Files
zeavis-edu/Machine_Learning/__pycache__/preprocessing.cpython-312.pyc
T

138 lines
24 KiB
Plaintext
Raw Normal View History

Ë
++j†Gã óVddlZddlZddlZddlZddlZddlZddlmZddlm Z m
Z
ejejd¬«eje«Zgd¢ZdZdZd ZdZd
d
d d d d d d d
œZgd¢Zd\ZZdZdZdZdZdZdZdZdZ dZ!dZ"dZ#dZ$dZ%dZ&dZ'dZ(d „Z)ed!k(rwejUd"«ed#e«ed$e«ed%e«e «e"«e$«e%«e&«e'«e(«e)«ejUd&«ejVjYe«rædZ-e.ej^e««DZ0ejVjcee0«Z2ejVjge2«sŒ;e4ej^e2«Dcgc]:}ejVjkejVjce2|««sŒ9|Œ<c}«Z6e-e6z
Z-ejUd'e0d(e6d)«ŒµejUd*e-d)«yyycc}w)+éN)ÚPath)ÚImageÚUnidentifiedImageErrorz'%(asctime)s [%(levelname)s] %(message)s)ÚlevelÚformat)ú
dataset_1.zipú
dataset_2.zipú
dataset_3.zipÚdatasetzndisan/corn-leaf-diseasez1smaranjitghose/corn-or-maize-leaf-disease-datasetú
Hawar Daunú Bercak Daunú
Karat Daun)u 大斑病u å°æ–‘ç—…u è¤æ–‘ç—…uå¼¯å­¢éœ‰å¶æ–‘ç—…u 圆斑病u ç°æ–‘ç—…u å—æ–¹é”ˆç—…u 普通锈病)z CBS28.jpgzCorn_Common_Rust (1275).jpgzCorn_Common_Rust (1289).jpgzCorn_Common_Rust (1295).jpgzCorn_Gray_Spot (1).jpg)é rg@icóh ddl}tjdtd«|j t«}tjd|«|S#t
$rtj
d«Yyt$r7}tj
d|«tj
d«Yd}~yd}~wwxYw) z:Download dataset_1 (ndisan/corn-leaf-disease) from Kaggle.rNz% Downloading dataset_1 from Kaggle: ú...z [OK] dataset_1 downloaded to úE [SKIP] kagglehub not installed. Install with: pip install kagglehubz$ [FAIL] dataset_1 download failed: zX Please download manually from https://www.kaggle.com/datasets/ndisan/corn-leaf-disease)Ú kagglehubÚlogÚinfoÚ
KAGGLE_DS1Údataset_downloadÚ ImportErrorÚwarningÚ Exception©rÚpathÚes ú9/home/asephs/ZeaVis-Edu/Machine_Learning/preprocessing.pyÚdownload_dataset_1r6s•ð ÛÜ Ð¸ ÀCÐ×)¬*ÓÜ Ð2°4°&Ј øÜ òÜ ÐÜ òÜ Ð:¸1¸#Ð Ðûðúó‚AAÁB1Á2B1Á:-B,Â,B1cóh ddl}tjdtd«|j t«}tjd|«|S#t
$rtj
d«Yyt$r7}tj
d|«tj
d«Yd}~yd}~wwxYw) zSDownload dataset_2 (smaranjitghose/corn-or-maize-leaf-disease-dataset) from Kaggle.rNz% Downloading dataset_2 from Kaggle: rz [OK] dataset_2 downloaded to rz$ [FAIL] dataset_2 download failed: zq Please download manually from https://www.kaggle.com/datasets/smaranjitghose/corn-or-maize-leaf-disease-dataset)rrrÚ
KAGGLE_DS2rrrrrs rÚdownload_dataset_2r#Gsð ÛÜ Ð¸ ÀCÐ×)¬*ÓÜ Ð2°4°&Ј øÜ òÜ ÐÜ òÜ Ð:¸1¸#Ð ðHô IÜûðúr cód} ddl}|j|«}tjd|«|S#t$rYnwxYwtj d«tj d«tj d«y)z¹Download dataset_3 (SciDB China Agricultural Dataset).
Attempt: Kaggle alternative host, then Google Drive, then warn.
