def test_point_map():
x_data = []
y_data = []
# y = 150
for i in range(100, 200):
x_data.append(i)
y_data.append(150)
# y = x - 50
for i in range(100, 200):
x_data.append(i)
y_data.append(i - 50)
# y = 50
for i in range(100, 200):
x_data.append(i)
y_data.append(50)
arr_x = pandas.Series(x_data)
arr_y = pandas.Series(y_data)
vega_circle2d = vega_pointmap(
1024, 896, [-73.998427, 40.730309, -73.954348, 40.780816], 3,
"#2DEF4A", 0.5, "EPSG:43")
vega_json = vega_circle2d.build()
curve_z1 = arctern.point_map(arr_x, arr_y, vega_json.encode('utf-8'))
save_png(curve_z1, "/tmp/test_curve_z1.png")
def test_point_map():
x_data = []
y_data = []
# y = 150
for i in range(100, 200):
x_data.append(i)
y_data.append(150)
# y = x - 50
for i in range(100, 200):
x_data.append(i)
y_data.append(i - 50)
# y = 50
for i in range(100, 200):
x_data.append(i)
y_data.append(50)
arr_x = pandas.Series(x_data)
arr_y = pandas.Series(y_data)
vega_circle2d = VegaCircle2d(300, 200, 30, "#ff0000", 0.5)
vega_json = vega_circle2d.build()
curve_z = arctern.point_map(arr_x, arr_y, vega_json.encode('utf-8'))
save_png(curve_z, "/tmp/curve_z.png")
def test_point_map():
x_data = []
y_data = []
# y = 150
for i in range(100, 200):
x_data.append(i)
y_data.append(150)
# y = x - 50
for i in range(100, 200):
x_data.append(i)
y_data.append(i - 50)
# y = 50
for i in range(100, 200):
x_data.append(i)
y_data.append(50)
arr_x = pandas.Series(x_data)
arr_y = pandas.Series(y_data)
points = arctern.ST_Point(arr_x, arr_y)
vega = vega_pointmap(1024, 896, [-73.998427, 40.730309, -73.954348, 40.780816], 3, "#2DEF4A", 0.5, "EPSG:4326")
curve_z1 = arctern.point_map(vega, points)
save_png(curve_z1, "/tmp/test_curve_z1.png")
def draw_heat_map(spark):
df = spark.read.format("csv").option("header", True).option(
"delimiter", ","
).schema(
"VendorID string, tpep_pickup_datetime timestamp, tpep_dropoff_datetime timestamp, passenger_count long, trip_distance double, pickup_longitude double, pickup_latitude double, dropoff_longitude double, dropoff_latitude double, fare_amount double, tip_amount double, total_amount double, buildingid_pickup long, buildingid_dropoff long, buildingtext_pickup string, buildingtext_dropoff string"
).load("file:///tmp/0_5M_nyc_taxi_and_building.csv").cache()
df.show(20, False)
df.createOrReplaceTempView("nyc_taxi")
# df.createOrReplaceGlobalTempView("nyc_taxi")
res = spark.sql(
"select pickup_latitude as x, pickup_longitude as y, passenger_count as w from nyc_taxi"
)
res.printSchema()
res.createOrReplaceTempView("pickup")
register_funcs(spark)
res = spark.sql(
"select ST_Transform(ST_Point(x, y), 'EPSG:4326','EPSG:3857' ) as pickup_point, w from pickup"
)
res.show(20, False)
res.createOrReplaceTempView("project")
res = spark.sql(
"select Projection(pickup_point, 'POINT (4534000 -12510000)', 'POINT (4538000 -12513000)', 1024, 896) as point, w from project"
)
res.show(20, False)
vega_heat_map = VegaHeatMap(300, 200, 10.0)
vega = vega_heat_map.build()
res = heatmap(res, vega)
save_png(res, '/tmp/heatmap.png')
spark.sql("show tables").show()
spark.catalog.dropGlobalTempView("nyc_taxi")
def draw_world_include_province_weighted_point_map(spark):
# 1
df = spark.read.format("csv").option("header", True).option(
"delimiter", ","
).schema(
"Province string, Country string, Longitude double, Latitude double, ConfirmedCount int,"
"DeadCount int, CuredCount int, LastUpdateTime string").load(
country_with_province_csv).cache()
df.createOrReplaceTempView("COVID_country_province")
register_funcs(spark)
res2 = spark.sql(
"select ST_Point(Longitude, Latitude) as point, ConfirmedCount as s from COVID_country_province "
"where LastUpdateTime like '%03-29%'")
res2.createOrReplaceTempView("res2")
res2 = spark.sql("select * from res2 where point != 'POINT (nan nan)' ")
vega2 = vega_weighted_pointmap(
3000, 2000, [-289.095983, -73.863121, 289.095983, 73.863121],
"#F0356D", [2, 60], [6, 60], 1.0, "EPSG:4326")
