feature_pairs_plot.py

# Extract the columns to  plot
plot_data = features[['score', 'Site EUI (kBtu/ft²)', 
                      'Weather Normalized Source EUI (kBtu/ft²)', 
                      'log_Total GHG Emissions (Metric Tons CO2e)']]

# Replace the inf with nan
plot_data = plot_data.replace({np.inf: np.nan, -np.inf: np.nan})

# Rename columns 
plot_data = plot_data.rename(columns = {'Site EUI (kBtu/ft²)': 'Site EUI', 
                                        'Weather Normalized Source EUI (kBtu/ft²)': 'Weather Norm EUI',
                                        'log_Total GHG Emissions (Metric Tons CO2e)': 'log GHG Emissions'})

# Drop na values
plot_data = plot_data.dropna()

# Function to calculate correlation coefficient between two columns
def corr_func(x, y, **kwargs):
    r = np.corrcoef(x, y)[0][1]
    ax = plt.gca()
    ax.annotate("r = {:.2f}".format(r),
                xy=(.2, .8), xycoords=ax.transAxes,
                size = 20)

# Create the pairgrid object
grid = sns.PairGrid(data = plot_data, size = 3)

# Upper is a scatter plot
grid.map_upper(plt.scatter, color = 'red', alpha = 0.6)

# Diagonal is a histogram
grid.map_diag(plt.hist, color = 'red', edgecolor = 'black')

# Bottom is correlation and density plot
grid.map_lower(corr_func);
grid.map_lower(sns.kdeplot, cmap = plt.cm.Reds)

# Title for entire plot
plt.suptitle('Pairs Plot of Energy Data', size = 36, y = 1.02);