Data Scientist Practice Tests: 5 Practice Tests and 205 Questions
Data Scientist Skills
205
Statistics and Probability | Descriptive statistics, distributions, hypothesis tests, confidence intervals and Bayes (15%)
Deep Learning | Neural network layers, activations, CNNs, RNNs and LSTMs, optimisers and training (16%)
Machine Learning Algorithms | Regression, trees, ensembles, SVMs, k-NN, clustering and dimensionality reduction (14%)
Model Evaluation and Metrics | Confusion matrix, precision, recall, F1, ROC AUC, regression metrics and validation (14%)
Machine Learning Fundamentals | Learning types, overfitting, regularisation, gradient descent and hyperparameters (12%)
Data Preparation and Feature Engineering | Cleaning, missing values, outliers, encoding, scaling and leakage (11%)
NLP and Computer Vision | Tokenization, n-grams, embeddings, NER, image classification, detection and segmentation (9%)
Data Tools and Databases | Python, R, pandas, SQL, relational databases and JSON (5%)
Responsible AI and MLOps | Bias, privacy, interpretability, model drift and reproducibility (4%)
Data Preparation and Feature Engineering
A data scientist standardises the whole dataset with StandardScaler and then splits it into training and test sets. What is wrong with this workflow?
StandardScaler cannot be used before a train-test split
The scaler learned the mean and standard deviation from the test data too, leaking information into training
Standardisation should only be applied to the target column
Nothing; fitting the scaler on all data is the recommended practice
B
Any preprocessing step that learns statistics must be fitted on the training data only and then applied to the test data. Fitting the scaler on the full dataset leaks test-set information and makes the evaluation look better than it is. A scikit-learn Pipeline prevents this by refitting every step on each training fold.
https://exametics.com/product/certified-data-scientist-practice-exams/
Course Content
Supporting Resources
You don't currently have access to this content
Data Scientist Mastery Assessment – Practice Test #1
You don't currently have access to this content
Data Scientist Mastery Assessment – Practice Test #2
You don't currently have access to this content
Data Scientist Mastery Assessment – Practice Test #3
You don't currently have access to this content
Data Scientist Mastery Assessment – Practice Test #4
You don't currently have access to this content
Exam Mode: Data Scientist Mastery Assessment – Practice Test #5
You don't currently have access to this content
