Py.Cafe
Megastore Sales Performance
- app.py
- requirements.txt
app.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
############ Imports ##############
import vizro.models as vm
from vizro.models.types import capture
from vizro import Vizro
import pandas as pd
from vizro.managers import data_manager
import plotly.graph_objects as go
import numpy as np
from vizro.models.types import capture
####### Function definitions ######
@capture("graph")
def horizontal_category_subcategory_sales(data_frame):
# Group by Product Category and Product Sub-Category to get total sales and profit
grouped = (
data_frame.groupby(["Product Category", "Product Sub-Category"])
.agg({"Sales": "sum", "Profit": "sum"})
.reset_index()
)
# Sort by Product Category, then by Sales DESCENDING within each category (highest first)
grouped = grouped.sort_values(
["Product Category", "Sales"], ascending=[True, False]
)
# Normalize profit values for color mapping (0 to 1 scale)
min_profit = grouped["Profit"].min()
max_profit = grouped["Profit"].max()
profit_range = max_profit - min_profit
# Create color scale from pale blue (low profit) to dark blue (high profit)
def get_color(profit_value):
if profit_range == 0:
return "#1f4e79" # Default dark blue if no variation
# Normalize profit to 0-1 scale
normalized = (profit_value - min_profit) / profit_range
# Interpolate between pale blue and dark blue
# Pale Blue: #add8e6, Dark Blue: #1f4e79
pale_r, pale_g, pale_b = 173, 216, 230
dark_r, dark_g, dark_b = 31, 78, 121
r = int(pale_r + (dark_r - pale_r) * normalized)
g = int(pale_g + (dark_g - pale_g) * normalized)
b = int(pale_b + (dark_b - pale_b) * normalized)
return f"rgb({r},{g},{b})"
# Create colors for each bar based on profit
colors = [get_color(profit) for profit in grouped["Profit"]]
# Create y-axis labels that maintain the sorted order (reverse for plotly display)
y_labels = grouped["Product Sub-Category"].tolist()
y_labels.reverse() # Reverse so highest sales appear at top
fig = go.Figure()
# Reverse the data order for display (highest sales at top)
grouped_reversed = grouped.iloc[::-1].reset_index(drop=True)
colors_reversed = colors[::-1]
fig.add_trace(
go.Bar(
y=grouped_reversed["Product Sub-Category"],
x=grouped_reversed["Sales"],
orientation="h",
marker=dict(
color=colors_reversed,
line=dict(width=0.5, color="rgba(255,255,255,0.4)"),
),
hovertemplate="<b>%{y}</b><br>Sales: $%{x:,.0f}<br>Profit: $%{customdata:,.0f}<br><extra></extra>",
customdata=grouped_reversed["Profit"],
name="Sales by Sub-Category",
)
)
# Add dividing lines between product categories (adjust for reversed order)
categories = grouped["Product Category"].unique()
total_items = len(grouped)
y_position = 0
for i, category in enumerate(categories):
category_count = len(grouped[grouped["Product Category"] == category])
# Calculate position from bottom for reversed display
if i > 0:
line_position = total_items - y_position - 0.5
fig.add_hline(
y=line_position,
line=dict(color="rgba(255,255,255,0.6)", width=2, dash="solid"),
)
y_position += category_count
# Create gradient bar for legend
gradient_x = np.linspace(0, 1, 100)
gradient_colors = [
get_color(min_profit + (max_profit - min_profit) * x) for x in gradient_x
]
# Add gradient bar as a separate subplot area
fig.add_trace(
go.Bar(
x=gradient_x,
y=["Profit Level"] * 100,
orientation="h",
marker=dict(color=gradient_colors, line=dict(width=0)),
showlegend=False,
hoverinfo="skip",
yaxis="y2",
xaxis="x2",
)
)
fig.update_layout(
xaxis_title="Sales ($)",
yaxis_title="Product Sub-Category",
height=800,
hovermode="closest",
paper_bgcolor="rgba(0,0,0,0)",
plot_bgcolor="rgba(0,0,0,0)",
showlegend=False,
yaxis=dict(categoryorder="array", categoryarray=y_labels, domain=[0, 0.85]),
# Second y-axis for gradient legend
yaxis2=dict(
domain=[0.9, 0.95],
anchor="x2",
showticklabels=False,
showgrid=False,
zeroline=False,
),
# Second x-axis for gradient legend
xaxis2=dict(
domain=[0.7, 0.98],
anchor="y2",
showticklabels=False,
showgrid=False,
zeroline=False,
),
annotations=[
# Gradient legend labels
dict(
x=0.68,
y=0.925,
xref="paper",
yref="paper",
text="Low Profit",
showarrow=False,
font=dict(size=10, color="white"),
xanchor="right",
),
dict(
x=1.0,
y=0.925,
xref="paper",
yref="paper",
text="High Profit",
showarrow=False,
font=dict(size=10, color="white"),
xanchor="left",
),
dict(
x=0.84,
y=0.97,
xref="paper",
yref="paper",
text="<b>Profit Level</b>",
showarrow=False,
font=dict(size=11, color="white"),
xanchor="center",
),
],
)
return fig
####### Data Manager Settings #####
data_manager["megastore_data"] = pd.read_csv(
"https://raw.githubusercontent.com/stichbury/vizro_projects/main/Megastore/MegastoreData.csv"
)
########### Model code ############
model = vm.Dashboard(
pages=[
vm.Page(
components=[
vm.Graph(
type="graph",
figure=horizontal_category_subcategory_sales(
data_frame="megastore_data"
),
title="Sales by Product Sub-Category (Color = Profit)",
)
],
title="Megastore Sales Analysis",
)
],
theme="vizro_dark",
title="Megastore Dashboard",
)
Vizro().build(model).run()