Argthtjtr

The Dataset

I've been playing around the Pima Indians Dataset on Classifying using Decision Tree Classifier. However I've got my results and as obvious stage I've been looking for Visualization of same.

here's the head of the dataset:

   TimesPregnant  GlucoseConcentration  BloodPrs  SkinThickness  Serum   BMI  

0              6                   148        72             35      0  33.6   

1              1                    85        66             29      0  26.6   

2              8                   183        64              0      0  23.3   

3              1                    89        66             23     94  28.1   

4              0                   137        40             35    168  43.1   



   DiabetesFunct  Age  Class  

0          0.627   50      1  

1          0.351   31      0  

2          0.672   32      1  

3          0.167   21      0  

4          2.288   33      1 

Plotting more than 2 features?

Here's the code I've assembled using references and tutorials around web. Apparently it doesn't work for more than 2 features. In here, as you can notice except the last column, all the others are my features.

The code

# Visualising the Training set results

from matplotlib.colors import ListedColormap

X_set, y_set = X_train, y_train

X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),

                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))

plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),

             alpha = 0.75, cmap = ListedColormap(('red', 'green')))

plt.xlim(X1.min(), X1.max())

plt.ylim(X2.min(), X2.max())

for i, j in enumerate(np.unique(y_set)):

    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],

                c = ListedColormap(('red', 'green'))(i), label = j)

plt.title('Decision Tree (Train set)')

plt.xlabel('Age')

plt.ylabel('Estimated Salary')

plt.legend()

plt.show() 

You may notice those X1, X2 making up from meshgrid so as to utilize the space I'm using for coloring, however you are free to ignore if solution you propose covers plotting more than 2 features as far as it is on matplotlib.

Now, I can't make 8 X's for 8 Features here, I look for quite efficient way to do same.

Here's how you can do it:

from itertools import product

from matplotlib import pyplot as plt

import numpy as np

import scipy.stats as sts



features = [np.linspace(0, 5),



            np.linspace(9, 14),



            np.linspace(6, 11),

            np.linspace(3, 8)]



labels = ['height',

          'weight',

          'bmi',

          'age']



n = len(features)

fig, axarr = plt.subplots(n, n, figsize=(4*n, 4*n))

fig.subplots_adjust(0, 0, 1, 1, 0, 0)



for (x,y),ax in zip(product(features, features), axarr.T.flat):

    X,Y = np.meshgrid(x, y)



    # get some fake data for demo purposes

    mnorm = sts.multivariate_normal([x.mean()**(7/10), y.mean()**(11/10)])

    Z = mnorm.pdf(np.stack([X, Y], 2))



    ax.contourf(X, Y, Z)



# label and style the plot

# ...in progress

Output: