Missing data strategies decision in Pandas - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Choosing the best strategy for missing data in a dataset

You have a dataset with 10% missing values in a column that represents age. The missing values are random and not related to other variables. Which missing data strategy is most appropriate?

A Fill missing age values with the mean age of the column.

B Remove all rows with missing age values.

C Fill missing age values with zero.

D Leave the missing values as they are.

💡 Hint

Think about preserving as much data as possible and using a simple method for random missing values.

Since missing values are random and only 10%, filling with the mean preserves data and avoids bias. Removing rows loses data unnecessarily. Filling with zero is misleading. Leaving missing values can cause errors in analysis.

❓ Predict Output

intermediate

Output of filling missing values with forward fill

What is the output of the following code?

Pandas

import pandas as pd

data = {'score': [10, None, None, 20, None, 30]}
df = pd.DataFrame(data)
df_filled = df.fillna(method='ffill')
print(df_filled)

A

   score
0   10.0
1   10.0
2   10.0
3   20.0
4   20.0
5    NaN

B

   score
0   10.0
1    NaN
2    NaN
3   20.0
4    NaN
5   30.0

C

   score
0   10.0
1   10.0
2   10.0
3   20.0
4    NaN
5   30.0

D

   score
0   10.0
1   10.0
2   10.0
3   20.0
4   20.0
5   30.0

💡 Hint

Forward fill replaces missing values with the last known value above.

Forward fill replaces each missing value with the previous non-missing value. So the None values after 10 become 10, after 20 become 20, and so on.

❓ data_output

advanced

Result of dropping rows with missing values

Given the DataFrame below, what is the result after dropping rows with any missing values?

Pandas

import pandas as pd

data = {'A': [1, 2, None, 4], 'B': [None, 2, 3, 4]}
df = pd.DataFrame(data)
df_clean = df.dropna()
print(df_clean)

A

   A    B
1  2.0  2.0
3  4.0  4.0

B Empty DataFrame with columns A and B and 0 rows

C

   A    B
0  1.0  NaN
1  2.0  2.0
2  NaN  3.0
3  4.0  4.0

D

   A    B
0  1.0  NaN
3  4.0  4.0

💡 Hint

dropna() removes rows with any missing value.

Rows 0 and 2 have missing values, so they are dropped. Rows 1 and 3 have no missing values and remain.

🔧 Debug

advanced

Identify the error in filling missing values with median

What error does the following code raise?

Pandas

import pandas as pd

data = {'height': [150, 160, None, 170, None]}
df = pd.DataFrame(data)
df['height'] = df['height'].fillna(df['height'].median())
print(df)

A TypeError because median() returns a string.

B No error, prints DataFrame with missing values filled by median.

C KeyError because 'height' column does not exist.

D AttributeError because fillna() is not a method of Series.

💡 Hint

Check if the methods and column names are correct.

The code correctly fills missing values with the median of the 'height' column. No error occurs.

🚀 Application

expert

Choosing the best missing data strategy for time series data

You have a time series dataset with missing temperature readings at random times. You want to fill missing values to keep the time order intact and avoid introducing bias. Which strategy is best?

A Fill missing values with the overall mean temperature.

B Remove all rows with missing temperature values.

C Use forward fill to propagate last known temperature forward.

D Fill missing values with zero.

💡 Hint

Think about preserving time order and realistic values.

Forward fill keeps the time order and uses the last known value, which is common for time series. Mean or zero can distort trends. Removing rows loses data and breaks continuity.