2. Prepare input data of Yoshii River¶

Written by Men Vuthy, 2022

Import modules

[1]:

import os
import numpy as np
import pandas as pd

import matplotlib.pyplot as plt

import rasterio
import geopandas as gpd

Label

[2]:

yoshii_class_img = rasterio.open('data/yoshii_river/out_img/class/yoshii_class.tiff')

[3]:

yoshii_class = yoshii_class_img.read(1).reshape(-1)

[4]:

yoshii_label = pd.DataFrame({'label':yoshii_class})

Dataframe of Season 1

[5]:

season1_rgbn = rasterio.open('data/yoshii_river/out_img/rgbn/yoshii_20190409_rgbn.tiff')
season1_ndvi = rasterio.open('data/yoshii_river/out_img/ndvi/yoshii_20190409_ndvi.tiff')
season1_ndwi = rasterio.open('data/yoshii_river/out_img/ndwi/yoshii_20190409_ndwi.tiff')
season1_bsi = rasterio.open('data/yoshii_river/out_img/bsi/yoshii_20190409_bsi.tiff')

[6]:

blue_1 = season1_rgbn.read(1).reshape(-1)
green_1 = season1_rgbn.read(2).reshape(-1)
red_1 = season1_rgbn.read(3).reshape(-1)
nir_1 = season1_rgbn.read(4).reshape(-1)

ndvi_1 = season1_ndvi.read(1).reshape(-1)
ndwi_1 = season1_ndwi.read(1).reshape(-1)
bsi_1 = season1_bsi.read(1).reshape(-1)

[7]:

Season_1 = pd.DataFrame({'B1':blue_1, 'G1':green_1, 'R1':red_1, 'NIR1':nir_1, 'NDVI1':ndvi_1, 'NDWI1':ndwi_1, 'BSI1':bsi_1})

[8]:

Season_1

[8]:

	B1	G1	R1	NIR1	NDVI1	NDWI1	BSI1
0	0	0	0	0	NaN	NaN	NaN
1	0	0	0	0	NaN	NaN	NaN
2	0	0	0	0	NaN	NaN	NaN
3	0	0	0	0	NaN	NaN	NaN
4	0	0	0	0	NaN	NaN	NaN
...	...	...	...	...	...	...	...
38283940	0	0	0	0	NaN	NaN	NaN
38283941	0	0	0	0	NaN	NaN	NaN
38283942	0	0	0	0	NaN	NaN	NaN
38283943	0	0	0	0	NaN	NaN	NaN
38283944	0	0	0	0	NaN	NaN	NaN

38283945 rows × 7 columns

Dataframe of Season 2

[9]:

season2_rgbn = rasterio.open('data/yoshii_river/out_img/rgbn/yoshii_20190805_rgbn.tiff')
season2_ndvi = rasterio.open('data/yoshii_river/out_img/ndvi/yoshii_20190805_ndvi.tiff')
season2_ndwi = rasterio.open('data/yoshii_river/out_img/ndwi/yoshii_20190805_ndwi.tiff')
season2_bsi = rasterio.open('data/yoshii_river/out_img/bsi/yoshii_20190805_bsi.tiff')

[10]:

blue_2 = season2_rgbn.read(1).reshape(-1)
green_2 = season2_rgbn.read(2).reshape(-1)
red_2 = season2_rgbn.read(3).reshape(-1)
nir_2 = season2_rgbn.read(4).reshape(-1)

ndvi_2 = season2_ndvi.read(1).reshape(-1)
ndwi_2 = season2_ndwi.read(1).reshape(-1)
bsi_2 = season2_bsi.read(1).reshape(-1)

[11]:

Season_2 = pd.DataFrame({'B2':blue_2, 'G2':green_2, 'R2':red_2, 'NIR2':nir_2, 'NDVI2':ndvi_2, 'NDWI2':ndwi_2, 'BSI2':bsi_2})

[12]:

Season_2

[12]:

