Why exploratory inspection guides analysis in Data Analysis Python - Challenge Your Understanding

Challenge - 5 Problems

🧠 Conceptual

intermediate

Why is exploratory data inspection important before analysis?

Which of the following best explains why we perform exploratory data inspection before starting formal analysis?

A To finalize conclusions without looking at the data distribution.

B To understand data quality, spot missing values, and detect unusual patterns that affect analysis.

C To immediately apply machine learning models without checking data.

D To skip data cleaning and jump directly to visualization.

💡 Hint

Think about what problems might exist in raw data that could mislead your analysis.

Exploratory inspection helps identify data issues like missing values or outliers early. This ensures analysis is based on clean, reliable data.

❓ data_output

intermediate

Output of basic exploratory commands on a dataset

Given the dataset below, what is the output of df.describe()?

import pandas as pd
data = {'age': [25, 30, 22, 40, 28], 'income': [50000, 60000, 45000, 80000, 52000]}
df = pd.DataFrame(data)
print(df.describe())

A

       age        income
count   5.0      5.000000
mean   29.0  57400.000000
std     7.0  13629.969289
min    22.0  45000.000000
25%    25.0  50000.000000
50%    28.0  52000.000000
75%    30.0  60000.000000
max    40.0  80000.000000

B

       age        income
count   4.0      4.000000
mean   29.0  57400.000000
std     7.0  13629.969289
min    22.0  45000.000000
25%    25.0  50000.000000
50%    28.0  52000.000000
75%    30.0  60000.000000
max    40.0  80000.000000

C

       age        income
count   5.0      5.000000
mean   30.0  57400.000000
std     7.0  13629.969289
min    22.0  45000.000000
25%    25.0  50000.000000
50%    28.0  52000.000000
75%    30.0  60000.000000
max    40.0  80000.000000

D

       age        income
count   5.0      5.000000
mean   29.0  57000.000000
std     7.0  13629.969289
min    22.0  45000.000000
25%    25.0  50000.000000
50%    28.0  52000.000000
75%    30.0  60000.000000
max    40.0  80000.000000

💡 Hint

Check the count and mean values carefully for both columns.

The describe() method shows count, mean, std, min, quartiles, and max for numeric columns. The count is 5 for both columns since there are 5 rows.

❓ visualization

advanced

Identifying outliers with boxplot visualization

Which boxplot below correctly shows an outlier in the dataset [10, 12, 12, 13, 14, 15, 100]?

Data Analysis Python

import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns

data = [10, 12, 12, 13, 14, 15, 100]
df = pd.DataFrame({'values': data})
sns.boxplot(x='values', data=df)
plt.show()

A Boxplot with whiskers extending beyond 100.

B Boxplot showing multiple outliers below 10.

C Boxplot with a single point far above the upper whisker at 100, indicating an outlier.

D Boxplot with no points outside whiskers, all data within range 10 to 100.

💡 Hint

Outliers appear as points outside the whiskers in a boxplot.

The value 100 is much larger than the rest and appears as a single outlier point above the whisker in the boxplot.

🔧 Debug

advanced

Error in inspecting missing data with pandas

What error does the following code produce?

import pandas as pd
data = {'A': [1, 2, None], 'B': [4, None, 6]}
df = pd.DataFrame(data)
print(df.isnull().sum())
print(df.missing())

A No error, prints counts of missing values

B TypeError: unsupported operand type(s) for +: 'int' and 'NoneType'

C KeyError: 'missing'

D AttributeError: 'DataFrame' object has no attribute 'missing'

💡 Hint

Check if missing() is a valid pandas DataFrame method.

There is no missing() method in pandas DataFrame. The correct method to check missing values is isnull().

🚀 Application

expert

Choosing next steps after exploratory inspection

You have a dataset with many missing values in some columns and a few extreme outliers in others. After exploratory inspection, what is the best next step?

A Remove or impute missing values and consider transforming or removing outliers before analysis.

B Ignore missing values and outliers and proceed with analysis as is.

C Only visualize data without cleaning or transformation.

D Delete entire dataset and start over with new data.

💡 Hint

Think about how missing data and outliers affect analysis results.

Cleaning missing data and handling outliers ensures more accurate and reliable analysis results.