res_png2 = weighted_pointmap(res2, vega2)
save_png(res_png2, './COVID_country_weighted_point_map2.png')
spark.catalog.dropGlobalTempView("COVID_country_province")
def test_heat_map():
x_data = []
y_data = []
c_data = []
x_data.append(-73.96524)
x_data.append(-73.96118)
x_data.append(-73.97324)
x_data.append(-73.98456)
y_data.append(40.73747)
y_data.append(40.74507)
y_data.append(40.75890)
y_data.append(40.77654)
c_data.append(10)
c_data.append(20)
c_data.append(30)
c_data.append(40)
arr_x = pandas.Series(x_data)
arr_y = pandas.Series(y_data)
arr_c = pandas.Series(c_data)
points = arctern.ST_Point(arr_x, arr_y)
vega = vega_heatmap(
1024,
896,
bounding_box=[-73.998427, 40.730309, -73.954348, 40.780816],
map_zoom_level=13.0,
coordinate_system='EPSG:4326')
heat_map1 = arctern.heat_map_layer(vega, points, arr_c)
save_png(heat_map1, "/tmp/test_heat_map1.png")
def test_choropleth_map():
wkt_data = []
count_data = []
wkt_data.append("POLYGON (("
"-73.97324 40.73747, "
"-73.96524 40.74507, "
"-73.96118 40.75890, "
"-73.95556 40.77654, "
"-73.97324 40.73747))")
count_data.append(5.0)
arr_wkt = pandas.Series(wkt_data)
arr_wkb = arctern.ST_GeomFromText(arr_wkt)
arr_count = pandas.Series(count_data)
vega = vega_choroplethmap(
1024,
896,
bounding_box=[-73.998427, 40.730309, -73.954348, 40.780816],
color_gradient=["#0000FF", "#FF0000"],
color_bound=[2.5, 5],
opacity=1.0,
coordinate_system='EPSG:4326')
choropleth_map1 = arctern.choropleth_map_layer(vega, arr_wkb, arr_count)
save_png(choropleth_map1, "/tmp/test_choropleth_map1.png")
def test_icon_viz():
x_data = []
y_data = []
x_data.append(-73.96524)
x_data.append(-73.96118)
x_data.append(-73.97324)
x_data.append(-73.98456)
y_data.append(40.73747)
y_data.append(40.74507)
y_data.append(40.75890)
y_data.append(40.77654)
arr_x = pandas.Series(x_data)
arr_y = pandas.Series(y_data)
points = arctern.ST_Point(arr_x, arr_y)
import os
dir_path = os.path.dirname(os.path.realpath(__file__))
png_path = dir_path + "/../images/taxi.png"
vega = vega_icon(
1024,
896,
bounding_box=[-73.998427, 40.730309, -73.954348, 40.780816],
icon_path=png_path,
coordinate_system="EPSG:4326")
icon_buf = arctern.icon_viz_layer(vega, points)
save_png(icon_buf, "/tmp/test_icon_viz.png")
def test_point_map():
x_data = []
y_data = []
# y = 150
for i in range(100, 200):
x_data.append(i)
y_data.append(150)
# y = x - 50
for i in range(100, 200):
x_data.append(i)
y_data.append(i - 50)
# y = 50
for i in range(100, 200):
x_data.append(i)
y_data.append(50)
arr_x = pandas.Series(x_data)
arr_y = pandas.Series(y_data)
points = arctern.ST_Point(arr_x, arr_y)
vega = vega_pointmap(
1024,
896,
bounding_box=[-73.998427, 40.730309, -73.954348, 40.780816],
point_size=3,
point_color="#2DEF4A",
opacity=0.5,
coordinate_system="EPSG:4326")
curve_z1 = arctern.point_map(vega, points)
save_png(curve_z1, "/tmp/test_curve_z1.png")
def draw_world_weighted_point_map(spark):
df = spark.read.format("csv").option("header", True).option(
"delimiter", ","
).schema(
"continent string, country string, locationId string, longitude double, latitude double,"
"currentConfirmedCount int, confirmedCount int, suspectedCount int, curedCount int, deadCount int, "
"updateTime timestamp").load(country_csv).cache()
df.createOrReplaceTempView("COVID_country")
register_funcs(spark)
# 1
res1 = spark.sql(
"select ST_Point(longitude, latitude) as point from COVID_country ")
res1.createOrReplaceTempView("res1")
res1 = spark.sql("select * from res1 where point != 'POINT (nan nan)' ")
res1.show(20, False)
vega1 = vega_weighted_pointmap(
3000, 2000, [-289.095983, -73.863121, 289.095983, 73.863121],
"#EEEEEE", [2, 60], [6], 1.0, "EPSG:4326")
res_png1 = weighted_pointmap(res1, vega1)
save_png(res_png1, './COVID_country_weighted_point_map1.png')
spark.catalog.dropGlobalTempView("COVID_country")
def test_choropleth_map():
wkt_data = []
count_data = []
wkt_data.append("POLYGON (("
"200 200, "
"200 300, "
"300 300, "
"300 200, "
