sklearn feature importance pipeline

sklearn_ft_importance.py

# Loading the data
_cali_data = fetch_california_housing(as_frame=True)
X, y = _cali_data.data, _cali_data.target

# Droping the geo coordinate featuress
X = X.drop(columns=['Latitude', 'Longitude'])

# Droping the population feature; In real life modeling, this could be used as weight. 
# For educational and inference purposes, we drop it.
X = X.drop(columns=['Population'])

# Saving the feature names 
features = X.columns.tolist()

# Train test split 
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=0)

# Defining the hyper parameters 
hps = {
    'max_depth': 3,
    'min_samples_split': 4,
    'random_state': 0
}

# Loading the tree object 
tree = DecisionTreeRegressor(**hps)

# Fitting on the training data 
tree.fit(X_train, y_train)

# Extracting the importances by sklearn 
importances_sk = tree.feature_importances_

# Creating a dataframe with the feature importance by sklearn
feature_importance_sk = {}
for i, feature in enumerate(features):
    feature_importance_sk[feature] = round(importances_sk[i], 3)

print(f"Feature importance by sklearn: {feature_importance_sk}")