Handling missing values in Series in Data Analysis Python - Step-by-Step Execution

Concept Flow - Handling missing values in Series

Start with Series

↓

Check for missing values

↓

Option 1: Drop missing values

↓

Clean Series without NaNs

↓

Option 2: Fill missing values

↓

Series with NaNs replaced

↓

Use cleaned Series for analysis

We start with a Series that may have missing values. We check for these missing values, then either remove them or fill them with a value, resulting in a clean Series ready for analysis.

Execution Sample

Data Analysis Python

import pandas as pd
s = pd.Series([1, None, 3, None, 5])
s_drop = s.dropna()
s_fill = s.fillna(0)

This code creates a Series with missing values, then shows how to drop them or fill them with zero.

Execution Table

Step	Series State	Action	Resulting Series
1	[1, NaN, 3, NaN, 5]	Initial Series with missing values	[1, NaN, 3, NaN, 5]
2	[1, NaN, 3, NaN, 5]	Drop missing values using dropna()	[1, 3, 5]
3	[1, NaN, 3, NaN, 5]	Fill missing values with 0 using fillna(0)	[1, 0, 3, 0, 5]

💡 All missing values handled by either dropping or filling, resulting in clean Series.

Variable Tracker

Variable	Start	After dropna()	After fillna(0)
s	[1, NaN, 3, NaN, 5]	[1, NaN, 3, NaN, 5]	[1, NaN, 3, NaN, 5]
s_drop	N/A	[1, 3, 5]	N/A
s_fill	N/A	N/A	[1, 0, 3, 0, 5]

Key Moments - 2 Insights

Why does dropna() remove elements instead of replacing them?

dropna() removes any element that is missing (NaN) to keep only valid data, as shown in step 2 of the execution_table where the Series shrinks from 5 to 3 elements.

What happens to the original Series after fillna(0)?

fillna(0) creates a new Series with missing values replaced by 0, but the original Series remains unchanged, as seen in variable_tracker where 's' stays the same.

Visual Quiz - 3 Questions

Look at the execution_table at step 2. What is the length of the Series after dropna()?

A 2

B 5

C 3

D 4

💡 Hint

Check the 'Resulting Series' column at step 2 in the execution_table.

According to variable_tracker, what value replaces NaN in s_fill?

A NaN

B 0

C 1

D None

💡 Hint

Look at the 'After fillna(0)' column for s_fill in variable_tracker.

If we used fillna(99) instead of fillna(0), how would the resulting Series in step 3 change?

A [1, 99, 3, 99, 5]

B [1, 0, 3, 0, 5]

C [1, NaN, 3, NaN, 5]

D [1, 3, 5]

💡 Hint

Consider how fillna(value) replaces NaNs as shown in step 3 of execution_table.

Concept Snapshot

Handling missing values in Series:
- Use dropna() to remove missing values
- Use fillna(value) to replace missing values
- Original Series stays unchanged unless reassigned
- Clean Series is ready for analysis

Full Transcript

We start with a Series that has some missing values (NaN). We can handle these missing values in two main ways: dropping them or filling them. Using dropna(), we remove all missing values, resulting in a shorter Series with only valid data. Using fillna(value), we replace missing values with a chosen number, like zero, keeping the Series length the same. The original Series does not change unless we assign the result back. This process helps prepare data for analysis by ensuring no missing values remain.

Practice

1. What does the isna() method do when applied to a pandas Series?

easy

A. It replaces missing values with zeros.

B. It removes all missing values from the Series.

C. It counts the number of missing values in the Series.

D. It returns a Series of booleans indicating which values are missing (NaN).

Solution

1. Step 1: Understand the purpose of isna()

   The isna() method checks each element in the Series and returns True if the value is missing (NaN), otherwise False.

2. Step 2: Compare with other options

   Removing values is done by dropna(), replacing by fillna(), and counting missing values requires sum() on the boolean Series.

3. Final Answer:

   It returns a Series of booleans indicating which values are missing (NaN). -> Option D

4. Quick Check:

   isna() = boolean mask [OK]

Hint: Remember: isna() marks missing values as True [OK]

Common Mistakes:

• Confusing isna() with dropna()
• Thinking isna() replaces values
• Assuming isna() counts missing values

2. Which of the following is the correct syntax to remove missing values from a pandas Series named data?

easy

A. data.dropna()

B. data.isna()

C. data.fillna()

D. data.remove_na()

Solution

1. Step 1: Identify the method to remove missing values

   The method dropna() removes missing values from a Series.

2. Step 2: Check other options for correctness

   isna() finds missing values, fillna() replaces them, and remove_na() is not a valid pandas method.

3. Final Answer:

   data.dropna() -> Option A

4. Quick Check:

   dropna() removes NaNs [OK]

Hint: Use dropna() to delete missing values from Series [OK]

Common Mistakes:

• Using fillna() instead of dropna() to remove values
• Calling a non-existent method remove_na()
• Confusing isna() with dropna()

3. Given the Series import pandas as pd s = pd.Series([1, None, 3, None, 5]) result = s.fillna(0), what is the value of result?

medium

A. [1, 0, 3, 0, 5]

B. [1, None, 3, None, 5]

C. [0, 0, 0, 0, 0]

D. [1, 1, 3, 3, 5]

Solution

1. Step 1: Understand fillna(0) on the Series

   The fillna(0) replaces all missing values (None/NaN) with 0.

2. Step 2: Apply fillna(0) to the Series

   Original Series: [1, None, 3, None, 5]. After fillna(0): [1, 0, 3, 0, 5].

3. Final Answer:

   [1, 0, 3, 0, 5] -> Option A

4. Quick Check:

   fillna(0) replaces NaN with 0 [OK]

Hint: fillna(value) replaces NaNs with value [OK]

Common Mistakes:

• Expecting fillna() to remove values
• Thinking fillna(0) replaces all values with 0
• Confusing None with zero already present

4. What is wrong with this code snippet to remove missing values from Series s?

clean_s = s.dropna(inplace=True)
print(clean_s)

medium

A. dropna() does not have an inplace parameter.

B. print(clean_s) will print the original Series with NaNs.

C. dropna(inplace=True) returns None, so clean_s is None.

D. dropna(inplace=True) modifies a copy, not the original Series.

Solution

1. Step 1: Understand dropna(inplace=True) behavior

   When inplace=True is used, dropna() modifies the Series in place and returns None.

2. Step 2: Analyze assignment and print

   Assigning clean_s = s.dropna(inplace=True) sets clean_s to None. Printing it shows None, not the cleaned Series.

3. Final Answer:

   dropna(inplace=True) returns None, so clean_s is None. -> Option C

4. Quick Check:

   inplace=True returns None [OK]

Hint: dropna(inplace=True) returns None, don't assign it [OK]

Common Mistakes:

• Assigning dropna(inplace=True) to a variable
• Expecting dropna() to return cleaned Series with inplace=True
• Confusing inplace behavior with default dropna()

5. You have a Series s = pd.Series([1, None, 2, None, 100]). You want to replace missing values with the mean of the non-missing values. Which code correctly does this?

hard

A. s.replace(None, s.mean())

B. s.fillna(s.mean())

C. s.dropna().mean()

D. s.fillna(s.median())

Solution

1. Step 1: Calculate mean of non-missing values

   Using s.mean() calculates the average ignoring missing values.

2. Step 2: Replace missing values with mean

   fillna(s.mean()) replaces NaNs with the calculated mean.

3. Step 3: Check other options

   fillna(s.median()) replaces with median, not mean. dropna().mean() calculates mean but does not fill. replace(None, s.mean()) does not work properly for NaN.

4. Final Answer:

   s.fillna(s.mean()) -> Option B

5. Quick Check:

   fillna(mean) replaces NaNs with average [OK]

Hint: Use fillna(s.mean()) to replace NaNs with average [OK]

Common Mistakes:

• Using median instead of mean
• Calculating mean but not filling missing values
• Using replace() which doesn't handle NaN properly