"200 200))")
count_data.append(5.0)
arr_wkt = pandas.Series(wkt_data)
arr_wkb = arctern.wkt2wkb(arr_wkt)
arr_count = pandas.Series(count_data)
vega = vega_choroplethmap(
1900,
1410,
bounding_box=[-73.994092, 40.753893, -73.977588, 40.759642],
color_gradient=["#0000FF", "#FF0000"],
color_bound=[2.5, 5],
opacity=1.0,
coordinate_system='EPSG:4326')
choropleth_map1 = arctern.choropleth_map(vega, arr_wkb, arr_count)
save_png(choropleth_map1, "/tmp/test_choropleth_map1.png")
def draw_choropleth_map(spark):
start_time = time.time()
df = spark.read.format("csv").option("header", True).option(
"delimiter", ","
).schema(
"VendorID string, tpep_pickup_datetime timestamp, tpep_dropoff_datetime timestamp, passenger_count long, trip_distance double, pickup_longitude double, pickup_latitude double, dropoff_longitude double, dropoff_latitude double, fare_amount double, tip_amount double, total_amount double, buildingid_pickup long, buildingid_dropoff long, buildingtext_pickup string, buildingtext_dropoff string"
).load("file:///tmp/0_5M_nyc_taxi_and_building.csv").cache()
df.createOrReplaceTempView("nyc_taxi")
register_funcs(spark)
res = spark.sql(
"select ST_GeomFromText(buildingtext_dropoff) as polygon, passenger_count as w from nyc_taxi where (buildingtext_dropoff!='')"
)
vega1 = vega_choroplethmap(
1900,
1410,
bounding_box=[-73.994092, 40.753893, -73.977588, 40.759642],
color_gradient=["#0000FF", "#FF0000"],
color_bound=[2.5, 5],
opacity=1.0,
coordinate_system='EPSG:4326')
res1 = choroplethmap(vega1, res)
save_png(res1, '/tmp/choroplethmap1.png')
spark.sql("show tables").show()
spark.catalog.dropGlobalTempView("nyc_taxi")
print("--- %s seconds ---" % (time.time() - start_time))
def draw_point_map(spark):
start_time = time.time()
# file 0_5M_nyc_taxi_and_building.csv could be obtained from arctern-turoial warehouse under zilliztech account. The link on github is https://github.com/zilliztech/arctern-tutorial
df = spark.read.format("csv").option("header", True).option(
"delimiter", ","
).schema(
"VendorID string, tpep_pickup_datetime timestamp, tpep_dropoff_datetime timestamp, passenger_count long, trip_distance double, pickup_longitude double, pickup_latitude double, dropoff_longitude double, dropoff_latitude double, fare_amount double, tip_amount double, total_amount double, buildingid_pickup long, buildingid_dropoff long, buildingtext_pickup string, buildingtext_dropoff string"
).load("file:///tmp/0_5M_nyc_taxi_and_building.csv").cache()
df.createOrReplaceTempView("nyc_taxi")
register_funcs(spark)
res = spark.sql(
"select ST_Point(pickup_longitude, pickup_latitude) as point from nyc_taxi where ST_Within(ST_Point(pickup_longitude, pickup_latitude), ST_GeomFromText('POLYGON ((-73.998427 40.730309, -73.954348 40.730309, -73.954348 40.780816 ,-73.998427 40.780816, -73.998427 40.730309))'))"
)
vega = vega_pointmap(
1024,
896,
bounding_box=[-73.998427, 40.730309, -73.954348, 40.780816],
point_size=3,
point_color="#2DEF4A",
opacity=0.5,
coordinate_system="EPSG:4326")
res = pointmap(vega, res)
save_png(res, '/tmp/pointmap.png')
spark.sql("show tables").show()
spark.catalog.dropGlobalTempView("nyc_taxi")
print("--- %s seconds ---" % (time.time() - start_time))
def test_point_map():
x_data = []
y_data = []
x_data.append(-73.96524)
x_data.append(-73.96118)
x_data.append(-73.97324)
x_data.append(-73.98456)
y_data.append(40.73747)
y_data.append(40.74507)
y_data.append(40.75890)
y_data.append(40.77654)
arr_x = pandas.Series(x_data)
arr_y = pandas.Series(y_data)
points = arctern.ST_Point(arr_x, arr_y)
vega = vega_pointmap(
1024,
896,
bounding_box=[-73.998427, 40.730309, -73.954348, 40.780816],
point_size=10,
point_color="#0000FF",
opacity=1.0,
coordinate_system="EPSG:4326")
curve_z1 = arctern.point_map_layer(vega, points)
save_png(curve_z1, "/tmp/test_curve_z1.png")
def draw_point_map(spark):
