Summary - ML fundamentals

In this group you learned the definition, types, and core concepts of ML.

Summary: the ML workflow

In this section you saw the basic machine learning loop:

Prepare the data as X (two-dimensional) and y (one-dimensional).
Split it into training and test sets with train_test_split.
Train the model with fit(X_train, y_train).
Predict with predict and measure on the test set with score.

from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
X_tr, X_te, y_tr, y_te = train_test_split(X, y, test_size=0.2, random_state=0)
model = KNeighborsClassifier().fit(X_tr, y_tr)
print(model.score(X_te, y_te))

Exercise End to end

Split the data with test_size=0.25, random_state=0, train a KNeighborsClassifier(n_neighbors=3) and print the test accuracy.

Show example solution

from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier

X = [[i] for i in range(40)]
y = [0 if i < 20 else 1 for i in range(40)]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=0)
model = KNeighborsClassifier(n_neighbors=3)
model.fit(X_train, y_train)
print(model.score(X_test, y_test))

Test yourself

With which data should the model's success be measured?
- There's no need to measure
- With test data not used in training
- With the training data
- With all the data
Show answer

With test data not used in training — Real success is success on examples the model has never seen.

Measure success on the test set.

print(model.____(X_test, y_test))

Show answer

print(model.score(X_test, y_test))

Match the steps with their methods.

Splitting

train_test_split
Training

fit
Prediction

predict
Measuring

score

Next lesson: What is NumPy?

We Are Enhancing Your Experience

Cookie Preferences

Strictly Necessary Cookies

Analytical Cookies