Calculate field

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

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

# Path to the Atlantic hurricanes data
data_path = r"https://sampleserver6.arcgisonline.com/arcgis/rest/services/Hurricanes/MapServer/0"

# Create an Atlantic hurricanes DataFrame
df = spark.read.format("feature-service").load(data_path) \
                    .st.set_time_fields("Date_Time")

# Use Calculate Field  to create a new column containing the average windspeed in
# miles per hour based on the previous, current, and next observation in the track.
result = CalculateField() \
            .setField(field_name="avg_windspeed", field_type="DOUBLE") \
            .setExpression(expression="Mean($track.field['WINDSPEED'].window(-1,2))") \
            .setTrackFields("EVENTID") \
            .run(dataframe=df)

# View the first 5 rows of the result DataFrame
result.filter(result["EVENTID"] == "Alberto") \
      .select("EVENTID", F.date_format("Date_Time", "yyyy-MM-dd").alias("Date_Time"), "WINDSPEED", "avg_windspeed") \
      .sort("avg_windspeed", ascending=False).show(5)

1
2
3
4
5
6
7
8
9
10
+-------+----------+---------+------------------+
|EVENTID| Date_Time|WINDSPEED|     avg_windspeed|
+-------+----------+---------+------------------+
|Alberto|2000-08-12|    110.0|108.33333333333333|
|Alberto|2000-08-12|    110.0|106.66666666666667|
|Alberto|2000-08-13|    105.0|103.33333333333333|
|Alberto|2000-08-12|    100.0|             100.0|
|Alberto|2000-08-13|     95.0|              95.0|
+-------+----------+---------+------------------+
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
# Get the world continents data for plotting
continents_path = "https://services.arcgis.com/P3ePLMYs2RVChkJx/ArcGIS/rest" \
    "/services/World_Continents/FeatureServer/0"
continents_subset_df = spark.read.format("feature-service").load(continents_path) \
                                .where("""CONTINENT = 'North America' or
                                          CONTINENT = 'South America' or
                                          CONTINENT = 'Europe' or
                                          CONTINENT = 'Africa'""")

# Plot the Alantic hurricanes data with the continents subset data
continents_subset_plot = continents_subset_df.st.plot(facecolor="none",
                                                      edgecolors="lightblue",
                                                      figsize=(14,8))
result_plot = result.st.plot(cmap_values="avg_windspeed",
                             cmap="YlOrRd",
                             legend=True,
                             ax=continents_subset_plot,
                             basemap="light")
result_plot.set_title("Alantic hurricanes average windspeed (miles per hour)")
result_plot.set_xlabel("X (Meters)")
result_plot.set_xlim(right=10000000)
result_plot.set_ylabel("Y (Meters)");