Basic imputation methods | Train in Data

This site uses cookies

Cookies are important for this site to function properly, to guarantee your safety, and to provide you with the best experience. By continuing to browse, you agree to the use of these cookies.
Learn More.

Autoplay
Autocomplete

Previous Lesson Complete and Continue

Feature Engineering for Machine Learning

Welcome

Introduction (5:14)
Course curriculum (5:39)
Course requirements (2:28)
How to approach this course (1:56)
Setting up your computer
Refer a friend program

Course material

Course material (2:05)
Download Jupyter notebooks
Download datasets
Download presentations
How did you hear about us?

Variable types

Variables | Intro (2:37)
Numerical variables (4:05)
Categorical variables (3:43)
Date and time variables (1:50)
Mixed variables (2:17)
How are we doing? (0:26)
Exercise

Variable characteristics

Variable characteristics (2:44)
Missing data (6:43)
Cardinality (5:04)
Rare labels (4:54)
Variable distribution (5:13)
Outliers (8:27)
Linear models assumptions (8:59)
Variable magnitude (3:09)
How are we doing? (0:24)
Summary table
Additional reading resources
Exercise

Missing data imputation - Basic

Basic imputation methods (3:52)
Mean or median imputation (4:53)
Arbitrary value imputation (3:16)
Frequent category imputation (3:30)
Missing category imputation (1:22)
Adding a missing indicator (3:42)
Basic methods - considerations (11:15)
Basic imputation with pandas (6:45)
Basic imputation with pandas - demo (12:35)
Basic methods with Scikit-learn (9:44)
Mean or median imputation with Scikit-learn (10:53)
Arbitrary value imputation with Scikit-learn (3:57)
Frequent category imputation with Scikit-learn (4:38)
Missing category imputation with Scikit-learn (2:24)
Adding a missing indicator with Scikit-learn (4:59)
Imputation with GrdiSearch - Scikit-learn (8:24)
Basic methods with Feature-engine (7:19)
Mean or median imputation with Feature-engine (6:50)
Arbitrary value imputation with Feature-engine (3:16)
Frequent category imputation with Feature-engine (2:34)
Arbitrary string imputation with Feature-engine (3:24)
Adding a missing indicator with Feature-engine (4:52)
Wrapping up (2:19)
How are we doing? (0:24)
Exercise
Added Treat: A Movie We Recommend🍿

Missing data imputation - Alternative methods

Alternative imputation methods (2:59)
Complete Case Analysis (6:30)
CCA - considerations with code demo (3:45)
End of distribution imputation (4:14)
Random sample imputation (14:14)
Random imputation - considerations with code (7:56)
Mean or median imputation per group (4:32)
CCA with pandas (5:19)
End of distribution imputation with pandas (5:24)
Random sample imputation with pandas (4:46)
Mean imputation per group with pandas (5:34)
CCA with Feature-engine (6:47)
End of distribution imputation with Feature-engine (5:13)
Random sample imputation with Feature-engine (2:25)
Wrapping up (5:52)
Imputation - Summary table
Exercise

Multivariate imputation

Multivariate Imputation (5:18)
KNN imputation (4:22)
KNN imputation - Demo (7:04)
MICE (7:07)
missForest (1:07)
MICE and missForest - Demo (3:58)
Additional reading resources
Exercise
Extra Treat: Our Reading Suggestion 📕

Categorical encoding - Basic methods

Categorical encoding | Introduction (4:59)
One hot encoding (6:03)
One hot encoding with pandas (7:29)
One hot encoding with sklearn (11:06)
One hot encoding with Feature-engine (2:19)
One hot encoding with Category encoders (5:04)
Ordinal encoding (1:50)
Ordinal encoding with pandas (3:16)
Ordinal encoding with sklearn (4:05)
Ordinal encoding with Feature-engine (1:49)
Ordinal encoding with Category encoders (1:43)
Count or frequency encoding (3:11)
Count encoding with pandas (2:58)
Count encoding with Feature-engine (1:21)
Count encoding with Category encoders (1:42)
Unseen categories (11:35)
Wrapping up (3:03)

Categorical encoding - monotonic

Categorical encoding | Monotonic (5:09)
Ordered ordinal encoding (2:25)
Ordered ordinal encoding with pandas (8:11)
Ordered ordinal encoding with Feature-engine (2:36)
Mean encoding (1:34)
Mean encoding with pandas (4:39)
Mean encoding with Feature-engine (2:36)
Mean encoding with Category encoders (2:15)
Mean encoding plus smoothing (4:55)
Mean encoding plus smoothing - Category encoders (6:35)
Mean encoding plus smoothing - Feature-engine (6:15)
Weight of evidence (WoE) (4:36)
Weight of Evidence with pandas (9:47)
Weight of Evidence with Feature-engine (1:40)
Weight of Evidence with Category encoders (1:12)
Weight of evidence - gotchas (3:05)
Unseen categories (2:15)
Wrapping up (3:24)
Comparison of categorical variable encoding (9:09)
Additional reading resources

