running report GPT3 prompt

GPT3 prompt

This example demonstrates how a generative prompt can transform raw running statistics into personalized, motivational narratives. It shows a template where runner data—name, distance, total runs, hours, streak, climb, and classification—are inserted into a structured story, with comparisons like "run around the world in 14 years" making the numbers relatable. The code relies on string templating (likely via a language like JavaScript or Python) to populate the narrative field, while the data source is a simple text file with key-value pairs. The rendering is plain text output, with no visual charts or libraries involved.

CColinEberhardt

86% match

Gist fb66506b6acde1bc784498d56ae697f3

The visualization charts a 31-day running plan, showing daily distances that alternate between rest days (0 miles) and active runs peaking at 8 miles. It uses a line chart to reveal the repeating weekly pattern of three running days followed by a rest day, with gradual increases in mileage over the month. The code parses the CSV data from the gist file and renders a simple SVG path, relying on D3’s scale functions for axes and data mapping. No interactive or animated features are present, focusing solely on static comparison of daily effort.

63% match

Gist ab5ccee1fb22209a4bcd0bd65dd71ca1

The visualization tracks a 31-day running plan by comparing planned distances with actual run times. It shows how each day’s planned mileage relates to the time spent running, with zero-mile rest days clearly marked. The code uses `d3.scaleLinear` for axes, `d3.line` for the distance and time paths, and `d3.axisBottom` for the day labels. Data comes from two CSV-like sources embedded in the gist, and the chart renders as an SVG with a smooth line for distance and a separate line for time, making the daily variation and rest-day pattern immediately visible.

63% match

Gist 2d3cb8226bab03a0e983307f69227635

The visualization charts a runner’s daily logged miles for May 2017, revealing a pattern of alternating effort and rest days, with distances ranging from zero to eight miles. It shows how the runner consistently pairs a zero-mile recovery day after every three to four active days, while gradually increasing peak distances over the month. The chart is built using D3.js, likely with a line or bar encoding for the distance values, and parses the CSV data from the provided file. The implementation relies on D3’s scales and axes to map dates and miles, though no interactive or animated features are present in the source data.

62% match

Gist a47a4a5c5f7039022881d0b2dc84a1d6

The visualization tracks a month of daily running activity, plotting each day’s distance, time, and heart rate as a dual-axis scatterplot with a connected line. It shows how distance and time peak on high-mileage days while resting heart rate dips, with zero-distance rest days marked as gaps. Built using d3.scaleLinear for axes, d3.line for the path, and d3.axisBottom/axisLeft for gridlines, the chart reads from the CSV data via d3.csv. Points are rendered with d3.point circles, and the y-axis encodes time, while the x-axis uses a time scale for dates.

Gist 568d5eb25a35dbbb8d9e9e87521b4221

This example visualizes a two-week running schedule from a small CSV dataset, showing daily mileage with a pattern of rest days every fourth day. It uses a line chart rendered with D3.js, where the x-axis maps sequential day numbers and the y-axis encodes miles, with data points joined by a path generated through d3.line. The visualization highlights the alternating effort and recovery rhythm, with zero-mile rest days clearly visible as dips to the baseline. The code loads the data via d3.csv and applies a linear scale for both axes, while a smooth curve interpolation (d3.curveLinear) connects the points to emphasize the cyclical nature of the training plan.

Gist ce952252c3e624bba1310e716183d77f

This visualization tracks daily running distances for May 2017, showing a clear pattern of alternating effort and rest days. It uses a line chart where the y-axis encodes miles run and the x-axis represents dates, with zero-distance days plotted as gaps to emphasize recovery periods. The code relies on D3.js (likely `d3.scaleLinear` and `d3.line`) to generate the path, while the data is parsed from the CSV file `May_2017_new_log_miles.csv`. The chart highlights a gradual increase in peak distances from 6 to 8 miles over the month, with a consistent rest every third day.

Gist 1f1da38f38f58e6eff32b167edbf487f

The visualization displays a 31-day running log as a line chart, with daily distances on the y-axis and days on the x-axis. It highlights a pattern of alternating active and rest days, with distances peaking at 8 miles on day 30. The chart is rendered using D3.js, likely with `d3.scaleLinear` for axes and `d3.line` for the path. Data is loaded from a CSV file via `d3.csv`, and the line’s smooth curve suggests a `d3.curve` interpolator. The visualization emphasizes the cyclic structure of the training schedule rather than individual data points.