Data Preprocessing, Cleaning and preparing raw data before using it to train a machine learning model., GIGO, The principle that poor-quality input data leads to unreliable or inaccurate results., Missing Data, Values that are absent or have not been recorded in a dataset., Deletion, Removing records that contain missing or invalid values., Imputation, Replacing missing values with estimated values, such as the mean, median or mode., Outlier, A data value that is unusually high or low compared with other values., Data Validation, Checking whether data follows predefined rules or acceptable formats., Data Scaling, Adjusting numerical features so that differences in their scales do not unfairly influence a model., Normalisation, Rescaling numerical values to a common range, typically between 0 and 1., Standardisation, Transforming numerical values so that the resulting data has a mean of 0 and a standard deviation of 1., Feature, An individual input variable or characteristic used by a machine learning model., Feature Selection, Choosing relevant features from a dataset while removing unnecessary or irrelevant ones., Overfitting, When a model learns noise or specific details from training data and performs poorly on new data., Data Sparsity, A situation where data points become widely spread out in a high-dimensional space., Dimensionality Reduction, Reducing the number of features or dimensions in a dataset while retaining useful information.

Data Preprocessing_3

Style visuel

Afficher tout

Paramètres d’activité

Classement

Changer de modèle

Restauration auto-sauvegardé :  ?