Scribd
Upload
2 views9 pages

Supermarket SQL&Python

The document outlines SQL commands to create a sales table, import data from a CSV file, and perform various data analysis queries. It includes commands for calculating total revenue, sales by city, customer demographics, and visualizing data using Python with pandas and matplotlib. Additionally, it provides code snippets for connecting to a PostgreSQL database and generating different types of plots based on sales data.

Uploaded by

eswar anusuri
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views9 pages

Supermarket SQL&Python

The document outlines SQL commands to create a sales table, import data from a CSV file, and perform various data analysis queries. It includes commands for calculating total revenue, sales by city, customer demographics, and visualizing data using Python with pandas and matplotlib. Additionally, it provides code snippets for connecting to a PostgreSQL database and generating different types of plots based on sales data.

Uploaded by

eswar anusuri
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 9

‭Task 4‬

‭CREATE TABLE sales (‬

‭invoice_id VARCHAR(20),‬

‭branch VARCHAR(5),‬

‭city VARCHAR(50),‬

‭customer_type VARCHAR(20),‬

‭gender VARCHAR(10),‬

‭product_line VARCHAR(50),‬

‭unit_price NUMERIC(10, 2),‬

‭quantity INT,‬

‭tax_5 NUMERIC(10, 2),‬

‭total NUMERIC(10, 2),‬

‭date DATE,‬

‭time TIME,‬

‭payment VARCHAR(20),‬

‭cogs NUMERIC(10, 2),‬

‭gross_margin_percentage NUMERIC(5, 2),‬

‭gross_income NUMERIC(10, 2),‬

‭rating NUMERIC(3, 1)‬

‭);‬

‭COPY sales FROM 'C:/supermarket_sales.csv'‬

‭DELIMITER ',' CSV HEADER;‬

‭SELECT * FROM sales LIMIT 10;‬


‭SELECT SUM(total) AS total_revenue FROM sales;‬

‭SELECT city, SUM(total) AS total_sales‬

‭FROM sales‬

‭GROUP BY city‬

‭ORDER BY total_sales DESC;‬

‭SELECT gender, COUNT(*) AS total_customers‬

‭FROM sales‬

‭GROUP BY gender;‬

‭SELECT product_line, ROUND(AVG(rating), 2) AS avg_rating‬

‭FROM sales‬

‭GROUP BY product_line‬

‭ORDER BY avg_rating DESC;‬

‭SELECT payment, COUNT(*) AS total_transactions‬

‭FROM sales‬
‭GROUP BY payment‬

‭ORDER BY total_transactions DESC;‬

‭SELECT date, SUM(total) AS daily_sales‬

‭FROM sales‬

‭GROUP BY date‬

‭ORDER BY date;‬

‭SELECT EXTRACT(HOUR FROM time::time) AS hour, COUNT(*) AS sales_count‬

‭FROM sales‬

‭GROUP BY hour‬

‭ORDER BY sales_count DESC;‬

‭SELECT city, SUM(total) AS total_sales‬

‭FROM sales‬

‭GROUP BY city‬

‭HAVING SUM(total) > (‬

‭SELECT AVG(total) FROM sales‬

‭);‬

‭SELECT city, SUM(total) AS total_sales,‬


‭RANK() OVER (ORDER BY SUM(total) DESC) AS sales_rank‬

‭FROM sales‬

‭GROUP BY city;‬

‭SELECT date, SUM(total) AS daily_sales,‬

‭SUM(SUM(total)) OVER (ORDER BY date) AS running_total‬

‭FROM sales‬

‭GROUP BY date‬

‭ORDER BY date;‬

‭SELECT product_line, SUM(total) AS total_sales‬

‭FROM sales‬

‭GROUP BY product_line‬

‭ORDER BY total_sales DESC‬

‭LIMIT 1;‬
‭pip install pandas matplotlib psycopg2‬

‭import pandas as pd‬

‭import matplotlib.pyplot as plt‬

‭import psycopg2‬

‭# Connect to your PostgreSQL database‬

‭conn = psycopg2.connect(‬

‭dbname="supermarket_sales_db", # Replace with your DB name‬

‭user="postgres", # Replace with your PostgreSQL username‬

‭password="yourpassword", # Replace with your PostgreSQL password‬

‭host="localhost",‬

‭port="5432"‬

‭)‬

‭# 1. Total Sales by City‬

‭query1 = """‬

‭SELECT city, SUM(total) AS total_sales‬

‭FROM sales‬

‭GROUP BY city‬

‭ORDER BY total_sales DESC;‬

‭"""‬

‭df1 = pd.read_sql(query1, conn)‬

‭ f1.plot(kind='bar', x='city', y='total_sales', title='Total Sales by City', legend=False,‬


