Get started

1
2
3
4

import geoanalytics_fabric
from geoanalytics_fabric.sql import functions as ST
spark.sql("show user functions like 'ST_*'").show()

1
2
3
4
5
import geoanalytics_fabric
df = spark.read.format("feature-service").load("https://services.arcgis.com/P3ePLMYs2RVChkJx/ArcGIS/rest/services/USA_Census_Counties/FeatureServer/0")
df.printSchema()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
root
 |-- OBJECTID: long (nullable = false)
 |-- NAME: string (nullable = true)
 |-- STATE_NAME: string (nullable = true)
 |-- STATE_ABBR: string (nullable = true)
 |-- STATE_FIPS: string (nullable = true)
 |-- COUNTY_FIPS: string (nullable = true)
 |-- FIPS: string (nullable = true)
 |-- POPULATION: integer (nullable = true)
 |-- POP_SQMI: double (nullable = true)
 |-- SQMI: double (nullable = true)
 |-- Shape__Area: double (nullable = true)
 |-- Shape__Length: double (nullable = true)
 |-- shape: polygon (nullable = true)

1
2
3
4
5
6
7
import geoanalytics_fabric.sql.functions as ST
# Calculate the centroid of each county polygon
county_centroids = df.select("Name", ST.centroid("shape"))
# Display the first 5 rows of the result
county_centroids.show(5)

1
2
3
4
5
6
7
8
9
10
+--------------+--------------------+
|          Name|  ST_Centroid(shape)|
+--------------+--------------------+
|Autauga County|{"x":-86.64275399...|
|Baldwin County|{"x":-87.72434612...|
|Barbour County|{"x":-85.39320138...|
|   Bibb County|{"x":-87.12644474...|
| Blount County|{"x":-86.56737589...|
+--------------+--------------------+
only showing top 5 rows

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
from geoanalytics_fabric.tracks import functions as TRK
from geoanalytics_fabric.sql import functions as ST
from pyspark.sql import functions as F

data = [
    ("LINESTRING M (-117.27 34.05 1633455010, -117.22 33.91 1633456062, -116.96 33.64 1633457132)",),
    ("LINESTRING M (-116.89 33.96 1633575895, -116.71 34.01 1633576982, -116.66 34.08 1633577061)",),
    ("LINESTRING M (-116.24 33.88 1633575234, -116.33 34.02 1633576336)",)
]

# Create tracks from WKT
trk_df = spark.createDataFrame(data, ["wkt",]) \
         .withColumn("track", ST.line_from_text("wkt", srid=4326))

# Calculate the length of each track and display it
trk_df.select(F.round(TRK.length("track", "miles"), 3).alias("length")).show()

1
2
3
4
5
6
7
+------+
|length|
+------+
|33.947|
|16.507|
|10.947|
+------+

1
2
3
4
5
6
7
8
9
10
11
12
13
14
from geoanalytics_fabric.tools import FindSimilarLocations

# Use Find Similar Locations to find counties with population count and density like Alexander County
fsl = FindSimilarLocations() \
	.setAnalysisFields("POP_SQMI","POPULATION") \
	.setMostOrLeastSimilar("MostSimilar") \
	.setNumberOfResults(5) \
    .setAppendFields("NAME", "STATE_NAME") \
	.run(df.where("NAME = 'Alexander County'"), df.where("NAME != 'Alexander County'"))

# Show the result
fsl.select("simrank", "NAME", "STATE_NAME").filter("NAME is not NULL").sort("simrank").show()

1
2
3
4
5
6
7
8
9
+-------+----------------+--------------+
|simrank|            NAME|    STATE_NAME|
+-------+----------------+--------------+
|      1|St. James Parish|     Louisiana|
|      2|   Greene County|North Carolina|
|      3|   Dakota County|      Nebraska|
|      4| McDuffie County|       Georgia|
|      5|    Union County|     Tennessee|
+-------+----------------+--------------+

1
2
3
4
# Plot counties in Georgia and symbolize on population
df.where("STATE_NAME = 'Georgia'").st.plot(cmap_values="POPULATION", cmap="RdPu", figsize=(6,6), basemap="light")

1
2
3
4
# Write a DataFrame returned from tool as a collection of shapefiles to an S3 bucket
fsl.write.format("shapefile").save("s3a://my-bucket/fsl_result")