Reproducible analysis patterns in Data Analysis Python - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the output of this code using a fixed random seed?

This code sets a random seed before generating random numbers. What will be the printed output?

Data Analysis Python

import numpy as np
np.random.seed(42)
random_numbers = np.random.rand(3)
print(random_numbers)

A [0.37454012 0.95071431 0.73199394]

B [0.37454012 0.95071431 0.59865848]

C [0.5488135 0.71518937 0.60276338]

D [0.64589411 0.43758721 0.891773 ]

💡 Hint

Setting a random seed fixes the sequence of random numbers generated.

Using np.random.seed(42) fixes the random number generator's state, so np.random.rand(3) always produces the same three numbers: approximately 0.3745, 0.9507, and 0.7320.

❓ data_output

intermediate

What is the shape of the DataFrame after filtering?

Given this DataFrame and filtering code, what is the shape of the resulting DataFrame?

Data Analysis Python

import pandas as pd
data = {'A': [1, 2, 3, 4], 'B': [5, 6, 7, 8]}
df = pd.DataFrame(data)
filtered_df = df[df['A'] > 2]

A (3, 1)

B (3, 2)

C (2, 2)

D (2, 1)

💡 Hint

Count how many rows have 'A' values greater than 2.

Rows where 'A' > 2 are those with values 3 and 4, so 2 rows remain. The DataFrame has 2 columns, so shape is (2, 2).

❓ visualization

advanced

Which plot shows a reproducible histogram with fixed bins?

You want to create a histogram that looks the same every time you run the code. Which option produces a reproducible histogram with fixed bins?

Data Analysis Python

import matplotlib.pyplot as plt
import numpy as np
np.random.seed(0)
data = np.random.randn(1000)

A plt.hist(data, bins=np.linspace(-4,4,21)); plt.show()

B plt.hist(data, bins=20); plt.show()

C plt.hist(data); plt.show()

D plt.hist(data, bins='auto'); plt.show()

💡 Hint

Fixed bins mean the bin edges are explicitly set.

Option A uses fixed bin edges from -4 to 4 with 20 bins, ensuring the histogram is reproducible and consistent across runs.

🔧 Debug

advanced

What error does this code raise when saving a DataFrame without specifying index?

This code saves a DataFrame to CSV. What error or issue occurs?

Data Analysis Python

import pandas as pd
df = pd.DataFrame({'x':[1,2], 'y':[3,4]})
df.to_csv('output.csv', index=False)
with open('output.csv') as f:
    lines = f.readlines()
print(lines[0])

A IndexError

B '0,x,y\n'

C FileNotFoundError

D 'x,y\n'

💡 Hint

Check the first line of the CSV file when index=False is used.

When index=False, the CSV header contains only column names without an index column, so the first line is 'x,y\n'.

🚀 Application

expert

Which option ensures reproducible train-test split in scikit-learn?

You want to split your dataset into training and testing sets reproducibly. Which code snippet guarantees the same split every time?

Data Analysis Python

from sklearn.model_selection import train_test_split
X = [[i] for i in range(10)]
y = [0,1,0,1,0,1,0,1,0,1]

A train_test_split(X, y, test_size=0.3, shuffle=False)

B train_test_split(X, y, test_size=0.3, random_state=42)

C train_test_split(X, y, test_size=0.3)

D train_test_split(X, y, test_size=0.3, random_state=None)

💡 Hint

Setting random_state fixes the randomness of the split.

Only specifying random_state=42 ensures the split is the same every time you run the code.