Log transformation for skewed data in Data Analysis Python - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of log transformation on skewed data

What is the output of the following Python code that applies a log transformation to a skewed data list?

Data Analysis Python

import numpy as np
import pandas as pd

skewed_data = pd.Series([1, 10, 100, 1000, 10000])
log_data = np.log(skewed_data)
print(log_data.round(2))

A [0.69, 2.30, 4.61, 6.91, 9.21]

B [0.00, 2.30, 4.61, 6.91, 9.21]

C [1, 10, 100, 1000, 10000]

D [0.00, 1.00, 2.00, 3.00, 4.00]

💡 Hint

Remember that np.log() computes the natural logarithm (base e).

The natural log of 1 is 0.00, and the logs of 10, 100, 1000, and 10000 are approximately 2.30, 4.61, 6.91, and 9.21 respectively.

❓ data_output

intermediate

Effect of log transformation on skewness

Given a skewed dataset, which option shows the correct skewness values before and after applying a log transformation?

Data Analysis Python

import numpy as np
import pandas as pd
from scipy.stats import skew

skewed_data = pd.Series([1, 2, 2, 3, 100])
skew_before = skew(skewed_data)
skew_after = skew(np.log(skewed_data))
print(round(skew_before, 2), round(skew_after, 2))

A 2.24 2.24

B 1.50 1.50

C 2.24 0.68

D 0.00 0.00

💡 Hint

Log transformation reduces skewness by compressing large values.

The original data is highly skewed (2.24), and after log transformation, skewness reduces significantly (0.68).

❓ visualization

advanced

Identify the correct plot after log transformation

Which plot correctly shows the distribution of data before and after log transformation?

Data Analysis Python

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

skewed_data = pd.Series([1, 2, 2, 3, 100])
log_data = np.log(skewed_data)

plt.figure(figsize=(8,4))
plt.subplot(1,2,1)
plt.hist(skewed_data, bins=5, color='blue')
plt.title('Original Data')
plt.subplot(1,2,2)
plt.hist(log_data, bins=5, color='green')
plt.title('Log Transformed Data')
plt.tight_layout()
plt.show()

A Left plot is right-skewed; right plot is more symmetric

B Left plot is symmetric; right plot is right-skewed

C Both plots are symmetric

D Both plots are left-skewed

💡 Hint

Log transformation reduces right skewness.

The original data histogram is right-skewed due to the large value 100. After log transform, the distribution looks more balanced.

🧠 Conceptual

advanced

Why use log transformation on skewed data?

Which option best explains why log transformation is applied to skewed data in data science?

A To reduce skewness and make data distribution more normal-like for better modeling

B To increase the range of data values for better visualization

C To convert categorical data into numerical data

D To remove missing values from the dataset

💡 Hint

Think about how skewness affects statistical models.

Log transformation compresses large values, reducing skewness and helping models that assume normality.

🔧 Debug

expert

Identify the error in log transformation code

What error will the following code raise when applying log transformation to data containing zero or negative values?

Data Analysis Python

import numpy as np
import pandas as pd

data = pd.Series([0, 1, 2, -1, 3])
log_data = np.log(data)
print(log_data)

A No error, prints log values with NaN for invalid entries

B ValueError: math domain error

C TypeError: unsupported operand type(s) for log

D RuntimeWarning: divide by zero encountered in log

💡 Hint

Logarithm of zero or negative numbers is undefined in real numbers.

np.log(0) causes a divide by zero warning; np.log of negative values results in NaN but no ValueError.