1] = text_emb(tf.reshape(tf.cast(feature_cols['K'][feats['feature']], tf.string), [-1]))
662 |
663 | ###Create MODEL
664 | ####Concatenate all features( Numerical input )
665 | numeric_features_count = 0
666 | if len(feat_numeric) > 0:
667 | numeric_features_count += 1
668 | x_input_numeric = tf.keras.layers.concatenate(feat_numeric)
669 |
670 | #DEEP - This Dense layer connects to input layer - Numeric Data
671 | deep_neurons = hp.Int('deep_neurons', min_value=self.hpt_config[self._model_complexity]['deep_neurons']['min'],
672 | max_value=self.hpt_config[self._model_complexity]['deep_neurons']['max'])
673 | x_numeric = tf.keras.layers.Dense(deep_neurons, kernel_initializer='lecun_normal',
674 | activation='selu')(x_input_numeric)
675 | x_numeric = tf.keras.layers.BatchNormalization()(x_numeric)
676 |
677 | ####Concatenate all Categorical features( Categorical converted )
678 | text_features_count = 0
679 | if len(feat_text) > 0:
680 | text_features_count += 1
681 | x_input_text = tf.keras.layers.concatenate(feat_text)
682 |
683 | ####Concatenate all Categorical features( Categorical converted )
684 | categ_features_count = 0
685 | if len(feat_cat) > 0:
686 | categ_features_count += 1
687 | x_input_categ = tf.keras.layers.concatenate(feat_cat)
688 |
689 | #WIDE - This Dense layer connects to input layer - Categorical Data
690 | wide_neurons = hp.Int('wide_neurons', min_value=self.hpt_config[self._model_complexity]['wide_neurons']['min'],
691 | max_value=self.hpt_config[self._model_complexity]['wide_neurons']['max'])
692 | x_categ = tf.keras.layers.Dense(wide_neurons, kernel_initializer='lecun_normal',
693 | activation='selu')(x_input_categ)
694 |
695 | ####Concatenate both Wide and Deep layers
696 | if numeric_features_count > 0 and categ_features_count > 0 and text_features_count > 0:
697 | x = tf.keras.layers.concatenate([x_numeric, x_categ, x_input_text])
698 | elif numeric_features_count == 0 and categ_features_count > 0 and text_features_count > 0:
699 | x = tf.keras.layers.concatenate([x_categ, x_input_text])
700 | elif numeric_features_count > 0 and categ_features_count == 0 and text_features_count > 0:
701 | x = tf.keras.layers.concatenate([x_numeric, x_input_text])
702 | elif numeric_features_count > 0 and categ_features_count > 0 and text_features_count == 0:
703 | x = tf.keras.layers.concatenate([x_numeric, x_categ])
704 | elif numeric_features_count > 0 and categ_features_count == 0 and text_features_count == 0:
705 | x = x_numeric
706 | elif numeric_features_count == 0 and categ_features_count > 0 and text_features_count == 0:
707 | x = x_categ
708 | elif numeric_features_count == 0 and categ_features_count == 0 and text_features_count > 0:
709 | x = x_input_text
710 |
711 | prefinal_dense = hp.Int('prefinal_dense', min_value=self.hpt_config[self._model_complexity]['prefinal_dense']['min'],
712 | max_value=self.hpt_config[self._model_complexity]['prefinal_dense']['max'])
713 | l1_reg = hp.Float('l1_regularization', min_value=self.hpt_config[self._model_complexity]['l1_regularization']['min'],
714 | max_value=self.hpt_config[self._model_complexity]['l1_regularization']['max'])
715 | x = tf.keras.layers.Dense(prefinal_dense, kernel_initializer='lecun_normal',
716 | activation='selu',
717 | activity_regularizer=tf.keras.regularizers.l2(l1_reg))(x)
718 | x = tf.keras.layers.BatchNormalization()(x)
719 |
720 | #Final Layer
721 | # out = tf.keras.layers.Dense(1, activation='sigmoid', name='out')(x)
722 | out = tf.keras.layers.Dense(num_classes, activation='softmax', name='out')(x)
723 | model = tf.keras.Model(input_feats, out)
724 |
725 | #Set optimizer
726 | hp_learning_rate = hp.Float('learning_rate', min_value=self.hpt_config[self._model_complexity]['learning_rate']['min'],
727 | max_value=self.hpt_config[self._model_complexity]['learning_rate']['max'])
728 | opt = tf.keras.optimizers.Adam(lr = hp_learning_rate)
729 |
730 | #Compile model
731 | model.compile(loss='sparse_categorical_crossentropy', optimizer=opt, metrics = METRICS)
732 |
733 | return model
734 |
735 | def create_keras_model_regression(self, hp):
736 | with self.strategy.scope():
737 | METRICS = [
738 | keras.metrics.RootMeanSquaredError(name='rmse'),
739 | keras.metrics.MeanAbsolutePercentageError(name='mape')
740 | ]
741 |
742 | # params = self.params_default
743 | feature_cols = self._feature_cols
744 |
745 | #Input layers
746 | input_feats = []
747 | for inp in feature_cols['K'].keys():
748 | input_feats.append(feature_cols['K'][inp])
749 |
750 | ##Input processing
751 | ##https://keras.io/examples/structured_data/structured_data_classification_from_scratch/
752 | ##https://github.com/tensorflow/community/blob/master/rfcs/20191212-keras-categorical-inputs.md
753 |
754 | ##Automated feature handling
755 | #Handle categorical attributes( One-hot encoding )
756 | feat_cat = []
757 | for feats in self._config_json['data_schema']:
758 | if feats['feature'] in self._features and feats['Type'] == 'CATEGORICAL':
759 | feat_cat.append('')
760 | cat_len = feats['num_categorical_values']
761 | cat = tf.keras.layers.experimental.preprocessing.StringLookup(vocabulary=feats['categorical_values'], mask_token=None, oov_token = '~UNK~')(feature_cols['K'][feats['feature']])
762 | feat_cat[-1] = tf.keras.layers.experimental.preprocessing.CategoryEncoding(num_tokens = cat_len + 1)(cat)
763 |
764 | #Handle numerical attributes
765 | feat_numeric = []
766 | for feats in self._config_json['data_schema']:
767 | if feats['feature'] in self._features and feats['Type'] not in [ 'CATEGORICAL', 'STRING', 'BYTES' ]:
768 | feat_numeric.append('')
769 |
770 | #apply normalization
771 | if feats['std_dev'] != 0:
772 | feat_numeric[-1] = ( tf.cast(feature_cols['K'][feats['feature']], tf.float32) - feats['mean'] ) / feats['std_dev']
773 | else:
774 | feat_numeric[-1] = tf.cast(feature_cols['K'][feats['feature']], tf.float32)