# file 0_5M_nyc_taxi_and_building.csv could be obtained from arctern-turoial warehouse under zilliztech account. The link on github is https://github.com/zilliztech/arctern-tutorial
df = spark.read.format("csv").option("header", True).option(
"delimiter", ","
).schema(
"VendorID string, tpep_pickup_datetime timestamp, tpep_dropoff_datetime timestamp, passenger_count long, trip_distance double, pickup_longitude double, pickup_latitude double, dropoff_longitude double, dropoff_latitude double, fare_amount double, tip_amount double, total_amount double, buildingid_pickup long, buildingid_dropoff long, buildingtext_pickup string, buildingtext_dropoff string"
).load("file:///tmp/0_5M_nyc_taxi_and_building.csv").cache()
df.show(20, False)
df.createOrReplaceTempView("nyc_taxi")
# df.createOrReplaceGlobalTempView("nyc_taxi")
res = spark.sql(
"select pickup_latitude as x, pickup_longitude as y from nyc_taxi")
res.printSchema()
res.createOrReplaceTempView("pickup")
register_funcs(spark)
res = spark.sql(
"select ST_Transform(ST_Point(x, y), 'EPSG:4326','EPSG:3857' ) as pickup_point from pickup"
)
res.show(20, False)
res.createOrReplaceTempView("project")
res = spark.sql(
"select Projection(pickup_point, 'POINT (4534000 -12510000)', 'POINT (4538000 -12513000)', 1024, 896) as point from project"
)
res.show(20, False)
vega_point_map = VegaCircle2d(1900, 1410, 3, "#2DEF4A", 0.5)
vega = vega_point_map.build()
res = pointmap(res, vega)
save_png(res, '/tmp/pointmap.png')
spark.sql("show tables").show()
spark.catalog.dropGlobalTempView("nyc_taxi")
def draw_heat_map(spark):
start_time = time.time()
df = spark.read.format("csv").option("header", True).option(
"delimiter", ","
).schema(
"VendorID string, tpep_pickup_datetime timestamp, tpep_dropoff_datetime timestamp, passenger_count long, trip_distance double, pickup_longitude double, pickup_latitude double, dropoff_longitude double, dropoff_latitude double, fare_amount double, tip_amount double, total_amount double, buildingid_pickup long, buildingid_dropoff long, buildingtext_pickup string, buildingtext_dropoff string"
).load("file:///tmp/0_5M_nyc_taxi_and_building.csv").cache()
df.createOrReplaceTempView("nyc_taxi")
register_funcs(spark)
res = spark.sql(
"select ST_Point(pickup_longitude, pickup_latitude) as point, passenger_count as w from nyc_taxi where ST_Within(ST_Point(pickup_longitude, pickup_latitude), ST_GeomFromText('POLYGON ((-73.998427 40.730309, -73.954348 40.730309, -73.954348 40.780816 ,-73.998427 40.780816, -73.998427 40.730309))'))"
)
res.show()
vega = vega_heatmap(1024, 896,
[-73.998427, 40.730309, -73.954348, 40.780816], 10.0,
'EPSG:4326')
res = heatmap(vega, res)
save_png(res, '/tmp/heatmap.png')
spark.sql("show tables").show()
spark.catalog.dropGlobalTempView("nyc_taxi")
print("--- %s seconds ---" % (time.time() - start_time))
def draw_weighted_point_map(spark):
start_time = time.time()
df = spark.read.format("csv").option("header", True).option(
"delimiter", ","
).schema(
"VendorID string, tpep_pickup_datetime timestamp, tpep_dropoff_datetime timestamp, passenger_count long, trip_distance double, pickup_longitude double, pickup_latitude double, dropoff_longitude double, dropoff_latitude double, fare_amount double, tip_amount double, total_amount double, buildingid_pickup long, buildingid_dropoff long, buildingtext_pickup string, buildingtext_dropoff string"
).load("file:///tmp/0_5M_nyc_taxi_and_building.csv").cache()
df.createOrReplaceTempView("nyc_taxi")
register_funcs(spark)
# single color and single stroke width
res1 = spark.sql(
"select ST_Point(pickup_longitude, pickup_latitude) as point from nyc_taxi where ST_Within(ST_Point(pickup_longitude, pickup_latitude), ST_GeomFromText('POLYGON ((-73.998427 40.730309, -73.954348 40.730309, -73.954348 40.780816 ,-73.998427 40.780816, -73.998427 40.730309))'))"
)
vega1 = vega_weighted_pointmap(
1024, 896, [-73.998427, 40.730309, -73.954348, 40.780816], ["#87CEEB"],
[0, 2], [5], 1.0, "EPSG:4326")
res1 = weighted_pointmap(vega1, res1)
