Created
March 27, 2019 21:27
-
-
Save Corwinpro/7b674e00d1cfc190e89cd0b9f266f19c to your computer and use it in GitHub Desktop.
This file contains hidden or 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
| from sklearn.base import BaseEstimator | |
| from sklearn.model_selection import cross_val_score | |
| from sklearn.metrics import roc_auc_score | |
| class RandomForestClassifierCustom(BaseEstimator): | |
| def __init__(self, n_estimators=10, max_depth=10, max_features=10, | |
| random_state=SEED): | |
| self.n_estimators = n_estimators | |
| self.max_depth = max_depth | |
| self.max_features = max_features | |
| self.random_state = random_state | |
| self.trees = [] | |
| self.feat_ids_by_tree = [] | |
| def fit(self, X, y): | |
| features = X.columns.values.tolist() | |
| for i in range(self.n_estimators): | |
| current_seed = self.random_state + i | |
| np.random.seed(current_seed) | |
| # Create random feature set without replacement | |
| random_feature_set = np.random.choice(features, self.max_features, replace=False) | |
| self.feat_ids_by_tree.append(random_feature_set) | |
| # Create bootstrap sample | |
| indices = np.random.randint(0, len(y), len(y)) | |
| X_train = X.iloc[indices][random_feature_set] | |
| y_train = y.iloc[indices] | |
| # Training | |
| tree = DecisionTreeClassifier(max_depth=self.max_depth, max_features=self.max_features, | |
| random_state=current_seed) | |
| tree.fit(X_train, y_train) | |
| self.trees.append(tree) | |
| return self | |
| def predict_proba(self, X): | |
| results = [] | |
| for i, tree in enumerate(self.trees): | |
| X_test = X[self.feat_ids_by_tree[i]] | |
| result = tree.predict_proba(X_test) | |
| results.append(result) | |
| final_result = sum(results)/len(self.trees) | |
| return final_result[:,1] | |
| skf = StratifiedKFold(n_splits=5, shuffle=True, random_state=SEED) | |
| score = 0 | |
| for train_index, test_index in skf.split(X, y): | |
| my_classifier = RandomForestClassifierCustom(max_depth=6, max_features=7) | |
| X_train, X_test = X.iloc[train_index], X.iloc[test_index] | |
| y_train, y_test = y.iloc[train_index], y.iloc[test_index] | |
| my_classifier.fit(X_train, y_train) | |
| y_score = my_classifier.predict_proba(X_test) | |
| score += roc_auc_score(y_test, y_score) / 5. | |
| print(score) # 0.8269868195120791 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment