Abdullah Musa
AI Data Analyst | CSV & Python
New to Contra
Abdullah is ready for their next project!
Dairy Sales Dashboard — Interactive Business Intelligence Report
Built a fully interactive sales dashboard for a dairy company dataset containing 3,346 SKUs across 50 companies, cleaned and structured from raw messy data.
What this dashboard includes:
KPI summary cards (Total Revenue, Stock Value, Units Sold, Expiration Rate)
Units Sold & Revenue breakdown by product type (Milk, Cheese, Yogurt, Ice Cream, Butter, Cream)
Inventory Status breakdown (In Stock, Low Stock, Out of Stock, Backordered, etc.)
Price Distribution analysis across price ranges
Tools & Skills used: Python, Pandas, data cleaning, data visualization, business insight generation
Business value: Helps business owners instantly spot which products are selling, which are expiring, and where inventory risks are — without touching a single spreadsheet.
1
1
37
[AI-Powered Product Data Analysis using Python & Groq]
Analyzed a messy product dataset with 3,348 rows
and 13 columns using Python, pandas, matplotlib,
seaborn, and Groq AI.
Key Findings:
→ 71.5% of products marked expired
→ Top companies identified with highest expired stock
→ Price distribution analyzed across all products
→ AI generated executive business summary
Tools used: Python, pandas, numpy, matplotlib,
seaborn, Groq API, LLaMA model
0
77
[Data cleaning using pandas (Titanic dataset) ]
Before analysis, I cleaned the Titanic dataset:
1. Filled missing Age values with the median age (177 missing → 0)
2.Dropped the Cabin column (687 missing values, too sparse)
3.Filled missing Embarked with the most common port (2 missing → 0)
Result: 891 rows, 11 columns, no missing values in critical fields. Clean, consistent data ready for AI processing.
0
101
I used Python and Groq AI (Llama 3.3 model) to analyze the Titanic passenger dataset. The AI automatically identified:
1. All 12 columns in the dataset
2. Two patterns: higher class passengers paid higher fares, missing values in Age and Cabin
3. A summary of the data
This demonstrates how AI can quickly extract insights from structured data without manual work.
0
103
This Python script uses the Groq API (Llama 3.3 model) to analyze CSV files. It reads the data, sends it to AI, and returns insights including column names, patterns, and a summary. I wrote this script as part of my Titanic dataset project.
0
93