Practice

1. Why is exploratory inspection important before starting data analysis?

easy

A. It helps understand data quality and guides cleaning steps.

B. It automatically fixes all data errors.

C. It replaces the need for any analysis.

D. It only shows the last rows of data.

Solution

1. Step 1: Understand the purpose of exploratory inspection

   Exploratory inspection helps us see what the data looks like and if there are any problems.

2. Step 2: Connect inspection to analysis planning

   Knowing data quality helps decide how to clean and analyze the data properly.

3. Final Answer:

   It helps understand data quality and guides cleaning steps. -> Option A

4. Quick Check:

   Exploratory inspection guides analysis = B [OK]

Hint: Exploratory inspection reveals data issues early [OK]

Common Mistakes:

• Thinking inspection fixes errors automatically
• Believing inspection replaces analysis
• Confusing head() with tail()

2. Which of the following Python commands is correct to quickly see the first 5 rows of a DataFrame named df?

easy

A. df.show()

B. df.first5()

C. df.top()

D. df.head()

Solution

1. Step 1: Recall the method to view first rows

   The standard method to view the first 5 rows in pandas is head().

2. Step 2: Check other options for validity

   Methods like first5(), top(), and show() do not exist in pandas DataFrame.

3. Final Answer:

   df.head() -> Option D

4. Quick Check:

   df.head() shows first rows [OK]

Hint: Use df.head() to preview first rows [OK]

Common Mistakes:

• Using non-existent methods like df.top()
• Confusing df.head() with df.tail()
• Forgetting parentheses after method name

3. Given the code:

import pandas as pd
data = {'age': [25, 30, 22, 40], 'income': [50000, 60000, 45000, 80000]}
df = pd.DataFrame(data)
print(df.describe())

What will be the output?

medium

A. Summary statistics including count, mean, std, min, 25%, 50%, 75%, max for each column.

B. Only the first 5 rows of the DataFrame.

C. Data types of each column.

D. An error because describe() needs parameters.

Solution

1. Step 1: Understand what df.describe() does

   The describe() method gives summary statistics like count, mean, std, min, quartiles, and max for numeric columns.

2. Step 2: Check the code context

   The DataFrame has numeric columns 'age' and 'income', so describe() will output their statistics.

3. Final Answer:

   Summary statistics including count, mean, std, min, 25%, 50%, 75%, max for each column. -> Option A

4. Quick Check:

   df.describe() = summary stats [OK]

Hint: describe() summarizes numeric columns [OK]

Common Mistakes:

• Thinking describe() shows data rows
• Expecting data types from describe()
• Assuming describe() needs arguments

4. What is wrong with this code snippet for inspecting a DataFrame df?

print(df.info)

medium

A. print() cannot be used with info().

B. Missing parentheses to call the info() method.

C. info() is not a valid method for DataFrame.

D. df.info() returns data, not info.

Solution

1. Step 1: Identify the method call syntax error

   The code uses df.info without parentheses, so it refers to the method object, not calls it.

2. Step 2: Explain correct usage

   To execute and print the info, it should be print(df.info()) with parentheses.

3. Final Answer:

   Missing parentheses to call the info() method. -> Option B

4. Quick Check:

   Method call needs () [OK]

Hint: Always add () to call methods like info() [OK]

Common Mistakes:

• Forgetting parentheses on method calls
• Thinking info() is not a DataFrame method
• Trying to print method object instead of output

5. You have a DataFrame df with columns ['name', 'age', 'salary']. You want to check if there are missing values before analysis. Which code snippet correctly helps you decide the next steps?

hard

A. print(df.columns)

B. print(df.head(10))

C. print(df.isnull().sum())

D. print(df.describe())

Solution

1. Step 1: Identify method to check missing values

   The method isnull() returns True for missing values; summing counts them per column.

2. Step 2: Understand why other options don't help

   head() shows rows but not missing counts, describe() summarizes numeric data, and columns lists column names only.

3. Final Answer:

   print(df.isnull().sum()) -> Option C

4. Quick Check:

   Use isnull().sum() to count missing data [OK]

Hint: Use isnull().sum() to find missing values fast [OK]

Common Mistakes:

• Using head() to find missing data
• Expecting describe() to show missing counts
• Confusing columns attribute with data content