save_png(res1, '/tmp/weighted_pointmap_0_0.png')
# multiple color and single stroke width
res2 = spark.sql(
"select ST_Point(pickup_longitude, pickup_latitude) as point, tip_amount as c from nyc_taxi where ST_Within(ST_Point(pickup_longitude, pickup_latitude), ST_GeomFromText('POLYGON ((-73.998427 40.730309, -73.954348 40.730309, -73.954348 40.780816 ,-73.998427 40.780816, -73.998427 40.730309))'))"
)
vega2 = vega_weighted_pointmap(
1024, 896, [-73.998427, 40.730309, -73.954348, 40.780816],
["#0000FF", "#FF0000"], [0, 2], [5], 1.0, "EPSG:4326")
res2 = weighted_pointmap(vega2, res2)
save_png(res2, '/tmp/weighted_pointmap_1_0.png')
# single color and multiple stroke width
res3 = spark.sql(
"select ST_Point(pickup_longitude, pickup_latitude) as point, fare_amount as s from nyc_taxi where ST_Within(ST_Point(pickup_longitude, pickup_latitude), ST_GeomFromText('POLYGON ((-73.998427 40.730309, -73.954348 40.730309, -73.954348 40.780816 ,-73.998427 40.780816, -73.998427 40.730309))'))"
)
vega3 = vega_weighted_pointmap(
1024, 896, [-73.998427, 40.730309, -73.954348, 40.780816], ["#87CEEB"],
[0, 2], [0, 10], 1.0, "EPSG:4326")
res3 = weighted_pointmap(vega3, res3)
save_png(res3, '/tmp/weighted_pointmap_0_1.png')
# multiple color and multiple stroke width
res4 = spark.sql(
"select ST_Point(pickup_longitude, pickup_latitude) as point, tip_amount as c, fare_amount as s from nyc_taxi where ST_Within(ST_Point(pickup_longitude, pickup_latitude), ST_GeomFromText('POLYGON ((-73.998427 40.730309, -73.954348 40.730309, -73.954348 40.780816 ,-73.998427 40.780816, -73.998427 40.730309))'))"
)
vega4 = vega_weighted_pointmap(
1024, 896, [-73.998427, 40.730309, -73.954348, 40.780816],
["#0000FF", "#FF0000"], [0, 2], [0, 10], 1.0, "EPSG:4326")
res4 = weighted_pointmap(vega4, res4)
save_png(res4, '/tmp/weighted_pointmap_1_1.png')
spark.sql("show tables").show()
spark.catalog.dropGlobalTempView("nyc_taxi")
print("--- %s seconds ---" % (time.time() - start_time))
def test_choropleth_map():
wkt_data = []
count_data = []
wkt_data.append("POLYGON (("
"200 200, "
"200 300, "
"300 300, "
"300 200, "
"200 200))")
count_data.append(5.0)
arr_wkt = pandas.Series(wkt_data)
arr_wkb = arctern.wkt2wkb(arr_wkt)
arr_count = pandas.Series(count_data)
vega = vega_choroplethmap(1900, 1410, [-73.994092, 40.753893, -73.977588, 40.759642], ["#0000FF", "#FF0000"], [2.5, 5], 1.0, 'EPSG:4326')
choropleth_map1 = arctern.choropleth_map(vega, arr_wkb, arr_count)
save_png(choropleth_map1, "/tmp/test_choropleth_map1.png")
def test_heat_map():
x_data = []
y_data = []
c_data = []
for i in range(0, 5):
x_data.append(i + 50)
y_data.append(i + 50)
c_data.append(i + 50)
arr_x = pandas.Series(x_data)
arr_y = pandas.Series(y_data)
arr_c = pandas.Series(y_data)
vega_heat_map = VegaHeatMap(300, 200, 10.0)
vega_json = vega_heat_map.build()
heat_map = arctern.heat_map(arr_x, arr_y, arr_c, vega_json.encode('utf-8'))
save_png(heat_map, "/tmp/test_heat_map.png")
def draw_weighted_point_map(spark):
df = spark.read.format("csv").option("header", True).option(
"delimiter", ","
).schema(
"VendorID string, tpep_pickup_datetime timestamp, tpep_dropoff_datetime timestamp, passenger_count long, trip_distance double, pickup_longitude double, pickup_latitude double, dropoff_longitude double, dropoff_latitude double, fare_amount double, tip_amount double, total_amount double, buildingid_pickup long, buildingid_dropoff long, buildingtext_pickup string, buildingtext_dropoff string"
).load(data_path).cache()
df.show(20, False)
df.createOrReplaceTempView("nyc_taxi")
register_funcs(spark)
# single color and single stroke width
res1 = spark.sql(
"select ST_Point(pickup_longitude, pickup_latitude) as point from nyc_taxi where ST_Within(ST_Point(pickup_longitude, pickup_latitude), 'POLYGON ((-73.998427 40.730309, -73.954348 40.730309, -73.954348 40.780816 ,-73.998427 40.780816, -73.998427 40.730309))')"
)
vega1 = vega_weighted_pointmap(
