{"id":4322,"date":"2020-10-15T15:02:04","date_gmt":"2020-10-15T15:02:04","guid":{"rendered":"https:\/\/data-science.gotoauthority.com\/2020\/10\/15\/how-to-ace-the-data-science-coding-challenge\/"},"modified":"2020-10-15T15:02:04","modified_gmt":"2020-10-15T15:02:04","slug":"how-to-ace-the-data-science-coding-challenge","status":"publish","type":"post","link":"https:\/\/wealthrevelation.com\/data-science\/2020\/10\/15\/how-to-ace-the-data-science-coding-challenge\/","title":{"rendered":"How to ace the data science coding challenge"},"content":{"rendered":"
\n

\"\"<\/p>\n

Image Source: Pexels.<\/em><\/p>\n

The Take-Home Challenge Problem (Coding Exercise)<\/h3>\n

\u00a0<\/p>\n

So, you\u2019ve successfully gone through the initial screening phase of the interview process. It is now time for the most important step in the interview process, namely, the take-home coding challenge<\/strong>. This is generally a data science problem, e.g., machine learning model, linear regression, classification problem, time series analysis, etc.<\/p>\n

Data science coding projects vary in scope and complexity. Sometimes, the project could be as simple as producing summary statistics, charts, and visualizations. It could also involve building a regression model, classification model, or forecasting using a time-dependent dataset. The project could also be very complex and difficult. In this case, no clear guidance is provided as to the specific type of model to use. In this case, you\u2019ll have to come up with your own model that is best suitable for addressing project goals and objectives.<\/p>\n

Generally, the interview team will provide you with project directions and a dataset. If you are fortunate, they may provide a small dataset that is clean and stored in a comma-separated value (CSV) file format. That way, you don\u2019t have to worry about mining the data and transforming it into a form suitable for analysis. For the couple of interviews I had, I worked with 2 types of datasets: one had 160 observations (rows), while the other had 50,000 observations with lots of missing values. The take-home coding exercise clearly differs from companies to companies, as further described below.<\/p>\n

In this article, I will share some useful tips from my personal experience that would help you excel in the coding challenge project. Before delving into the tips, let\u2019s first examine some sample coding exercises.<\/p>\n

\u00a0<\/p>\n

Sample 1 Coding Exercise: Model for recommending cruise ship crew size<\/h3>\n

\u00a0<\/p>\n

\n

Instructions<\/em><\/strong><\/p>\n

This coding exercise should be performed in python (which is the programming language used by the team). You are free to use the internet and any other libraries. Please save your work in a Jupyter notebook and email it to us for review.<\/em><\/p>\n

Data file: cruise_ship_info.csv (this file will be emailed to you)<\/em><\/p>\n

Objective: <\/em><\/strong>Build a regressor that recommends the \u201ccrew\u201d size for potential ship buyers. Please do the following steps (hint: use numpy, scipy, pandas, sklearn and matplotlib)<\/em><\/p>\n

    \n
  1. Read the file and display columns.<\/em><\/li>\n
  2. Calculate basic statistics of the data (count, mean, std, etc) and examine data and state your observations.<\/em><\/li>\n
  3. Select columns that will probably be important to predict \u201ccrew\u201d size.<\/em><\/li>\n
  4. If you removed columns, explain why you removed those.<\/em><\/li>\n
  5. Use one-hot encoding for categorical features.<\/em><\/li>\n
  6. Create training and testing sets (use 60% of the data for the training and reminder for testing).<\/em><\/li>\n
  7. Build a machine learning model to predict the \u2018crew\u2019 size.<\/em><\/li>\n
  8. Calculate the Pearson correlation coefficient for the training set and testing datasets.<\/em><\/li>\n
  9. Describe hyper-parameters in your model and how you would change them to improve the performance of the model.<\/em><\/li>\n
  10. What is regularization? What is the regularization parameter in your model?<\/em><\/li>\n<\/ol>\n

    Plot regularization parameter value vs Pearson correlation for the test and training sets, and see whether your model has a bias problem or variance problem.<\/em><\/p>\n<\/blockquote>\n

    This is an example of a very straightforward problem. The dataset is clean and small (160 rows and 9 columns), and the instructions are very clear. So, all that is needed is to follow the instructions and generate your code. Notice also that the instruction clearly specifies that python must be used as the programming language for model building. The time allowed for completing this coding assignment was three days. Only the final Jupyter notebook has to be submitted, and no formal project report is required.<\/p>\n

    \u00a0<\/p>\n

    Tips for Acing Sample 1 Coding Exercise<\/h3>\n

    \u00a0<\/p>\n

    Since the project involves building a machine learning model, the first step is to ensure we understand the machine learning process:<\/p>\n

    \"\"<\/strong><\/p>\n

    Figure 1<\/strong>. Illustrating the Machine Learning Process. Image by Benjamin O. Tayo.<\/em><\/p>\n

    1. Problem Framing<\/strong><\/p>\n

    Define your project goals. What do you want to find out? Do you have the data to analyze?<\/em><\/p>\n

    Objective<\/strong>:\u00a0<\/em>The goal of this project is to build a regressor model that recommends the \u201ccrew\u201d size for potential cruise ship buyers using the cruise ship dataset\u00a0cruise_ship_info.csv<\/strong><\/a>.<\/strong><\/p>\n

