(WIP) Clustering allows mw

[RobinL]

import altair as alt
import pandas as pd

# Assuming 'dc_df' is your DataFrame
# dc_df = pd.DataFrame({...})

# Define the options for the x-axis
x_axis_options = ['threshold_match_probability', 'threshold_match_weight']

# Create a selection parameter with radio buttons
x_axis_param = alt.param(
    name='x_field',
    bind=alt.binding_radio(options=x_axis_options, name='X-axis: '),
    value='threshold_match_probability'
)

# Base chart with dynamic x-axis based on the parameter
base_chart = (
    alt.Chart(dc_df)
    .transform_fold(
        fold=['threshold_match_probability', 'threshold_match_weight'],
        as_=['variable', 'x_value']
    )
    .transform_filter(
        alt.datum.variable == x_axis_param
    )
    .add_params(x_axis_param)
    .encode(
        x=alt.X('x_value:Q', title='X-axis')
    )
    .properties(width=400, height=150)
)

# Define the subcharts
num_clusters = (
    base_chart.mark_line()
    .encode(
        y=alt.Y("num_clusters:Q", title="Number of Clusters")
    )
    .properties(title="Number of Clusters vs X-axis")
)

max_cluster_size = (
    base_chart.mark_line()
    .encode(
        y=alt.Y("max_cluster_size:Q", title="Max Cluster Size")
    )
    .properties(title="Maximum Cluster Size vs X-axis")
)

avg_cluster_size = (
    base_chart.mark_line()
    .encode(
        y=alt.Y("avg_cluster_size:Q", title="Average Cluster Size")
    )
    .properties(title="Average Cluster Size vs X-axis")
)

# Combine the charts
combined_chart = alt.vconcat(
    num_clusters, max_cluster_size, avg_cluster_size
).resolve_scale(y="independent")