feature importance random forest code example

Example 1: random forrest plotting feature importance function

def plot_feature_importances(model):
    n_features = data_train.shape[1]
    plt.figure(figsize=(20,20))
    plt.barh(range(n_features), model.feature_importances_, align='center') 
    plt.yticks(np.arange(n_features), data_train.columns.values) 
    plt.xlabel('Feature importance')
    plt.ylabel('Feature')

Example 2: sklearn random forest feature importance

import pandas as pd
forest_importances = pd.Series(importances, index=feature_names)

fig, ax = plt.subplots()
forest_importances.plot.bar(yerr=std, ax=ax)
ax.set_title("Feature importances using MDI")
ax.set_ylabel("Mean decrease in impurity")
fig.tight_layout()

Example 3: feature_importances_ sklearn

print(__doc__)

import numpy as np
import matplotlib.pyplot as plt

from sklearn.datasets import make_classification
from sklearn.ensemble import ExtraTreesClassifier

# Build a classification task using 3 informative features
X, y = make_classification(n_samples=1000,
                           n_features=10,
                           n_informative=3,
                           n_redundant=0,
                           n_repeated=0,
                           n_classes=2,
                           random_state=0,
                           shuffle=False)

# Build a forest and compute the impurity-based feature importances
forest = ExtraTreesClassifier(n_estimators=250,
                              random_state=0)

forest.fit(X, y)
importances = forest.feature_importances_
std = np.std([tree.feature_importances_ for tree in forest.estimators_],
             axis=0)
indices = np.argsort(importances)[::-1]

# Print the feature ranking
print("Feature ranking:")

for f in range(X.shape[1]):
    print("%d. feature %d (%f)" % (f + 1, indices[f], importances[indices[f]]))

# Plot the impurity-based feature importances of the forest
plt.figure()
plt.title("Feature importances")
plt.bar(range(X.shape[1]), importances[indices],
        color="r", yerr=std[indices], align="center")
plt.xticks(range(X.shape[1]), indices)
plt.xlim([-1, X.shape[1]])
plt.show()

Example 4: sklearn random forest feature importance

from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split

X, y = make_classification(
    n_samples=1000, n_features=10, n_informative=3, n_redundant=0,
    n_repeated=0, n_classes=2, random_state=0, shuffle=False)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, stratify=y, random_state=42)

Example 5: sklearn random forest feature importance

from sklearn.ensemble import RandomForestClassifier

feature_names = [f'feature {i}' for i in range(X.shape[1])]
forest = RandomForestClassifier(random_state=0)
forest.fit(X_train, y_train)

Example 6: sklearn random forest feature importance

import time
import numpy as np

start_time = time.time()
importances = forest.feature_importances_
std = np.std([
    tree.feature_importances_ for tree in forest.estimators_], axis=0)
elapsed_time = time.time() - start_time

print(f"Elapsed time to compute the importances: "
      f"{elapsed_time:.3f} seconds")