PyCafe - Dash - Iris k-means Clustering Demo

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
import dash
import dash_bootstrap_components as dbc
import pandas as pd
import plotly.graph_objs as go
from dash import Input, Output, dcc, html
from sklearn import datasets
from sklearn.cluster import KMeans

iris_raw = datasets.load_iris()
iris = pd.DataFrame(iris_raw["data"], columns=iris_raw["feature_names"])

app = dash.Dash(external_stylesheets=[dbc.themes.BOOTSTRAP])

controls = dbc.Card(
    [
        html.Div(
            [
                dbc.Label("X variable"),
                dcc.Dropdown(
                    id="x-variable",
                    options=[
                        {"label": col, "value": col} for col in iris.columns
                    ],
                    value="sepal length (cm)",
                ),
            ]
        ),
        html.Div(
            [
                dbc.Label("Y variable"),
                dcc.Dropdown(
                    id="y-variable",
                    options=[
                        {"label": col, "value": col} for col in iris.columns
                    ],
                    value="sepal width (cm)",
                ),
            ]
        ),
        html.Div(
            [
                dbc.Label("Cluster count"),
                dbc.Input(id="cluster-count", type="number", value=3),
            ]
        ),
    ],
    body=True,
)

app.layout = dbc.Container(
    [
        html.H1("Iris k-means clustering"),
        html.Hr(),
        dbc.Row(
            [
                dbc.Col(controls, md=4),
                dbc.Col(dcc.Graph(id="cluster-graph"), md=8),
            ],
            align="center",
        ),
    ],
    fluid=True,
)


@app.callback(
    Output("cluster-graph", "figure"),
    [
        Input("x-variable", "value"),
        Input("y-variable", "value"),
        Input("cluster-count", "value"),
    ],
)
def make_graph(x, y, n_clusters):
    # minimal input validation, make sure there's at least one cluster
    km = KMeans(n_clusters=max(n_clusters, 1))
    df = iris.loc[:, [x, y]]
    km.fit(df.values)
    df["cluster"] = km.labels_

    centers = km.cluster_centers_

    data = [
        go.Scatter(
            x=df.loc[df.cluster == c, x],
            y=df.loc[df.cluster == c, y],
            mode="markers",
            marker={"size": 8},
            name="Cluster {}".format(c),
        )
        for c in range(n_clusters)
    ]

    data.append(
        go.Scatter(
            x=centers[:, 0],
            y=centers[:, 1],
            mode="markers",
            marker={"color": "#000", "size": 12, "symbol": "diamond"},
            name="Cluster centers",
        )
    )

    layout = {"xaxis": {"title": x}, "yaxis": {"title": y}}

    return go.Figure(data=data, layout=layout)


# make sure that x and y values can't be the same variable
def filter_options(v):
    """Disable option v"""
    return [
        {"label": col, "value": col, "disabled": col == v}
        for col in iris.columns
    ]


# functionality is the same for both dropdowns, so we reuse filter_options
app.callback(Output("x-variable", "options"), [Input("y-variable", "value")])(
    filter_options
)
app.callback(Output("y-variable", "options"), [Input("x-variable", "value")])(
    filter_options
)


if __name__ == "__main__":
    app.run_server(debug=True, port=8888)
Py.Cafe

dash-bootstrap-components-example-iris-k-means

Iris k-means Clustering Demo - Dash
