Weiter zum Inhalt

Startseite Python

Kostenlos Kurs

Feature Engineering für Machine Learning in Python

FortgeschrittenSchwierigkeitsgrad

Aktualisiert 02/2023

Hier entwickelst du neue Features, um die Leistung deiner Machine-Learning-Modelle zu verbessern.

Kostenlosen Kurs starten

Kostenlos enthalten

PythonMachine Learning

4 Std.

16 Videos

53 Übungen

4,350 XP

38,646

Leistungsnachweis

Beliebt bei Lernenden in Tausenden Unternehmen

Training a Team?

Try for Business

Kursbeschreibung

Jeden Tag liest du von beeindruckenden Durchbrüchen, wie neue Anwendungen des Machine Learning die Welt verändern. Oft wird dabei übersehen, dass vor dem Einsatz dieser ausgeklügelten Modelle eine Menge Datenaufbereitung und Feature Engineering nötig ist. In diesem Kurs lernst du genau das. Du arbeitest mit der Stack Overflow Developers Survey und historischen US-Antrittsreden von Präsidenten, um zu verstehen, wie du kategoriale, kontinuierliche und unstrukturierte Daten am besten vorverarbeitest und daraus Features entwickelst. Dieser Kurs gibt dir praktische Erfahrung darin, wie du beliebige Daten für deine eigenen Machine-Learning-Modelle vorbereitest.

Voraussetzungen

Supervised Learning with scikit-learn

1

Creating Features

In this chapter, you will explore what feature engineering is and how to get started with applying it to real-world data. You will load, explore and visualize a survey response dataset, and in doing so you will learn about its underlying data types and why they have an influence on how you should engineer your features. Using the pandas package you will create new features from both categorical and continuous columns.

Why generate features?

Getting to know your data

Selecting specific data types

Dealing with categorical features

One-hot encoding and dummy variables

Dealing with uncommon categories

Numeric variables

Binarizing columns

Binning values

Kapitel starten

2

Dealing with Messy Data

This chapter introduces you to the reality of messy and incomplete data. You will learn how to find where your data has missing values and explore multiple approaches on how to deal with them. You will also use string manipulation techniques to deal with unwanted characters in your dataset.

Why do missing values exist?

How sparse is my data?

Finding the missing values

Dealing with missing values (I)

Listwise deletion

Replacing missing values with constants

Dealing with missing values (II)

Filling continuous missing values

Imputing values in predictive models

Dealing with other data issues

Dealing with stray characters (I)

Dealing with stray characters (II)

Method chaining

Kapitel starten

3

Conforming to Statistical Assumptions

In this chapter, you will focus on analyzing the underlying distribution of your data and whether it will impact your machine learning pipeline. You will learn how to deal with skewed data and situations where outliers may be negatively impacting your analysis.

Data distributions

What does your data look like? (I)

What does your data look like? (II)

When don't you have to transform your data?

Scaling and transformations

Normalization

Standardization

Log transformation

When can you use normalization?

Removing outliers

Percentage based outlier removal

Statistical outlier removal

Scaling and transforming new data

Train and testing transformations (I)

Train and testing transformations (II)

Kapitel starten

4

Dealing with Text Data

Finally, in this chapter, you will work with unstructured text data, understanding ways in which you can engineer columnar features out of a text corpus. You will compare how different approaches may impact how much context is being extracted from a text, and how to balance the need for context, without too many features being created.

Encoding text

Cleaning up your text

High level text features

Word counts

Counting words (I)

Counting words (II)

Limiting your features

Text to DataFrame

Term frequency-inverse document frequency

Inspecting Tf-idf values

Transforming unseen data

Using longer n-grams

Finding the most common words

Kapitel starten

Feature Engineering für Machine Learning in Python

Kurs
abgeschlossen

Leistungsnachweis verdienen

Füge diesen Fähigkeitsnachweis zu Deinem LinkedIn-Profil, Anschreiben oder Lebenslauf hinzu
Teile es auf Social Media und in Deiner LeistungsbeurteilungJetzt anmelden

Schließe dich 19 Millionen Lernenden an und starte Feature Engineering für Machine Learning in Python heute!

DataCamp gibt es auch für Mobilgeräte

Mit unseren Kursen für Mobilgeräte und täglichen Programmier-Challenges erweiterst du deine Datenkompetenz von unterwegs.