Web analytics data pattern in Data Analysis Python - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a web analytics data pattern?

A web analytics data pattern is a repeated trend or behavior found in website data, like user visits, clicks, or time spent on pages. It helps understand how people use a website.

beginner

Why is identifying patterns in web analytics important?

Identifying patterns helps businesses improve their website by knowing what users like or dislike, which pages are popular, and where users leave the site.

beginner

Which Python library is commonly used to analyze web analytics data?

Pandas is commonly used to organize and analyze web analytics data because it handles tables of data easily.

intermediate

What does a time series pattern in web analytics show?

A time series pattern shows how website metrics like visits or clicks change over time, helping spot trends like daily or weekly peaks.

beginner

How can visualization help with web analytics data patterns?

Visualization like line charts or heatmaps makes it easier to see patterns and trends in web data quickly, helping make better decisions.

What does a web analytics data pattern help you understand?

A Server hardware specs

B How to code a website

C User behavior on a website

D Email marketing strategies

Web analytics data patterns show how users behave on a website, like which pages they visit or how long they stay.

Which Python library is best for handling web analytics data tables?

A Pandas

B Matplotlib

C NumPy

D Requests

Pandas is designed to work with tables of data, making it ideal for web analytics data.

What kind of pattern shows website visits changing over days or weeks?

A Categorical pattern

B Random pattern

C Geographical pattern

D Time series pattern

Time series patterns track changes in data over time, like daily or weekly website visits.

Why use visualization in web analytics?

A To write code faster

B To see data patterns clearly

C To increase website speed

D To store data securely

Visualization helps reveal patterns and trends in data that are hard to spot in raw numbers.

Which metric is NOT typically part of web analytics data?

A Server CPU usage

B Click rates

C User age

D Page views

Server CPU usage is a technical metric, not part of user-focused web analytics data.

Explain what a web analytics data pattern is and why it matters.

Think about repeated trends in website user data.

Describe how you would use Python to find patterns in web analytics data.

Consider data tables and charts.

Practice

1. What does a web analytics data pattern typically help you understand about website visitors?

easy

A. The website's server hardware specifications

B. The programming language used to build the website

C. How visitors interact with the website

D. The color scheme of the website

Solution

1. Step 1: Understand the purpose of web analytics data

   Web analytics data tracks visitor actions like page views and clicks.

2. Step 2: Identify what patterns reveal

   Patterns show how visitors interact, such as popular pages and visit duration.

3. Final Answer:

   How visitors interact with the website -> Option C

4. Quick Check:

   Visitor interaction = Understanding web analytics data [OK]

Hint: Web analytics = visitor behavior on site [OK]

Common Mistakes:

• Confusing analytics with technical website details
• Thinking analytics shows website design choices
• Assuming analytics reveals server specs

2. Which Python code snippet correctly counts page visits from a list of page names called pages?

easy

A. from collections import Counter
visit_counts = Counter(pages)

B. visit_counts = pages.count()

C. visit_counts = sum(pages)

D. visit_counts = pages.length()

Solution

1. Step 1: Identify correct method to count items in a list

   Python's collections.Counter counts occurrences of each item in a list.

2. Step 2: Check each option's validity

   from collections import Counter visit_counts = Counter(pages) uses Counter(pages) correctly. Others use invalid methods or wrong functions.

3. Final Answer:

   from collections import Counter\nvisit_counts = Counter(pages) -> Option A

4. Quick Check:

   Use Counter to count list items [OK]

Hint: Use Counter to count list items quickly [OK]

Common Mistakes:

• Using .count() without argument
• Trying to sum strings
• Using .length() which is not a Python method

3. Given this code, what is the output?

import pandas as pd

# Sample data
web_data = pd.DataFrame({
    'page': ['home', 'about', 'home', 'contact', 'home', 'about'],
    'duration': [30, 45, 25, 10, 35, 50]
})

# Calculate average duration per page
avg_duration = web_data.groupby('page')['duration'].mean().round(1)
print(avg_duration)

medium

A. page
about 47.5
contact 10.0
home 30.0
Name: duration, dtype: int64

B. page
about 45.0
contact 10.0
home 30.0
Name: duration, dtype: float64

C. page
about 47.5
contact 10.0
home 30.5
Name: duration, dtype: float64

D. page
about 47.5
contact 10.0
home 30.0
Name: duration, dtype: float64

Solution

1. Step 1: Group data by 'page' and calculate mean duration

   For 'about': (45 + 50) / 2 = 47.5; 'contact': 10; 'home': (30 + 25 + 35) / 3 = 30.0

2. Step 2: Round the means to 1 decimal place

   Values are 47.5, 10.0, and 30.0 respectively, matching page about 47.5 contact 10.0 home 30.0 Name: duration, dtype: float64.

3. Final Answer:

   page\nabout 47.5\ncontact 10.0\nhome 30.0\nName: duration, dtype: float64 -> Option D

4. Quick Check:

   Mean durations rounded = page about 47.5 contact 10.0 home 30.0 Name: duration, dtype: float64 [OK]

Hint: Calculate group means carefully and round [OK]

Common Mistakes:

• Incorrect averaging of durations
• Not rounding results
• Confusing data types in output

4. The following code is intended to find the most visited page, but it raises an error. What is the error?

import pandas as pd

web_data = pd.DataFrame({
    'page': ['home', 'about', 'home', 'contact', 'home', 'about']
})

most_visited = web_data['page'].max()
print(most_visited)

medium

A. The DataFrame is missing a 'visits' column

B. Using max() returns the lexicographically largest page, not the most visited

C. max() function is not defined for pandas Series

D. The code has a syntax error in DataFrame creation

Solution

1. Step 1: Understand what max() does on a string column

   max() returns the largest value alphabetically, not the count of visits.

2. Step 2: Identify correct method to find most visited page

   Use value_counts().idxmax() to find the page with highest visits.

3. Final Answer:

   Using max() returns the lexicographically largest page, not the most visited -> Option B

4. Quick Check:

   max() on strings = lex order, not frequency [OK]

Hint: Use value_counts() to find most visited page [OK]

Common Mistakes:

• Assuming max() finds most frequent item
• Expecting max() to count occurrences
• Confusing max() with mode()

5. You have a DataFrame visits with columns user_id, page, and duration (seconds spent). How would you find the average duration per user for only pages visited more than twice by that user?

hard

A. Group by user and page, filter groups with count > 2, then average durations per user

B. Filter rows where duration > 2, then group by user and average duration

C. Group by user, count pages, then average duration ignoring counts

D. Sum durations per user and divide by total pages visited

Solution

1. Step 1: Group data by user and page to count visits

   Use groupby(['user_id', 'page']) and filter groups with count > 2.

2. Step 2: Calculate average duration per user from filtered data

   After filtering, group by user_id and compute mean duration.

3. Final Answer:

   Group by user and page, filter groups with count > 2, then average durations per user -> Option A

4. Quick Check:

   Filter by visit count, then average durations per user [OK]

Hint: Filter groups by count > 2 before averaging durations [OK]

Common Mistakes:

• Filtering by duration instead of visit count
• Ignoring grouping by page before filtering
• Averaging durations without filtering visits