775 |
776 | ##More feature engineering( Squaring )
777 | feat_numeric.append('')
778 | feat_numeric[-1] = tf.math.pow(feat_numeric[-2], 2)
779 |
780 | #Apply min-max scaling
781 | if feats['max'] - feats['min'] != 0:
782 | feat_numeric.append('')
783 | feat_numeric[-1] = ( tf.cast(feature_cols['K'][feats['feature']], tf.float32) - feats['min'] ) / ( feats['max'] - feats['min'] )
784 |
785 | ##SPECIAL HANDLING CONVERT NUMERIC TO CATEG
786 | #Bucketization( 2 to 40 )
787 | feat_cat.append('')
788 | no_of_bins = hp.Int('bins_' + feats['feature'], min_value=self.hpt_config[self._model_complexity]['bins']['min'],
789 | max_value=self.hpt_config[self._model_complexity]['bins']['max'])
790 | bins = tf.linspace(feats['min'], feats['max'], no_of_bins)
791 | layer_discretization = tf.keras.layers.Discretization(bin_boundaries=bins)(feature_cols['K'][feats['feature']])
792 | feat_cat[-1] = tf.keras.layers.experimental.preprocessing.CategoryEncoding(num_tokens = no_of_bins + 2)(layer_discretization)
793 |
794 | #Handle Text attributes
795 | feat_text = []
796 | if self._model_complexity < 2:
797 | #Without fine-tuning
798 | text_emb = TextEncoder(self.strategy)
799 | else:
800 | #With fine-tuning
801 | text_emb = TextEncoder(self.strategy, trainable=True)
802 |
803 | for feats in self._config_json['data_schema']:
804 | if feats['Type'] in ['STRING', 'BYTES']:
805 | feat_text.append('')
806 |
807 | #Apply Text Encoding from TFHub
808 | feat_text[-1] = text_emb(tf.reshape(tf.cast(feature_cols['K'][feats['feature']], tf.string), [-1]))
809 |
810 | ###Create MODEL
811 | ####Concatenate all features( Numerical input )
812 | numeric_features_count = 0
813 | if len(feat_numeric) > 0:
814 | numeric_features_count += 1
815 | x_input_numeric = tf.keras.layers.concatenate(feat_numeric)
816 |
817 | #DEEP - This Dense layer connects to input layer - Numeric Data
818 | deep_neurons = hp.Int('deep_neurons', min_value=self.hpt_config[self._model_complexity]['deep_neurons']['min'],
819 | max_value=self.hpt_config[self._model_complexity]['deep_neurons']['max'])
820 | x_numeric = tf.keras.layers.Dense(deep_neurons, kernel_initializer='lecun_normal',
821 | activation='selu')(x_input_numeric)
822 | x_numeric = tf.keras.layers.BatchNormalization()(x_numeric)
823 |
824 | ####Concatenate all Categorical features( Categorical converted )
825 | text_features_count = 0
826 | if len(feat_text) > 0:
827 | text_features_count += 1
828 | x_input_text = tf.keras.layers.concatenate(feat_text)
829 |
830 | ####Concatenate all Categorical features( Categorical converted )
831 | categ_features_count = 0
832 | if len(feat_cat) > 0:
833 | categ_features_count += 1
834 | x_input_categ = tf.keras.layers.concatenate(feat_cat)
835 |
836 | #WIDE - This Dense layer connects to input layer - Categorical Data
837 | wide_neurons = hp.Int('wide_neurons', min_value=self.hpt_config[self._model_complexity]['wide_neurons']['min'],
838 | max_value=self.hpt_config[self._model_complexity]['wide_neurons']['max'])
839 | x_categ = tf.keras.layers.Dense(wide_neurons, kernel_initializer='lecun_normal',
840 | activation='selu')(x_input_categ)
841 |
842 | ####Concatenate both Wide and Deep layers
843 | if numeric_features_count > 0 and categ_features_count > 0 and text_features_count > 0:
844 | x = tf.keras.layers.concatenate([x_numeric, x_categ, x_input_text])
845 | elif numeric_features_count == 0 and categ_features_count > 0 and text_features_count > 0:
846 | x = tf.keras.layers.concatenate([x_categ, x_input_text])
847 | elif numeric_features_count > 0 and categ_features_count == 0 and text_features_count > 0:
848 | x = tf.keras.layers.concatenate([x_numeric, x_input_text])
849 | elif numeric_features_count > 0 and categ_features_count > 0 and text_features_count == 0:
850 | x = tf.keras.layers.concatenate([x_numeric, x_categ])
851 | elif numeric_features_count > 0 and categ_features_count == 0 and text_features_count == 0:
852 | x = x_numeric
853 | elif numeric_features_count == 0 and categ_features_count > 0 and text_features_count == 0:
854 | x = x_categ
855 | elif numeric_features_count == 0 and categ_features_count == 0 and text_features_count > 0:
856 | x = x_input_text
857 |
858 | prefinal_dense = hp.Int('prefinal_dense', min_value=self.hpt_config[self._model_complexity]['prefinal_dense']['min'],
859 | max_value=self.hpt_config[self._model_complexity]['prefinal_dense']['max'])
860 | l1_reg = hp.Float('l1_regularization', min_value=self.hpt_config[self._model_complexity]['l1_regularization']['min'],
861 | max_value=self.hpt_config[self._model_complexity]['l1_regularization']['max'])
862 | x = tf.keras.layers.Dense(prefinal_dense, kernel_initializer='lecun_normal',
863 | activation='selu',
864 | activity_regularizer=tf.keras.regularizers.l2(l1_reg))(x)
865 | x = tf.keras.layers.BatchNormalization()(x)
866 |
867 | #Final Layer
868 | out = tf.keras.layers.Dense(1, activation='linear', name='out')(x)
869 | model = tf.keras.Model(input_feats, out)
870 |
871 | #Set optimizer
872 | hp_learning_rate = hp.Float('learning_rate', min_value=self.hpt_config[self._model_complexity]['learning_rate']['min'],
873 | max_value=self.hpt_config[self._model_complexity]['learning_rate']['max'])
874 | opt = tf.keras.optimizers.Adam(lr = hp_learning_rate)
875 |
876 | #Compile model
877 | model.compile(loss='mean_squared_error', optimizer=opt, metrics = METRICS)
878 |
879 | return model
880 |
881 | def keras_train_and_evaluate(self, model, epochs=100, mode='Train'):
882 | #Add callbacks
883 | reduce_lr = keras.callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.2,
884 | patience=5, min_lr=0.00001, verbose = 1)
885 |
886 | tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir="./logs")
887 |
888 | #Create dataset input functions
889 | if os.path.isdir(self._train_data_path):
890 | train_file_path = self._train_data_path + "*"
891 | elif os.path.isfile(self._train_data_path):
