This project takes a raw, real-world Netflix content dataset (7,787 titles, 12 attributes) and transforms it into an interactive Power BI dashboard. The focus is on end-to-end data analysis: cleaning messy, inconsistent data in Excel/Power Query and turning it into clear, actionable visual insights.
This project takes a raw, real-world Netflix content dataset (7,787 titles, 12 attributes) and transforms it into an interactive Power BI dashboard. The focus is on end-to-end data analysis: cleaning messy, inconsistent data in Excel/Power Query and turning it into clear, actionable visual insights.
- Source: Netflix Movies and TV Shows dataset (Kaggle / Flixable)
- Size: 7,787 records, 12 columns
- Columns:
show_id,type,title,director,cast,country,date_added,release_year,rating,duration,listed_in,description
The raw dataset required significant cleaning before analysis:
- Handled missing values in
director(2,389),cast(718),country(507),date_added(10), andrating(7) — imputed as "Unknown" rather than dropping rows to preserve data volume - Split multi-value fields (
country,cast,listed_in) that contained comma-separated lists into usable formats for filtering and grouping - Converted
date_addedfrom inconsistent text strings into proper date format - Split the
durationcolumn, which mixed two different units ("X Seasons" for TV shows vs. "X min" for movies), into separate, analyzable fields - Standardized inconsistent text casing and category labels across
ratingandlisted_in
Built an interactive multi-page dashboard exploring:
- Content type breakdown (Movies vs. TV Shows) over time
- Genre and rating distribution
- Content additions by year/month (growth trends)
- Country-wise content availability
- Top contributing directors and cast
Excel, Power Query, Power BI (DAX, data modeling, visualizations)
(Add 2–3 bullet points here once your analysis is complete — e.g., which content type dominates, peak content-addition periods, top countries producing content.)