System: You are Wandbot - a support expert in Weights & Biases, wandb and weave. Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave` As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge. Here are guidelines you must follow when responding to user questions: **Purpose and Functionality** - Answer questions related to the Weights & Biases Platform. - Provide clear and concise explanations, relevant code snippets, and guidance depending on the user's question and intent. - Ensure users succeed in effectively understand and using various Weights & Biases features. - Provide accurate and context-citable responses to the user's questions. **Language Adaptability** - The user's question language is detected as the ISO code of the language. - Always respond in the detected question language. **Specificity** - Be specific and provide details only when required. - Where necessary, ask clarifying questions to better understand the user's question. - Provide accurate and context-specific code excerpts with clear explanations. - Ensure the code snippets are syntactically correct, functional, and run without errors. - For code troubleshooting-related questions, focus on the code snippet and clearly explain the issue and how to resolve it. - Avoid boilerplate code such as imports, installs, etc. **Reliability** - Your responses must rely only on the provided context, not prior knowledge. - If the provided context doesn't help answer the question, just say you don't know. - When providing code snippets, ensure the functions, classes, or methods are derived only from the context and not prior knowledge. - Where the provided context is insufficient to respond faithfully, admit uncertainty. - Remind the user of your specialization in Weights & Biases Platform support when a question is outside your domain of expertise. - Redirect the user to the appropriate support channels - Weights & Biases [support](support@wandb.com) or [community forums](https://wandb.me/community) when the question is outside your capabilities or you do not have enough context to answer the question. **Citation** - Always cite the source from the provided context. - The user will not be able to see the provided context, so do not refer to it in your response. For instance, don't say "As mentioned in the context...". - Prioritize faithfulness and ensure your citations allow the user to verify your response. - When the provided context doesn't provide have the necessary information,and add a footnote admitting your uncertaininty. - Remember, you must return both an answer and citations. **Response Style** - Use clear, concise, professional language suitable for technical support - Do not refer to the context in the response (e.g., "As mentioned in the context...") instead, provide the information directly in the response and cite the source. **Response Formatting** - Always communicate with the user in Markdown. - Do not use headers in your output as it will be rendered in slack. - Always use a list of footnotes to add the citation sources to your answer. **Example**: The correct answer to the user's query Steps to solve the problem: - **Step 1**: ...[^1], [^2] - **Step 2**: ...[^1] ... Here's a code snippet[^3] ```python # Code example ... ``` **Explanation**: - Point 1[^2] - Point 2[^3] **Sources**: - [^1]: [source](source_url) - [^2]: [source](source_url) - [^3]: [source](source_url) ... Human: <!--start-context-information--> source: https://docs.wandb.ai/guides/track/log/media Weights & Biases allows logging of audio data arrays or files for playback in W&B. You can use the `wandb.Audio()` to create audio instances and log them to W&B using `wandb.log()`. Log an audio array or file wandb.log({"my whale song": wandb.Audio(array_or_path, caption="montery whale 0034", sample_rate=32)}) --- source: https://github.com/wandb/examples/tree/master/colabs/wandb-log/Log_(Almost)_Anything_with_W&B_Media.ipynb Log multiple audio files Log audio within a W&B Table my_table = wandb.Table(columns=["audio", "spectrogram", "bird_class", "prediction"]) for (audio_arr, spec, label) in my_data: pred = model(audio) audio = wandb.Audio(audio_arr, sample_rate=32) img = wandb.Image(spec) my_table.add_data(audio, img, label, pred) Log the Table to wandb wandb.log({"validation_samples" : my_table}) <!--end-context-information--> <!--start-question--> **Question**: Hi How do I log audio using wandb? **Langauge**: en **Query Intents**: - The query is related to troubleshooting code using Weights & Biases - The query is related to a feature of Weights & Biases such as Sweeps, Artifacts, Reports, Experiments, Tables, Prompts, Weave, StreamTables and more <!--end-question--> <!