892 | train_file_path = self._train_data_path
893 |
894 | if os.path.isdir(self._test_data_path):
895 | test_file_path = self._test_data_path + "*"
896 | elif os.path.isfile(self._test_data_path):
897 | test_file_path = self._test_data_path
898 |
899 | train_batch = 128
900 | train_dataset = self.make_input_fn(filename = train_file_path,
901 | mode = tf.estimator.ModeKeys.TRAIN,
902 | batch_size = train_batch)()
903 | # eval_file = '/content/tfauto/CsvExampleGen/examples/1/Split-train/*'
904 | # train_dataset = self.make_input_fn_gz(dir_uri = eval_file,
905 | # mode = tf.estimator.ModeKeys.TRAIN,
906 | # batch_size = 10)()
907 |
908 | train_steps_per_epoch = int(self._config_json['len_train']) // train_batch
909 |
910 | validation_dataset = self.make_input_fn(filename = test_file_path,
911 | mode = tf.estimator.ModeKeys.EVAL,
912 | batch_size = 512)()
913 | # validation_dataset = self.make_input_fn_gz(dir_uri = eval_file,
914 | # mode = tf.estimator.ModeKeys.TRAIN,
915 | # batch_size = 10)()
916 |
917 | #Train and Evaluate
918 | #Best model chosen from tuning is just refitted here on full data
919 | if mode == 'Train':
920 | if self._model_type == 'REGRESSION':
921 | print("Training a regression model...")
922 | elif self._model_type == 'CLASSIFICATION':
923 | print("Training a classification model...")
924 |
925 | #Start training loop
926 | self._model.fit(train_dataset,
927 | validation_data = validation_dataset,
928 | epochs=epochs,
929 | # validation_steps = 3, ###Keep this none for running evaluation on full EVAL data every epoch
930 | steps_per_epoch = train_steps_per_epoch, ###Has to be passed - Cant help it :) [ Number of batches per epoch ]
931 | callbacks=[reduce_lr, #modelsave_callback, #tensorboard_callback,
932 | keras.callbacks.EarlyStopping(patience=20, restore_best_weights=True, verbose=True)],
933 | class_weight = self._class_weights
934 | )
935 | else:
936 | #Model is created during Tuning cycle
937 | if self._model_type == 'REGRESSION':
938 | print("Hyper-Tuning a regression model...")
939 | mod_func = self.create_keras_model_regression
940 | objective = 'val_loss'
941 | elif self._model_type == 'CLASSIFICATION':
942 | print("Hyper-Tuning a classification model...")
943 | mod_func = self.create_keras_model_classification
944 | objective = 'val_sparse_categorical_accuracy'
945 |
946 | ###Create Tuner
947 | ###########################################
948 | tuner = kt.Hyperband(
949 | mod_func,
950 | objective=objective,
951 | overwrite='True',
952 | max_epochs=20)
953 | stop_early = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=10)
954 |
955 | tuner.search(train_dataset, validation_data=validation_dataset, epochs=epochs, steps_per_epoch = train_steps_per_epoch, callbacks=[stop_early],
956 | class_weight = self._class_weights)
957 | # print(f"""
958 | # The hyperparameter search is complete. The optimal number of units in the first densely-connected
959 | # layer is {best_hps.get('units')} and the optimal learning rate for the optimizer
960 | # is {best_hps.get('learning_rate')}.
961 | # """)
962 | best_hps=tuner.get_best_hyperparameters(num_trials=1)[0]
963 | print("Best LR: ", best_hps.get('learning_rate'))
964 | self._model = tuner.hypermodel.build(best_hps)
965 |
966 | return self._model
967 |
968 | def save_model(self):
969 | version = "1" #{'serving_default': call_output}
970 | tf.saved_model.save(
971 | self._model, #Model
972 | self._model_root + "/" + version #Location
973 | )
974 |
975 | def search_hpt(self):
976 | #Create feature columns dynamically and model too
977 | self._feature_cols = self.create_feature_cols()
978 |
979 | #Start HPT
980 | self._model = self.keras_train_and_evaluate(None, epochs=50, mode='Tune')
981 |
982 | #Print summary
983 | print(self._model.summary())
984 |
985 | def start_train(self):
986 | #Create feature columns dynamically and model too
987 | self._feature_cols = self.create_feature_cols()
988 |
989 | #Start training loop on HPT best found model
990 | try:
991 | tf.keras.utils.plot_model(self._model, rankdir="LR")
992 | except:
993 | 1 - 1
994 |
995 | self._model = self.keras_train_and_evaluate(self._model, epochs=9999, mode='Train')
996 |
997 | #Save model
998 | self.save_model()
999 |
1000 | def generate_examples_for_wit(self):
1001 | max_samples = 100
1002 | examples = []
1003 | record_defaults=[]
1004 | out = {}
1005 | path = self._test_data_path
1006 | #Create dataset input functions
1007 | if os.path.isdir(path):
1008 | path = path + "*"
1009 | elif os.path.isfile(path):
1010 | path = path
1011 |
1012 | # Create list of files that match pattern
1013 | file_list = tf.io.gfile.glob(path)
1014 |
1015 | # Create dataset from file list
1016 | dataset = tf.data.experimental.make_csv_dataset(file_list, header=True, batch_size=max_samples
1017 | ,num_epochs=1, column_defaults=self._defaults)
1018 |
1019 | #Get first batch
1020 | for features in dataset.take(1):
1021 | for i, (name, value) in enumerate(features.items()):
1022 | out[name] = value.numpy()
1023 |
1024 | #Generate examples
1025 | for row in range(max_samples):
1026 | try:
1027 | example = tf.train.Example()
1028 | #For each column in file
1029 | for f_ in self._config_json['file_headers']:
1030 | for feats in self._config_json['data_schema']:
1031 | if feats['feature'] != f_:
1032 | continue
1033 |
1034 | #Prepare example data
1035 | if feats['Type'] in [ 'CATEGORICAL', 'STRING', 'BYTES' ]:
1036 | example.features.feature[f_].bytes_list.value.append(out[f_][row])
1037 | elif feats['Type'] == 'FLOAT':
1038 | example.features.feature[f_].float_list.value.append(out[f_][row])
1039 | elif feats['Type'] == 'INT':
1040 | example.features.feature[f_].int64_list.value.append(int(out[f_][row]))
1041 | examples.append(example)
1042 | except:
1043 | pass
1044 | return examples
1045 |
1046 | #Create prediction function to link in WIT
