Exploratory Data Analysis in Python: Bike-Share Demand in the Monsoon

Kayal Cycles runs a public bike-share scheme in Kochi. Six weeks into the monsoon, a board member says rain halves ridership and wants the fleet cut until September. Nisha Thomas, the company's analyst, has the raw trip log and the hourly weather, and three questions from the operations head: how many real rides did we do, when in the day are bikes needed, and how much does rain really cost us?Across five lessons you do her exploratory data analysis in Python on your own copy of the data: profiling a raw export and deciding what counts as a ride; converting UTC timestamps to IST; daily counts with a proper 7-day average; weekday and weekend hourly profiles built on a full grid so the zero-ride hours count; joining hourly weather, treating gauge failures as unknown, and a like-for-like comparison that removes time-of-day confounding. Every lesson ends with a chart built to tell the truth: a histogram, a trend line, a profile and a grouped bar chart, then a four-panel dashboard. In every lesson you build the step yourself first, then hand the same job to your AI (ChatGPT, Claude, Copilot or Gemini) and learn exactly where it goes wrong: the wrong time zone, averages that skip the zeros, blanks filled with zero, drizzle counted as rain. In the capstone your AI writes the whole analysis from one brief, and you prove every number before it reaches the board.Bartman runs your script on its own servers against your data and checks the files it writes, so every check is about your real output, not a screenshot.

Tools: Python, pandas, matplotlib, Exploratory Data Analysis, Data Visualization, Time Series, Time Zones, AI Assistants for Python