FilesExpand file tree

develop

/

ExploderTests.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

65 lines (52 loc) · 2.3 KB

develop

/

ExploderTests.py

Copy path

Top

File metadata and controls

• Code
• Blame

65 lines (52 loc) · 2.3 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

61

62

63

64

65

#

# This software is licensed under the Apache 2 license, quoted below.

#

# Copyright 2019 Astraea, Inc.

#

# Licensed under the Apache License, Version 2.0 (the "License"); you may not

# use this file except in compliance with the License. You may obtain a copy of

# the License at

#

# [http://www.apache.org/licenses/LICENSE-2.0]

#

# Unless required by applicable law or agreed to in writing, software

# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT

# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the

# License for the specific language governing permissions and limitations under

# the License.

#

# SPDX-License-Identifier: Apache-2.0

#

from pyrasterframes.rasterfunctions import *

from pyrasterframes.rf_types import *

from pyspark.ml import Pipeline, PipelineModel

from pyspark.ml.feature import VectorAssembler

from pyspark.sql.functions import *

from pyrasterframes import TileExploder

def test_tile_exploder_pipeline_for_prt(spark, img_uri):

# NB the tile is a Projected Raster Tile

df = spark.read.raster(img_uri)

t_col = "proj_raster"

assert t_col in df.columns, "proj_raster column not found"

assembler = VectorAssembler().setInputCols([t_col])

pipe = Pipeline().setStages([TileExploder(), assembler])

pipe_model = pipe.fit(df)

tranformed_df = pipe_model.transform(df)

assert tranformed_df.count() > df.count(), "DF count has not the expected size"

def test_tile_exploder_pipeline_for_tile(spark, img_uri):

t_col = "tile"

df = spark.read.raster(img_uri).withColumn(t_col, rf_tile("proj_raster")).drop("proj_raster")

assembler = VectorAssembler().setInputCols([t_col])

pipe = Pipeline().setStages([TileExploder(), assembler])

pipe_model = pipe.fit(df)

tranformed_df = pipe_model.transform(df)

assert tranformed_df.count() > df.count(), "DF count has not the expected size"

def test_tile_exploder_read_write(spark, img_uri):

path = "test_tile_exploder_read_write.pipe"

df = spark.read.raster(img_uri)

assembler = VectorAssembler().setInputCols(["proj_raster"])

pipe = Pipeline().setStages([TileExploder(), assembler])

pipe.fit(df).write().overwrite().save(path)

read_pipe = PipelineModel.load(path)

assert len(read_pipe.stages) == 2

assert isinstance(read_pipe.stages[0], TileExploder)