Setting User Frequency Distribution for Detailed Data Analysis
how to set frequency distribution per user to show the data per each value (0 times, 1 time, etc instead of 0-2 times, 2-4 times)
how to set frequency distribution per user to show the data per each value (0 times, 1 time, etc instead of 0-2 times, 2-4 times)
Hi Gabriel W., Please stand by as I search the Mixpanel knowledge base for an AI-powered answer. I normally take about 15 seconds or so. In case AI cannot answer your question, feel free to reach out to Mixpanel support at mixpanel.com/get-support. If you have follow-up questions for this thread, please tag me again with your question: @kapa.ai <follow-up question> 👋
Feel free to ask a follow-up question once I've answered by mentioning me with @kapa.ai
To show frequency distribution per user for each exact value (e.g., 0 times, 1 time, 2 times, etc.) instead of default bucketed ranges (like 0-2 times, 2-4 times), you need to customize the bucketing in Mixpanel: 1. Use Custom Buckets (Varied Bucketing):
- When breaking down a numeric property (such as event frequency), open the custom buckets modal.
- Choose Varied Bucketing.
- Enter your desired breakpoints: for integer values, input 0, 1, 2, etc. This will generate buckets like <0, ≥0 & <1 (which is 0), ≥1 & <2 (which is 1), ≥2 & <3 (which is 2), and so on. This approach ensures each bucket represents a single value, allowing you to see the distribution for each exact count.
- For decimals, use values like 0, 0.0001, 1, etc., to approximate exact values as needed. Example from the documentation:
** Choose Varied bucket values 0, 1, 2…
** This would generate buckets: <0, ≥0 & <1, ≥1 & <2, ≥2.
** ≥0 & <1 would be equal to bucket 0
```LBKS <https://docs.mixpanel.com/docs/features/advanced#faq|See more details here>.LBKS2. **Typecasting (if needed):*
- If you want to see the exact numeric values without any bucketing, you can typecast the number property to a string. This removes the automatic range bucketing and displays each value as-is. This is useful if you want a raw, unbucketed view.
[See more details here](https://docs.mixpanel.com/docs/reports#typecasting).LBKSBy using custom varied buckets or typecasting to string, you can display the frequency distribution per user for each exact value (0, 1, 2, etc.) instead of grouped ranges.
kapa.ai is still learning and improving, please let me know how I did by reacting below.
ℹ️ Tip: Mention @kapa.ai in the thread for follow-ups or DM the app for 1-to-1 help.
kapa.ai Im using the "measuring" inside an event and selecting "frequency distribution per user", so it's not triggered from the "breakdowns" section. >How can i do it?
Let me check the knowledge base for you again. One moment! 📚
When you use the "frequency distribution per user" measurement directly (not via the breakdowns section), Mixpanel by default aggregates the frequency per user and then displays the distribution. However, the documentation does not specify a built-in way to force the frequency distribution to show each exact value (e.g., 0, 1, 2, 3, ...) as separate bars or rows directly from the measurement selector alone.The available options for customizing buckets (to show each value separately) are described in the context of breakdowns and custom buckets, not the measurement selector. If you want to see the distribution for each exact frequency value, the documentation suggests using custom buckets, which is accessible from the breakdowns or property bucketing interface—not directly from the measurement selector for "frequency per user" Docs: Advanced.If you need to see the exact values (0, 1, 2, etc.) in your frequency distribution per user, you may need to: - Add a breakdown on the frequency property and then use custom buckets to define each value as its own bucket. - Alternatively, typecast the property to a string to avoid automatic bucketing, but this is also described in the context of breakdowns Docs: Typecasting.Summary: Based on the documentation, there is no explicit way to configure the "frequency distribution per user" measurement alone (without using breakdowns or custom buckets) to show each value separately. The customization options are available when using breakdowns or custom buckets, not directly from the measurement selector.If you need this level of granularity, you will likely need to use the breakdowns section with custom buckets as described above. If this is a critical workflow, you may want to provide feedback to Mixpanel for more granular control directly in the measurement selector.I'm sorry, but the knowledge sources do not contain information about achieving this directly from the "measuring" selector without using breakdowns or custom buckets.
kapa.ai is still learning and improving, please let me know how I did by reacting below.
ℹ️ Tip: Mention @kapa.ai in the thread for follow-ups or DM the app for 1-to-1 help.