保留正文与补采附件。源页面当前未重新核验；具体限制见交付清单。

Revisit consent button We value your privacy We use cookies to enhance your browsing experience, serve personalised ads or content, and analyse our traffic. By clicking "Accept All", you consent to our use of cookies. Customise Reject All Accept All Customise Consent Preferences We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below. The cookies that are categorised as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... Show more NecessaryAlways Active Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

Functional Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

Analytics Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

Performance Performance cookies are used to understand and analyse the key performance indexes of the website which helps in delivering a better user experience for the visitors.

Advertisement Advertisement cookies are used to provide visitors with customised advertisements based on the pages you visited previously and to analyse the effectiveness of the ad campaigns.

Uncategorised Other uncategorised cookies are those that are being analysed and have not been classified into a category as yet. No cookies to display. Reject All Save My Preferences Accept All Toggle SearchToggle Mobile Navigation Publish AI, ML & data-science insights to a global community of data professionals. Sign inSubmit an Article LatestEditor's PicksNewsletterShipAI

Write For TDS LinkedInXToggle Search Data Science

EDA in Public (Part 2): Product Deep Dive & Time-Series Analysis in Pandas

Learn how to analyze product performance, extract time-series features, and uncover key seasonal trends in your sales data. Ibrahim Salami December 20, 20259 min read Exploratory Data Analysis with Pandas Image by Author. Created with Gemini Hi everyone! Welcome back to the “EDA in Public” series! This is Part 2 of the series; if you haven’t seen Part 1 yet, read it here. Here’s a recap of what we conquered. EDA in Public (Part 1): Cleaning and Exploring Sales Data with PandasLearn how to clean messy CSVs, summarize data, and visualize basic trends in e-commerce sales.Ibrahim Salami · 10 min read In Part 1, we took a messy, half-million-row sales file and got it into shape. Specifically, we:

We now have a clean, revenue-ready Pandas DataFrame ready to be exploited for insights! By the end of this series, I want to have mastered exploratory data analysis using Pandas. Feel free to follow along if you’re a data enthusiast. Learn this step by step with the interactive AI and Data Scientist roadmap. Now we shift our focus to delivering truly impactful business intelligence for NovaShop. Our overall goal for Part 2 is to answer the fundamental questions: What products are the best performers, and when is the best time to sell them? This part is all about analysis using powerful Pandas aggregation techniques (.groupby()) and feature engineering using the datetime column (.dt accessor). We'll break down our analysis into two key areas:

Without further ado, let’s get to it.

Loading the clean data

To improve performance, let’s export our cleaned dataset and import it again for analysis python

df.to_csv('online_retail_clean.csv', index=False)

Now, I can create a new project and start afresh. When loading CSVs that contain date columns, I try to use the parse_dates argument in pd.read_csv(). This saves me the step of manually converting the column type later, ensuring the date features are correct from the start. python

import pandas as pd
df = pd.read_csv('online_retail_clean.csv', parse_dates=['InvoiceDate'])
print(f"Successfully loaded clean data. Total rows: {len(df)}")

Output: markup

Successfully loaded clean data. Total rows: 52933

Product Deep Dive: Who Are the True Money Makers?

With the clean data loaded, let’s jump straight into product performance. Products can be considered "best-sellers" in two different ways: by volume (units sold) or by value (revenue generated).

Insight 2: Top 10 Bestsellers (by Quantity)

The quantity list tells us which products are popular and in high demand, even if their price is low. This is important for warehouse stocking and inventory management. We’ll group by the product Description, sum the Quantity, and sort it descendingly. python

# Top 10 Bestsellers (by Quantity)
df.groupby(‘Description’)[‘Quantity’].sum().sort_values(ascending=False).head(10)

Output: markup

DescriptionMEDIUM CERAMIC TOP STORAGE JAR 74698WORLD WAR 2 GLIDERS ASSTD DESIGNS 9419GIN + TONIC DIET METAL SIGN 5016ASSORTED COLOURS SILK FAN 4684JUMBO BAG RED RETROSPOT 4671PACK OF 72 RETROSPOT CAKE CASES 3561MINI PAINT SET VINTAGE 3285ASSORTED COLOUR BIRD ORNAMENT 2783BROCADE RING PURSE 2525POPCORN HOLDER 2508Name: Quantity, dtype: int64

Insight 3: Top 10 Revenue Drivers (The True Money-Makers)

