Classic Approach

In [1]:

    

import warnings
warnings.filterwarnings('ignore')


    

In [2]:

    

%matplotlib inline
%pylab inline


    

    




Populating the interactive namespace from numpy and matplotlib

In [3]:

    

import pandas as pd
print(pd.__version__)


    

    




0.22.0

In [4]:

    

df = pd.read_csv('./insurance-customers-300.csv', sep=';')


    

In [5]:

    

y=df['group']


    

In [6]:

    

df.drop('group', axis='columns', inplace=True)


    

In [7]:

    

X = df.as_matrix()


    

In [8]:

    

df.describe()


    

    
Out[8]:







  

    

      

      
max speed
      
age
      
thousand km per year
    
  
  

    

      
count
      
300.000000
      
300.000000
      
300.000000
    
    

      
mean
      
171.863333
      
44.006667
      
31.220000
    
    

      
std
      
18.807545
      
16.191784
      
15.411792
    
    

      
min
      
132.000000
      
18.000000
      
5.000000
    
    

      
25%
      
159.000000
      
33.000000
      
18.000000
    
    

      
50%
      
171.000000
      
42.000000
      
30.000000
    
    

      
75%
      
187.000000
      
52.000000
      
43.000000
    
    

      
max
      
211.000000
      
90.000000
      
99.000000
    
  

In [9]:

    

# ignore this, it is just technical code
# should come from a lib, consider it to appear magically 
# http://scikit-learn.org/stable/auto_examples/neighbors/plot_classification.html

import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap

cmap_print = ListedColormap(['#AA8888', '#004000', '#FFFFDD'])
cmap_bold = ListedColormap(['#AA4444', '#006000', '#AAAA00'])
cmap_light = ListedColormap(['#FFAAAA', '#AAFFAA', '#FFFFDD'])
font_size=25

def meshGrid(x_data, y_data):
    h = 1  # step size in the mesh
    x_min, x_max = x_data.min() - 1, x_data.max() + 1
    y_min, y_max = y_data.min() - 1, y_data.max() + 1
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                         np.arange(y_min, y_max, h))
    return (xx,yy)
    
def plotPrediction(clf, x_data, y_data, x_label, y_label, colors, title="", mesh=True, fname=None):
    xx,yy = meshGrid(x_data, y_data)
    plt.figure(figsize=(20,10))

    if clf and mesh:
        Z = clf.predict(np.c_[yy.ravel(), xx.ravel()])
        # Put the result into a color plot
        Z = Z.reshape(xx.shape)
        plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
    
    plt.xlim(xx.min(), xx.max())
    plt.ylim(yy.min(), yy.max())
    if fname:
        plt.scatter(x_data, y_data, c=colors, cmap=cmap_print, s=200, marker='o', edgecolors='k')
    else:
        plt.scatter(x_data, y_data, c=colors, cmap=cmap_bold, s=80, marker='o', edgecolors='k')
    plt.xlabel(x_label, fontsize=font_size)
    plt.ylabel(y_label, fontsize=font_size)
    plt.title(title, fontsize=font_size)
    if fname:
        plt.savefig(fname)


    

In [10]:

    

# 0: red
# 1: green
# 2: yellow

class ClassifierBase:
    def predict(self, X):
        return np.array([ self.predict_single(x) for x in X])
    def score(self, X, y):
        n = len(y)
        correct = 0
        predictions = self.predict(X)
        for prediction, ground_truth in zip(predictions, y):
            if prediction == ground_truth:
                correct = correct + 1
        return correct / n

from random import randrange

class RandomClassifier(ClassifierBase):
    def predict_single(self, x):
        return randrange(3)


    

In [11]:

    

random_clf = RandomClassifier()


    

In [12]:

    

plotPrediction(random_clf, X[:, 1], X[:, 0], 
               'Age', 'Max Speed', y,
                title="Max Speed vs Age (Random)")


    

In [13]:

    

random_clf.score(X, y)


    

    
Out[13]:





0.35

In [14]:

    

class BaseLineClassifier(ClassifierBase):
    def predict_single(self, x):
        try:
            speed, age, km_per_year = x
        except:
            speed, age = x
            km_per_year = 0
        if age < 25:
            if speed > 180:
                return 0
            else:
                return 2
        if age > 75:
            return 0
        if km_per_year > 50:
            return 0
        if km_per_year > 35:
            return 2
        return 1


    

In [15]:

    

base_clf = BaseLineClassifier()


    

In [16]:

    

plotPrediction(base_clf, X[:, 1], X[:, 0], 
               'Age', 'Max Speed', y,
                title="Max Speed vs Age with Classification")


    

In [17]:

    

base_clf.score(X, y)


    

    
Out[17]:





0.43666666666666665