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/stacey/sfmlearner/reports/--Vmlldzo2Nzg2Nw== source_type: report has_code: False * Charts are zoomed into the most relevant regions. For example, the bottom left "smooth_loss" zooms in on the first 400 steps and shows that setting smooth_weight around 0.5 results in less stable initial training with a spike around step 100. * The view synthesis objective chart shows all the pixel_losses smoothed, sorted, and added to each other instead of plotting them on top of each other. This makes the relative ordering and size of the pixel_loss more clear across different experiments. The increased spikiness is an artifact of this plot style--each successive loss plot is at least as noisy as the layer below it. * The final value for total loss sometimes increases slightly as the model trains past 100K to 300K iterations, likely because of the inherent noisiness of the loss. Perhaps early stopping or interleaving validation stages with visual confirmation would help. * Noticed the number of trainable parameters in the model didn't change when I tried to change the number of depth scales from 4 to 3 or 5—turns out this hyperparameter is fixed to 4 deeper in the code The model performs remarkably well in complicated lighting conditions. Overall, training for longer seems to improve the model and add to the level of detail, although some false positives worsen (such as perceiving certain textures/shapes as dark/far away "holes"). Scroll through the two panels side-by-side to see more examples. Interesting edge cases * first row: glare from car perceived as a nearby vertical object * first row, third row: asphalt texture and potholes perceived as "holes" or very far away patches of background instead of foreground * sixth row: patch of bright sun perceived as "hole" * third to last row: occluding bus is basically invisible * last row: the strange shape of car, perhaps inferred from long shadow? ' --- 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://docs.wandb.ai/guides/app/pages/project-page source_type: documentation has_code: False Click the section dropdown menu and click "Add section" to create a new section for panels. You can rename sections, drag them to reorganize them, and expand and collapse sections. Each section has options in the upper right corner: * **Switch to custom layout**: The custom layout allows you to resize panels individually. * **Switch to standard layout**: The standard layout lets you resize all panels in the section at once, and gives you pagination. * **Add section**: Add a section above or below from the dropdown menu, or click the button at the bottom of the page to add a new section. * **Rename section**: Change the title for your section. * **Export section to report**: Save this section of panels to a new report. * **Delete section**: Remove the whole section and all the charts. This can be undone with the undo button at the bottom of the page in the workspace bar. * **Add panel**: Click the plus button to add a panel to the section. Drag and drop panels to reorder and organize into sections. You can also click the "Move" button in the upper right corner of a panel to select a section to move the panel to. * **Standard layout**: All panels maintain the same size, and there are pages of panels. You can resize the panels by clicking and dragging the lower right corner. Resize the section by clicking and dragging the lower right corner of the section. * **Custom layout**: All panels are sized individually, and there are no pages. Use the search box in the workspace to filter down the panels. This search matches the panel titles, which are by default the name of the metrics visualized. Use the table to filter, group, and sort your results. View a live example → --- source: https://wandb.ai/wandb/posts/reports/--VmlldzoyNjk3Nzg= source_type: report has_code: True We've built six ready-to-use charts. You can add them anywhere in the UI by creating a Custom Chart panel and then picking them from the dropdown, or log them from Python with W&B 0.10.5 or later. The first four look like this: All of our built-in plots support smooth pan and zoom interactions and have useful hover states. Try clicking and dragging, or scrolling, on the plots above. Our built-in plots are always comparable across runs and respond to your run color settings. Click on the eyeballs and colors swatches in the table above to update the plots. You can log the "Height v. Distance" plot above yourself, by running the following code: ``` import wandb, random, math wandb.init() data = [i, random.random() + math.sin(i / 10) for i in range(100)] table = wandb.Table(data=data, columns=["distance", "height"]) wandb.log({'line-plot': wandb.plots.line(table, x="distance", y="height", title="Height v. Distance") }) ``` To learn about the built-in plots and how to use them, check out the detailed wandb.plot reports by Stacey Svetlichnaya, another engineer on our team. You can find them here in our [Gallery](https://wandb.ai/gallery/visualizations). Each report shows the plot in context, describes its usage and gives examples showing how to customize them to your needs. Customizable chart presets * * * * In addition to the plots above, we've updated our PR and ROC plots to use this new system. Check out Stacey's documentation reports for examples and usage information: * * Keep an an eye on the [Gallery](https://wandb.ai/gallery/visualizations) for announcements about new built-in plots! --- source: https://github.com/wandb/examples/tree/master/colabs/intro/Report_API_Quickstart.ipynb source_type: notebook has_code: True # title\_y="y axis title", groupby='encoder', groupby\_aggfunc="median", groupby\_rangefunc="stddev", max\_runs\_to\_show=20, max\_bars\_to\_show=3, font\_size="auto", ), wr.ScalarChart( title="Maximum