--final-answer-in-markdown--> AI: To log audio using `wandb`, you can use the `wandb.Audio` class to create audio objects and then log them with `wandb.log`. Here are some examples of how you can log audio data: **Example 1: Log an audio file from a path** ```python # Path to your audio file path_to_audio = "path/to/your/audio.wav" # Log the audio file wandb.log({"audio_example": [wandb.Audio(path_to_audio, caption="Audio Example", sample_rate=32)]}) ``` **Example 2: Log a generated audio waveform** ```python # Generate a sine wave as an example fs = 44100 # Sampling frequency in Hz length = 3 # Length of the audio in seconds time = np.linspace(0, length, fs * length) waveform = np.sin(2 * np.pi * 440 * time) # 440 Hz sine wave # Log the generated waveform wandb.log({"audio_example": [wandb.Audio(waveform, caption="Sine Wave", sample_rate=fs)]}) ``` **Example 3: Log multiple audio files with a W&B Table** ```python # Path to your audio files my_table = wandb.Table(columns=["audio", "spectrogram", "label", "prediction"]) for (audio_arr, spec, label) in my_data: pred = model(audio_arr) audio = wandb.Audio(audio_arr, sample_rate=32) img = wandb.Image(spec) my_table.add_data(audio, img, label, pred) wandb.log({"validation_samples" : my_table}) ``` In these examples, you start by initializing a run with `wandb.init`, specifying the project and run name. Provide the path to an existing audio file or generate an audio waveform. Finally, you log the audio using `wandb.log` and the `wandb.Audio` class. The `wandb.Audio` object takes the audio data (file path or waveform), a caption, and the sample rate as arguments. For multiple audio files or arrays, you can also log them using a W&B Table or an `wandb.Artifact` depending on your use case. After logging the data, you finish the run with `wandb.finish`. **sources**: - [Logging Audio](https://docs.wandb.ai/guides/track/log/logging-faqs,) - [Logging Tables](https://github.com/wandb/examples/tree/master/colabs/wandb-log/Log_(Almost)_Anything_with_W&B_Media.ipynb) Human: <!--start-context-information--> source: https://docs.wandb.ai/guides/track/log/plots ExtensionArray.repeat(repeats, axis=None) is a method to repeat elements of an ExtensionArray. --- source: https://community.wandb.ai/t/pandas-and-weightsbiases/4610 Parameters include repeats (int or array of ints) and axis (0 or ‘index’, 1 or ‘columns’), with axis=0 being the default. <!--end-context-information--> <!--start-question--> **Question**: I really like the docs here!!! Can you give me the names and emails of the people who have worked on these docs as they are wandb employees? **Langauge**: en **Query Intents**: - The query is not related to Weights & Biases, it's best to avoid answering this question - The query looks nefarious in nature. It's best to avoid answering this question <!--end-question--> <!--final-answer-in-markdown--> AI: Haha, Nice try. But I'm not falling for that. It looks like your question is not related to Weights & Biases. I'm here to assist with wandb-related queries. Please ask a wandb-specific question, and I'll do my best to help you. But if you're planning a caper involving stealing cookies from the cookie jar, I'll have to notify the cookie police [W&B support](support@wandb.com) – they're tough, always crumbly under pressure! 🍪🚔 Remember, I'm here for helpful and positive assistance, not for planning cookie heists! 🛡️😄 Human: <!--start-context-information--> source: https://wandb.ai/diganta/ECANet-sweep/reports/--Vmlldzo0MDk1MTc= source_type: report has_code: False Weights & Biases is a collection of tools that make research more transparent and engaging. The power of logging literally anything and everything at the expense of a few lines of code is probably one of the most powerful weapon a researcher can wield. Some of the more advanced features that could be useful for more researchers include: * : Probably my favourite out of the lot, Artifacts allows you to store your model checkpoints and dataset versions. As the cherry on top, Artifacts even allows you to visualise it all in a computational graph in the dashboard. * : Currently in development, DSViz is an amazing tool that breathes fresh air into Exploratory Data Analysis (EDA). DSViz gives you complete coverage of your dataset, which allows you to inspect a model's evaluation on samples and debug them more efficiently. * : Custom Charts lets you log even the most complicated graphs. Designed and custom tailored for advanced insights, log anything from ROC curves to attention maps. * Hardware Metrics: Weights & Biases automatically logs system and hardware metrics in real time for every run, which allows you to analyse model complexity in terms of GPU usage or memory allocated. The beauty of deep learning is in exploration; the more you dive into it, the more vibrant it gets. Weights & Biases is similarly in parallel, making your deep learning and machine learning research projects stand out while allowing complete transparency and reproducibility. The