The IIT Madras BS Machine Learning Practice (MLP) End Term paper sat on 22 Dec 2024, in the September 2024 term, set QDD1: 37 questions for 100 marks in 180 minutes. Every question is below with its answer. Take it as a timed mock test to be marked, or read it through first.
Dataset: Employee Details
| Name | Age | Department | Salary | Joining_Year | Performance_Score |
|---|---|---|---|---|---|
| Alice | 25 | HR | 50000 | 2018 | 85 |
| Bob | 30 | Finance | 60000 | 2015 | 90 |
| Charlie | 35 | IT | 55000 | 2019 | 88 |
| Diana | 28 | HR | 52000 | 2020 | 75 |
| Eve | 22 | Finance | 48000 | 2021 | 80 |
| Frank | 40 | IT | 65000 | 2010 | 92 |
Based on the above data, answer the given subquestions.
Which of the following commands will return the average age of employees?
Correct answer
Dataset: Employee Details
| Name | Age | Department | Salary | Joining_Year | Performance_Score |
|---|---|---|---|---|---|
| Alice | 25 | HR | 50000 | 2018 | 85 |
| Bob | 30 | Finance | 60000 | 2015 | 90 |
| Charlie | 35 | IT | 55000 | 2019 | 88 |
| Diana | 28 | HR | 52000 | 2020 | 75 |
| Eve | 22 | Finance | 48000 | 2021 | 80 |
| Frank | 40 | IT | 65000 | 2010 | 92 |
Based on the above data, answer the given subquestions.
Which of the following commands will return the number of employees in the 'HR ’ department?
Correct answers
Dataset: Employee Details
| Name | Age | Department | Salary | Joining_Year | Performance_Score |
|---|---|---|---|---|---|
| Alice | 25 | HR | 50000 | 2018 | 85 |
| Bob | 30 | Finance | 60000 | 2015 | 90 |
| Charlie | 35 | IT | 55000 | 2019 | 88 |
| Diana | 28 | HR | 52000 | 2020 | 75 |
| Eve | 22 | Finance | 48000 | 2021 | 80 |
| Frank | 40 | IT | 65000 | 2010 | 92 |
Based on the above data, answer the given subquestions.
Which of the following methods can be used to filter employees with a salary greater than 50,000?
Correct answers
Dataset: Employee Details
| Name | Age | Department | Salary | Joining_Year | Performance_Score |
|---|---|---|---|---|---|
| Alice | 25 | HR | 50000 | 2018 | 85 |
| Bob | 30 | Finance | 60000 | 2015 | 90 |
| Charlie | 35 | IT | 55000 | 2019 | 88 |
| Diana | 28 | HR | 52000 | 2020 | 75 |
| Eve | 22 | Finance | 48000 | 2021 | 80 |
| Frank | 40 | IT | 65000 | 2010 | 92 |
Based on the above data, answer the given subquestions.
What does the following code return?
The row with the employee who has the lowest performance score.
The row with the employee who has the highest performance score.
The row with the highest salary.
None of these.
Correct answer
The row with the employee who has the highest performance score.
Which of the following code snippets will plot the learning curve for training over 100 epochs? Assume that all necessary imports, parameter settings, and initializations are correctly done, and the variable names suggest the data they hold or point to.
Correct answer
Consider the following initialization of a DecisionTreeClassifier:
clf = DecisionTreeClassifier(max_depth=3, random_state=42, splitter='best')If the training data consists of 100 samples and 10 features, what is the maximum possible number of leaf nodes that can exist in the decision tree, assuming the following conditions:
min_samples_split, min_samples_leaf, max_leaf_nodes).8
16
32
100
Correct answer
8
Consider the following code:
import numpy as npfrom sklearn.linear_model import LinearRegressionX = np.array([[2, 3], [3, 4], [4, 5], [5, 6], [6, 7], [7, 8]])# y = 4 * x_0 + 5 * x_1 + 6y = np.dot(X, np.array([4, 5])) + 6
reg1 = LinearRegression(fit_intercept=True).fit(X, y)s1 = reg1.score(X, y)
reg2 = LinearRegression(fit_intercept=False).fit(X, y)s2 = reg2.score(X, y)Which of the following is true in this case?
Correct answer
Consider the following code:
from sklearn.preprocessing import PolynomialFeaturesimport numpy as np
X = np.array([[1], [2], [3]])poly = PolynomialFeatures(degree=2)X_poly = poly.fit_transform(X)print(X_poly)What will be the output of the above code?
Correct answer
Correct answer
The following code produces an output of 0.9125 on the training data. What is the expected effect on the training accuracy if we increase the max_depth value ?:
from sklearn.datasets import load_winefrom sklearn.tree import DecisionTreeClassifierfrom sklearn.model_selection import train_test_splitX,y = load_wine(as_frame = True, return_X_y = True)
X_train,X_test,y_train,y_test = train_test_split(X, y, test_size = 0.10, random_state = 12)
clf = DecisionTreeClassifier(max_depth = 2, min_samples_split = 2, min_samples_leaf=3, random_state = 81)
clf.fit(X_train, y_train)print(clf.score(X_train, y_train))Output score is likely to increase.