This is what NovaShop really wants to know. These products drive profitability. They might not sell as many units as the items in the previous list, but their higher price or larger bulk orders make them far more valuable. We follow the same process, but this time we aggregate on the Revenue column we engineered in Part 1. python

# Top 10 Revenue Drivers (The True Money-Makers)
df.groupby(‘Description’)[‘Revenue’].sum().sort_values(ascending=False).head(10)

Output: markup

DescriptionMEDIUM CERAMIC TOP STORAGE JAR 77785.74DOTCOM POSTAGE 18456.13REGENCY CAKESTAND 3 TIER 15093.38AMAZON FEE 13541.33PARTY BUNTING 9491.60GIN + TONIC DIET METAL SIGN 9480.51JUMBO BAG RED RETROSPOT 8996.65Manual 8966.96CHILLI LIGHTS 8395.20POSTAGE 7194.51Name: Revenue, dtype: float64

Discussion: What These Lists Tell NovaShop This is where the power of EDA truly shines, because these two lists tell a very different story:

We now have a complete picture of what NovaShop sells best. Time to figure out when!

Preparing for Time-Series Analysis: Feature Engineering

We know what sold well. Now, let’s figure out when sales peak. Our goal is to break down the InvoiceDate column into components that allow us to group and analyze sales by year, month, day, and even hour. This is a classic feature engineering move. Since we already made sure InvoiceDate is a proper Pandas datetime object (thanks to parse_dates in our loading step!), we can use the extremely useful .dt accessor.

Extracting Time Components

To understand seasonality (monthly) and operational efficiency (hourly), we’ll create four new columns.

Let’s generate these columns: python

print(“\n — — Time Series Feature Extraction — -”)

# Extract Year, Month, DayName, and Hour from the InvoiceDate column
df[‘Year’] = df[‘InvoiceDate’].dt.year
df[‘Month’] = df[‘InvoiceDate’].dt.month
df[‘DayName’] = df[‘InvoiceDate’].dt.day_name()
df[‘Hour’] = df[‘InvoiceDate’].dt.hour
print(“New time features added: Year, Month, DayName, Hour.”)
print(df[[‘InvoiceDate’, ‘Year’, ‘Month’, ‘DayName’, ‘Hour’]].head())

Output: markup

--- Time Series Feature Extraction ---New time features added: Year, Month, DayName, Hour.InvoiceDate Year Month DayName Hour0 2011-06-01 12:05:00 2011 6 Wednesday 121 2011-05-27 17:14:00 2011 5 Friday 172 2011-04-21 17:05:00 2011 4 Thursday 173 2011-11-16 10:39:00 2011 11 Wednesday 104 2011-03-10 08:40:00 2011 3 Thursday 8

Perfect! We can move right into mapping the sales patterns in the next section.

Mapping Sales Patterns (Time-Series Insights)

With our time features ready, we can now ask and answer our questions about when sales occur. We’ll start big (monthly trends) and drill down small (hourly trends).

Insight 4: Sales Trends by Month (Seasonality)

Monthly aggregation is crucial for spotting seasonality — the predictable pattern of sales repeating every year. This data is used for financial forecasting and planning inventory levels for the peak season. We’ll group by the Month column and calculate the total revenue for each. python

print(“\n — — Insight 4: Sales Trends by Month (Seasonality) — -”)
# Group by month and sum the revenue
monthly_revenue = df.groupby(‘Month’)[‘Revenue’].sum().sort_values(ascending=False)
# Print the results, which should show the seasonal peaks
print(monthly_revenue)

Output: markup

--- Insight 4: Sales Trends by Month (Seasonality) ---Month11 143576.3601 142013.42012 133178.98010 119533.5409 103929.4203 72968.2708 71302.8905 70424.5106 68722.5207 68713.8314 51882.0102 50178.730Name: Revenue, dtype: float64

Interpretation: The Massive Q4 and January Surprise The data clearly shows that NovaShop’s sales are heavily skewed toward the end of the year, confirming the typical retail Q4 (October, November, December) rush.

