Random Forest

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26

import numpy as np
from .decision_tree import DecisionTree

class RandomForest():
    forest = []

    def __init__(self, df, n_trees=5, n_bootstrap=3000, n_features=7, max_depth=5):
        for i in range(n_trees):
            df_bootstrapped = self.bootstrap(df, n_bootstrap)
            tree = DecisionTree(df=df_bootstrapped,
                                max_depth=max_depth, random_feature=n_features)
            self.forest.append(tree)

    def bootstrap(self, df, n_bootstrap):
        bootstrap_indices = np.random.randint(
            low=0, high=len(df), size=n_bootstrap)
        df_bootstrapped = df.iloc[bootstrap_indices]
        return df_bootstrapped

    def predict(self, entry):
        predictions = []
        for tree in self.forest:
            prediction = tree.predict(entry)
            predictions.append(prediction)
        # return most frequently elements in list
        return max(set(predictions), key=predictions.count)