Course Content

ML Introduction with scikit-learn

1. Machine Learning Concepts

What is ML Types of Machine Learning Training Set Types of Data Machine Learning Workflow

2. Preprocessing Data with Scikit-learn

Scikit-learn Concepts Getting Familiar with Dataset Dealing with Missing Values Challenge: Imputing Missing Values OrdinalEncoder One-Hot Encoder LabelEncoder Challenge: Encoding Categorical Variables Why Scale the Data?StandardScaler, MinMaxScaler, MaxAbsScaler Challenge: Scaling the Features Preprocessing Summary

3. Pipelines

What is Pipeline ColumnTransformer Efficient Data Preprocessing with Pipelines Challenge: Creating a Pipeline Final Estimator Challenge: Creating a Complete ML Pipeline

4. Modeling

Models KNeighborsClassifier Evaluating the Model Cross-Validation Challenge: Evaluating the Model with Cross-Validation GridSearchCV The Flaw of GridSearchCV Challenge: Tuning Hyperparameters with RandomizedSearchCV Modeling Summary Challenge: Putting It All Together

Challenge: Imputing Missing Values

The SimpleImputer class is designed to handle missing data by automatically replacing missing values.

When initialized, it can also be customized by setting its parameters:

missing_value: specifies the placeholder for the missing values. By default, this is np.nan;
strategy: the strategy used to impute missing values. 'mean' is the default value;
fill_value: Specifies the value to use for filling missing values when the strategy is 'constant'. By default, this is None.

Being a transformer, it has the following methods:

However, we also need to choose the value to impute.

The popular approach is to impute missing numerical values with the mean and missing categorical values with the mode (the most frequent value), as such imputation minimally impacts the distribution of the values.

The approach can be controlled using the strategy parameter:

strategy='mean': impute with mean along each column;
strategy='median': impute with median along each column;
strategy='most_frequent': impute with mode along each column;
strategy='constant': impute with constant number specified in fill_value parameter.

The missing_values parameter controls what values are considered missing. By default, it is NaN, but in different datasets, it can be an empty string '' or anything else.

When you use the .fit_transform() method of the SimpleImputer, it produces a 2D array as output. However, when updating a single column in a pandas DataFrame, you need a 1D array (or a Series).

To convert the 2D array into a 1D array suitable for assignment to a DataFrame column, you can apply the .ravel() method. This method flattens the array. Here's how you can update a column after imputation:

This approach ensures that the imputed values are correctly formatted and assigned back to the DataFrame.

Task

Swipe to show code editor

Your task is to impute the NaN values of the 'sex' column using SimpleImputer. Since you are dealing with a categorical column, you will replace null values with the most frequent value (the most common approach).

Import the SimpleImputer.
Create a SimpleImputer object with the desired strategy.
Impute the missing of the 'sex' column using the imputer object.

_{Once you've completed this task, click the button below the code to check your solution.}

Great! We dealt with the missing values problem in our dataset. We removed the rows with more than one null and imputed the 'sex' column with the most frequent value – MALE.

Switch to desktop for real-world practiceContinue from where you are using one of the options below

Everything was clear?

Thanks for your feedback!

Section 2. Chapter 4

Challenge: Imputing Missing Values

The SimpleImputer class is designed to handle missing data by automatically replacing missing values.

When initialized, it can also be customized by setting its parameters:

missing_value: specifies the placeholder for the missing values. By default, this is np.nan;
strategy: the strategy used to impute missing values. 'mean' is the default value;
fill_value: Specifies the value to use for filling missing values when the strategy is 'constant'. By default, this is None.

Being a transformer, it has the following methods:

However, we also need to choose the value to impute.

The approach can be controlled using the strategy parameter:

strategy='mean': impute with mean along each column;
strategy='median': impute with median along each column;
strategy='most_frequent': impute with mode along each column;
strategy='constant': impute with constant number specified in fill_value parameter.

The missing_values parameter controls what values are considered missing. By default, it is NaN, but in different datasets, it can be an empty string '' or anything else.

This approach ensures that the imputed values are correctly formatted and assigned back to the DataFrame.

Task

Swipe to show code editor

Import the SimpleImputer.
Create a SimpleImputer object with the desired strategy.
Impute the missing of the 'sex' column using the imputer object.

_{Once you've completed this task, click the button below the code to check your solution.}

Great! We dealt with the missing values problem in our dataset. We removed the rows with more than one null and imputed the 'sex' column with the most frequent value – MALE.

Switch to desktop for real-world practiceContinue from where you are using one of the options below

Everything was clear?

Thanks for your feedback!

Section 2. Chapter 4

Switch to desktop for real-world practiceContinue from where you are using one of the options below