File size: 8,108 Bytes
f9c0284
 
 
 
 
 
b5e340d
f9c0284
 
 
b5e340d
f9c0284
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b5e340d
 
 
 
f9c0284
b5e340d
 
f9c0284
b5e340d
 
 
f9c0284
 
b5e340d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f9c0284
 
 
 
 
 
 
 
 
 
 
 
 
a5af9bb
 
 
 
 
 
 
b5e340d
 
 
 
 
 
 
 
 
 
 
 
f9c0284
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b5e340d
 
b213530
b9d47ff
 
b213530
b5e340d
f9c0284
 
 
 
 
 
b9d47ff
b5e340d
 
 
b9d47ff
b5e340d
 
 
f9c0284
b5e340d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f9c0284
 
b213530
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f9c0284
 
 
 
 
 
 
 
 
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
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
from io import BytesIO

import numpy as np
import pandas as pd
import plotly.express as px
import streamlit as st
from hilbertcurve.hilbertcurve import HilbertCurve
from sklearn.cluster import KMeans


def cluster_sites_hilbert_curve_same_size(
    df: pd.DataFrame,
    lat_col: str,
    lon_col: str,
    region_col: str,
    max_sites: int = 25,
    mix_regions: bool = False,
):
    clusters = []
    cluster_id = 0

    if not mix_regions:
        grouped = df.groupby(region_col)
    else:
        grouped = [("All", df)]

    # Create Hilbert Curve (higher p = more precision)
    p = 16  # Adjust based on your coordinate precision needs
    hilbert_curve = HilbertCurve(p, 2)  # 2D curve

    for region, group in grouped:
        if len(group) == 0:
            continue

        # Normalize coordinates to [0, 2^p-1] range
        lat_min, lat_max = group[lat_col].min(), group[lat_col].max()
        lon_min, lon_max = group[lon_col].min(), group[lon_col].max()

        group = group.copy()
        group["x"] = ((group[lat_col] - lat_min) / (lat_max - lat_min + 1e-10)) * (
            2**p - 1
        )
        group["y"] = ((group[lon_col] - lon_min) / (lon_max - lon_min + 1e-10)) * (
            2**p - 1
        )

        # Calculate Hilbert distance
        group["hilbert"] = group.apply(
            lambda row: hilbert_curve.distance_from_point(
                [int(row["x"]), int(row["y"])]
            ),
            axis=1,
        )

        # Sort by Hilbert value
        group = group.sort_values("hilbert")

        # Create fixed-size clusters
        for i in range(0, len(group), max_sites):
            cluster = group.iloc[i : i + max_sites].copy()
            cluster["Cluster"] = f"C{cluster_id}"
            clusters.append(cluster)
            cluster_id += 1

    result = pd.concat(clusters)
    return result.drop(columns=["x", "y", "hilbert"], errors="ignore")


def cluster_sites_kmeans_lower_to_fixed_size(
    df: pd.DataFrame,
    lat_col: str,
    lon_col: str,
    region_col: str,
    max_sites: int = 25,
    mix_regions: bool = False,
):
    clusters = []
    cluster_id = 0

    if not mix_regions:
        grouped = df.groupby(region_col)
    else:
        grouped = [("All", df)]

    for region, group in grouped:
        coords = group[[lat_col, lon_col]].to_numpy()
        remaining_sites = group.copy()

        while len(remaining_sites) > 0:
            # Calculate number of clusters needed for remaining sites
            n_remaining = len(remaining_sites)
            n_clusters = max(1, int(np.ceil(n_remaining / max_sites)))

            if n_remaining <= max_sites:
                # If remaining sites can fit in one cluster
                cluster_group = remaining_sites.copy()
                cluster_group["Cluster"] = f"C{cluster_id}"
                clusters.append(cluster_group)
                cluster_id += 1
                break
            else:
                # Apply KMeans to remaining sites
                kmeans = KMeans(n_clusters=n_clusters, random_state=42, n_init=10)
                labels = kmeans.fit_predict(
                    remaining_sites[[lat_col, lon_col]].to_numpy()
                )

                # Split into clusters and check sizes
                temp_df = remaining_sites.copy()
                temp_df["Cluster"] = labels
                temp_df["Temp_Cluster"] = labels

                for cluster_num in range(n_clusters):
                    cluster_group = temp_df[temp_df["Temp_Cluster"] == cluster_num]
                    if len(cluster_group) <= max_sites:
                        # If cluster is small enough, keep it
                        cluster_group = cluster_group.drop(columns=["Temp_Cluster"])
                        cluster_group["Cluster"] = f"C{cluster_id}"
                        clusters.append(cluster_group)
                        cluster_id += 1
                        # Remove these sites from remaining_sites
                        remaining_sites = remaining_sites.drop(cluster_group.index)
                    # Else these sites will remain for next iteration

    return pd.concat(clusters)


def to_excel(df: pd.DataFrame) -> bytes:
    output = BytesIO()
    with pd.ExcelWriter(output, engine="xlsxwriter") as writer:
        df.to_excel(writer, index=False, sheet_name="Clusters")
    return output.getvalue()


st.title("Automatic Site Clustering App")

# Add description
st.write(
    """This app allows you to cluster sites based on their latitude and longitude.
    **Please choose a file containing the latitude and longitude region and site code columns.**
                      """
)

# Download Sample file
clustering_sample_file_path = "samples/Site_Clustering.xlsx"

# Create a download button
st.download_button(
    label="Download Clustering Sample File",
    data=open(clustering_sample_file_path, "rb").read(),
    file_name="Site_Clustering.xlsx",
    mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
)

uploaded_file = st.file_uploader("Upload your Excel file ", type=["xlsx"])

if uploaded_file:
    df = pd.read_excel(uploaded_file)
    st.write("Sample of uploaded data:", df.head())

    columns = df.columns.tolist()

    with st.form("clustering_form"):
        lat_col = st.selectbox("Select Latitude column", columns)
        lon_col = st.selectbox("Select Longitude column", columns)
        region_col = st.selectbox("Select Region column", columns)
        code_col = st.selectbox("Select Site Code column", columns)
        max_sites = st.number_input(
            "Max sites per cluster", min_value=5, max_value=100, value=25
        )
        cluster_method = st.selectbox(
            "Select clustering method",
            [
                "Uniform number of sites for each cluster",  # Hilbert Curve
                "Number of sites Lower than max but not uniform",  # KMeans
            ],
        )
        mix_regions = st.checkbox(
            "Allow mixing different regions in clusters", value=False
        )
        submitted = st.form_submit_button("Run Clustering")

    if submitted:
        if cluster_method == "Uniform number of sites for each cluster":
            clustered_df = cluster_sites_hilbert_curve_same_size(
                df, lat_col, lon_col, region_col, max_sites, mix_regions
            )
        elif cluster_method == "Number of sites Lower than max but not uniform":
            clustered_df = cluster_sites_kmeans_lower_to_fixed_size(
                df, lat_col, lon_col, region_col, max_sites, mix_regions
            )
        st.success("Clustering completed!")

        # Show cluster size per cluster plot
        cluster_size = clustered_df["Cluster"].value_counts().sort_index()
        fig = px.bar(cluster_size, x=cluster_size.index, y=cluster_size.values)
        fig.update_layout(title="Cluster Size")
        st.plotly_chart(fig)

        # Show cluster size per region plot
        cluster_size_per_region = (
            clustered_df.groupby([region_col, "Cluster"])
            .size()
            .reset_index(name="count")
        )
        fig = px.bar(cluster_size_per_region, x="Cluster", y="count", color=region_col)
        fig.update_layout(title="Cluster Size per Region")
        st.plotly_chart(fig)

        # Map Plot
        clustered_df["size"] = 10
        fig = px.scatter_map(
            clustered_df,
            lat=lat_col,
            lon=lon_col,
            color="Cluster",
            size="size",
            hover_name=code_col,
            hover_data=[region_col],
            zoom=5,
            height=600,
        )
        fig.update_layout(mapbox_style="open-street-map")
        fig.update_traces(marker=dict(size=15))
        st.plotly_chart(fig)

        # Download button
        st.download_button(
            label="Download clustered Excel file",
            data=to_excel(clustered_df),
            file_name="clustered_sites.xlsx",
            mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
            on_click="ignore",
            type="primary",
        )