Assignment 6

1 files changed, 119 insertions, 0 deletions

diff --git a/Assignment 6/ex61.py b/Assignment 6/ex61.py
new file mode 100644
index 0000000..89a152c
--- /dev/null
+++ b/Assignment 6/ex61.py
@@ -0,0 +1,119 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Jan  8 13:15:01 2016
+
+@author: camil
+"""
+
+from random import shuffle
+
+import numpy as np
+
+import scipy.io as sciio
+from scipy.spatial.distance import cosine, correlation
+
+import matplotlib.pyplot as plt
+
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn import cross_validation
+from sklearn import datasets
+
+def ex611(sets=range(1,5)):
+    fs = 15
+    for n in sets:
+        synth = sciio.loadmat('./data/synth' + str(n) + '.mat')
+        X = synth['X']
+        y = synth['y']
+        
+        plt.figure(figsize=(18,3))
+        plt.subplot(1, 5, 1)
+        plt.scatter(X[:,1], X[:,0], c=y, s=50, alpha=0.5, marker='s')
+        plt.title('synth' + str(n), fontsize=fs)
+        
+        measures = ['euclidean', 'manhattan', cosine, correlation]
+        measure_names = ['euclidean', 'manhattan', 'cosine', 'correlation']
+        ns = np.arange(1, 41, 1)
+        
+        combined = zip(X, y)
+        shuffle(combined)
+        X[:], y[:] = zip(*combined)
+        
+        cv = cross_validation.KFold(len(X), n_folds=10)
+        
+        for measure, measure_name, d in zip(measures, measure_names, range(len(measures))):
+            accuracies = []
+            for i in ns:
+                acc = []
+                for train, test in cv:
+                    X_train, X_test, y_train, y_test = X[train], X[test], y[train], y[test]
+                    
+                    clf = KNeighborsClassifier(n_neighbors=i, metric=measure)
+                    clf.fit(X_train, y_train.ravel())
+                    acc.append(clf.score(X_test, y_test.ravel()))
+                accuracies.append(np.mean(acc))
+            errors = np.repeat(1, len(accuracies)) - accuracies            
+                
+            plt.subplot(1, 5, 2+d)
+            plt.plot(ns, accuracies, c='blue')
+            plt.plot(ns, errors, c='red')
+            plt.xlabel('N neighbors')
+            plt.ylabel('Accuracy / Error rate')
+            plt.ylim([-0.05, 1.05])
+            plt.title(measure_name, fontsize=fs)
+        
+        plt.tight_layout()
+        plt.show()
+       
+def ex612():
+    iris = datasets.load_iris()
+    X, y = iris.data, iris.target
+    
+    ns, scores = range(1,41), []
+    for n in ns:
+        cv = cross_validation.LeaveOneOut(len(X))
+        scores_ = []
+        for train, test in cv:
+            X_train, X_test, y_train, y_test = X[train], X[test], y[train], y[test]
+            
+            clf = KNeighborsClassifier(n_neighbors=n)
+            clf.fit(X_train, y_train)
+            scores_.append(1-clf.score(X_test, y_test))
+        scores.append(np.mean(scores_))
+        
+    plt.plot(ns, scores, color='red')
+    plt.ylim([min(scores) - (max(scores)-min(scores))*0.1,
+              max(scores) + (max(scores)-min(scores))*0.1])
+    plt.title('Classifying the Iris data set with KNN', fontsize=18)
+    plt.xlabel('N neighbors')
+    plt.ylabel('Error rate')
+    plt.show()
+    
+def ex613():
+    wine = sciio.loadmat('./data/wine.mat')
+    #classNames = [str(n[0][0]) for n in wine['classNames']]
+    X = wine['X'][:,:-1]
+    y = np.array(wine['X'][:,-1], dtype='f')
+    
+    ns, scores = range(1,41,1), []
+    for n in ns:
+        clf = KNeighborsClassifier(n_neighbors=n)
+        clf.fit(X, np.repeat(0, len(X)))
+        scores_ = []
+        for r, p, i in zip(X, y, range(len(X))):
+            ind = clf.kneighbors([r], n_neighbors=n+1, return_distance=False)
+            prediction = np.mean(y[[j for j in ind[0] if j != i]])
+            scores_.append((prediction - p) ** 2)
+        scores.append(np.mean(scores_))
+        
+    plt.plot(ns, scores, color='red')
+    plt.ylim([min(scores) - (max(scores)-min(scores))*0.1,
+              max(scores) + (max(scores)-min(scores))*0.1])
+    plt.title('Predicting alcohol percentage with KNN', fontsize=18)
+    plt.xlabel('N neighbors')
+    plt.ylabel('Average error')
+    plt.show()
+
+if __name__ == '__main__':
+    #ex611()
+    #ex612()
+    ex613()