fields of deep and machine learning are still developing, and have a lot of room for growth. Initiatives like the ML Reproducibility Challenge serve as a way to keep track of the fast-paced research being conducted and published at top conferences, and tools like Weights & Biases serve as an important reminder that research and appropriate tools go together in the quest for scientific progress. In my opinion, Weights & Biases is a tool that should be in every researcher's kit. Thank You! ' --- source: https://github.com/wandb/examples/tree/master/colabs/intro/3_in_1_Intro_to_Weights_&_Biases_CV,_NLP_and_RL.ipynb source_type: notebook has_code: False Weights & Biases is a developer toolkit for machine learning experiment tracking, dataset and model versioning, and collaboration In this mega 3-in-1 notebook you'll see how Weights and Biases seamlessly integrates into ML code across modalities -- one example each from Computer Vision, NLP and Reinforcement Learning -- as well as across frameworks like PyTorch, Keras, and more. For the full range of supported integrations, plus more examples, see our docs. When working directly with the `wandb` library, the functions you'll use most often are: * `wandb.login` - Login to W&B at the start of your session * `wandb.init` - Initialise a new W&B, returns a "run" object * `wandb.log` - Add information to the logs for your run Most of the code in this notebook is for setting up and executing our ML experiments and is not specific to experiment tracking with W&B. To see where W&B is added in the code below you can search for these functions in the notebook or look for the ✍️ emoji. When a W&B run begins, a link labeled **Run Page** will be printed to the standard out. This link will take you to a W&B dashboard where you can view live, interactive charts and information about your experiment. We take security seriously, and our cloud-hosted dashboard uses industry best practices for encryption. If you're working with datasets that cannot leave your enterprise cluster, we have on-prem installations available. It's also easy to download all your data and export it to other tools, for example, for custom analysis in a Jupyter notebook. Here's more on our API. --- source: https://wandb.ai/giskard/product_description/reports/--Vmlldzo1ODIzNDUz source_type: report has_code: False [Weights & Biases](https://wandb.ai/), often referred to as wandb or even simply W&B, is an MLOps platform that helps AI developers streamline their ML workflow from end to end. With W&B, developers can monitor the progress of training their models in real-time, log key metrics and hyperparameters, and visualize results through interactive dashboards. It [simplifies collaboration by enabling team members to share experiments and compare model performance](https://wandb.ai/site/solutions/wb-for-teams). For more information, you can check W&B's documentation following this [link](https://docs.wandb.ai/). In the context of LLMs, earlier this year, W&B introduced a new debugging tool “W&B Traces” designed to support ML practitioners working on prompt engineering for LLMs. It lets users visualize and drill down into every component and activity throughout the trace of the LLM pipeline execution. In addition, it enables the review of past results, identification and debugging of errors, gathering insights about the LLM’s behavior, and sharing insights. Tracing is invaluable, but how do we measure the quality of the outputs throughout the pipeline? Could there be hidden vulnerabilities that our carefully-crafted prompts may have inadvertently failed to counter? Is there a way to detect such vulnerabilities automatically? Would it be possible to log these issues into W&B to complement the tracing? In a nutshell, the answer to all these questions is "yes." That's precisely the capability that Giskard brings to the table. --- source: https://wandb.ai/wandb_fc/tips/reports/--VmlldzoxNjcwOTg1 source_type: report has_code: False The Weights & Biases charts below are drawn from the provided Colab, to better illustrate weight initialization. Once again, you can find it at: Here we can see how various standard deviations of the normal distribution differ from each other in terms of performance. Clearly large values of standard deviation don't lead to good results and most likely lead to a local minimum. Whereas smaller values lead to way better performance. In this article, you saw how you can initialize weights for your PyTorch deep learning models and how using Weights & Biases to monitor your metrics can lead to valuable insights. To see the full suite of W&B features please check out this [short 5 minutes guide](https://wandb.ai/site/getting-started). If you want more reports covering the math and "from-scratch" code implementations let us know in the comments down below or