Output score is likely to decrease.
Output score may increase or decrease depending on other factors.
Output score will remain the same.
Correct answer
Output score is likely to increase.
The number of base estimators to be trained.
The size of each sample batch for testing.
The maximum number of features used for training.
The number of samples to draw from X to train each base estimator
Correct answer
The number of samples to draw from X to train each base estimator
Performs hierarchical clustering and outputs cluster distances.
Outputs the silhouette score for the data points.
Groups data points into 2 clusters and outputs the labels of the clusters for each data point.
Reduces the dimensionality of the dataset to 2 dimensions.
Correct answer
Groups data points into 2 clusters and outputs the labels of the clusters for each data point.
You're working on a binary classification task using the ‘MLPClassifier’ to predict whether a customer will make a purchase based on their browsing behavior. You're concerned about overfitting due to the complexity of the model. You decide to increase the ‘alpha’ parameter to control overfitting. The following code snippet shows the application of ‘MLPClassifier’:
from sklearn.neural_network import MLPClassifierimport numpy as np
data = np.array([[10, 3], [20, 5], [5, 1], [15, 4], [8, 2]])
# Corresponding target labels (0: No Purchase, 1: Purchase)target = np.array([0, 1, 0, 1, 0])
# Initialize MLPClassifier with alpha parameterclf = MLPClassifier(alpha=0.01, random_state=42)clf.fit(data, target)
# Predict class labelspredicted_labels = clf.predict(data)What is the effect of increasing the alpha parameter to 0.1 in the MLPClassifier?
It increases the model’s capacity to fit the training data closely, potentially causing overfitting.
It adds a stronger regularization term to the loss function, reducing the model’s complexity and helping prevent overfitting.
It makes the model more prone to overfitting by increasing its sensitivity to noise in the training data.
It directly affects the learning rate, controlling how fast the model converges during training.
Correct answer
It adds a stronger regularization term to the loss function, reducing the model’s complexity and helping prevent overfitting.
What will be the output of the following code?
4
5
3
6
Correct answer
6
What will be the output of the following code?
[5, 6]
[4, 5]
[3, 4]
[2, 3]
Correct answer
[5, 6]
You have loaded a dataset with 500 samples and 50 features into a Pandas DataFrame. Some samples have missing values for a few features. If you want to remove rows with more than 5 missing values, what method would you use?
Correct answer
Statement 1 False, Statement 2 False
Statement 1 True, Statement 2 False
Statement 1 False, Statement 2 True
Both statements are True
Correct answer
Both statements are True
Correct answer
What will be the output of the code?
1.25
2.56
4.25
3.25
Given code will return an error.
Correct answer
2.56
Consider the following code snippet:
import numpy as npfrom sklearn.linear_model import SGDRegressorX = np.array([[1, 2], [3, 4], [5, 6], [7, 8], [9, 10]])y = np.array([3, 6, 9, 12, 15])
model = SGDRegressor(learning_rate='constant', eta0=0.1, max_iter=1000)model.fit(X, y)What does the learning_rate='constant' parameter in the SGDRegressor() function control?
It adjusts the learning rate based on the number of iterations.
It specifies the learning rate to decrease as the model converges.
It specifies the fraction of the dataset used for each step in the stochastic gradient descent.
It defines the initial value for the learning rate and keeps it constant throughout training.
Correct answer
It defines the initial value for the learning rate and keeps it constant throughout training.
Which of the following is NOT a hyperparameter in machine learning?
Learning rate in gradient descent
Bias in a linear regression model
Number of clusters in k-means
Minimum leaf size in decision trees
Correct answer
Bias in a linear regression model
Given below code to load a huge file name as filename.csv and this file is not loading at once in the system which parameter should be added to pd.read_csv to load this file ?
import pandas as pdfrom sklearn.linear_model import SGDRegressorfor train_df in pd.read_csv("filename.csv", __________=1024): X = train_df.iloc[:, :-1] y = train_df.iloc[:, -1] model = SGDRegressor() model.partial_fit(prep_X,y)Correct answer
It decreases the variance among individual trees.
It increases the variance among individual trees.
It reduces the number of samples used for training each tree.
It reduces overfitting by restricting tree depth.
Correct answer
It increases the variance among individual trees.
Consider the following code:
import numpy as npfrom sklearn.model_selection import KFold
X = np.array([47, 31, 18, 95, 85, 77])kf = KFold(n_splits=3)for train, test in kf.split(X): print(X[train])Which of the following sets of training data can not be printed during the iteration of StratifiedKFold splits, considering the stratification constraint?
