(1). Please report the accuracy of the prediction report

(2) choose the class with the highest confidence score

(3) Please report the errors (scatter plot)

(4) do not use scikit-learn library

Given the following code in python:

import numpy as np import pandas as pd import matplotlib.pyplot as plt

class SGDClassifier: def __init__(self, lr=0.01, n_iters=1000): self.lr = lr self.n_iters = n_iters self.weights = None self.bias = None

def fit(self, X, y): n_samples, n_features = X.shape

self.weights = np.zeros(n_features) self.bias = 0

for _ in range(self.n_iters): for idx, x_i in enumerate(X): y_pred = self._sigmoid(np.dot(x_i, self.weights) + self.bias) gradient = (y[idx] - y_pred) * x_i self.weights += self.lr * gradient self.bias += self.lr * (y[idx] - y_pred)

def predict(self, X): y_pred = np.dot(X, self.weights) + self.bias y_pred = np.round(self._sigmoid(y_pred)) return y_pred.astype(int)

def _sigmoid(self, x): return 1 / (1 + np.exp(-x))

class OneVsRestClassifier: def __init__(self, classifier=SGDClassifier()): self.classifier = classifier

def fit(self, X, y): self.binary_classifiers = [] for label in np.unique(y): binary_y = np.where(y == label, 1, 0) binary_classifier = self.classifier binary_classifier.fit(X, binary_y) self.binary_classifiers.append(binary_classifier)

def predict(self, X): y_pred = [] for x_i in X: predictions = [] for binary_classifier in self.binary_classifiers: predictions.append(binary_classifier.predict([x_i])[0]) y_pred.append(np.argmax(predictions)) return np.array(y_pred) # Each plant in the dataset has 4 attributes: # sepal length, sepal width, petal length, and petal width. # We will use our logistic regression model to predict flowers species using # just these attributes.

url = "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data" df = pd.read_csv(url, header=None, names=[ "Sepal length (cm)", "Sepal width (cm)", "Petal length (cm)", "Petal width (cm)", "Species"]) df.head()

# Now well encode the species to an integer value, shuffle the data, # and split it into training and test data: df['Species'] = df['Species'].astype('category').cat.codes data = np.array(df) np.random.shuffle(data) num_train = int(.8 * len(data)) # 80/20 train/test split x_train, y_train = data[:num_train, :-1], data[:num_train, -1] x_test, y_test = data[num_train:, :-1], data[num_train:, -1]

# Lets look at the distribution of the data: plt.scatter(x_train[:,2], x_train[:, 3], c=y_train, alpha=0.5) plt.xlabel("Petal Length (cm)"); plt.ylabel("Petal Width (cm)");

# ***************************************************************