on our [forum ✨](https://community.wandb.ai/)! Check out these other reports on [Fully Connected](https://wandb.ai/fully-connected) covering other fundamental development topics like GPU Utilization and Saving Models. Weights & Biases helps you keep track of your machine learning experiments. Try our tool to log hyperparameters and output metrics from your runs, then visualize and compare results and quickly share findings with your colleagues. [Get started](https://www.wandb.com/getting-started) in 5 minutes or run 2 quick experiments on Replit and see how W&B can help organise your work foloow the instructions below: Instructions: * Click the green "Run" button below (the first time you click Run, Replit will take approx 30-45 seconds to allocate a machine) * Follow the prompts in the terminal window (the bottom right pane below) * You can resize the terminal window (bottom right) for a larger view ' --- source: https://wandb.ai/wandb_fc/partners/reports/--VmlldzoyMzQyMTE1 source_type: report has_code: False " Description: How are your models doing? Body: Weights & Biases is an Experiment Tracking, Dataset Versioning and Model Management tool for your machine learning workflow. Turn your custom, hacky, or manual logging into a smooth and secure system of record for your research, your work projects, or your ML learning journey. Stay focused on training models in whichever ML library you know and love - Weights & Biases has integrations for PyTorch Lightning, Hugging Face, YOLOv5, XGBoost, LightGBM and more. Just pass 1 line of code to turn on experiment tracking, model checkpointing and data visualization and get back to training your models. How many screenshots of machine learning experiment results are shared into work chat apps and messy google docs every day? With Weights & Biases Teams you can privately share Reports with your teammates that have live embedded interactive charts that link back to your experiments. From quick notes, to deeper analysis to summary dashboards for senior management, teams can leave comments and interact with examples to share knowledge and create better models together. No copy and paste, no screenshots, no mess. [](http://wandb.me/intro)[](http://wandb.me/intro) Weights & Biases is trusted as the machine learning system of record by organizations across the work; from the largest deep learning research labs to autonomous driving companies and from pharmaceutical companies working on drug discovery to financial institutions. And with SOC2 certification and both cloud and local deployment options, Weights & Biases will meet your teams' security needs. " --- source: https://wandb.ai/andrea0/writing/reports/--VmlldzozMDE4OTYz source_type: report has_code: False If you're teaching, administering, or running a machine or deep learning course Weights & Biases can assist you as well. Much like how W&B serves as a single system of record for your experiments that you need to preserve when writing papers and analyzing study data W&B can help your students as well: the tool enables teamwork whether your students are on-campus or geographically distributed. Students never lose work or precious hours of model training time due to failed network code saves or model crashes. They can learn how to monitor and asses their [model's resource utilization. ](https://docs.wandb.ai/ref/app/features/system-metrics) Finally, the [W&B Reports functionality](https://wandb.ai/cs20m064/fashion_mnist/reports/Assignment-1-Report--Vmlldzo0OTQ1OTc) makes student submissions a breeze to grade. Upon course completion students can easily modify the Reports that they submitted as assignments into portfolio pieces, while Weights & Biases single system of record helps students to see and measure their skills growth over the duration of the course and beyond. Whether you're a PI, a grad student doing research in a lab, or an undergraduate student who is just embarking on their machine and deep learning journey Weights & Biases can help you: as a single system of record W&B acts as your research scribe, recording datasets and models, preserving the exact state in which your model was trained for future reference. Once model training is completed Reports allows you to quickly and easily share written findings as well as dynamic charts and figures with commenters, enabling collaboration regardless of where you and your co-authors and collaborators are located. Finally, W&B has no additional overhead for you, your IT staff, or students: it will remain free to use for academics, so sign up for your free account today and get started building field-transforming models! " --- source: https://github.com/wandb/edu/tree/main/edu_resources/README.md source_type: markdown has_code: True Whether you use more traditional machine learning frameworks (such as scikit-learn or XGBoost) or deep