Create A Program to Implement Machine Learning in Python Assignment Solution

Instructions

Objective

Write a python assignment program to implement machine learning in python language.

Requirements and Specifications

Source Code

from sklearn.datasets import load_digits from sklearn.model_selection import train_test_split from sklearn.neural_network import MLPClassifier from sklearn.ensemble import GradientBoostingClassifier from sklearn import svm from sklearn.neighbors import KNeighborsClassifier from sklearn import tree import matplotlib.pyplot as plt import numpy as np """### Import Dataset""" from sklearn.datasets import load_digits digits = load_digits() """## Display first 16 images""" plt.figure(figsize = (5,5)) for i in range(16): plt.subplot(4,4,i+1) plt.xticks([]) plt.yticks([]) plt.grid(False) p; plt.imshow(digits.images[i], cmap = plt.cm.binary) plt.xlabel(digits.target[i]) """## Organize dataset into X and y""" n_samples = len(digits.images) X = digits.images.reshape((n_samples, -1)) y = digits.target """## Split dataset into training and test""" X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, shuffle = True) # Usea 33% of the dataset for test """## Model 1: Decision Tree For this model, we will vary the depth of the tree and see when the accuraci stops increasing """ tree_accuracies = [] for d in range(1, 1001): model1 = tree.DecisionTreeClassifier(max_depth=40) model1 = model1.fit(X_train, y_train) # Measure Accuracy y_pred = model1.predict(X_test) acc1 = np.sum(np.where(y_pred == y_test))/n_samples tree_accuracies.append(acc1) plt.figure() plt.plot(range(1,1001), tree_accuracies) plt.xlabel('Depth') plt.ylabel('Accuracy') plt.grid(True) plt.title("Accuracy vs. Tree depth") plt.show() #print("The accuracy of the Decision Tree model is {:.2f}%".format(acc1)) """We don't see that the accuracy stops increasing, it just oscillates. So, we will just get the depth that returned the highest accuracy and build the model with that value""" idx = np.argmax(np.array(tree_accuracies)) highest_acc = tree_accuracies[idx] optimal_depth = range(1,1001)[np.argmax(np.array(tree_accuracies))] model1 = tree.DecisionTreeClassifier(max_depth=optimal_depth) model1 = model1.fit(X_train, y_train) y_pred1 = model1.predict(X_test) acc1 = np.sum(np.where(y_pred1 == y_test))/n_samples print("The highest accuracy of the Decision Tree Model is obtained with a depth of {0} and is {1:.2f}%".format(optimal_depth, highest_acc)) """## Model 2: Neural Network (MLP Classifier) ### First, with SGD optimizer """ model2 = MLPClassifier(hidden_layer_sizes=(50, ), max_iter=100, alpha=1e-4, solver='sgd', random_state=1, learning_rate_init=.01) model2.fit(X_train, y_train) # Measure accuracy y_pred2 = model2.predict(X_test) acc2 = np.sum(np.where(y_pred2 == y_test))/n_samples print("The accuracy of the MLP model with SGD is {:.2f}%".format(acc2)) """### Now, with ADAM optimizer""" model2 = MLPClassifier(hidden_layer_sizes=(50, ), max_iter=100, alpha=1e-4, solver='adam', random_state=1, learning_rate_init=.01) model2.fit(X_train, y_train) # Measure accuracy y_pred2 = model2.predict(X_test) acc2 = np.sum(np.where(y_pred2 == y_test))/n_samples print("The accuracy of the MLP model with Adam is {:.2f}%".format(acc2)) """## Model 3: Boosting""" model3 = GradientBoostingClassifier(n_estimators=100, learning_rate=1e-1, max_depth=1, random_state=0) model3.fit(X_train, y_train) # Measure accuracy y_pred3 = model3.predict(X_test) acc3 = np.sum(np.where(y_pred3 == y_test))/n_samples print("The accuracy of the Boosting model is {:.2f}%".format(acc3)) """## Model 4: Support Vector Machine""" model4 = svm.SVC() model4.fit(X_train, y_train) # Measure accuracy y_pred4 = model4.predict(X_test) acc4 = np.sum(np.where(y_pred4 == y_test))/n_samples print("The accuracy of the Support Vector Machine model is {:.2f}%".format(acc4)) """## Model 5: K-Nearest Neighbors For this case, we will test with k = 1, 2, ..., 10 and check which value of k returns the highest accuracy. Note that we test up to k = 10 since there are only 10 classes """ k_accuracies = [] for k in range(1,11): model5 = KNeighborsClassifier(n_neighbors=k) model5 = model5.fit(X_train, y_train) # Measure accuracy y_pred5 = model5.predict(X_test) acc5 = np.sum(np.where(y_pred5 == y_test))/n_samples k_accuracies.append(acc5) plt.figure() plt.plot(range(1,11),k_accuracies) plt.xlabel('k') plt.ylabel('Accuracy') plt.grid(True) plt.title("Accuracy (%) vs. number of Neighbors (k)") plt.show() # Get optimal value of k optimal_k = range(1,11)[np.argmax(np.array(k_accuracies))] print(f"The optimal value of k is k = {optimal_k}") """Now, the highest value of **k** is used for the final version of the model""" model5 = KNeighborsClassifier(n_neighbors=optimal_k) model5 = model5.fit(X_train, y_train) # Measure accuracy y_pred5 = model5.predict(X_test) acc5 = np.sum(np.where(y_pred5 == y_test))/n_samples print("The accuracy of the K-Nearest Neighbors model is {:.2f}%".format(acc5)) """## Bar Graph showing Accuracies""" accuracies = [acc1, acc2, acc3, acc4, acc5] models = ["Decision Tree", "Neural Network", "Boosting", "SVM", "K-Nearest"] plt.figure(figsize=(10,10)) plt.bar(models, accuracies, width=0.5) plt.grid(True) plt.show() """It can be seen that, the best model is th