1024, 896, [-73.998427, 40.730309, -73.954348, 40.780816], "#87CEEB",
[0, 2], [5], 1.0, "EPSG:4326")
res1 = weighted_pointmap(res1, vega1)
save_png(res1, '/tmp/weighted_pointmap_0_0.png')
# multiple color and single stroke width
res2 = spark.sql(
"select ST_Point(pickup_longitude, pickup_latitude) as point, tip_amount as c from nyc_taxi where ST_Within(ST_Point(pickup_longitude, pickup_latitude), 'POLYGON ((-73.998427 40.730309, -73.954348 40.730309, -73.954348 40.780816 ,-73.998427 40.780816, -73.998427 40.730309))')"
)
vega2 = vega_weighted_pointmap(
1024, 896, [-73.998427, 40.730309, -73.954348, 40.780816],
"blue_to_red", [0, 2], [5], 1.0, "EPSG:4326")
res2 = weighted_pointmap(res2, vega2)
save_png(res2, '/tmp/weighted_pointmap_1_0.png')
# single color and multiple stroke width
res3 = spark.sql(
"select ST_Point(pickup_longitude, pickup_latitude) as point, fare_amount as s from nyc_taxi where ST_Within(ST_Point(pickup_longitude, pickup_latitude), 'POLYGON ((-73.998427 40.730309, -73.954348 40.730309, -73.954348 40.780816 ,-73.998427 40.780816, -73.998427 40.730309))')"
)
vega3 = vega_weighted_pointmap(
1024, 896, [-73.998427, 40.730309, -73.954348, 40.780816], "#87CEEB",
[0, 2], [0, 10], 1.0, "EPSG:4326")
res3 = weighted_pointmap(res3, vega3)
save_png(res3, '/tmp/weighted_pointmap_0_1.png')
# multiple color and multiple stroke width
res4 = spark.sql(
"select ST_Point(pickup_longitude, pickup_latitude) as point, tip_amount as c, fare_amount as s from nyc_taxi where ST_Within(ST_Point(pickup_longitude, pickup_latitude), 'POLYGON ((-73.998427 40.730309, -73.954348 40.730309, -73.954348 40.780816 ,-73.998427 40.780816, -73.998427 40.730309))')"
)
vega4 = vega_weighted_pointmap(
1024, 896, [-73.998427, 40.730309, -73.954348, 40.780816],
"blue_to_red", [0, 2], [0, 10], 1.0, "EPSG:4326")
res4 = weighted_pointmap(res4, vega4)
save_png(res4, '/tmp/weighted_pointmap_1_1.png')
spark.sql("show tables").show()
spark.catalog.dropGlobalTempView("nyc_taxi")
def test_heat_map():
x_data = []
y_data = []
c_data = []
for i in range(0, 5):
x_data.append(i + 50)
y_data.append(i + 50)
c_data.append(i + 50)
arr_x = pandas.Series(x_data)
arr_y = pandas.Series(y_data)
points = arctern.ST_Point(arr_x, arr_y)
arr_c = pandas.Series(y_data)
vega = vega_heatmap(1024, 896, [-73.998427, 40.730309, -73.954348, 40.780816], 10.0, 'EPSG:4326')
heat_map1 = arctern.heat_map(vega, points, arr_c)
save_png(heat_map1, "/tmp/test_heat_map1.png")
def draw_choropleth_map(spark):
df = spark.read.format("csv").option("header", True).option(
"delimiter", ","
).schema(
"VendorID string, tpep_pickup_datetime timestamp, tpep_dropoff_datetime timestamp, passenger_count long, trip_distance double, pickup_longitude double, pickup_latitude double, dropoff_longitude double, dropoff_latitude double, fare_amount double, tip_amount double, total_amount double, buildingid_pickup long, buildingid_dropoff long, buildingtext_pickup string, buildingtext_dropoff string"
).load("file:///tmp/0_5M_nyc_taxi_and_building.csv").cache()
df.createOrReplaceTempView("nyc_taxi")
res = spark.sql(
"select buildingtext_dropoff as wkt, passenger_count as w from nyc_taxi"
)
vega = vega_choroplethmap(1900, 1410,
[-73.994092, 40.753893, -73.977588, 40.759642],
"blue_to_red", [2.5, 5], 1.0, 'EPSG:4326')
res = choroplethmap(res, vega)
save_png(res, '/tmp/choroplethmap.png')
spark.sql("show tables").show()
spark.catalog.dropGlobalTempView("nyc_taxi")
def test_weighted_point_map():
x_data = []
y_data = []
c_data = []
s_data = []
x_data.append(10)
x_data.append(20)
x_data.append(30)
x_data.append(40)
x_data.append(50)
y_data.append(10)
y_data.append(20)
y_data.append(30)
y_data.append(40)
y_data.append(50)
c_data.append(1)
c_data.append(2)
c_data.append(3)
c_data.append(4)
c_data.append(5)
s_data.append(2)
s_data.append(4)
s_data.append(6)
s_data.append(8)
s_data.append(10)
arr_x = pandas.Series(x_data)
arr_y = pandas.Series(y_data)
