randomforestimpl

"""# Q.2 Write Python script to implement Random Forest Classifier. Use standard Class of Python to implement the algorithm by choosing your own dataset.

Data Set Characteristics:
Number of Instances
1797
Number of Attributes
64
Attribute Information
8x8 image of integer pixels in the range 0..16.
Missing Attribute Values
None
The data set contains images of hand-written digits: 10 classes where each class refers to a digit.
"""

# using standard class of python
from collections import Counter

import numpy as np

from sklearn.tree import DecisionTreeClassifier


def bootstrap_sample(X, y):
    n_samples = X.shape[0]
    idxs = np.random.choice(n_samples, n_samples, replace=True)
    return X[idxs], y[idxs]


def most_common_label(y):
    counter = Counter(y)
    most_common = counter.most_common(1)[0][0]
    return most_common


class RandomForest:
    def __init__(self, n_trees=10, min_samples_split=2, max_depth=100, n_feats=None):
        self.n_trees = n_trees
        self.min_samples_split = min_samples_split
        self.max_depth = max_depth
        self.n_feats = n_feats
        self.trees = []

    def fit(self, X, y):
        self.trees = []
        for _ in range(self.n_trees):
            tree =  DecisionTreeClassifier(min_samples_split=self.min_samples_split,max_depth=self.max_depth,max_features=self.n_feats,)
            X_samp, y_samp = bootstrap_sample(X, y)
            tree.fit(X_samp, y_samp)
            self.trees.append(tree)

    def predict(self, X):
        tree_preds = np.array([tree.predict(X) for tree in self.trees])
        tree_preds = np.swapaxes(tree_preds, 0, 1)
        y_pred = [most_common_label(tree_pred) for tree_pred in tree_preds]
        return np.array(y_pred)

# Importing relevant libraries
from sklearn import datasets
from sklearn.model_selection import train_test_split

#function for accuracy
def accuracy(y_true, y_pred):
    accuracy = np.sum(y_true == y_pred) / len(y_true)
    return accuracy

#loading dataset
data = datasets.load_digits()
X = data.data
y = data.target

#splitting dataset into training and testing data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1234)

clf = RandomForest(n_trees=3, max_depth=10)

clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
acc = accuracy(y_test, y_pred)

print("Accuracy:", acc)