1047 | def wit_prediction_fn_dyn(self, examples, check_mode=False):
1048 | version = "1"
1049 | out = []
1050 | examples_out = []
1051 |
1052 | #LOCAL: Predict using Keras prediction function
1053 | saved_mod = tf.saved_model.load(self._model_root + "/" + version) #Location)
1054 |
1055 | #Get prediction function from serving
1056 | mod_fn = saved_mod.signatures['serving_default']
1057 |
1058 | for ex in examples:
1059 | #Extract features from each example
1060 | keyword_args = {}
1061 | test_data = ex.features
1062 |
1063 | for f_ in self._config_json['file_headers']:
1064 | if f_ == self._label or f_ in self._config_json['ignore_features'] :
1065 | continue
1066 | for feats in self._config_json['data_schema']:
1067 | if feats['feature'] != f_:
1068 | continue
1069 |
1070 | #Prepare example data
1071 | if feats['Type'] in [ 'CATEGORICAL', 'STRING', 'BYTES' ]:
1072 | keyword_args[f_] = tf.convert_to_tensor([test_data.feature[f_].bytes_list.value])
1073 | elif feats['Type'] == 'FLOAT':
1074 | keyword_args[f_] = tf.convert_to_tensor([test_data.feature[f_].float_list.value])
1075 | elif feats['Type'] == 'INT':
1076 | keyword_args[f_] = tf.convert_to_tensor([test_data.feature[f_].int64_list.value])
1077 |
1078 | #Run prediction function on saved model
1079 | # print(keyword_args)
1080 | # break
1081 | try:
1082 | pred = mod_fn(**keyword_args)
1083 |
1084 | p_ = pred['out'].numpy()
1085 | out.append(p_[0])
1086 | examples_out.append(ex)
1087 | except:
1088 | 1 - 1
1089 |
1090 | if check_mode==True:
1091 | #If we want to find also the valid examples
1092 | return out, examples_out
1093 | else:
1094 | return out
1095 |
1096 | def call_wit(self):
1097 | #Generate examples for WIT and also check for valid examples
1098 | examples_wit = self.generate_examples_for_wit()
1099 | _, examples_wit = self.wit_prediction_fn_dyn(examples_wit, check_mode=True)
1100 |
1101 | if self._model_type == 'REGRESSION':
1102 | wit_type = 'regression'
1103 | config_builder = (WitConfigBuilder(examples_wit, self._config_json['file_headers'])
1104 | .set_custom_predict_fn(self.wit_prediction_fn_dyn)
1105 | .set_model_type(wit_type))
1106 | elif self._model_type == 'CLASSIFICATION':
1107 | wit_type = 'classification'
1108 | config_builder = (WitConfigBuilder(examples_wit, self._config_json['file_headers'])
1109 | .set_custom_predict_fn(self.wit_prediction_fn_dyn)
1110 | .set_model_type(wit_type)
1111 | .set_label_vocab(self._label_vocab))
1112 |
1113 | WitWidget(config_builder)
1114 |
1115 | def prechecks(self):
1116 | '''Set of tests to run before training'''
1117 | success_flag = True
1118 | #Test 1 -> Label Data Type check
1119 | for feats in self._config_json['data_schema']:
1120 | if feats['feature'] != self._label:
1121 | continue
1122 |
1123 | # Only allow numerical values for REGRESSION models
1124 | if feats['Type'] in [ 'CATEGORICAL', 'STRING', 'BYTES' ] and self._model_type == "REGRESSION":
1125 | print("Error: REGRESSION - labels should be numerical only")
1126 | success_flag = False
1127 | return success_flag
1128 |
1129 | #Test 2 -> Label values check
1130 | for feats in self._config_json['data_schema']:
1131 | if feats['feature'] != self._label:
1132 | continue
1133 |
1134 | #For classification, minimum value should be 0 for INT labels
1135 | if self._model_type == "CLASSIFICATION" and feats['Type'] in ['INT', 'FLOAT']:
1136 | if int(feats['min']) != 0:
1137 | print("Error: CLASSIFICATION - Integer labels should start from 0")
1138 | success_flag = False
1139 | return success_flag
1140 |
1141 | return success_flag
1142 |
1143 | def run_initial(self, label_column, model_type='REGRESSION', model_complexity=1):
1144 | self.__init__(self._tfx_root, self._train_data_path, self._test_data_path)
1145 | """Run all modeling steps in pipeline and generate results"""
1146 | self._label = label_column
1147 | self._model_type = model_type
1148 | self._model_complexity = model_complexity
1149 | self.load_config_json()
1150 | self._run = True #Run flag
1151 |
1152 | #Prechecks
1153 | if self.prechecks() == False:
1154 | raise Exception("Error: Precheck failed for Training start")
1155 |
1156 | #Run HPT
1157 | self.search_hpt()
1158 |
1159 | #Run Trainining and Evaluation
1160 | self.start_train()
1161 |
1162 | class TFAuto():
1163 | def __init__(self, train_data_path, test_data_path, path_root='/tfx'):
1164 | '''
1165 | Initialize TFAuto engine
1166 | train_data_path: Path where Training data is stored
1167 | test_data_path: Path where Test / Eval data is stored
1168 | path_root: Directory for running TFAuto( Directory should NOT exist )
1169 | '''
1170 | ##Define all constants
1171 | self._tfx_root = os.path.join(os.getcwd(), path_root)
1172 | self._pipeline_root = os.path.join(self._tfx_root, 'pipelines'); # Join ~/tfx/pipelines/
1173 | self._metadata_db_root = os.path.join(self._tfx_root, 'metadata.db'); # Join ~/tfx/metadata.db
1174 | self._metadata = os.path.join(self._tfx_root, 'metadata'); # Join ~/tfx/metadata
1175 | self._log_root = os.path.join(self._tfx_root, 'logs');
1176 | self._model_root = os.path.join(self._tfx_root, 'model');
1177 | self._train_data_path = train_data_path
1178 | self._test_data_path = test_data_path
1179 |
1180 | self._input_fn_module_file = 'inputfn_trainer.py'
1181 | self._constants_module_file = 'constants_trainer.py'
1182 | self._model_trainer_module_file = 'model_trainer.py'
1183 |
1184 | #Instantiate other services
1185 | self.tfautils = TFAutoUtils(data_path=train_data_path, path_root=path_root)
1186 | self.tfadata = TFAutoData()
1187 | self.tfamodel = TFAutoModel(self._tfx_root, train_data_path, test_data_path)
1188 |
1189 | #Create all required directories
1190 | self.tfautils.create_directories()
1191 |
1192 | #Set interactive context
1193 | # self.context = InteractiveContext(pipeline_root=self._tfx_root)
1194 |
1195 | #Output
1196 | print("TF initialized...")
1197 | print("All paths setup at {}".format(self._tfx_root))
1198 |
1199 | def generate_config_json(self):
1200 | #Generate JSON for data modeling etc
1201 | config_dict = {}
1202 | config_json = os.path.join(self._tfx_root, 'config.json')
1203 | config_dict['root_path'] = self._tfx_root
1204 | config_dict['data_schema'] = self.tfadata.features_list
1205 | config_dict['len_train'] = self.tfadata._len_train
1206 | config_dict['ignore_features'] = ['ADD_FEATURES_TO_IGNORE_FROM_MODEL']
1207 | config_dict['file_headers'] = list(self.tfadata.file_headers)
1208 |
1209 | #Write JSON file
1210 | with open(config_json, 'w') as fp:
1211 | json.dump(config_dict, fp, indent = 4)
1212 |
1213 | def step_data_explore(self, viz=False):
1214 | '''
1215 | Method to automatically estimate schema of Data
1216 | Viz: (False) Is data visualization required ?
1217 | '''
1218 | self.pipeline = self.tfadata.run_initial(self._train_data_path, self._test_data_path, self._tfx_root, self._metadata_db_root, self.tfautils, viz)
1219 | self.generate_config_json()
1220 |
1221 | def step_model_build(self, label_column, model_type='REGRESSION', model_complexity=1):
1222 | '''
1223 | Method to automatically create models from data
1224 | Parameters
1225 | label_column: The feature to be used as Label
1226 | model_type: Either of 'REGRESSION', 'CLASSIFICATION'
1227 | model_complexity: 0 to 2 (0: Model without HPT, 1: Model with HPT, 2: Complexity 1 + Trainable Text Layer)
1228 | '''
1229 | # #Run Modeling steps
1230 | if self.tfadata._run == True:
1231 | print("Success: Started AutoML Training")
1232 | self.tfamodel.run_initial(label_column, model_type, model_complexity)
1233 | else:
1234 | print("Error: Please run Step 1 - step_data_explore")
1235 |
1236 | print("Success: Model Training complete. Exported to: {}".format(self._model_root + "/"))
1237 |
1238 | def step_model_whatif(self):
1239 | '''
1240 | Run What-IF tool for trained model
1241 | '''
1242 | # #Run Modeling steps
1243 | if self.tfadata._run == True:
1244 | self.tfamodel.call_wit()
1245 | else:
1246 | print("Error: Please run Step 2 - step_model_build")
1247 |
--------------------------------------------------------------------------------
/header.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/rafiqhasan/auto-tensorflow/ec80d21d2c88f308f567a11f4b3d820c9af1aa42/header.png
--------------------------------------------------------------------------------
/logo.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/rafiqhasan/auto-tensorflow/ec80d21d2c88f308f567a11f4b3d820c9af1aa42/logo.png
--------------------------------------------------------------------------------
/pyproject.toml:
--------------------------------------------------------------------------------
1 | [build-system]
2 | requires = [
3 | "setuptools>=42",
4 | "wheel"
5 | ]
6 | build-backend = "setuptools.build_meta"
7 |
--------------------------------------------------------------------------------
/setup.py:
--------------------------------------------------------------------------------
1 | ############################################################################################
2 | #Licensed under the Apache License, Version 2.0 (the "License");
3 | #you may not use this file except in compliance with the License.
4 | #You may obtain a copy of the License at
5 | #
6 | # https://www.apache.org/licenses/LICENSE-2.0
7 | #
8 | #Unless required by applicable law or agreed to in writing, software
9 | #distributed under the License is distributed on an "AS IS" BASIS,
10 | #WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
11 | #See the License for the specific language governing permissions and
12 | #limitations under the License.
