Pandas Facetplot histograms for categorical data

categorical_hist.py

# which columns from the data frame to plot
columns_to_plot = df.ix[:, df.columns != 'Customer ID'].columns

# facet plot dimensions
plot_columns = 5
plot_rows =math.ceil(len(columns_to_plot)/plot_columns)

# create figure
fig, ax = plt.subplots(plot_rows, plot_columns, figsize=(15,20))
fig.subplots_adjust(hspace=0.6)      # adjust vertical spacing between plots

# iterate through columns and create each chart
for i, column in enumerate(columns_to_plot):
    
    # split the title into four-word long lines
    title = column.split(' ')
    title = [' '.join(title[i:i+4]) for i in range(0, len(title), 4)]
    title = '\n'.join(title)
    
    # bin the data to create histograms for numeric and categorical data
    df_ = df[column].value_counts().reset_index().sort_values('index').set_index('index')
    
    # create integer list of x_ticks.  Can't plot string values
    x_ticks = [j for j in range(0, len(df_.index))]
    
    # we only want about 10 ticks on the x_axis so calcualte the tick interval
    x_label_count = 1 if len(x_ticks) < 10 else math.ceil(len(x_ticks)/10)
    
    # plot the data
    ax[int(i/plot_columns), i%plot_columns].bar(x_ticks, df_.values)
    ax[int(i/plot_rows), i%plot_columns].set_title(title)
    
    # use the original index data (e.g. including strings) as labels on the x_axis
    # but, offset their position by 0.4 time the interval between ticks (assumes bars are 0.8 wide)
    x_ticks = [x + (x_ticks[1] - x_ticks[0])*0.4 for x in x_ticks]
    ax[int(i/plot_rows), i%plot_columns].set_xticks(x_ticks[::x_label_count]);
    ax[int(i/plot_rows), i%plot_columns].set_xticklabels(df_.index[::x_label_count], rotation=90);