Categorical encoding - Rare labels

Grouping rare labels (4:17)
One hot encoding of top categories (3:06)
OHE of top categories with pandas (5:33)
OHE of top categories with Feature-engine (2:14)
OHE of top categories with sklearn (5:35)
Rare label encoding (4:31)
Rare label encoding with pandas (8:12)
Rare label encoding with Feature-engine (1:39)
Wrapping up (2:20)
Categorical encoding - More... (3:31)
More Wisdom: Our Chosen Podcast Episode 🎧

Variable transformation

Variable transformation - Introduction (3:36)
Variable transformation (6:46)
Box-Cox transformation (2:47)
Yeo-Johnson transformation (3:00)
Logarithm transformation with Numpy (5:14)
Reciprocal transformation with Numpy (1:55)
Square-root transformation with Numpy (1:12)
Power transformation with Numpy (1:17)
Box-Cox transformation with Scipy (1:37)
Yeo-Johnson transformation with Scipy (1:05)
Arcsin transformation with Numpy (1:16)
Logarithm transformation with sklearn (2:49)
Reciprocal transformation with sklearn (1:01)
Square-root transformation with sklearn (0:52)
Power transformation with sklearn (0:35)
Box-Cox transformation with sklearn (2:05)
Yeo-Johnson transformation with sklearn (0:56)
Arcsin transformation with sklearn (1:12)
Logarithm transformation with Feature-engine (3:41)
Reciprocal transformation with Feature-engine (0:44)
Square-root transformation with Feature-engine (0:57)
Power transformation with Feature-engine (0:53)
Box-Cox transformation with Feature-engine (1:07)
Yeo-Johnson transformation with Feature-engine (0:38)
Arcsin transformation with Feature-engine (1:28)
Wrapping up (4:59)
Additional reading resources
Quiz

Discretization - Basic methods

Discretization (4:43)
Discretization methods (3:53)
Equal-width discretization (4:06)
Equal-width discretization with pandas (5:52)
Equal-width discretization with sklearn (1:59)
Equal-width discretization with Feature-engine (2:36)
Equal-frequency discretization (4:13)
Equal-frequency discretization with pandas (3:59)
Equal-frequency discretization with sklearn (1:03)
Equal-frequency discretization with Feature-engine (1:32)
Arbitrary discretization (1:44)
Arbitrary discretization with pandas (3:06)
Arbitrary discretization with Feature-engine (2:20)
Discretization plus categorical encoding (2:54)
Discretization plus encoding | Demo (5:45)
Wrapping up (12:29)
Additional reading resources

Discretization - Alternative methods

Discretization - section intro (2:56)
K-means discretization (4:13)
K-means discretization with sklearn (2:43)
Discretization with classification trees (5:05)
Discretization with decision trees using Scikit-learn (11:55)
Discretization with decision trees using Feature-engine (3:48)
Binarization (2:13)
Binarization with sklearn (4:11)
Additional reading resources

Outliers

Outlier Engineering (7:16)
Outlier trimming with pandas (6:56)
Outlier trimming with Feature-engine (4:49)
Outlier capping with pandas (4:22)
Outlier capping with Feature-engine (2:34)
Arbitrary capping with Feature-engine (2:52)
Additional reading resources

Datetime variables

Datetime variables (4:40)
Date features with pandas (12:36)
Time features with pandas (4:08)
Date and time features with Feature-engine (5:34)
Cyclical features (6:24)
Cyclical features with pandas (4:02)
Cyclical features with Feature-engine (3:22)

Engineering mixed variables

Mixed variables (3:14)
Mixed variables | Demo (6:11)

Feature creation

Feature creation (2:11)
Math functions (5:06)
Math functions with pandas (2:52)
Math functions with Feature-engine (2:58)
Relative functions with pandas (1:53)
Relative functions with Feature-engine (2:57)
Polynomial features (3:54)
Polynomial features demo (3:45)
Features from decision trees (3:36)

Feature scaling

Feature scaling (3:10)
Scaling and distributions (3:49)
Standardisation (3:53)
Standardisation | Demo (2:26)
Scaling to minimum and maximum values (1:43)
MinMaxScaling | Demo (1:53)
Mean normalisation (2:12)
Mean normalisation | Demo (4:09)
Maximum absolute scaling (1:35)
MaxAbsScaling | Demo (2:08)
Scaling to median and quantiles (1:49)
Robust Scaling | Demo (1:40)
Scaling to vector unit length (5:45)
Scaling to vector unit length | Demo (4:24)
Scaling categorical variables
Additional reading resources

Assembling feature engineering pipelines

Putting it all together (6:17)
Feature Engineering Pipeline (8:09)
Classification pipeline (13:15)
Regression pipeline (13:51)
Feature engineering pipeline with cross-validation (6:47)
More examples

Congratulations! You did it!

Congratulations
Next steps

Basic imputation methods

Complete and Continue

Discussion

0 comments

Lesson Content Locked

Your session expired. Please sign in again to continue.

Login