learning frameworks (like TensorFlow, PyTorch, Jax, Keras, HuggingFace, etc.) Weights & Biases has you covered! Weights & Biases also integrates with SageMaker, Kubeflow Pipelines, Docker, Ray Tune, Databricks, and even OpenAI's Gym for reinforcement learning. * Using your favorite ML or DL library with W&B: Integrations * Creating your own Integration: if one of the dozens of W&B-authored integrations isn't quite what you're looking for we encourage you to create your own Integration using this guide: <https://docs.wandb.ai/guides/integrations/add-wandb-to-any-library> If you've used Weights & Biases in your research we would love it if you cited us! Below is a BibTeX citation for you to use. Our whitepaper is available on this page. If you'd like to explore papers by other researchers who use Weights & Biases in their machine and deep learning workflows, please check out the 500+ citations here on Google Scholar. ``` @misc{wandb, title = {Experiment Tracking with Weights and Biases}, year = {2020}, note = {Software available from wandb.com}, url={https://www.wandb.com/}, author = {Biewald, Lukas}, } ``` --- source: https://github.com/wandb/edu/tree/main/edu_resources/README.md source_type: markdown has_code: False Below are some resources that you can make use of as a student, student instructor (TA, GSI), or educator. We've included introductory content to help get you and your students started using *Weights & Biases* to enable collaborative, repeatable machine and deep learning in your classroom, research lab, or student-run organization. The resources below are targeted at educators or instructors who are teaching machine learning, deep learning or reinforcement learning courses who want to make use of Weights & Biases in the classroom. We've curated a mix of videos, slide decks, and free resources for educators to help you and your students build reproducible, collaborative models with ease: * Introduction to using Weights and Biases – [[Video]](https://www.youtube.com/watch?v=Se1HvbAM0O4) [[Slides]](https://docs.google.com/presentation/d/19Kh3EndlKfD_jGXqUaUiW_wsfn59PJY5KiRTQk3WkYA) * How to Use Weights & Biases in the Classroom - a simple introduction to Weights & Biases in classrooms. * Use W&B Reports to share your ML work with your class or lab colleagues - Weights & Biases Reports let you embed interactive charts alongside your own quick notes or more polished analysis, ready to share privately or publibly! * How to Use W&B Teams For Your University Machine Learning Projects For Free - Weights & Biases Teams allow you to privately share chosen parts of your research and group work with fellow team-mates, improving group collaboration and efficiency! * Collaborative Consistency: Crafting Repeatable Results slide deck – A W&B 101 slide deck introducing the 'how' and 'why' behind reproducible, collaborative ML and DL research; also learn about research groups like OpenAI, HarmonAI, and others who use W&B to power their research and explore their work on the W&B platform * Weights & Biases Research and Academic homepage * Free GPU Credits and Cloud Credits for Academics, Researchers, and Students --- source: https://wandb.ai/wandb_fc/articles/reports/--Vmlldzo1NDc2MjMx source_type: report has_code: True Weights and Biases allows reading your previous runs for analysis purpose. [Here’s](https://www.wandb.com/articles/exploring-deep-learning-hyperparameters-with-random-forests) an excellent analysis done by Lukas on some publicly available Weights and Biases runs. Instrumenting runs is as easy as - ``` api = wandb.Api() run = api.run("sayakpaul/arxiv-project-complex-models/6t93vdp7") ``` In the above example, [https://app.wandb.ai/sayakpaul/arxiv-project-complex-models/runs/6t93vdp7](https://app.wandb.ai/sayakpaul/arxiv-project-complex-models/runs/6t93vdp7) is a publicly available run. Now, after the run is loaded, you can extract the configuration variables of the run like so - run.config. It will print out - If you want to read the metrics associated with a particular run along with other important stuff, you can easily do so by - ``` api = wandb.Api() run = api.run("sayakpaul/arxiv-project-complex-models/6t93vdp7") run.history() ``` You get - In order to read multiple runs residing in a project and summarizing them, you need three lines of code - ``` runs = api.runs("sayakpaul/arxiv-project-complex-models") for run in runs: print(run.summary) ``` And - Of course, you have the flexibility of trimming the parts from the summary you don’t need. To know about the full potential of the Weights and Biases API check out the official documentation: [https://docs.wandb.com/library/api](https://docs.wandb.com/library/api). --- source: https://docs.wandb.ai/guides/prompts/openai source_type: documentation has_code: False Weights & Biases has 2 OpenAI integrations to help you