Modeltraining
End-to-End Machine Learning
Joshua Stapleton
Machine Learning Engineer
Occam's scheermes
- De simpelste toereikende uitleg is het best
- Kies bij voorkeur eenvoudige modellen
Modelkeuzes
Logistische regressie
- Vindt de beslisgrens tussen klassen
sklearn.linear_model.LogisticRegression
Support Vector Classifier
- Vindt een vlak dat klassen scheidt
sklearn.svm.SVC
Beslisboom
- Maakt simpele ‘regels’ om data te classificeren
sklearn.tree.DecisionTreeClassifier
Random Forest
- Combineert meerdere beslisbomen
sklearn.ensemble.RandomForestClassifier
Andere modellen
Deep learning-modellen
- Neurale netwerken
- Convolutionele neurale netwerken
- Generative Pretrained Transformer (GPT)
K-Nearest Neighbors (KNN)
- Supervised learning-algoritme
XGBoost
- Gradient boosted model
- https://xgboost.readthedocs.io/en/stable/
Trainingsprincipes
Model:
- Gebruikt opgeschoonde data met features verwerkt
- Leert patronen in trainingsdata
- Doel: voorspellen of iemand hartziekte heeft
Principes:
- Model moet generaliseren naar onzichtbare data (buiten de trainingsset)
- Houd een deel apart om na training te testen
- Train/test-splits vaak 70/30 of 80/20
- Gebruik
sklearn.model_selection.train_test_split
Een model trainen
# Importing necessary libraries from sklearn.model_selection import train_test_split from sklearn.linear_model import LogisticRegression# Split the data into training and testing sets (80:20) X_train, X_test, y_train, y_test = train_test_split(features, heart_disease_y, test_size=0.2, random_state=42)# Define the models logistic_model = LogisticRegression(max_iter=200)# Train the model logistic_model.fit(X_train, y_train)
Modelvoorspellingen krijgen
# Jane Doe's health data, for example: [age, cholesterol level, blood pressure, etc.] jane_doe_data = [45, 230, 120, ...]# Reshape the data to 2D, because scikit-learn expects a 2D array-like input jane_doe_data = jane_doe_data.reshape(1, -1)# Use the model to predict Jane's heart disease diagnosis probabilities jane_doe_probabilities = logistic_model.predict_proba(jane_doe_data) jane_doe_prediction = logistic_model.predict(jane_doe_data)
Modelvoorspellingen (vervolg)
# Print the probabilities
print(f"Jane Doe's predicted probabilities: {jane_doe_probabilities[0]}")
print(f"Jane Doe's predicted health condition: {jane_doe_prediction[0]}")
Jane Doe's predicted health condition probabilities: [0.2 0.8]Jane Doe's predicted health condition: 1
Laten we oefenen!
End-to-End Machine Learning
