Merekayasa fitur secara manual

Setelah melakukan riset bersama tim, Anda ingat bahwa gaya tarik gravitasi antara dua benda mengikuti rumus Newton:

$$F = G\frac{m_1m_2}{r^2}$$.

Anda tidak dapat menggunakan rumus tersebut secara langsung karena massanya tidak diketahui, tetapi Anda dapat menyesuaikan model regresi dari force sebagai fungsi inv_square_distance. Himpunan data tambahan df yang Anda bangun pada latihan sebelumnya telah dimuat untuk Anda.

Latihan ini adalah bagian dari kursus

Rekayasa Fitur di R

Lihat Kursus

Petunjuk latihan

Buat variabel baru inv_square_distance yang didefinisikan sebagai kebalikan dari jarak kuadrat, lalu tambahkan ke data frame df.
Bangun model regresi sederhana menggunakan lm() dari force terhadap inv_square_distance dan simpan sebagai lr_force_2.
Gabungkan prediksi Anda ke df_inverse.

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

# Create a new variable inv_square_distance
df_inverse <- df %>% ___(inv_square_distance = 1/distance^2)

# Build a simple regression model
lr_force_2 <- lm(force ~ ___, data = df_inverse)

# Bind your predictions to df_inverse
df_inverse <- df_inverse %>% ___(lr2_pred = predict(lr_force_2))

df_inverse %>% ggplot(aes(x = distance, y = force)) +
  geom_point() +
  geom_line(aes(y = lr2_pred), col = "blue", lwd = .75) +
  ggtitle("Linear regression of force vs. inv_square_distance") +
  theme_classic()

Edit dan Jalankan Kode

Rekayasa Fitur di R

SkillTag.level.intermediateSkillTag.label

4.8+

120 reviews

You’ll wrap up the course by learning about feature engineering and machine learning techniques. You’ll begin by focusing on the problems associated with using all available features in a model and the importance of identifying irrelevant and redundant features and learning to remove these features using embedded methods such as lasso and elastic-net. Next, you’ll explore shrinkage methods such as lasso, ridge, and elastic-net, which can be used to regularize feature weights or select features by setting coefficients to zero. Finally, you’ll finish by focusing on creating an end-to-end feature engineering workflow and reviewing and practicing the previously learned concepts and functions in a small project.

Exercise 1: Reducing the model's features Exercise 2: Sifting through variable importance Exercise 3: Assessing model performance using all available predictors Exercise 4: Building a reduced model Exercise 5: Shrinkage methods Exercise 6: Manual regularization with Lasso Exercise 7: Tuning the penalty Exercise 8: Finalizing the model Exercise 9: Putting it all together Exercise 10: Prep and split Exercise 11: Preprocess Exercise 12: Model Exercise 13: Assess Exercise 14: Congratulations!