def draw_icon_viz(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 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))'))")
icon_path = "/tmp/taxi.png"
vega = vega_icon(1024, 896, [-73.998427, 40.730309, -73.954348, 40.780816], icon_path, "EPSG:4326")
res = icon_viz(vega, res)
save_png(res, '/tmp/icon_viz.png')
spark.sql("show tables").show()
spark.catalog.dropGlobalTempView("nyc_taxi")
print("--- %s seconds ---" % (time.time() - start_time))
def db_query():
"""
/db/query handler
"""
log.INSTANCE.info('POST /db/query: {}'.format(request.json))
if not utils.check_json(request.json, 'id') \
or not utils.check_json(request.json, 'query') \
or not utils.check_json(request.json['query'], 'type') \
or not utils.check_json(request.json['query'], 'sql'):
return jsonify(status='error', code=-1, message='query format error')
query_sql = request.json['query']['sql']
query_type = request.json['query']['type']
content = {}
content['sql'] = query_sql
content['err'] = False
db_instance = db.CENTER.get(str(request.json['id']), None)
if db_instance is None:
return jsonify(status="error",
code=-1,
message='there is no database whose id equal to ' +
str(request.json['id']))
if query_type == 'sql':
res = db_instance.run_for_json(query_sql)
data = []
for row in res:
obj = json.loads(row)
data.append(obj)
content['result'] = data
else:
if not utils.check_json(request.json['query'], 'params'):
return jsonify(status='error',
code=-1,
message='query format error')
query_params = request.json['query']['params']
res = db_instance.run(query_sql)
if query_type == 'point':
vega = vega_pointmap(int(query_params['width']),
int(query_params['height']),
query_params['point']['bounding_box'],
int(query_params['point']['point_size']),
query_params['point']['point_color'],
float(query_params['point']['opacity']),
query_params['point']['coordinate_system'])
data = pointmap(vega, res)
content['result'] = data
elif query_type == 'heat':
vega = vega_heatmap(int(query_params['width']),
int(query_params['height']),
query_params['heat']['bounding_box'],
float(query_params['heat']['map_zoom_level']),
query_params['heat']['coordinate_system'],
query_params['heat']['aggregation_type'])
data = heatmap(vega, res)
content['result'] = data
elif query_type == 'choropleth':
vega = vega_choroplethmap(
int(query_params['width']), int(query_params['height']),
query_params['choropleth']['bounding_box'],
query_params['choropleth']['color_gradient'],
query_params['choropleth']['color_bound'],
float(query_params['choropleth']['opacity']),
query_params['choropleth']['coordinate_system'],
query_params['choropleth']['aggregation_type'])
data = choroplethmap(vega, res)
content['result'] = data
elif query_type == 'weighted':
vega = vega_weighted_pointmap(
int(query_params['width']), int(query_params['height']),
query_params['weighted']['bounding_box'],
query_params['weighted']['color_gradient'],
query_params['weighted']['color_bound'],
query_params['weighted']['size_bound'],
float(query_params['weighted']['opacity']),
query_params['weighted']['coordinate_system'])
data = weighted_pointmap(vega, res)
content['result'] = data
elif query_type == 'icon':
vega = vega_icon(int(query_params['width']),
int(query_params['height']),
query_params['icon']['bounding_box'],
query_params['icon']['icon_path'],
query_params['icon']['coordinate_system'])
data = icon_viz(vega, res)
content['result'] = data
else:
return jsonify(status="error",
code=-1,
message='{} not support'.format(query_type))
return jsonify(status="success", code=200, data=content)
opacity=1.0,
coordinate_system="EPSG:4326")
res = choroplethmap(vega, pickup_df)
save_png(res, "/tmp/arctern_choroplethmap.png")
# 在指定地理区域（经度范围：-73.991504 至 -73.945155；纬度范围：40.770759 至 40.783434）中随机选取 25 个坐标点。
pickup_sql = f"select st_point(pickup_longitude, pickup_latitude) from nyc_taxi where (pickup_longitude between {pos1[0]} and {pos2[0]}) and (pickup_latitude between {pos1[1]} and {pos2[1]}) limit 25"
pickup_df = spark.sql(pickup_sql)
# 根据查询结果绘制图标图图层。
# 注意： 请将 /path/to/icon.png 改为 png 文件所在的绝对路径
vega = vega_icon(1024,
384,
bounding_box=[pos1[0], pos1[1], pos2[0], pos2[1]],
icon_path='/path/to/icon.png',
coordinate_system="EPSG:4326")
res = icon_viz(vega, pickup_df)
save_png(res, "/tmp/arctern_iconviz.png")
# 在指定地理区域（经度范围：-73.991504 至 -73.945155；纬度范围：40.770759 至 40.783434）中随机选取 200 个坐标点，并将 fare_amount 作为颜色权重。
pickup_sql = f"select st_point(pickup_longitude, pickup_latitude) as point, fare_amount as weight from nyc_taxi where (pickup_longitude between {pos1[0]} and {pos2[0]}) and (pickup_latitude between {pos1[1]} and {pos2[1]}) limit {limit_num}"
pickup_df = spark.sql(pickup_sql)
# 根据查询结果绘制渔网图图层。
vega = vega_fishnetmap(1024,
384,
bounding_box=[pos1[0], pos1[1], pos2[0], pos2[1]],
cell_size=8,
cell_spacing=1,
opacity=1.0,
coordinate_system="EPSG:4326")
res = fishnetmap(vega, pickup_df)
save_png(res, "/tmp/arctern_fishnetmap.png")