Skip to content
TriedPrompts

More in Large datasets & analysis.

Analyze two years of hourly home electricity data with ChatGPT

WorkedEvidence: Described by posterPosted Last checked

ChatGPT parsed Carlo Costanzo's 500K-line Duke Energy export and charted usage peaks by weekday, hour and season.

How to use this

  1. Tap Copy prompt.
  2. Open ChatGPT.
  3. Paste it into the message box.
  4. Send it, then read the answer before acting on it.
New to this? What's a prompt?

A prompt is the message you send to the AI tool. Copy the one on this page, put your own details where it asks, and read the answer before you act on it.

Prompt

Recreated prompt

The source didn't share its exact prompt, so we wrote one from what it describes. The result shown is the source's, not ours.

What the prompt labels mean

The person didn't share their exact words, so we wrote this from what they described. We haven't tested it, and they didn't use this exact version.

I'm uploading my utility's hourly electricity usage export in XML. Parse it into a table with the start time, reading quality and kWh for each interval. Then give me totals and averages, and chart usage by weekday, hour of day, season, day versus night and weekday versus weekend, and point out patterns worth acting on.

Try this in:

ChatGPT Used in sourceGemini Grok Claude

Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini and Claude open empty, so we copy the prompt for you to paste. Every button also copies it.

Opens in a new tab. We don't see what you send.

These links are only a shortcut. We're not affiliated with OpenAI, Google, Anthropic or xAI, and your results may not match the source.

Optional stronger version

Our rewrite with extra checks. The poster didn't test it.

Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish.

Goal: Turn a raw utility usage export into clear patterns I can act on.

Questions to ask me first:
- Which utility and what file format?
- Do I have solar, an EV or other big loads?
- Which time-of-use rates apply, if any?

Inputs (fill in or confirm):
- File: [USAGE EXPORT IN XML OR CSV]
- Home details: [SOLAR / EV / AC]
- Rate plan: [FLAT / TIME-OF-USE]

Rules:
- Show how many rows were parsed and any that were skipped.
- Keep units in kWh and label every chart.
- Separate observations from guesses about causes.

Checkpoint: Show the parsed table's first rows and the row count before analysis.

If you get stuck: If the file is too large, split it by year and analyze each part.

Verify before you finish: Totals by month add up to the overall total.

Output: Summary stats, labeled charts and a short list of patterns.

Done when: I can see when my home uses the most power and why.

AI tool

ChatGPT

Outcome

Carlo Costanzo, a Duke Energy customer in Florida with solar panels and an electric car, downloaded the utility's usage export—an XML file of over 500K lines, about 72k readings across two years—and uploaded it to ChatGPT. ChatGPT parsed the readings into a pandas DataFrame, computed totals, averages, minimums and maximums, and charted the patterns: higher use on Wednesdays and Saturdays, in the early-morning hours, and in summer months, which lined up with air conditioning.

Evidence: Described by posterThe person describes what happened in words, without screenshots or video.

Source

Posted
by Carlo Costanzo
Last checked
Method:
How we verify

https://www.vcloudinfo.com/2023/07/using-chatgpt-to-dive-deep-into-my-home-electric-data.html

Context: 2023 post from the ChatGPT file-analysis (Code Interpreter) era; no bill savings are reported.

More in Large datasets & analysis

Similar cases