d
‭color='skyblue')‬

‭plt.ylabel('Total Sales')‬
‭plt.tight_layout()‬

‭plt.show()‬

‭# 2. Average Rating by Product Line‬

‭query2 = """‬

‭SELECT product_line, ROUND(AVG(rating), 2) AS avg_rating‬

‭FROM sales‬

‭GROUP BY product_line‬

‭ORDER BY avg_rating DESC;‬

‭"""‬

‭df2 = pd.read_sql(query2, conn)‬

‭ f2.plot(kind='barh', x='product_line', y='avg_rating', title='Average Rating by Product‬


d
‭Line', legend=False, color='orange')‬

‭plt.xlabel('Average Rating')‬

‭plt.tight_layout()‬

‭plt.show()‬

‭# 3. Sales by Payment Method‬

‭query3 = """‬

‭SELECT payment, COUNT(*) AS total_transactions‬

‭FROM sales‬

‭GROUP BY payment;‬

‭"""‬

‭df3 = pd.read_sql(query3, conn)‬

‭ f3.set_index('payment').plot.pie(y='total_transactions', autopct='%1.1f%%',‬
d
‭title='Sales by Payment Method', legend=False)‬
‭plt.ylabel('')‬

‭plt.tight_layout()‬

‭plt.show()‬

‭# 4. Daily Sales Trend‬

‭query4 = """‬

‭SELECT date, SUM(total) AS daily_sales‬

‭FROM sales‬

‭GROUP BY date‬

‭ORDER BY date;‬

‭"""‬

‭df4 = pd.read_sql(query4, conn)‬

‭df4['date'] = pd.to_datetime(df4['date'])‬

‭df4.set_index('date', inplace=True)‬

‭df4.plot(title='Daily Sales Trend', linewidth=2, color='green')‬

‭plt.ylabel('Sales')‬

‭plt.tight_layout()‬

‭plt.show()‬

‭# 5. Revenue by Gender‬

‭query5 = """‬

‭SELECT gender, SUM(total) AS revenue‬

‭FROM sales‬

‭GROUP BY gender;‬

‭"""‬
‭df5 = pd.read_sql(query5, conn)‬

‭ f5.plot(kind='bar', x='gender', y='revenue', title='Revenue by Gender', legend=False,‬


d
‭color='purple')‬

‭plt.ylabel('Revenue')‬

‭plt.tight_layout()‬

‭plt.show()‬

‭# 6. Hourly Sales Activity‬

‭query6 = """‬

‭SELECT EXTRACT(HOUR FROM time::time) AS hour, COUNT(*) AS sales_count‬

‭FROM sales‬

‭GROUP BY hour‬

‭ORDER BY hour;‬

‭"""‬

‭df6 = pd.read_sql(query6, conn)‬

‭ f6.plot(kind='line', x='hour', y='sales_count', title='Sales by Hour', marker='o',‬


d
‭color='red')‬

‭plt.xlabel('Hour of Day')‬

‭plt.ylabel('Number of Sales')‬

‭plt.xticks(range(0, 24))‬

‭plt.tight_layout()‬

‭plt.show()‬

‭# 7. Top Product Line by Sales‬

‭query7 = """‬

‭SELECT product_line, SUM(total) AS total_sales‬


‭FROM sales‬

‭GROUP BY product_line‬

‭ORDER BY total_sales DESC‬

‭LIMIT 5;‬

‭"""‬

‭df7 = pd.read_sql(query7, conn)‬

‭ f7.plot(kind='bar', x='product_line', y='total_sales', title='Top 5 Product Lines by‬


d
‭Sales', legend=False, color='teal')‬

‭plt.ylabel('Total Sales')‬

‭plt.tight_layout()‬

‭plt.show()‬

‭# Close the connection‬

‭conn.close()‬

You might also like