rpgd60

# Source: https://jakevdp.github.io/PythonDataScienceHandbook/05.08-random-forests.html
#
def visualize_classifier(model, X, y, ax=None, cmap='rainbow'):
    ax = ax or plt.gca()
    
    # Plot the training points
    ax.scatter(X[:, 0], X[:, 1], c=y, s=30, cmap=cmap,
               clim=(y.min(), y.max()), zorder=3)
    ax.axis('tight')
    ax.axis('off')

rpgd60

# Preliminary investigation
# Shape of training data (num_rows, num_columns)
print(X_train.shape)

# Number of missing values in each column of training data
missing_val_count_by_column = (X_train.isnull().sum())
print(missing_val_count_by_column[missing_val_count_by_column > 0])

# Result
'''