In this task, I explored the Order_Details dataset and focused on data visualization and insights generation using Python libraries. The main goal was to create multiple types of plots that visually represent sales, profit, and customer-related trends, enabling better decision-making and storytelling through data. This task was designed to strengthen my data analysis and visualization skills by applying different chart types, each highlighting unique business insights. Visualization is one of the most powerful tools in data analytics, and this exercise gave me hands-on experience in turning raw data into meaningful patterns and dashboards.
- Imported the dataset using Pandas.
- Previewed the first few rows, checked columns, data types, and summary statistics.
- Verified numerical and categorical columns for plotting suitability.
- I generated 8 different visualizations, each focusing on specific insights:
- Bar Plot (Total Sales by Category) → Showcased which categories contributed the most revenue.
- Histogram (Profit Distribution) → Displayed the distribution of profit values, detecting skewness and outliers.
- Pie Chart (Payment Mode Share) → Highlighted customer preferences across different payment methods.
- Boxplot (Profit by Category) → Helped compare profit ranges across product categories, revealing variations.
- Scatter Plot (Sales vs. Profit) → Visualized the relationship between sales amount and profit across categories.
- Heatmap (Correlation Matrix) → Showed correlations between numerical features like Amount, Profit, and Quantity.
- Column Chart (Sales by Sub-Category) → Provided a clear comparison of total sales for each product sub-category.
- Treemap (Sales by Category – Alternative) → Represented proportional sales across categories in a compact manner.
- Categories like Technology and Furniture contributed the highest sales.
- The profit distribution revealed both positive profits and instances of losses, useful for risk analysis.
- Cashless payments (like Credit/Debit Card, UPI, Net Banking) showed higher usage compared to Cash on Delivery.
- Boxplots highlighted that some categories had higher profit fluctuations than others.
- Scatter plots showed that while higher sales often led to higher profit, there were cases of high sales but low/negative profit, suggesting cost inefficiencies.
- Correlation matrix confirmed that Amount and Quantity were positively correlated, while Profit had mixed correlation trends.
- Sub-category level insights pinpointed top-performing products in terms of revenue.
- Python (Jupyter Notebook / Script) → for coding and analysis.
- NumPy → handled numerical calculations.
- Pandas → data exploration, aggregation, and manipulation.
- Matplotlib & Seaborn → for plotting bar charts, histograms, scatter plots, heatmaps, and boxplots.
- 📊 Visualization Mastery → Strengthened my ability to select the right type of plot for different kinds of data and insights.
- 💡 Storytelling with Data → Learned how to transform raw datasets into interactive, decision-supporting visual insights.
- ⚡ Error Handling → Fixed common issues with groupby, palette warnings, and plot formatting, gaining debugging experience.
- 🌍 Business-Oriented Insights → Understood how visualization directly supports real-world decision-making (e.g., sales strategies, profit optimization, payment trends).
- 🧑💻 Portfolio-Ready Dashboard → Built a collection of Python visualization scripts that can be reused in future projects.
A clean and professional set of visualizations that provide actionable insights into sales, profit, and customer behavior, demonstrating practical data analytics and visualization expertise.
💼 Portfolio: https://linktr.ee/AbdullahUmar.DataAnalyst
📧 Email: umerabdullah048@gmail.com
Show what the Code and Output looks like.