Number of Steps", metric="Step", groupby\_aggfunc="max", groupby\_rangefunc="stderr", font\_size="large", ), wr.CodeComparer(diff="split"), wr.ParallelCoordinatesPlot( columns=[ wr.PCColumn("Step"), wr.PCColumn("c::model"), wr.PCColumn("c::optimizer"), wr.PCColumn("Step"), wr.PCColumn("val\_acc"), wr.PCColumn("val\_loss"), ], ), wr.ParameterImportancePlot(with\_respect\_to="val\_loss"), wr.RunComparer(diff\_only="split"), wr.CustomChart( query={'summary': ['val\_loss', 'val\_acc']}, chart\_name='wandb/scatter/v0', chart\_fields={'x': 'val\_loss', 'y': 'val\_acc'} ), wr.WeavePanelSummaryTable("my-table"), wr.WeavePanelArtifact('model-1', 'lineage', layout={'w': 24, 'h': 12}), wr.WeavePanelArtifactVersionedFile('model-1', 'v0', "dataframe.table.json", layout={'w': 24, 'h': 12}), ], ), ] ) report.save() ``` * A limited subset of weave panels are available today, including Artifact, ArtifactVersionedFile, and SummaryTable * Stay tuned for future updates around weave support! * Yep! Check out this example which creates a report via Github Actions * Suppose have have two reports like below: --- source: https://docs.wandb.ai/guides/app/features/custom-charts/ source_type: documentation has_code: False This can be enabled on the “Other settings” page of the custom chart editor. If you change your query to use a `historyTable` instead of the `summaryTable`, you'll get an option to “Show step selector” in the custom chart editor. This gives you a slider that lets you select the step. You can do this by going into the custom chart editor. Then click on the currently selected chart type, this will open up a menu with all your presets. Hover the mouse on a preset you want to delete and then click on the Trash icon. * Customize bar plots with error bars * Show model validation metrics which require custom x-y coordinates (like precision-recall curves) * Overlay data distributions from two different models/experiments as histograms * Show changes in a metric via snapshots at multiple points during training * Create a unique visualization not yet available in W&B (and hopefully share it with the world) --- source: https://docs.wandb.ai/guides/app/pages/workspaces source_type: documentation has_code: False To update a saved workspace view in Weights & Biases: * **Edit the Workspace:** Make the desired changes to your charts and data within the workspace. * **Save the Changes:** Click the **Save** button to confirm your changes. Saved changes overwrite the previous state of the saved view. Unsaved changes are not retained. :::info A confirmation dialog appears when you save your updates to a workspace view. If you prefer not to see this prompt in the future, select the option **Do not show this modal next time** before confirming your save. ::: To delete a view and manage your workspace menu in Weights & Biases: * Navigate to the view you wish to remove. * Click on the meatball menu (three horizontal lines) at the top right of the view. * Choose the option to **Delete view**. * Confirm the deletion to remove the view from your workspace menu. This process helps to declutter your workspace by removing any views that are no longer needed. Share your customized workspace with your team by sharing the workspace URL directly. All users with access to the workspace project can see the saved Views of that workspace. --- source: https://wandb.ai/andrea0/writing/reports/--VmlldzozMDE4OTk2 source_type: report has_code: False If you don't yet have a Team set up in Weights & Biases, you can still share individual Reports with collaborators. On any Report page click on the Share button toward the upper left of the Report. This creates a "magic link" (shown below) that you can send to people with or without a Weights & Biases account. This works in an identical fashion to when you share a Google Docs link with 'Anyone who has the link'. Users needn't be logged in to view this Report but they will be required to be logged in and added to your team before leaving comments and/or making edits. Users who are not added to your team (with or without a W&B account) will have view-only access to the Report. When sharing a report you may also want to embed it inside of another webpage – perhaps on your team's content management system, e.g., Confluence, Notion, or as an iFrame on a HTML page. The step for performing that operation is illustrated in the animation below and a documentation reference page on how to [Embed reports](https://docs.wandb.ai/guides/reports/embed-reports). On the off chance that your collaborators don't have access to the Weights & Biases website you can export your Report as well! Sometimes you or your collaborators will want to export your findings for use outside of the Reports ecosystem. Weights & Biases offers the ability to export single charts, datasets, experiment metrics (accuracy, etc.), hyperparameter lists, and more with a few mouse clicks or programmatically via the wandb API. --- source: https://wandb.ai/wandb/common-ml-errors/reports/--VmlldzozMzAxMDk= source_type: report has_code: False 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://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/wandb/common-ml-errors/reports/--VmlldzozMjg0MTE= source_type: report has_code: False 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 follow 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://docs.wandb.ai/guides/app/pages/workspaces source_type: documentation has_code: True You can sort charts into sections in your workspace programmatically or interactively with the W&B App UI. Add a prefix to the name of your metric when you log that metric to sort the chart into sections. For example, the proceeding code block will produce two chart sections called **section-a** and **section-b**: ``` run = wandb.init() with run: for idx in range(100): run.log({"section-a/metric": idx}) run.log({"section-b/metric": idx \* 2}) ``` 1. Navigate to your project workspace. 