13 | ############################################################################################
14 | import setuptools
15 |
16 | with open("README.md", "r", encoding="utf-8") as fh:
17 | long_description = fh.read()
18 |
19 | setuptools.setup(
20 | name="auto_tensorflow",
21 | version="1.3.4",
22 | author="Hasan Rafiq",
23 | description="""Build Low Code Automated Tensorflow, What-IF explainable models in just 3 lines of code. To make Deep Learning on Tensorflow absolutely easy for the masses with its low code framework and also increase trust on ML models through What-IF model explainability.""",
24 | long_description=long_description,
25 | long_description_content_type="text/markdown",
26 | license='Apache License 2.0',
27 | url="https://github.com/rafiqhasan/auto-tensorflow",
28 | packages = [
29 | "auto_tensorflow"
30 | ],
31 | include_package_data=True,
32 | install_requires=[
33 | "keras-tuner==1.0.4",
34 | "tensorflow_text==2.6.0",
35 | "tfx==1.4.0",
36 | "witwidget==1.8.0",
37 | "tensorflow==2.6.2",
38 | "tensorflow_hub==0.12.0",
39 | "tensorflow-metadata==1.4.0",
40 | "ipython==7.29.0",
41 | "tensorflow-estimator==2.6.0",
42 | "joblib==0.14.1",
43 | "tensorboard-plugin-wit==1.8.0",
44 | "tensorboard-data-server==0.6.1",
45 | "google-api-core==1.31.4",
46 | "google-cloud-aiplatform==1.10.0",
47 | "google-cloud==0.34.0",
48 | "apache-beam==2.34.0",
49 | "protobuf==3.19.5",
50 | "jupyterlab-widgets==3.0.3",
51 | "PyYAML==5.4.1",
52 | "pytz==2022.6",
53 | "tensorflow-model-analysis==0.35.0",
54 | "tensorflow-data-validation==1.4.0",
55 | "tensorboard==2.6.0",
56 | "six==1.15.0",
57 | "requests==2.28.1",
58 | "widgetsnbextension==3.6.1"
59 | ],
60 | classifiers=[
61 | "Programming Language :: Python :: 3",
62 | "Operating System :: OS Independent",
63 | ],
64 | )
65 |
--------------------------------------------------------------------------------
/tutorials/TFAuto_|_Classification.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "name": "TFAuto | Demo and Library testing.ipynb",
7 | "provenance": [],
8 | "collapsed_sections": [],
9 | "authorship_tag": "ABX9TyMvDPKTWtiaNqhEWo/BgCXR",
10 | "include_colab_link": true
11 | },
12 | "kernelspec": {
13 | "name": "python3",
14 | "display_name": "Python 3"
15 | },
16 | "language_info": {
17 | "name": "python"
18 | }
19 | },
20 | "cells": [
21 | {
22 | "cell_type": "markdown",
23 | "metadata": {
24 | "id": "view-in-github",
25 | "colab_type": "text"
26 | },
27 | "source": [
28 | "
"
29 | ]
30 | },
31 | {
32 | "cell_type": "code",
33 | "metadata": {
34 | "id": "qfbOrnbYi1CF"
35 | },
36 | "source": [
37 | "# !pip install git+https://github.com/rafiqhasan/auto-tensorflow.git\n",
38 | "!pip install auto-tensorflow"
39 | ],
40 | "execution_count": null,
41 | "outputs": []
42 | },
43 | {
44 | "cell_type": "code",
45 | "metadata": {
46 | "id": "JPfi5hIckYxY"
47 | },
48 | "source": [
49 | "from auto_tensorflow.tfa import TFAuto"
50 | ],
51 | "execution_count": null,
52 | "outputs": []
53 | },
54 | {
55 | "cell_type": "markdown",
56 | "metadata": {
57 | "id": "UwPONJGzkSmE"
58 | },
59 | "source": [
60 | "### **Download data**"
61 | ]
62 | },
63 | {
64 | "cell_type": "code",
65 | "metadata": {
66 | "id": "rbTX-qXJi7dd"
67 | },
68 | "source": [
69 | "!rm -rf data.*\n",
70 | "!rm -rf /content/*.png\n",
71 | "!rm -rf *trainer.py\n",
72 | "!rm -r /content/train_data\n",
73 | "!rm -r /content/test_data\n",
74 | "!rm -rf untitled_project\n",
75 | "!mkdir /content/train_data\n",
76 | "!mkdir /content/test_data\n",
77 | "!sudo rm -r /content/tfauto"
78 | ],
79 | "execution_count": null,
80 | "outputs": []
81 | },
82 | {
83 | "cell_type": "code",
84 | "metadata": {
85 | "id": "PY1LdrO-kWa3"
86 | },
87 | "source": [
88 | "# GRIR\n",
89 | "%%bash\n",
90 | "cd /content/train_data\n",
91 | "wget https://raw.githubusercontent.com/rafiqhasan/AI_DL_ML_Repo/master/Datasets/GRIR/train.csv\n",
92 | "\n",
93 | "cd ../test_data\n",
94 | "wget https://raw.githubusercontent.com/rafiqhasan/AI_DL_ML_Repo/master/Datasets/GRIR/eval.csv"
95 | ],
96 | "execution_count": null,
97 | "outputs": []
98 | },
99 | {
100 | "cell_type": "code",
101 | "metadata": {
102 | "id": "az8gJw7NlnCZ"
103 | },
104 | "source": [
105 | "##Initialize TFAuto with root and Data path\n",
106 | "tfa = TFAuto(train_data_path='/content/train_data/', test_data_path='/content/test_data/', path_root='/content/tfauto')"
107 | ],
108 | "execution_count": null,
109 | "outputs": []
110 | },
111 | {
112 | "cell_type": "code",
113 | "metadata": {
114 | "id": "_ddQF8rylpKS"
115 | },
116 | "source": [
117 | "##Step 1\n",
118 | "##Run Data setup -> Infer Schema, find anomalies, create profile and show viz\n",
119 | "tfa.step_data_explore(viz=False)"
120 | ],
121 | "execution_count": null,
122 | "outputs": []
123 | },
124 | {
125 | "cell_type": "code",
126 | "metadata": {
127 | "id": "NSj07bKPlryx"
128 | },
129 | "source": [
130 | "##Step 2\n",
131 | "##Run Model Training ->\n",
132 | "tfa.step_model_build(label_column = 'STATUS', model_type='CLASSIFICATION') ##--> Default model_complexity\n",
133 | "# tfa.step_model_build(label_column = 'STATUS', model_type='CLASSIFICATION', model_complexity = 0) ##--> Model_complexity = 0 ( Simple model - No HPT )"
