Criminal/confusion_matrix.py

import itertools
import os
import sys
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
from sklearn.svm import SVC
import numpy as np 


def set_trace():
    """A Poor mans break point"""
    # without this in iPython debugger can generate strange characters.
    from IPython.core.debugger import Pdb
    Pdb().set_trace(sys._getframe().f_back)
 

def plot_confusion_matrix(cm,
                          class_names,
                          title='Confusion matrix',
                          cmap=plt.cm.Blues):
    plt.imshow(cm, interpolation='nearest', cmap=cmap)
    plt.title(title)
    plt.colorbar()
    tick_marks = np.arange(len(class_names))
    plt.xticks(tick_marks, class_names, rotation=45)
    plt.yticks(tick_marks, class_names)
    plt.tight_layout()

    width, height = cm.shape

    for x in xrange(width):
        for y in xrange(height):
            plt.annotate(str(cm[x][y]), xy=(y, x),
                         horizontalalignment='center',
                         verticalalignment='center')
    plt.ylabel('True label')
    plt.xlabel('Predicted label')
    plt.show()

def svm_classifier(x, y, validation):
    """Split the data into a training set and a test set."""

    """Run SVM Classifier."""

    X_train, X_test, y_train, y_test = train_test_split(x, y, random_state=0)
    classifier = SVC(kernel='linear', C=0.01)
    y_pred = classifier.fit(X_train, y_train).predict(X_test)
    class_names = np.array(['Criminals','Non-criminals'])
    cm = confusion_matrix(y_test, y_pred)
    plot_confusion_matrix(cm, class_names)
'''
def plot_confusion_matrix(cm, classes, normalize=False,title='Confusion matrix',cmap=plt.cm.Blues):
    if normalize:
        cm =cm.astype('float') / cm.sum(axis=1)[:, np.newaxix]
        print('Confusion matrix, without normalization')     
        print(cm)
        plt.imshow(cm, interpolation='nearest', cmap=cmap)
        plt.title(title)
        plt.colorbar()
        tick_marks = np.arange(len(classes))
        plt.xticks(tick_marks, classes, rotation=45)
        plt.yticks(tick_marks, classes)
        fmt = '.2f' if normalize else 'd'
        thresh = cm.max() / 2.
        for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
            plt.text(j, i, format(cm[i, j], fmt),
                    horizontalalignment="center",
                    color="white" if cm[i, j] > thresh else "black")
    plt.tight_layout()
    plt.ylabel('True label')
    plt.xlabel('Predicted label')
'''
'''
# Compute confusion matrix
cnf_matrix = confusion_matrix(y_test, y_pred)
np.set_printoptions(precision=2)

# Plot non-normalized confusion matrix
plt.figure()
plot_confusion_matrix(cnf_matrix, classes=class_names,
                      title='Confusion matrix, without normalization')

# Plot normalized confusion matrix
plt.figure()
plot_confusion_matrix(cnf_matrix, classes=class_names, normalize=True,
                      title='Normalized confusion matrix')

plt.show()
'''