特征选择 feature_importance

%matplotlib inline
import matplotlib.pyplot as plt
import seaborn as sns
color = sns.color_palette()
sns.set_style('darkgrid')

features_list = X_train.columns.values
feature_importance = rf.feature_importances_
sorted_idx = np.argsort(feature_importance)
 
plt.figure(figsize=(5,7))
plt.barh(range(len(sorted_idx)), feature_importance[sorted_idx], align='center')
plt.yticks(range(len(sorted_idx)), features_list[sorted_idx])
plt.xlabel('Importance')
plt.title('Feature importances')
plt.draw()
plt.show()

# Extract feature importances
features = list(train.columns)
feature_importance_values = random_forest.feature_importances_
feature_importances = pd.DataFrame({'feature': features, 'importance': feature_importance_values})

def plot_feature_importances(df):
    """
    Plot importances returned by a model. This can work with any measure of
    feature importance provided that higher importance is better. 
    
    Args:
        df (dataframe): feature importances. Must have the features in a column
        called `features` and the importances in a column called `importance
        
    Returns:
        shows a plot of the 15 most importance features
        
        df (dataframe): feature importances sorted by importance (highest to lowest) 
        with a column for normalized importance
        """
    
    # Sort features according to importance
    df = df.sort_values('importance', ascending = False).reset_index()
    
    # Normalize the feature importances to add up to one
    df['importance_normalized'] = df['importance'] / df['importance'].sum()

    # Make a horizontal bar chart of feature importances
    plt.figure(figsize = (10, 6))
    ax = plt.subplot()
    
    # Need to reverse the index to plot most important on top
    ax.barh(list(reversed(list(df.index[:15]))), 
            df['importance_normalized'].head(15), 
            align = 'center', edgecolor = 'k')
    
    # Set the yticks and labels
    ax.set_yticks(list(reversed(list(df.index[:15]))))
    ax.set_yticklabels(df['feature'].head(15))
    
    # Plot labeling
    plt.xlabel('Normalized Importance'); plt.title('Feature Importances')
    plt.show()
    
    return df

# Show the feature importances for the default features
feature_importances_sorted = plot_feature_importances(feature_importances)