distribution_histogram.py

import matplotlib.pyplot as plt

def generate_distribution_histogram(dataframe, 
                                    column_name, 
                                    title, x_axis_label, y_axis_label,
                                    label_name,
                                    number_bins = 15):
    """
    This function generates a histogram.
    Args:
        dataframe:
        column_name: String. Name of the column whose distribution we
        want to visualize.
        title: String. Title of the histogram.
        x_axis_label: String. X-axis label.
        y_axis_label: String. Y-axis label.
    Outputs:
        Histogram containing distribution for specific column column_name.
    """
    plt.hist(dataframe[column_name], bins = number_bins, label = label_name)
    plt.title(title)
    plt.xlabel(x_axis_label)
    plt.ylabel(y_axis_label)
    plt.legend(loc='upper right')

#### MAIN FUNCTION ####
generate_distribution_histogram(df, 'age',
                                title = 'Age Distribution: US Population',
                                x_axis_label = 'Age (years)',
                                y_axis_label = 'Frequency',
                                label_name = 'Age')