	B2	G2	R2	NIR2	NDVI2	NDWI2	BSI2
0	0	0	0	0	NaN	NaN	NaN
1	0	0	0	0	NaN	NaN	NaN
2	0	0	0	0	NaN	NaN	NaN
3	0	0	0	0	NaN	NaN	NaN
4	0	0	0	0	NaN	NaN	NaN
...	...	...	...	...	...	...	...
38283940	0	0	0	0	NaN	NaN	NaN
38283941	0	0	0	0	NaN	NaN	NaN
38283942	0	0	0	0	NaN	NaN	NaN
38283943	0	0	0	0	NaN	NaN	NaN
38283944	0	0	0	0	NaN	NaN	NaN

38283945 rows × 7 columns

Dataframe of Season 3

[13]:

season3_rgbn = rasterio.open('data/yoshii_river/out_img/rgbn/yoshii_20191007_rgbn.tiff')
season3_ndvi = rasterio.open('data/yoshii_river/out_img/ndvi/yoshii_20191007_ndvi.tiff')
season3_ndwi = rasterio.open('data/yoshii_river/out_img/ndwi/yoshii_20191007_ndwi.tiff')
season3_bsi = rasterio.open('data/yoshii_river/out_img/bsi/yoshii_20191007_bsi.tiff')

[14]:

blue_3 = season3_rgbn.read(1).reshape(-1)
green_3 = season3_rgbn.read(2).reshape(-1)
red_3 = season3_rgbn.read(3).reshape(-1)
nir_3 = season3_rgbn.read(4).reshape(-1)

ndvi_3 = season3_ndvi.read(1).reshape(-1)
ndwi_3 = season3_ndwi.read(1).reshape(-1)
bsi_3 = season3_bsi.read(1).reshape(-1)

[15]:

Season_3 = pd.DataFrame({'B3':blue_3, 'G3':green_3, 'R3':red_3, 'NIR3':nir_3, 'NDVI3':ndvi_3, 'NDWI3':ndwi_3, 'BSI3':bsi_3})

[16]:

Season_3

[16]:

	B3	G3	R3	NIR3	NDVI3	NDWI3	BSI3
0	0	0	0	0	NaN	NaN	NaN
1	0	0	0	0	NaN	NaN	NaN
2	0	0	0	0	NaN	NaN	NaN
3	0	0	0	0	NaN	NaN	NaN
4	0	0	0	0	NaN	NaN	NaN
...	...	...	...	...	...	...	...
38283940	0	0	0	0	NaN	NaN	NaN
38283941	0	0	0	0	NaN	NaN	NaN
38283942	0	0	0	0	NaN	NaN	NaN
38283943	0	0	0	0	NaN	NaN	NaN
38283944	0	0	0	0	NaN	NaN	NaN

38283945 rows × 7 columns

Dataframe of Season 4

[17]:

season4_rgbn = rasterio.open('data/yoshii_river/out_img/rgbn/yoshii_20200104_rgbn.tiff')
season4_ndvi = rasterio.open('data/yoshii_river/out_img/ndvi/yoshii_20200104_ndvi.tiff')
season4_ndwi = rasterio.open('data/yoshii_river/out_img/ndwi/yoshii_20200104_ndwi.tiff')
season4_bsi = rasterio.open('data/yoshii_river/out_img/bsi/yoshii_20200104_bsi.tiff')

[18]:

blue_4 = season4_rgbn.read(1).reshape(-1)
green_4 = season4_rgbn.read(2).reshape(-1)
red_4 = season4_rgbn.read(3).reshape(-1)
nir_4 = season4_rgbn.read(4).reshape(-1)

ndvi_4 = season4_ndvi.read(1).reshape(-1)
ndwi_4 = season4_ndwi.read(1).reshape(-1)
bsi_4 = season4_bsi.read(1).reshape(-1)

[19]:

Season_4 = pd.DataFrame({'B4':blue_4, 'G4':green_4, 'R4':red_4, 'NIR4':nir_4, 'NDVI4':ndvi_4, 'NDWI4':ndwi_4, 'BSI4':bsi_4})