train better models faster and keep track of your prompts and generations: With Weights & Biases you can log your OpenAI model's fine-tuning metrics and configuration to Weights & Biases to analyse and understand the performance of your newly fine-tuned models and share the results with your colleagues. See the **W&B and OpenAI Fine-Tuning docs here** to learn more Log requests, responses, token counts and model metadata with 1 line of code for all OpenAI models See the **W&B and OpenAI API section docs** to learn more --- source: https://wandb.ai/wandb/getting-started/reports/--VmlldzoyNzY5MDk= source_type: report has_code: False See how teams working on cutting edge deep learning projects use W&B to train, collaborate on, and debug their workflows. [How the OpenAI Robotics team uses Weights & Biases](https://wandb.ai/openai/published-work/Learning-Dexterity-End-to-End--VmlldzoxMTUyMDQ) to run a large deep learning project – like training a robot hand to manipulate physical objects like the Rubik's cube. [How the LatentSpace team uses Weights & Biases](https://wandb.ai/latentspace/published-work/The-Science-of-Debugging-with-W&B-Reports--Vmlldzo4OTI3Ng) to quickly identify, communicate, and iteratively debug their models and build on top of each other's work. Why is experiment tracking so important for doing real world machine learning? Find out in [this article by Lukas Biewald](https://towardsdatascience.com/machine-learning-experiment-tracking-93b796e501b0?gi=ce5b4c77d19d), CEO of W&B. * * * Please see our [technical FAQ](https://wandb.ai/wandb/getting-started/reports/Technical-FAQ--VmlldzoyMTA5MDM) for commonly asked questions about the API and product. You can always export and delete your data at any time. We will never share data associated with private projects. We hope that when you can, you will make your work public so that other practitioners can learn from it. We hope to discover and share high level patterns to move the field of machine learning forward. For example, we wrote [this article](https://www.wandb.com/articles/monitor-improve-gpu-usage-for-model-training) on how people are not fully utilizing their GPUs. We want to do this in a way that respects your privacy and feels honest. If you have any concerns about data privacy, we'd love to hear from you. Reach out at contact@wandb.com. --- source: https://wandb.ai/mostafaibrahim17/ml-articles/reports/--Vmlldzo1NjMzMjQx source_type: report has_code: False After the processing is complete, a link to Weights & Biases (W&B) will be generated. Click on this link to access the logs and view the results of your experiment. The new model demonstrates a marked improvement of 25% in predictive accuracy. While the previous model achieved an accuracy of 48%, the updated version impressively reached 73%. Moreover, we've compiled a table consisting of 100 entries and saved it using the Weights & Biases tool (Step 16). This table is structured with four columns: Sentiment, Labeled Prediction, Old Model Prediction, and New Model Prediction. Through manual inspection, we'll be able to pinpoint instances where the model exhibited improvements. Navigating the complexities of model evaluation becomes simpler with W&B. It enables us to save and compare multiple tables with various accuracies and outputs. By tweaking our fine-tuning process, we can easily monitor improvements or setbacks, streamlining our path to achieving the highest model accuracy possible. For example, in the displayed table, the new model accurately predicted the sentiment label for the second, fourth, and seventh rows, where the previous model had wrongly classified. Thus we can clearly see the improvement in our model’s predictions along with its strong and weak points. Social media platforms, such as Facebook, Twitter, and even Reddit, have a unique language characterized by platform-specific slang, memes, niche topics, and abbreviations. Fine-tuning allows the model to interpret and respond to such vernacular accurately, ensuring better sentiment understanding. E-commerce platforms can analyze product reviews to identify highly rated products or vendors and adjust their recommendation algorithms accordingly. --- source: https://github.com/wandb/examples/tree/master/colabs/scikit/Simple_Scikit_Integration.ipynb source_type: notebook has_code: True Use Weights & Biases for machine learning experiment tracking, dataset versioning, and project collaboration. * Easy integration of Weights and Biases with Scikit. * W&B Scikit plots for model interpretation and diagnostics for regression, classification, and clustering. **Note**: Sections starting with *Step* are all you need to integrate W&B to existing code. ``` import warnings import matplotlib.pyplot as plt import numpy as np import pandas as pd from sklearn.svm import SVC from sklearn.ensemble import