[47, 31, 18, 95, 77]
[31, 41, 85, 31]
[47, 31, 18]
[47, 31, 85, 77]
[31, 41, 18, 95, 85, 77]
[18, 95, 85, 77]
Correct answers
[47, 31, 18, 95, 77]
[31, 41, 85, 31]
[47, 31, 18]
[31, 41, 18, 95, 85, 77]
What happens when the following code is executed?
from sklearn.ensemble import GradientBoostingClassifierfrom sklearn.model_selection import GridSearchCVimport numpy as np
# Example training data (100 samples, 10 features)X = np.random.rand(100, 10)y = np.random.randint(0, 2, 100)
param_grid = {'n_estimators': [50, 100], 'learning_rate': [0.1, 0.01]}grid = GridSearchCV(GradientBoostingClassifier(), param_grid, cv=3)grid.fit(X, y)Correct answers
The neural network contains 3 hidden layers with 5 neurons in each hidden layer
The neural network contains 5 hidden layers with 3 neurons in each hidden layer
The neural network contains 2 hidden layers with 3 neurons in the second hidden layer
The neural network contains 2 hidden layers with 5 neurons in the first hidden layer
None of the given options are correct
Correct answers
The neural network contains 2 hidden layers with 3 neurons in the second hidden layer
The neural network contains 2 hidden layers with 5 neurons in the first hidden layer
Consider the following code snippet using scikit-learn:
sgd_regressor = SGDRegressor()
param_dist = { 'loss': ['squared_loss', 'huber', 'epsilon_insensitive'], 'alpha': loguniform(1e-4, 1e0), 'penalty': ['l1', 'l2', 'elasticnet'], 'epsilon': loguniform(1e-4, 1e-1),}
random_search = RandomizedSearchCV(sgd_regressor, param_distributions=param_dist, n_iter=10, cv=3, scoring='neg_mean_squared_error')random_search.fit(X, y)Assume all the necessary imports and to be the training dataset. Which of the following statements about the given code are correct?
Correct answers
GaussianNB
LogisticRegression
SGDClassifier
RandomForestClassifier
Correct answers
GaussianNB
SGDClassifier
Correct answers
What parameters of the k-means clustering algorithm should be tuned to optimize the model performance?
Correct answers
Consider the following options for evaluating the optimal number of clusters in k-means. Which approaches are valid?
Using an Elbow Curve.
Computing Silhouette Scores.
Cross-validation with multiple folds.
All of these
Correct answers
Using an Elbow Curve.
Computing Silhouette Scores.
Which of the following statements are correct about the Silhouette Coefficient?
It measures how well each sample is clustered.
A higher score indicates better-defined clusters.
It requires ground truth labels (target variable) to compute.
It can be used to evaluate the quality of any clustering algorithm.
Correct answers
It measures how well each sample is clustered.
A higher score indicates better-defined clusters.
It can be used to evaluate the quality of any clustering algorithm.
Correct answers
Given a dataset with shape (4 samples and 3 features), apply the VarianceThreshold method with a threshold of 0.1. What will be the output of the following code?
from sklearn.feature_selection import VarianceThreshold
data = [ [1, 2, 3], [1, 2, 3], [1, 2, 4], [1, 2, 3] ]
# Apply VarianceThreshold with threshold 0.1vf = VarianceThreshold(threshold=0.1)
# Fit the VarianceThreshold and transform the dataselected_data = vf.fit_transform(data)
# Hint: Columns with variance below the threshold will be removedselected_data.shape[1]Correct answer: 1
What will be the output of the following code snippet?
from sklearn.neighbors import KNeighborsClassifier
X_train = [[1, 50], [2, 60], [3, 70], [4, 80]]y_train = [0, 0, 1, 1]
knn = KNeighborsClassifier(n_neighbors=3)knn.fit(X_train, y_train)
X_test = [[2.5, 66]]print(knn.predict(X_test))Correct answer: 1
What will be the output of the following code?
from sklearn.tree import DecisionTreeClassifier
X_train = [[2, 50], [3, 75], [4, 100], [5, 150], [6, 200]]y_train = [0, 0, 1, 1, 1]
clf = DecisionTreeClassifier(max_depth=2, random_state=42)clf.fit(X_train, y_train)
X_test = [[4, 120]]print(clf.predict(X_test))Correct answer: 1
Consider the following code and its output:
Keep the following symbols in mind:
>>> from sklearn.datasets import load_digits>>> from sklearn.svm import SVC
>>> X, y = load_digits(return_X_y=True)>>> clf = SVC(random_state=0).fit(X, y)
>>> print(y[50:60])[0 1 0 0 1 4 4 1 4 7]
>>> print(clf.predict(X[50:60, :]))[0 1 0 0 1 4 4 1 4 7]
>>> print(clf.score(X[50:60, :], y[50:60]))What will be the output of the above code? Enter your answer correct to one decimal place.
Correct answer: 1.0