hist-overall-sales.py

import pandas as pd
import plotly.express as px
import plotly.figure_factory as ff
import numpy as np

# Load the dataset
file_path = 'C:\\Users\\loydt\\Downloads\\Superstore Sales Dataset.csv'
data = pd.read_csv(file_path)

# Create the histogram with a logarithmic x-axis
fig1 = px.histogram(data, x='Sales', nbins=1000, title='Sales Distribution - Histogram', 
                     opacity=0.7, log_x=True)

# Customize the histogram's color
fig1.update_traces(marker_color='orange', selector=dict(type='histogram'))

# Create a KDE plot using figure_factory
kde_data = [data['Sales']]
group_labels = ['Sales']

# Adding the KDE overlay to the histogram
kde_fig = ff.create_distplot(kde_data, group_labels, show_rug=False, curve_type='kde', bin_size=0.5)

# Add the KDE line to the histogram figure
for trace in kde_fig['data']:
    fig1.add_trace(trace)

# Updating the layout to set a darker background and other enhancements
fig1.update_layout(
    xaxis_title='Sales (Log Scale)',
    yaxis_title='Frequency',
    title='Sales Distribution',
    xaxis_title_font=dict(size=14),
    yaxis_title_font=dict(size=14),
    title_font=dict(size=18),
    xaxis_showgrid=True,
    yaxis_showgrid=True,
    xaxis_gridcolor='gray',
    yaxis_gridcolor='gray',
   
    # Set the background color to a darker shade
    paper_bgcolor='rgba(50, 50, 50, 1)',  # Background outside the plot area
    plot_bgcolor='rgba(40, 40, 40, 1)',   # Background inside the plot area

    # Customize font colors to ensure readability on a dark background
    font=dict(color='white')
)

# Show the plot
fig1.show()