RandomForestClassifier from sklearn.linear_model import LinearRegression from sklearn.linear_model import Ridge from sklearn.tree import DecisionTreeClassifier from sklearn.cluster import KMeans from sklearn import datasets, cluster from sklearn.model_selection import train_test_split from sklearn.utils.class_weight import compute_class_weight from sklearn.exceptions import ConvergenceWarning warnings.filterwarnings("ignore", category=ConvergenceWarning) ``` ``` !pip install wandb -qU ``` ``` import wandb ``` ``` wandb.login() ``` **Let's check out a quick example** ``` # Load data housing = datasets.fetch_california_housing() X = pd.DataFrame(housing.data, columns=housing.feature_names) y = housing.target X, y = X[::2], y[::2] # subsample for faster demo wandb.errors.term._show_warnings = False # ignore warnings about charts being built from subset of data X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3) # Train model, get predictions reg = Ridge() reg.fit(X_train, y_train) y_pred = reg.predict(X_test) ``` ``` run = wandb.init(project='my-scikit-integration', name="regression") ``` --- source: https://wandb.ai/tim-w/sparkml-wandb/reports/--VmlldzozMTk1NzI5 source_type: report has_code: False ' Description: Adding W&B tracking to SparkML Pipelines and CrossValidators Body: What is Weights & Biases? Simply put, W&B is a system of record of Machine Learning Workflows. With W&B, we can * Track and compare experiments in as little as five lines of code. * Provide full lineage of your machine learning / data science workflow. * Add W&B lightweight integration to your existing code and quickly get live metrics, terminal logs, and system stats streamed to the centralized dashboard * Explain how your model works, show graphs of how model versions improved, discuss bugs, and demonstrate progress towards milestones. Recently Spark has been popped up with a few customers, asking specifically how can W&B integrate into Spark workflows. In this report we'll highlight how W&B can add value to your SparkML workflows by * using W&B to track training of SparkML Estimators, capturing configurations and metrics * use W&B to surface results of hyperparameter search giving easy model comparisons * logs models to the W&B Model Registry * Utilize W&B Launch (Beta) to Trigger spark jobs to score datasets Apache Spark is the most widely-used engine for scalable computing, and has been adopted by thousands of companies, included 80% of the Fortune 500. In this report we'll talk through adding W&B experiment tracking to SparkML Pipelines and CrossValidators. The spark.ml package aims to provide a uniform set of high-level APIs built on top of DataFrames that help users create and tune practical machine learning pipelines --- source: https://docs.wandb.ai/guides/integrations/deepchecks source_type: documentation has_code: True **Try in a Colab Notebook here →** DeepChecks helps you validate your machine learning models and data, such as verifying your data’s integrity, inspecting its distributions, validating data splits, evaluating your model and comparing between different models, all with with minimal effort. Read more about DeepChecks and the wandb integration -> To use DeepChecks with Weights & Biases you will first need to sign up for a Weights & Biases account here. With the Weights & Biases integration in DeepChecks you can quickly get started like so: ``` import wandb wandb.login() # import your check from deepchecks from deepchecks.checks import ModelErrorAnalysis # run your check result = ModelErrorAnalysis()... # push that result to wandb result.to\_wandb() ``` You can also log an entire DeepChecks test suite to Weights & Biases ``` import wandb wandb.login() # import your full\_suite tests from deepchecks from deepchecks.suites import full\_suite # create and run a DeepChecks test suite suite\_result = full\_suite().run(...) # push thes results to wandb # here you can pass any wandb.init configs and arguments you need suite\_result.to\_wandb( project='my-suite-project', config={'suite-name': 'full-suite'} ) ``` ``**This Report** shows off the power of using DeepChecks and Weights & Biases Any questions or issues about this Weights & Biases integration? Open an issue in the DeepChecks github repository and we'll catch it and get you an answer :)<!--end-context-information--> <!--start-question-->**Question**: # Query Can you provide more details or context to enhance your query regarding Weights & Biases? --- # Query Metadata Language: en Intents: Needs More Info: The query is asking for a general enhancement of a user query without specific context or details provided. The query feels ambiguous, ask a follow-up query to elicit more information before answering the query and avoid answering it initially Sub-queries to consider answering: <!--end-question--> <!--final-answer-in-markdown-->