Feature Importance

API reference for sovai.extensions.feature_importance

Module: sovai.extensions.feature_importance

Functions

random_projection_importance()

def random_projection_importance(df_filled, n_components = 100)

---

fast_nonlinear_diverse_selector()

def fast_nonlinear_diverse_selector(df_valid, n_components = 100, gamma = 1.0)

---

fast_ica_selector()

def fast_ica_selector(df_filled, n_components = 20)

---

truncated_svd_selector()

def truncated_svd_selector(df_filled, n_components = 20)

---

sparse_random_projection_selector()

def sparse_random_projection_selector(df_returns, n_components = 30)

---

pca_varimax_selection()

def pca_varimax_selection(df_returns, k = 30, n_components = 50)

---

pca_varimax_rolling_stats()

def pca_varimax_rolling_stats(df_returns, k = 30, window = 30, n_components = 50)

---

diverse_stock_selector()

def diverse_stock_selector(df_returns, n_components = 30, n_clusters = 20)

---