classes.py

# -*- coding: utf-8 -*-
"""
Created on Wed Dec 14 22:35:34 2016

@author: ben
"""

#grades = {
#    'Ben': [90,85, 76],
#    'Bob': [98, 77, 75]
#}

class Student(object):
    def __init__(self, name, grades, year_in_school, address):
        self.name = name
        self.grades = grades
        self.year_in_school = year_in_school
        self.address = address
        
    def print_average(self):
        print sum(self.grades)/float(len(self.grades))        
    
class Animal(object):
    def __init__(self, name):
        self.name = 'A pet named: ' + name
        
    def eat(self):
        print 'I ate a lot of food.'

class Cat(Animal):
    def speak(self):
        print 'Meow'

class Dog(Animal):
    def speak(self):
        print 'bark bark'

class Beagle(Dog):
    def speak(self):
        print 'Woof woof I am a beagle'
        

cat = Cat('Jimmmy')
dog = Beagle('Ruff')

print dog.name
dog.eat()
dog.speak()
#ben = Student('Ben', [90,85, 76], 8, 'Cambridge, MA')
#student2 = Student('Bob', [98,77, 100], 9, 'Boston, MA')
#
#student2.print_average()

ml.py

# -*- coding: utf-8 -*-
"""
Created on Thu Dec  8 21:45:56 2016
@author: ben
"""
import csv

import numpy
import matplotlib.pyplot as plt

myfile = open('/Users/Ben/Desktop/train.csv').readlines()

predictions = []
corrects = []

count = 0

datapoints = []
for line in csv.DictReader(myfile):
    prediction = predict(line)
    true_val = line['Survived']
    
    age = line['Age']
    sex = line['Sex']
    pclass = int(line['Pclass'])
    
    if sex == 'male':
        sex = 1
    else:
        sex = 0
    if age == '':
        age = 29.5
    else:
        age = float(age)

    datapoint = [age, sex, pclass]
    datapoints.append(datapoint)
    if true_val == '1':
        corrects.append(True)
    else:
        corrects.append(False)
    count += 1
    
#from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score

model = KNeighborsClassifier(n_neighbors=3, weights='distance')
model.fit(datapoints, corrects)

predictions = model.predict(datapoints)

print accuracy_score(predictions, corrects)