تحليل بيانات سوبر ماركت

* The dataset contains over 51,000 rows and 27 columns, including numerical, string, and datetime data types.

* Several columns have missing values, notably 'Postal Code' (over 41,000 missing) and 'image' (over 10,000 missing). Most other columns with missing values have only 2 missing entries.

* Outliers were detected in numerical columns, with 'Profit' having the highest percentage of outliers (19.02%), followed by 'Sales' (11.02%) and 'Shipping Cost' (11.52%).

* Sales, Profit, and Shipping Cost show positive correlations, while Discount has a negative correlation with Profit.

* The 'Consumer' segment, 'Technology' and 'Furniture' categories, 'Standard Class' ship mode, and 'Medium'/'High' order priorities are the most frequent.

* Sales, Profit, and Shipping Cost distributions vary significantly by region and category.

* Monthly and yearly trends show an increasing trajectory for sales and profit, with noticeable seasonality peaking towards the end of each year.

* Regional analysis revealed Western Europe as the top performer and Central Asia as the lowest, with negative profits in Western Asia and Western Africa.

* Technology leads in category performance, but some sub-categories, like Tables, are unprofitable despite high sales.

* Higher discounts are associated with lower profits and increased losses.

* Customer analysis provides insights into purchasing behavior based on total sales and order frequency.