Insight 5: Sales Trends by Day of Week and Hour (Operational Planning)

While seasonality is about finance and inventory, daily and hourly trends are about operations. NovaShop can use this to schedule warehouse staff, optimize ad spend, and time email campaigns.
We’ll run two separate aggregations here: one for the day of the week and one for the hour of the day. Revenue by Day of Week python

# 1. Sales by Day of Week
daily_revenue = df.groupby(‘DayName’)[‘Revenue’].sum()
print(“\n — — Revenue by Day of Week — -”)
print(daily_revenue)

Output: markup

--- Revenue by Day of Week ---DayNameFriday 163861.320Monday 171026.230Sunday 83125.890Thursday 219342.980Tuesday 282796.741Wednesday 176271.320Name: Revenue, dtype: float64

Interpretation: Tuesday is the Power Day The data reveals a clear and actionable pattern for the work week:

Revenue by Hour of Day python

# 2. Sales by Hour of Day
hourly_revenue = df.groupby(‘Hour’)[‘Revenue’].sum().sort_index()
print(“\n — — Revenue by Hour of Day — -”)
print(hourly_revenue)

Output: markup

--- Revenue by Hour of Day ---Hour7 2830.9108 26597.8009 76768.75010 209809.97111 115233.60012 142474.46013 130348.29014 119241.52015 145178.98016 70620.55017 36148.03018 14022.79019 4397.13020 2751.700

Interpretation: The Late Morning Boom The hourly data points directly to operational needs:

Conclusion: Setting the Stage for Customer Segmentation

We have officially finished the heavy-duty EDA! We know what sells best (the Ceramic Jar and fees), where sales are strongest (the UK), and when the sales peaks occur (Q4, Tuesdays, and 10 AM). However, we are still missing the most valuable piece of the puzzle: The Who. The best companies don’t just know what sells; they know who their most valuable customers are and how to keep them. In Part 3, we will dive into the most advanced analysis technique in this series: RFM (Recency, Frequency, Monetary) Customer Segmentation. This will allow us to classify customers into tiers like “Champions,” “Loyal Customers,” and “At-Risk,” giving NovaShop a true roadmap for personalised marketing. I hope you found this article helpful. Feel free to say hi to me on any of these platforms. I truly appreciate your feedback. Medium LinkedIn Twitter YouTube

Register Now to Continue Reading

Unlock Towards Data Science with a Free Account

All articles on Towards Data Science are available to registered users. Create a free account today to access this article and thousands more. Register for freeSign in to your account

Written By

Ibrahim Salami

See all from Ibrahim Salami Exploratory Data AnalysisMachine LearningPandasProgrammingPython Share This Article

Towards Data Science is a community publication. Submit your insights to reach our global audience and earn through the TDS Author Payment Program. Write for TDS

Related Articles

Machine learning that pays the bills: choosing models in business contexts

Machine Learning Sophisticated models look good on research papers but might not pay off in business use cases Fabio Baccarin December 28, 202014 min read

What Stops You From Getting Your First Data Science Job?

Machine Learning Walkthrough of the data science interview funnel and steps to get your first offer Alex Vamvakaris March 23, 202312 min read

Data Science Interview at Shopee Singapore

Artificial Intelligence Here are some tips for preparing for your next data science interviews. Lai Woen Yon August 15, 202118 min read

Time Series Modeling with Orbit 101

Programming An introductory tutorial for Orbit (Object-Oriented Bayesian Time Series Forecasting) Ariel Jiang April 28, 202212 min read

3 Key Career Decisions for Junior Data Scientists

Data Science A roadmap to avoiding the "default path" and finding fulfilment in work Matt Chapman November 2, 20237 min read

The Devil's Roulette: a Failure of Expected Value

Machine Learning Notes on Risk, Reward and Ruin in Stochastic Games Douglas Hamilton May 24, 20218 min read

Exploratory Data Analysis

Machine Learning There are a lot of engineers who have never been involved in the field of... Kirill Bobrov May 12, 20219 min read

Log Breadcrumbs: only show Logs leading up to an Error

Programming Hot to log Breadcrumbs using Python's built-int logging package Mike Huls November 5, 20245 min read

All you need to know about Non-Inferiority Hypothesis Test

Machine Learning A non-inferiority test proves that a new treatment is not worse than the standard by more than a clinically acceptable margin Prateek Jain October 18, 20245 min read

Your home for data science and AI. The world's leading publication for data science, data analytics, data engineering, machine learning, and artificial intelligence professionals. Subscribe to Our NewsletterWrite For TDS•About•Advertise•Privacy Policy•Terms of Use © Insight Media Group, LLC 2026•The New Stack•roadmap.sh•Creator Network

Recommended Articles

Close