Last active
December 7, 2018 01:50
-
-
Save doraneko94/f4575591628bfedf26d3a40757db3cd4 to your computer and use it in GitHub Desktop.
Calculating partial dependence of any classifier which has an attribute of "n_features_" and "n_classes_".
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
from scipy.stats.mstats import mquantiles | |
from math import sqrt, ceil | |
from matplotlib import pyplot as plt | |
def _grid_from_X(X, percentiles=(0.05, 0.95), grid_resolution=100): | |
if len(percentiles) != 2: | |
raise ValueError('percentile must be tuple of len 2') | |
if not all(0. <= x <= 1. for x in percentiles): | |
raise ValueError('percentile values must be in [0, 1]') | |
emp_percentiles = mquantiles(X, prob=percentiles, axis=0) | |
return np.array([np.linspace(emp_percentiles[0, col], emp_percentiles[1, col], num=grid_resolution, endpoint=True) for col in range(X.shape[1])]) | |
def pa_de(clf, X, f, val, target): | |
rp_x = np.insert(np.delete(X, f, axis=1), f, val, axis=1) | |
p = clf.predict_proba(rp_x) | |
if np.all(p) == False: | |
p += 1e-7 | |
rp_x_s = rp_x.shape[0] | |
pa_de = [np.sum(np.array([np.log(p[i][t]) - np.sum(np.log(p[i])) / p.shape[1] for i in range(rp_x_s)])) for t in target] | |
return pa_de | |
def partial_dependence(clf, X: np.ndarray, feature: list = [], target: list = [], percentiles=(0.05, 0.95), grid_resolution=100, scaler=None): | |
n_features_ = clf.n_features_ | |
n_classes_ = clf.n_classes_ | |
if feature == []: | |
feature = list(range(n_features_)) | |
if target == []: | |
target = list(range(n_classes_)) | |
axes = _grid_from_X(X, percentiles, grid_resolution) | |
pdp = np.array([[pa_de(clf, X, f, val, target) for val in axes[f]] for f in feature]) | |
if scaler != None: | |
axes = scaler.inverse_transform(axes.T).T | |
return pdp, axes | |
def partial_dependence_plot(clf, X: np.ndarray, feature_names: list, target_names: list, feature: list = [], target: list = [], percentiles=(0.05, 0.95), grid_resolution=100, scaler=None): | |
pdp, axes = partial_dependence(clf, X, feature, target, percentiles, grid_resolution, scaler) | |
n_features_ = clf.n_features_ | |
n_classes_ = clf.n_classes_ | |
if feature == []: | |
feature = list(range(n_features_)) | |
if target == []: | |
target = list(range(n_classes_)) | |
pdp_max = np.amax(pdp) | |
pdp_min = np.amin(pdp) | |
pdp = pdp / max([pdp_max, abs(pdp_min)]) * 2 | |
num_line = pdp.shape[2] | |
num_ax = pdp.shape[0] | |
if sqrt(num_ax) == int(sqrt(num_ax)): | |
row = int(sqrt(num_ax)) | |
col = int(sqrt(num_ax)) | |
else: | |
row = ceil(num_ax / (int(sqrt(num_ax)) + 1)) | |
col = int(sqrt(num_ax)) + 1 | |
_, ax = plt.subplots(row, col) | |
for i in range(num_ax): | |
x = int(i/col) | |
y = i - col * x | |
for j in range(num_line): | |
if row * col == 1: | |
plt.sca(ax) | |
ax.plot(axes[feature[i]], pdp[i, :, j]) | |
elif row == 1: | |
plt.sca(ax[y]) | |
ax[y].plot(axes[feature[i]], pdp[i, :, j]) | |
else: | |
plt.sca(ax[x, y]) | |
ax[x, y].plot(axes[feature[i]], pdp[i, :, j]) | |
if y == 0: | |
plt.ylabel("partial dependence") | |
plt.ylim([-2, 2]) | |
plt.xlabel(feature_names[feature[i]]) | |
plt.tight_layout() | |
plt.show() | |
return | |
if __name__ == "__main__": | |
from sklearn import datasets | |
from sklearn.ensemble import RandomForestClassifier | |
from sklearn.model_selection import train_test_split | |
data = datasets.load_breast_cancer() | |
X_train, X_test, y_train, y_test = train_test_split(data["data"], data["target"], test_size=0.33, random_state=42) | |
clf = RandomForestClassifier() | |
clf.fit(X_train, y_train) | |
partial_dependence_plot(clf, X_train, data["feature_names"], data["target_names"] , [0,1,2,3,4,5,6,7,8], [0]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment