Find point clusters

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
# Log in
import geoanalytics
geoanalytics.auth(username="myusername", password="mypassword")

# Imports
from geoanalytics.tools import FindPointClusters
from geoanalytics.sql import functions as ST
from pyspark.sql import functions as F

# Path to the Earthquakes data
data_path = r"https://sampleserver6.arcgisonline.com/arcgis/rest/services/" \
             "Earthquakes_Since1970/FeatureServer/0"

# Create an earthquakes DataFrame and transform the geometry to World Cylindrical Equal Area (54034)
df = spark.read.format("feature-service").load(data_path) \
                        .withColumn("shape", ST.transform("shape", 54034))

# Use Find Point Clusters to find clusters of earthquake occurrences across the globe
result = FindPointClusters() \
            .setClusterMethod(cluster_method="HDBSCAN") \
            .setMinPointsCluster(min_points_cluster=7) \
            .run(dataframe=df)

# Show a selection of columns for the first 5 output clusters sorted by cluster id
result.filter(result["CLUSTER_ID"] == 115) \
      .select("name", F.date_format("date_", "yyyy-MM-dd").alias("date_"), "CLUSTER_ID", "PROB", "STABILITY") \
      .sort("name", "date_", ascending=False).show(5, truncate=False)

1
2
3
4
5
6
7
8
9
10
+-----------------------------+----------+----------+-------------------+-------------------+
|name                         |date_     |CLUSTER_ID|PROB               |STABILITY          |
+-----------------------------+----------+----------+-------------------+-------------------+
|TAJIKISTAN: SHURAB, NEFTEABAD|1980-07-10|115       |0.180143468626724  |0.25173588399009866|
|TAJIKISTAN: SHARORA, GISSAR  |1989-01-21|115       |0.14929508441065453|0.25173588399009866|
|TAJIKISTAN: ROSHTKALA, KHOROG|1988-09-24|115       |0.17619107744283952|0.25173588399009866|
|TAJIKISTAN: ROGHUN           |2002-02-02|115       |0.18251933904618436|0.25173588399009866|
|TAJIKISTAN: ROGHUN           |2002-01-08|115       |0.18251933904618436|0.25173588399009866|
+-----------------------------+----------+----------+-------------------+-------------------+
only showing top 5 rows

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
# Create a continents DataFrame and transform the geometry to World Cylindrical Equal Area (54034)
continents_path = "https://services.arcgis.com/P3ePLMYs2RVChkJx/ArcGIS/rest/" \
                  "services/World_Continents/FeatureServer/0"
continents_df = spark.read.format("feature-service").load(continents_path) \
                                .withColumn("shape", ST.transform("shape", 54034))

# Plot the clustered results with the world continents data
continents_plot = continents_df.st.plot(facecolor="none",
                                        edgecolors="black",
                                        alpha=0.3,
                                        figsize=(14,12))
result_noise_plot = result.where("COLOR_ID == -1").st.plot(geometry="shape",
                                                           color="lightgrey",
                                                           ax=continents_plot,
                                                           basemap="light")
result_clusters_plot = result.where("COLOR_ID != -1").st.plot(geometry="shape",
                                                     cmap_values="COLOR_ID",
                                                     is_categorical=True,
                                                     cmap="Paired",
                                                     ax=continents_plot,
                                                     legend=True,
                                                     legend_kwds={"title": "Cluster ID",
                                                                  "loc": "lower right",
                                                                  "bbox_to_anchor": (1.09, 0)})
result_clusters_plot.set_title("Point clusters and noise results (grey) for world earthquake occurrences")
result_clusters_plot.set_xlabel("X (Meters)")
result_clusters_plot.set_ylabel("Y (Meters)");