Visualizing Decision Boundaries

# Import statements 
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
import pandas as pd
import numpy as np

# Import the train test split
from sklearn.model_selection import train_test_split

# Read in the data
df = pd.read_csv('visualizing-decision-boundaries/data.csv', header=None)
df.head()

data = np.asarray(df)

# Assign the features to the variable X, and the labels to the variable y
X = data[:,0:2]
y = data[:,2]

# Use train test split to split your data 
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

# Instantiate the model and fit it to the training data
model = DecisionTreeClassifier().fit(X_train, y_train)

# Use the trained model to make predictions
y_pred = model.predict(X_test)

# Calculate the accuracy and assign it to the variable acc on the test data
acc_percent = accuracy_score(y_pred, y_test)
acc_numerator = accuracy_score(y_pred, y_test, normalize=False)
accuracy_string = '{:2.1f}% ({}/{}) Accurate on the Test Set'.format(acc_percent*100.,
                                                                     acc_numerator,
                                                                     y_test.shape[0])
print(accuracy_string)

%matplotlib notebook

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

cmap_light = ListedColormap(['#FFCCCC', '#CCCCFF'])
cmap_bold = ListedColormap(['#FF1111', '#1111FF'])

mesh_step_size = .001
mark_symbol_size = 20

def plot_decision_boundaries(Xs, Ys, title):
    plt.figure()

    # Plot Decision Boundaries
    xx, yy = np.meshgrid(np.arange(0, 1, mesh_step_size),
                         np.arange(0, 1, mesh_step_size))
    Z = model.predict(np.c_[xx.ravel(), 
    yy.ravel()])
    Z = Z.reshape(xx.shape)
    plt.pcolormesh(xx, yy, Z, cmap=cmap_light)

    # Plot Points
    plt.scatter(Xs[:, 0],
                Xs[:, 1],
                s=mark_symbol_size,
                c=Ys,
                cmap=cmap_bold, 
                edgecolor='black')
    plt.title(title)
    
    for spine in plt.gca().spines.values():
        spine.set_visible(False)
    plt.xticks([0.0,1.0])
    plt.yticks([0.0,1.0]);
    
plot_decision_boundaries(X_train, y_train, 'Training Set');

plot_decision_boundaries(X_test, y_test, accuracy_string);