points = arctern.ST_Point(arr_x, arr_y)
arr_c = pandas.Series(c_data)
arr_s = pandas.Series(s_data)
vega1 = vega_weighted_pointmap(300, 200, [-73.998427, 40.730309, -73.954348, 40.780816], ["#87CEEB"], [1, 5], [5], 1.0, "EPSG:3857")
res1 = arctern.weighted_point_map(vega1, points)
save_png(res1, "/tmp/test_weighted_0_0.png")
vega2 = vega_weighted_pointmap(300, 200, [-73.998427, 40.730309, -73.954348, 40.780816], ["#0000FF", "#FF0000"], [1, 5], [5], 1.0, "EPSG:3857")
res2 = arctern.weighted_point_map(vega2, points, color_weights=arr_c)
save_png(res2, "/tmp/test_weighted_1_0.png")
vega3 = vega_weighted_pointmap(300, 200, [-73.998427, 40.730309, -73.954348, 40.780816], ["#87CEEB"], [1, 5], [1, 10], 1.0, "EPSG:3857")
res3 = arctern.weighted_point_map(vega3, points, size_weights=arr_s)
save_png(res3, "/tmp/test_weighted_0_1.png")
vega4 = vega_weighted_pointmap(300, 200, [-73.998427, 40.730309, -73.954348, 40.780816], ["#0000FF", "#FF0000"], [1, 5], [1, 10], 1.0, "EPSG:3857")
res4 = arctern.weighted_point_map(vega4, points, color_weights=arr_c, size_weights=arr_s)
save_png(res4, "/tmp/test_weighted_1_1.png")
def test_icon_viz():
x_data = []
y_data = []
for i in range(5):
x_data.append(i * 100)
y_data.append(i * 100)
arr_x = pandas.Series(x_data)
arr_y = pandas.Series(y_data)
points = arctern.ST_Point(arr_x, arr_y)
import os
dir_path = os.path.dirname(os.path.realpath(__file__))
png_path = dir_path + "/../images/taxi.png"
vega = vega_icon(800, 600, [-73.998427, 40.730309, -73.954348, 40.780816],
png_path, "EPSG:43")
icon_buf = arctern.icon_viz(vega, points)
save_png(icon_buf, "/tmp/test_icon_viz.png")
def draw_heat_map(spark):
df = spark.read.format("csv").option("header", True).option(
"delimiter", ","
).schema(
"VendorID string, tpep_pickup_datetime timestamp, tpep_dropoff_datetime timestamp, passenger_count long, trip_distance double, pickup_longitude double, pickup_latitude double, dropoff_longitude double, dropoff_latitude double, fare_amount double, tip_amount double, total_amount double, buildingid_pickup long, buildingid_dropoff long, buildingtext_pickup string, buildingtext_dropoff string"
).load(data_path).cache()
df.show(20, False)
df.createOrReplaceTempView("nyc_taxi")
register_funcs(spark)
res = spark.sql(
"select ST_Point(pickup_longitude, pickup_latitude) as point, passenger_count as w from nyc_taxi where ST_Within(ST_Point(pickup_longitude, pickup_latitude), 'POLYGON ((-73.998427 40.730309, -73.954348 40.730309, -73.954348 40.780816 ,-73.998427 40.780816, -73.998427 40.730309))')"
)
vega = vega_heatmap(1024, 896, 10.0,
[-73.998427, 40.730309, -73.954348, 40.780816],
'EPSG:4326')
res = heatmap(res, vega)
save_png(res, '/tmp/heatmap.png')
spark.sql("show tables").show()
spark.catalog.dropGlobalTempView("nyc_taxi")
def test_heat_map():
x_data = []
y_data = []
c_data = []
for i in range(0, 5):
x_data.append(i + 50)
y_data.append(i + 50)
c_data.append(i + 50)
arr_x = pandas.Series(x_data)
arr_y = pandas.Series(y_data)
arr_c = pandas.Series(y_data)
vega_heat_map = vega_heatmap(
1024, 896, 10.0, [-73.998427, 40.730309, -73.954348, 40.780816],
'EPSG:4326')
vega_json = vega_heat_map.build()
heat_map1 = arctern.heat_map(arr_x, arr_y, arr_c,
vega_json.encode('utf-8'))
save_png(heat_map1, "/tmp/test_heat_map1.png")
def draw_point_map(spark):
# file 0_5M_nyc_build.csv is generated from New York taxi data and taxi zone shapefile. Data is available at the following URL: https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page
df = spark.read.format("csv").option("header", True).option(
"delimiter", ","
).schema(
"VendorID string, tpep_pickup_datetime timestamp, tpep_dropoff_datetime timestamp, passenger_count long, trip_distance double, pickup_longitude double, pickup_latitude double, dropoff_longitude double, dropoff_latitude double, fare_amount double, tip_amount double, total_amount double, buildingid_pickup long, buildingid_dropoff long, buildingtext_pickup string, buildingtext_dropoff string"
).load(data_path).cache()
df.show(20, False)
df.createOrReplaceTempView("nyc_taxi")
register_funcs(spark)
res = spark.sql(
"select ST_Point(pickup_longitude, pickup_latitude) as point from nyc_taxi where ST_Within(ST_Point(pickup_longitude, pickup_latitude), 'POLYGON ((-73.998427 40.730309, -73.954348 40.730309, -73.954348 40.780816 ,-73.998427 40.780816, -73.998427 40.730309))')"
)
vega = vega_pointmap(1024, 896,
[-73.998427, 40.730309, -73.954348, 40.780816], 3,
"#2DEF4A", 0.5, "EPSG:4326")
res = pointmap(res, vega)
save_png(res, '/tmp/pointmap.png')
spark.sql("show tables").show()
spark.catalog.dropGlobalTempView("nyc_taxi")
def test_choropleth_map():
wkt_data = []
count_data = []
wkt_data.append("POLYGON (("
"-73.98128 40.754771, "
"-73.980185 40.754771, "
"-73.980185 40.755587, "
"-73.98128 40.755587, "
"-73.98128 40.754771))")
count_data.append(5.0)
arr_wkt = pandas.Series(wkt_data)
arr_count = pandas.Series(count_data)
vega_choropleth_map = VegaChoroplethMap(
1900, 1410, [-73.984092, 40.753893, -73.977588, 40.756342],
"blue_to_red", [2.5, 5], 1.0)
vega_json = vega_choropleth_map.build()
choropleth_map = arctern.choropleth_map(arr_wkt, arr_count,
vega_json.encode('utf-8'))
save_png(choropleth_map, "/tmp/test_choropleth_map.png")
def test_weighted_point_map():
x_data = []
y_data = []
c_data = []
s_data = []
x_data.append(-73.96524)
x_data.append(-73.96118)
x_data.append(-73.97324)
x_data.append(-73.98456)
y_data.append(40.73747)
y_data.append(40.74507)
y_data.append(40.75890)
y_data.append(40.77654)
c_data.append(1)
c_data.append(2)
c_data.append(3)
c_data.append(4)
s_data.append(4)
s_data.append(6)
s_data.append(8)
s_data.append(10)
arr_x = pandas.Series(x_data)
arr_y = pandas.Series(y_data)
points = arctern.ST_Point(arr_x, arr_y)
arr_c = pandas.Series(c_data)
arr_s = pandas.Series(s_data)
vega1 = vega_weighted_pointmap(1024, 896, bounding_box=[-73.998427, 40.730309, -73.954348, 40.780816], color_gradient=["#0000FF"], opacity=1.0, coordinate_system="EPSG:4326")
res1 = arctern.weighted_point_map_layer(vega1, points)
save_png(res1, "/tmp/test_weighted_0_0.png")
vega2 = vega_weighted_pointmap(1024, 896, bounding_box=[-73.998427, 40.730309, -73.954348, 40.780816], color_gradient=["#0000FF", "#FF0000"], color_bound=[1, 5], opacity=1.0, coordinate_system="EPSG:4326")
res2 = arctern.weighted_point_map_layer(vega2, points, color_weights=arr_c)
save_png(res2, "/tmp/test_weighted_1_0.png")
vega3 = vega_weighted_pointmap(1024, 896, bounding_box=[-73.998427, 40.730309, -73.954348, 40.780816], color_gradient=["#0000FF"], size_bound=[1, 10], opacity=1.0, coordinate_system="EPSG:4326")
res3 = arctern.weighted_point_map_layer(vega3, points, size_weights=arr_s)
save_png(res3, "/tmp/test_weighted_0_1.png")
vega4 = vega_weighted_pointmap(1024, 896, bounding_box=[-73.998427, 40.730309, -73.954348, 40.780816], color_gradient=["#0000FF", "#FF0000"], color_bound=[1, 5], size_bound=[1, 10], opacity=1.0, coordinate_system="EPSG:4326")
res4 = arctern.weighted_point_map_layer(vega4, points, color_weights=arr_c, size_weights=arr_s)
save_png(res4, "/tmp/test_weighted_1_1.png")
def test_fishnet_map():
x_data = []
y_data = []
c_data = []
x_data.append(-73.96524)
x_data.append(-73.96118)
x_data.append(-73.97324)
x_data.append(-73.98456)
y_data.append(40.73747)
y_data.append(40.74507)
y_data.append(40.75890)
y_data.append(40.77654)
c_data.append(10)
c_data.append(20)
c_data.append(30)
c_data.append(40)
arr_x = pandas.Series(x_data)
arr_y = pandas.Series(y_data)
arr_c = pandas.Series(c_data)
points = arctern.ST_Point(arr_x, arr_y)
vega = vega_fishnetmap(
1024,
896,
bounding_box=[-73.998427, 40.730309, -73.954348, 40.780816],
color_gradient=["#0000FF", "#FF0000"],
cell_size=4,
cell_spacing=1,
opacity=1.0,
coordinate_system='EPSG:4326')
heat_map1 = arctern.fishnet_map_layer(vega, points, arr_c)
save_png(heat_map1, "/tmp/test_fishnetmap.png")
