def plot_cumulative_features_importance(features,
threshold=0.90,
plot_size=(12, 8),
feature_type='features',
return_threshold=False):
"""
"""
plt.figure(figsize=plot_size)
# Number of features needed for threshold cumulative importance
importance_idx = np.min(np.where(features['cumulative_coefficient_frequency'] > threshold))
thr_percentage = 100 * threshold
required_features = importance_idx+1
l = '{} {} required for \n{:.0f}% cumulative importance.'.format(required_features,
feature_type,
thr_percentage)
# Cumulative importance plot
plt.plot(range(len(features)), features['cumulative_coefficient_frequency'], 'b-', label=l)
plt.xlabel('Number of {}'.format(feature_type.capitalize()), fontsize=12, labelpad=20)
plt.ylabel('Cumulative {} frequency'.format(feature_type.capitalize()), fontsize=12, labelpad=20)
plt.title('Cumulative {} Importance'.format(feature_type.capitalize()), fontsize=12, pad=20)
#plt.title(f'Cumulative Feature Importance\n\n{l}', fontsize=14, pad=20)
# Threshold vertical line plot
plt.vlines(importance_idx + 1, ymin=0, ymax=1.05, linestyles='--', colors='red')
plt.legend(loc='lower right', fontsize=10)
plt.tight_layout()
plt.show()
if return_threshold:
return required_features
def plot_n_top_features(features, model_label, n=10, x_label='feature', y_label='coefficient', plot_size=(12, 4)):
"""
"""
features.head(n).plot(x=x_label, y=y_label, kind='barh', figsize=plot_size)
plt.gca().invert_yaxis()
plt.title(f'{model_label} Top {n} Features', pad=20)
plt.xlabel('Coefficients', labelpad=20)
plt.ylabel('Features labels', labelpad=20)
plt.show()
def plot_n_top_features(features, model_label, n=10, x_label='feature', y_label='coefficient', plot_size=(12, 4)):
"""
:param features: a dataframe which contains features data
:param model_label:
:param n:
:param x_label:
:param y_label:
:param plot_size:
:return:
"""
features.head(n).plot(x=x_label, y=y_label, kind='barh', figsize=plot_size)
plt.gca().invert_yaxis()
plt.title(f'{model_label} Top {n} Features', pad=20)
plt.xlabel('Coefficients', labelpad=20)
plt.ylabel('Features labels', labelpad=20)
plt.show()
def plot_cumulative_features_importance(features, threshold=0.90, plot_size=(12, 8)):
"""
:param features: a dataframe which contains features data
:param threshold:
:param plot_size:
:return:
"""
plt.figure(figsize=plot_size)
# Number of features needed for threshold cumulative importance
importance_idx = np.min(np.where(features['cumulative_coefficient_frequency'] > threshold))
thr_percentage = 100 * threshold
l = '{} features required for {:.0f}% of cumulative importance.'.format(importance_idx+1, thr_percentage)
# Cumulative importance plot
plt.plot(range(len(features)), features['cumulative_coefficient_frequency'], 'b-', label=l)
plt.xlabel('Number of Features', fontsize=12, labelpad=20)
plt.ylabel('Cumulative Coefficient frequency', fontsize=12, labelpad=20)
plt.title('Cumulative Feature Importance', fontsize=14, pad=20)
# plt.title(f'Cumulative Feature Importance\n\n{l}', fontsize=14, pad=20)
# Threshold vertical line plot
plt.vlines(importance_idx + 1, ymin=0, ymax=1.05, linestyles='--', colors='red')
plt.legend(loc='lower right', fontsize=12)
plt.tight_layout()
plt.show()