134 | ],
135 | "execution_count": null,
136 | "outputs": []
137 | },
138 | {
139 | "cell_type": "code",
140 | "metadata": {
141 | "id": "NpOsECxjl3MH"
142 | },
143 | "source": [
144 | "##Step 3\n",
145 | "##Show model What-If Tool\n",
146 | "tfa.step_model_whatif()"
147 | ],
148 | "execution_count": null,
149 | "outputs": []
150 | },
151 | {
152 | "cell_type": "code",
153 | "metadata": {
154 | "id": "MJk0dJ1PmBeq"
155 | },
156 | "source": [
157 | "#Check signature\n",
158 | "!saved_model_cli show --dir \"/content/tfauto/model/1\" --all"
159 | ],
160 | "execution_count": null,
161 | "outputs": []
162 | },
163 | {
164 | "cell_type": "markdown",
165 | "metadata": {
166 | "id": "CDczgmy4knkU"
167 | },
168 | "source": [
169 | "## **Tensorflow Model Serving**"
170 | ]
171 | },
172 | {
173 | "cell_type": "code",
174 | "metadata": {
175 | "id": "At1xykbBqiEZ"
176 | },
177 | "source": [
178 | "!apt-get remove tensorflow-model-server\n",
179 | "!echo \"deb http://storage.googleapis.com/tensorflow-serving-apt stable tensorflow-model-server tensorflow-model-server-universal\" | tee /etc/apt/sources.list.d/tensorflow-serving.list && \\\n",
180 | "curl https://storage.googleapis.com/tensorflow-serving-apt/tensorflow-serving.release.pub.gpg | apt-key add -\n",
181 | "!apt update\n",
182 | "\n",
183 | "!apt-get install tensorflow-model-server"
184 | ],
185 | "execution_count": null,
186 | "outputs": []
187 | },
188 | {
189 | "cell_type": "code",
190 | "metadata": {
191 | "id": "QgWjBqkvks3D"
192 | },
193 | "source": [
194 | "###Start Tensorflow server\n",
195 | "# %%bash --bg \n",
196 | "# export TF_CPP_MIN_VLOG_LEVEL=0\n",
197 | "\n",
198 | "%%bash --bg \n",
199 | "nohup tensorflow_model_server \\\n",
200 | " --rest_api_port=8501 \\\n",
201 | " --model_name=model \\\n",
202 | " --model_base_path=\"/content/tfauto/model\" >server.log 2>&1"
203 | ],
204 | "execution_count": null,
205 | "outputs": []
206 | },
207 | {
208 | "cell_type": "code",
209 | "metadata": {
210 | "id": "SU3J6T-zk1UR"
211 | },
212 | "source": [
213 | "!tail server.log"
214 | ],
215 | "execution_count": null,
216 | "outputs": []
217 | },
218 | {
219 | "cell_type": "code",
220 | "metadata": {
221 | "id": "BMG1-nA7k3fn"
222 | },
223 | "source": [
224 | "import json\n",
225 | "import requests\n",
226 | "\n",
227 | "#Create payload\n",
228 | "data_py = {\"inputs\":{'WERKS': [[\"ML01\"]],\n",
229 | " 'DIFGRIRD': [[-80]],\n",
230 | " 'SCENARIO': [[3]],\n",
231 | " 'TOTIRQTY': [[80]],\n",
232 | " 'VSTATU': [[1]],\n",
233 | " 'EKGRP': [[\"A\"]],\n",
234 | " 'TOTGRQTY': [[0]],\n",
235 | " 'VPATD': [[30]],\n",
236 | " 'EKORG': [[1]],\n",
237 | " 'NODLGR': [[0]],\n",
238 | " 'DIFGRIRV': [[-38100]],\n",
239 | " 'NODLIR': [[90]],\n",
240 | " 'KTOKK': [[1]]}}\n",
241 | "\n",
242 | "data = json.dumps(data_py)\n",
243 | "print(\"payload: \", data)\n",
244 | "\n",
245 | "#Run request on TMS\n",
246 | "headers = {\"content-type\": \"application/json\"}\n",
247 | "json_response = requests.post('http://localhost:8501/v1/models/model:predict', data=data, headers=headers)\n",
248 | "json_response.text"
249 | ],
250 | "execution_count": null,
251 | "outputs": []
252 | },
253 | {
254 | "cell_type": "code",
255 | "metadata": {
256 | "id": "W441stydlIh0"
257 | },
258 | "source": [
259 | ""
260 | ],
261 | "execution_count": null,
262 | "outputs": []
263 | }
264 | ]
265 | }
--------------------------------------------------------------------------------
/tutorials/TFAuto_|_Regression.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "name": "TFAuto | Demo and Library testing.ipynb",
7 | "provenance": [],
8 | "collapsed_sections": [],
9 | "authorship_tag": "ABX9TyMuQ65ItlfK8se1uePCq6eE",
10 | "include_colab_link": true
11 | },
12 | "kernelspec": {
13 | "name": "python3",
14 | "display_name": "Python 3"
15 | },
16 | "language_info": {
17 | "name": "python"
18 | }
19 | },
20 | "cells": [
21 | {
22 | "cell_type": "markdown",
23 | "metadata": {
24 | "id": "view-in-github",
25 | "colab_type": "text"
26 | },
27 | "source": [
28 | "
"
29 | ]
30 | },
31 | {
32 | "cell_type": "code",
33 | "metadata": {
34 | "id": "qfbOrnbYi1CF"
35 | },
36 | "source": [
37 | "# !pip install git+https://github.com/rafiqhasan/auto-tensorflow.git\n",
38 | "!pip install auto-tensorflow"
39 | ],
40 | "execution_count": null,
41 | "outputs": []
42 | },
43 | {
44 | "cell_type": "code",
45 | "metadata": {
46 | "id": "JPfi5hIckYxY"
47 | },
48 | "source": [
49 | "from auto_tensorflow.tfa import TFAuto"
50 | ],
51 | "execution_count": null,
52 | "outputs": []
53 | },
54 | {
55 | "cell_type": "markdown",
56 | "metadata": {
57 | "id": "UwPONJGzkSmE"
58 | },
59 | "source": [
60 | "### **Download data**"
61 | ]
62 | },
63 | {
64 | "cell_type": "code",
65 | "metadata": {
66 | "id": "rbTX-qXJi7dd"
67 | },
68 | "source": [
69 | "!rm -rf data.*\n",
70 | "!rm -rf /content/*.png\n",
71 | "!rm -rf *trainer.py\n",
72 | "!rm -r /content/train_data\n",
73 | "!rm -r /content/test_data\n",
74 | "!rm -rf untitled_project\n",
75 | "!mkdir /content/train_data\n",
76 | "!mkdir /content/test_data\n",
77 | "!sudo rm -r /content/tfauto"
78 | ],
79 | "execution_count": null,
80 | "outputs": []
81 | },
82 | {
83 | "cell_type": "code",
84 | "metadata": {
85 | "id": "PY1LdrO-kWa3"
86 | },
87 | "source": [
88 | "# # House price\n",
89 | "%%bash\n",
90 | "cd /content/train_data\n",
91 | "wget https://raw.githubusercontent.com/rafiqhasan/AI_DL_ML_Repo/master/Datasets/house_price/data.csv\n",
92 | "\n",
93 | "cd ../test_data\n",
94 | "wget https://raw.githubusercontent.com/rafiqhasan/AI_DL_ML_Repo/master/Datasets/house_price/data.csv ##Taken same data for demonstration purposes only"
95 | ],
96 | "execution_count": null,
97 | "outputs": []
98 | },
99 | {
100 | "cell_type": "code",
101 | "metadata": {
102 | "id": "az8gJw7NlnCZ"
103 | },
104 | "source": [
105 | "##Initialize TFAuto with root and Data path\n",
106 | "tfa = TFAuto(train_data_path='/content/train_data/', test_data_path='/content/test_data/', path_root='/content/tfauto')"
107 | ],
108 | "execution_count": null,
109 | "outputs": []
110 | },
111 | {
112 | "cell_type": "code",
113 | "metadata": {
114 | "id": "_ddQF8rylpKS"
115 | },
116 | "source": [
117 | "##Step 1\n",
118 | "##Run Data setup -> Infer Schema, find anomalies, create profile and show viz\n",
119 | "tfa.step_data_explore(viz=False)"
120 | ],
121 | "execution_count": null,
122 | "outputs": []
123 | },
124 | {
125 | "cell_type": "code",
126 | "metadata": {
127 | "id": "NSj07bKPlryx"
128 | },
129 | "source": [
130 | "##Step 2\n",
131 | "##Run Model Training ->\n",
132 | "tfa.step_model_build(label_column = 'price', model_type='REGRESSION') ##--> Default model_complexity\n",
133 | "# tfa.step_model_build(label_column = 'price', model_type='REGRESSION', model_complexity=0) ##--> Model_complexity = 0 ( Simple model - No HPT )"
134 | ],
135 | "execution_count": null,
136 | "outputs": []
137 | },
138 | {
139 | "cell_type": "code",
140 | "metadata": {
141 | "id": "NpOsECxjl3MH"
142 | },
143 | "source": [
144 | "##Step 3\n",
145 | "##Show model What-If Tool\n",
146 | "tfa.step_model_whatif()"
147 | ],
148 | "execution_count": null,
149 | "outputs": []
150 | },
151 | {
152 | "cell_type": "code",
153 | "metadata": {
154 | "id": "MJk0dJ1PmBeq"
155 | },
156 | "source": [
157 | "#Check signature\n",
158 | "!saved_model_cli show --dir \"/content/tfauto/model/1\" --all"
159 | ],
160 | "execution_count": null,
161 | "outputs": []
162 | },
163 | {
164 | "cell_type": "markdown",
165 | "metadata": {
166 | "id": "CDczgmy4knkU"
167 | },
168 | "source": [
169 | "## **Tensorflow Model Serving**"
170 | ]
171 | },
172 | {
173 | "cell_type": "code",
174 | "metadata": {
175 | "id": "At1xykbBqiEZ"
176 | },
177 | "source": [
178 | "!apt-get remove tensorflow-model-server\n",
179 | "!echo \"deb http://storage.googleapis.com/tensorflow-serving-apt stable tensorflow-model-server tensorflow-model-server-universal\" | tee /etc/apt/sources.list.d/tensorflow-serving.list && \\\n",
180 | "curl https://storage.googleapis.com/tensorflow-serving-apt/tensorflow-serving.release.pub.gpg | apt-key add -\n",
181 | "!apt update\n",
182 | "\n",
183 | "!apt-get install tensorflow-model-server"
184 | ],
185 | "execution_count": null,
186 | "outputs": []
187 | },
188 | {
189 | "cell_type": "code",
190 | "metadata": {
191 | "id": "QgWjBqkvks3D"
192 | },
193 | "source": [
194 | "###Start Tensorflow server\n",
195 | "# %%bash --bg \n",
196 | "# export TF_CPP_MIN_VLOG_LEVEL=0\n",
197 | "\n",
198 | "%%bash --bg \n",
199 | "nohup tensorflow_model_server \\\n",
200 | " --rest_api_port=8502 \\\n",
201 | " --model_name=model \\\n",
202 | " --model_base_path=\"/content/tfauto/model\" >server.log 2>&1"
203 | ],
204 | "execution_count": null,
205 | "outputs": []
206 | },
207 | {
208 | "cell_type": "code",
209 | "metadata": {
210 | "id": "SU3J6T-zk1UR"
211 | },
212 | "source": [
213 | "!tail server.log"
214 | ],
215 | "execution_count": null,
216 | "outputs": []
217 | },
218 | {
219 | "cell_type": "code",
220 | "metadata": {
221 | "id": "BMG1-nA7k3fn"
222 | },
223 | "source": [
224 | "import json\n",
225 | "import requests\n",
226 | "\n",
227 | "#Create payload\n",
228 | "data_py = {\"inputs\":{'bedrooms': [[3]],\n",
229 | " 'bathrooms': [[2.0]],\n",
230 | " 'sqft_living': [[1180]],\n",
231 | " 'sqft_lot': [[5650]],\n",
232 | " 'floors': [[2.0]],\n",
233 | " 'waterfront': [[1]],\n",
234 | " 'view': [[1]],\n",
235 | " 'condition': [[3]],\n",
236 | " 'grade': [[7]],\n",
237 | " 'sqft_above': [[1180]],\n",
238 | " 'sqft_basement': [[0]],\n",
239 | " 'yr_built': [[1997]],\n",
240 | " 'sqft_living15': [[1340]],\n",
241 | " 'sqft_lot15': [[5650]]\n",
242 | " }}\n",
243 | " \n",
244 | "data = json.dumps(data_py)\n",
245 | "print(\"payload: \", data)\n",
246 | "\n",
247 | "#Run request on TMS\n",
248 | "headers = {\"content-type\": \"application/json\"}\n",
249 | "json_response = requests.post('http://localhost:8502/v1/models/model:predict', data=data, headers=headers)\n",
250 | "json_response.text"
251 | ],
252 | "execution_count": null,
253 | "outputs": []
254 | },
255 | {
256 | "cell_type": "code",
257 | "metadata": {
258 | "id": "W441stydlIh0"
259 | },
260 | "source": [
261 | ""
262 | ],
263 | "execution_count": null,
264 | "outputs": []
265 | }
266 | ]
267 | }
--------------------------------------------------------------------------------