[20]:

Season_4

[20]:

	B4	G4	R4	NIR4	NDVI4	NDWI4	BSI4
0	0	0	0	0	NaN	NaN	NaN
1	0	0	0	0	NaN	NaN	NaN
2	0	0	0	0	NaN	NaN	NaN
3	0	0	0	0	NaN	NaN	NaN
4	0	0	0	0	NaN	NaN	NaN
...	...	...	...	...	...	...	...
38283940	0	0	0	0	NaN	NaN	NaN
38283941	0	0	0	0	NaN	NaN	NaN
38283942	0	0	0	0	NaN	NaN	NaN
38283943	0	0	0	0	NaN	NaN	NaN
38283944	0	0	0	0	NaN	NaN	NaN

38283945 rows × 7 columns

Features and Label

[21]:

# concat dataframe of all seasons and label into one dataframe
Yoshii_dataframe = pd.concat([Season_1, Season_2, Season_3, Season_4, yoshii_label], axis=1)

[22]:

# Remove all rows where NDVI1 is NaN
Yoshii_classified = Yoshii_dataframe.dropna(subset=['NDVI1'])

[23]:

Yoshii_classified

[23]:

	B1	G1	R1	NIR1	NDVI1	NDWI1	BSI1	B2	G2	R2	...	NDWI3	BSI3	B4	G4	R4	NIR4	NDVI4	NDWI4	BSI4	label
4371353	558	601	513	889	-0.023003	0.081056	0.279785	324	421	385	...	-0.054566	0.235740	349	489	457	686	0.135323	-0.030485	0.222090	7
4371354	558	601	513	889	-0.023003	0.081056	0.279785	324	421	385	...	-0.054566	0.235740	349	489	457	686	0.135323	-0.030485	0.222090	7
4371355	614	639	533	1012	-0.006031	0.047061	0.282591	334	440	420	...	-0.118004	0.259052	387	540	571	843	0.127158	-0.083739	0.253888	7
4371356	705	715	606	1203	0.011312	0.016838	0.292253	391	507	509	...	-0.222598	0.262350	458	627	705	1027	0.120572	-0.107544	0.273603	1
4371357	816	794	681	1472	0.039086	-0.031651	0.304678	501	614	648	...	-0.257952	0.264777	557	733	838	1254	0.133792	-0.128988	0.285978	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
34076326	896	883	753	2833	0.309235	-0.296701	0.300410	473	619	575	...	-0.482353	0.253913	492	664	795	1464	0.233941	-0.251074	0.292699	1
34076327	919	904	775	2700	0.275665	-0.263721	0.301996	484	628	582	...	-0.464620	0.253741	489	667	818	1428	0.208541	-0.237249	0.296889	1
34076328	949	929	803	2563	0.236333	-0.226434	0.304925	523	659	616	...	-0.424649	0.263849	519	704	875	1397	0.165456	-0.201109	0.301471	1
34076329	964	951	827	2445	0.206467	-0.192717	0.304421	559	695	657	...	-0.351897	0.268711	507	736	859	1422	0.183002	-0.188259	0.271648	1
34076330	1010	989	869	2362	0.167315	-0.156990	0.308427	615	750	733	...	-0.318919	0.269634	573	791	897	1501	0.188206	-0.179563	0.274091	1

1152991 rows × 29 columns

[24]:

# Data dir
data_dir = "data/yoshii_river/out_img/classified"

# Output dataframe
out_df = os.path.join(data_dir, 'yoshii_classified.csv')

# export dataframe to csv
Yoshii_classified.to_csv(out_df, index=False)

[25]:

# Data dir
data_dir = "data/yoshii_river/out_img/classified"

# Output dataframe
out_df = os.path.join(data_dir, 'yoshii_classified_index.csv')

# export dataframe to csv
Yoshii_classified.to_csv(out_df)