2. Scroll down to the bottom of the panel section of your workspace. 3. Click on the **Add section** button to add a new section. Improve team collaboration with tailored workspace views. * **Personal Workspaces:** Exclusive to you, these are customizable spaces for in-depth analysis of models and data visualizations. You have edit control, while teammates can view configurations without altering them. * **Saved Views:** These are collaborative snapshots of your workspace, viewable and usable by all project collaborators. They serve as fixed references of particular workspace states for collective review and discussion. A Workspace View in Weights & Biases lets you organize and save your preferred workspace setup of charts and data. You can easily create a new View by following these steps: * **Open a Workspace or View:** Start by going to the Workspace or View you wish to save. * **Save View:** Look for the meatball menu (three horizontal dots) at the top right corner of your workspace. Click on it and then choose **Save as a new view**. Once saved, you can also give your new view a descriptive name. * **Find Your New View:** Once saved, new views appear in the workspace navigation menu. --- 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://github.com/wandb/weave/tree/master/examples/reference/create_plots_ui_guide.ipynb source_type: notebook has_code: True Use the "New Series +" button to add one or more series of points. You can treat each of the Series 1, 2, 3... in a plot as an independent group/collection of settings with a separate instance of the specifications described above. When a plot contains multiple series, all of the series are overlayed/rendered on the same plot area when visualized and their settings combined in the legend/titles/etc. With our sample dataset, we may want to configure a different series/visual settings for each domain: language models in one series, computer vision in another, etc. There are two ways to convert a plot axis to log scale: 1. Use the **Advanced properties editor**: click the pencil "edit" icon on a plot to expand the config menu on the right, then select "Advanced properties" at the end of the first 'Properties" section. Set x- and y- axes to be log scale instead of linear in the dropdown menu. 2. Convert the Weave expression to **log base 10 mathematically**: e.g. convert `row["Parameters"]` to `row["Parameters"] ** 0.1`. This will not adust the grid scale markers like the first option, but it will apply to any expression/dimension (not only x- and y- axes) and can be easier to try in the flow of editing charts. Sometimes a log scale or zooming in is still insufficient. You can remove outliers by filtering the input data based on a range of column values. Use the `.filter` Weave op on the `Input` field to plot only the points that meet the specified condition. For example, compare the default starter plot with dropping any models that have >= 1e12 parameters: Try editing some of these settings from the Table below: ``` show(df) ``` The `Mark` setting intially determines the plot style: scatter plot, line plot, bar chart, etc. This defaults to "auto" and picks the best option based on the incoming data types. If `Mark` is set explicitly to `point`, this reveals controls for the shape and size of the points. --- source: https://wandb.ai/wandb/plots/reports/--VmlldzozMTAxMjU= source_type: report has_code: False ' Description: This article explains how to easily adapt a Weights & Biases Custom Chart preset for individual, specific use cases. Body: How do you modify one of the W&B Custom Charts for your particular project? In this article, I extend the [Custom Histogram](https://wandb.ai/wandb/plots/reports/Custom-Histograms--VmlldzoyNzE0NzM) to * adjust details like bin size and max height by editing the chart code in * save the modified version as a custom preset * log to this new chart type programmatically from Python. You can follow these steps to customize any of our [presets (line plot, bar plot, scatter plot, histogram, PR curve, and ROC curve)](https://docs.wandb.com/app/features/custom-charts#builtin-presets). The default histogram appears on the left below (from [Custom Histogram](https://wandb.ai/wandb/plots/reports/Custom-Histograms--VmlldzoyNzE0NzM)). On the right, I've edited the default histogram to use smaller bins and cut off at a count of 50 so I can see the fine detail. If you'd like to try this yourself in a Colab notebook, I recommend * * In both charts, you can zoom, pan, and hover to see more information. Both charts show four different model variants (same validation data, different epoch count and numbers of training examples) on the same axes for easy comparison. You can use the "eye" icons to the left of the run names to toggle the display of individual runs on/off.<!--end-context-information--> <!--start-question-->**Question**: # Query Can I get an enlarged/focused view for charts? --- # Query Metadata Language: en Intents: Product Features: The user is inquiring about a specific feature of Weights & Biases related to data visualization. The query is related to a feature of Weights & Biases such as Sweeps, Artifacts, Reports, Experiments, Tables, Prompts, Launch, Weave, StreamTables and more. Provide a link to the relevant documentation and explain the feature in detail Sub-queries to consider answering: How to enlarge or focus on a specific area of a chart in Weights & Biases? Is there a zoom feature for charts in Weights & Biases? Can you customize the view of charts in Weights & Biases for better visualization? <!--end-question--> <!--final-answer-in-markdown-->