PYTHON APPLIEDChapter 13 · Python for Data Science
Intro to machine learning with scikit-learn
scikit-learn provides a consistent API for machine learning in Python. The core workflow is: prepare data, split into training and test sets, choose a model, call .fit() to train, and .predict() to classify or regress on new data.
Worked example
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
# Sample dataset: cloud features -> rain prediction
X = [[8000, 10], [2000, 80], [1500, 90], [7000, 15],
[2500, 75], [9000, 5], [1800, 85], [6000, 20]]
y = [0, 1, 1, 0, 1, 0, 1, 0] # 0 = no rain, 1 = rain
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.25, random_state=42
)
model = DecisionTreeClassifier()
model.fit(X_train, y_train)
predictions = model.predict(X_test)
print("Accuracy:", accuracy_score(y_test, predictions))How it reads
- train_test_split divides data into training and evaluation portions
- model.fit(X_train, y_train) trains the model on labeled examples
- model.predict(X_test) generates predictions on unseen data
Cloud tip: Always evaluate on a held-out test set, never on training data. Training accuracy can be misleadingly high if the model memorizes rather than generalizes.