    2. Data Analysis<\/strong><\/p>\n

    Import and clean the dataset, analyze features to select the relevant features that correlate with the target variable.<\/em><\/p>\n

    \u00a0<\/em>2.1 Import dataset and display features and the target variable<\/strong><\/p>\n

    \n
    df = pd.read_csv(\"cruise_ship_info.csv\")\r\n\r\ndf.head()\r\n\r\n<\/pre>\n<\/div>\n
    \u00a0<\/p>\n
    \"\"<\/p>\n
    Table 1<\/strong>: Shows first 5 rows of dataset.<\/em><\/p>\n
    In this example, the dataset is clean and pristine, with no missing values. So, no cleaning is required.<\/p>\n
    Remarks on Data Quality<\/strong>: One of the major flaws with the dataset is that it does not provide the units for the features. For example, the passenger\u2019s column doesn\u2019t tell if this column is in hundreds or thousands. The units for cabin length, passenger density, and crew are not provided as well. The passenger_density<\/em> feature seems to have been derived from other features, but there is no explanation of how it was derived. These kinds of issues can be addressed by contacting the interview team to ask more about the dataset. It is important to understand the intricacies of your data before using it for building real-world models. Keep in mind that a bad dataset leads to bad predictive models.<\/p>\n
    2.2 Calculate and visualize the covariance matrix<\/strong><\/p>\n
    The covariance matrix plot can be used for feature selection and for quantifying the correlation between features (multi-collinearity). We observe from Figure 2 that there are strong correlations between features.<\/p>\n
    \"\"<\/p>\n
    Figure 2<\/strong>. Covariance matrix plot.<\/em><\/p>\n
    \u00a0<\/p>\n
    2.3 Perform feature engineering by transforming features into the principal component analysis (PCA) space<\/strong><\/p>\n
    \u00a0<\/strong>Since the covariance matrix shows multi-collinearity, it is important to transform features into PCA space before training your model. This is important because multi-collinearity between features can lead to a model that is complex and difficult to interpret. PCA can also be used for variable selection and dimensionality reduction. In this case, only components that contribute significantly to the total explained variance can be retained and used for modeled building.<\/p>\n
    3. Model Building<\/strong><\/p>\n
    \u00a0<\/strong>Pick the machine learning tool that matches your data and desired outcome. Train the model with available data.<\/em><\/p>\n
    3.1 Model building and evaluation<\/strong><\/p>\n
    \u00a0<\/strong>Since our goal is to use regression, one could implement different regression algorithms such as\u00a0Linear Regression (LR)<\/strong>,\u00a0KNeighbors Regression (KNR)<\/strong>, and\u00a0Support Vector Regression (SVR)<\/strong>. The dataset has to be divided into training, validation, and test sets.\u00a0Hyperparameter tuning has to be used to fine-tune the model in order to prevent overfitting. Cross-validation is essential to ensure the model performs well on the validation set. After fine-tuning model parameters, the model is applied has to be applied to the test dataset.\u00a0The model\u2019s performance on the test dataset is approximately equal to what would be expected when the model is used for making predictions using unseen data.<\/p>\n
    3.2 Uncertainty Quantification<\/strong><\/p>\n
    \u00a0<\/strong>This can be done by training a model using different random partitions of the training dataset, then averaging the cross-validation score for each random state parameter.<\/p>\n
    \"\"<\/p>\n
    Figure 3<\/strong>. Mean cross-validation shows for different regression models.<\/em><\/p>\n
    4. Application<\/strong><\/p>\n
    Score your final model to generate predictions. Make your model available for production. Retrain your model as needed.<\/em><\/p>\n
    In this stage, the final machine learning model is selected and put into production. The model is evaluated in a production setting in order to assess its performance. Any mistakes encountered when transforming from an experimental model to its actual performance on the production line has to be analyzed. This can then be used in fine-tuning the original model.<\/p>\n
    Based on the mean cross-validation score from Figure 3<\/strong>, we observe that Linear Regression and Support Vector Regression perform almost at the same level and better than KNeighbors Regression. So, the final model selected could either be Linear Regression or Support Vector Regression.<\/p>\n
    For a complete solution of sample 1 coding exercise, please see the following links:<\/strong><\/p>\n
    Sample 1 recommended solution<\/em><\/a><\/p>\n
    Machine Learning Process Tutorial<\/em><\/a><\/p>\n
    Remarks on Sample 1 Coding Exercise<\/strong><\/p>\n
    Sometimes the coding exercise would ask you to submit a Jupyter notebook only, or it may ask for a full project report. Make sure your Jupyter notebook is well organized to reflect every stage of the machine learning process. A sample Jupyter notebook can be found here: <\/em>ML_Model_for_Predicting_Ships_Crew_Size<\/a>.<\/p>\n
    \u00a0<\/p>\n
    Sample 2 Coding Exercise: Model for forecasting loan status<\/h3>\n
    \u00a0<\/p>\n
    \n
    Instructions<\/em><\/strong><\/p>\n
    In this problem, you will forecast the outcome of a portfolio of loans. Each loan is scheduled to be repaid over 3 years and is structured as follows:<\/em><\/p>\n