If all fail, user must download manually from SciDB.
z0disease-identification/corn-leaf-disease-chineserNz2 [OK] dataset_3 downloaded from Kaggle mirror to z9 [SKIP] dataset_3 could not be downloaded automatically.z Please download manually from:zM https://www.scidb.cn/en/detail?dataSetId=19536c73f6d74946a212719a94f53ab3)rrrrrr)Ú
KAGGLE_DS3rrs rÚdownload_dataset_3r&XsyðD€Jð
ÛØ×)¨*ÓÜ ÐEÀdÀVЈ øÜ ò
Ù ð
úô‡K‡K‡K s „.3³ ?¾?có0|tjj|«sy tj|j dd«d|«t jd|d|«y#t$r%}t jd |d
|«Yd}~yd}~wwxYw) zLCopy kagglehub download into a local ZIP so extraction step works unchanged.NFz.zipÚÚzipz [OK] Packed ú -> Tz [FAIL] Could not pack ú: )
ÚosrÚexistsÚshutilÚ make_archiveÚreplacerrrr)Úsrc_pathÚtarget_zip_namers rÚcopy_kaggle_downloadr3nsˆàМrŸw™wŸ~™~¨hÔðÜ×јO×3°F¸BÓÈÔ > ¨4°Ð/@ÐøÜ òÜ Ð.¨x¨j¸¸1¸#Ðûðús¤AA'Á' BÁ0BÂBcóÒtjj|«rtj d|d«ytj d|d«|«}|yt ||«S)z3Attempt auto-download if ZIP doesn't exist locally.z
[CACHE] z# already exists, skipping download.Tz--- Downloading z ---F)r,rr-rrr3)Úzip_nameÚ download_fnrs rÚdownload_datasetr7|s]ä ‡ww‡~~Ü :˜h˜ZÐ'JÐ܇H ˜z¨Ð
 ‹=€DØ €|Øä   hÓ có>tjd«tD}tjj |«r‡tjj
|«d}tj|d¬« tj|d«5}|j|«ddd«tjd|d|d«Œ©tjd |d «ŒÃy#1swYŒBxYw#tj$rtjd |d
«YŒÿwxYw)
Nz%--- TAHAP 1: Mengekstrak File ZIP ---rÚexist_okÚ [OK] r*ú/z
[ERROR] z rusak.z [SKIP] File z0 tidak ditemukan. Beberapa kelas mungkin kosong.)rrÚ
DAFTAR_ZIPr,rr-ÚsplitextÚmakedirsÚzipfileÚZipFileÚ
extractallÚ
BadZipFileÚerrorr)Úzip_fileÚ folder_nameÚzip_refs rÚekstrak_semua_ziprJŒÜ‡H
ò eˆÜ
7‰7>‰>˜ Ÿ'™'×*¨8Ó4°QÑ7ˆ K‰K˜ ¨dÕ 
—_‘_ X¨sÓ4°wØ×& ˜7 8 *¨D°°
¸
K‰K˜¨
Ð2bÐ  e÷
4ûô×
 ˜J x Ð
:ús*Á8C-ÂC! $C-Ã!C* Ã&C-Ã-,DÄDcótjj|«sytj|«D]H}|j «Št ˆfd|D««sŒ(tjj
||«cSy)Nc3ó&K|]}|vŒ
y­w))Ú.0Úf_lowers €rú <genexpr>z"cari_folder_ds2.<locals>.<genexpr>¤søèø€ÒˆqGŒ|Ñ.ùsƒ)r,rr-ÚlistdirÚlowerÚanyÚjoin)Ú base_pathÚkeywordsÚfrPs @rÚcari_folder_ds2rYŸsaø€Ü
7‰7>‰>˜ Ü
Z‰Z˜ Ó
.ˆØ—''“)ˆÜ Ó.  —77—<<  ¨1Ó  r8c ótjd«tjtd¬«gd¢}|D]™}tj
j
d|«}tj
j
t|«}tj
j|«sŒgtj||d¬«tjd|d|«Œ›tj
jd «r{d }tj
j
|d
«}tj
j|«r|}d d d
œ}|j«D]\}}t||«} tj
j
t|«}
tj|
d¬«| r¶tj
j| «r—d} tj| «D]]} tj
j
| | «}
tj
j|
«sŒCtj|
|
«| dz
} Œ_tjd| d| d|
«Œtjd|d«Œ!ytjd«y)Nz,--- TAHAP 2: Menggabungkan Dataset 1 & 2 ---Tr:)r
ú
Daun Sehatr Ú dataset_1)Ú
dirs_exist_okz [OK] Menyalin folder z ke Ú dataset_2Údatarr[))Ú common_rustÚ commont_rust)Úhealthyréz [OK] Menyalin z
gambar dari z [SKIP] Folder untuk 'z' tidak ditemukan di dataset_2z? [SKIP] Folder dataset_2/ tidak ada, dataset_2 tidak diproses.)rrr,rAÚ
TARGET_DIRrrUr-r.ÚcopytreeÚitemsrYrRÚisfileÚcopyr)Úfolder_dari_ds1ÚfolderÚsrcÚdstÚbase_ds2Údata_subÚ mapping_ds2rWÚtarget_subfolderÚ
src_folderÚ
dst_folderÚ
file_countÚ file_nameÚfull_file_names rÚgabungkan_dataset_1_dan_2rv©Ü‡H
‡KK”
 TÕB€OØÜg‰gl‰l˜;¨ÓÜg‰gl‰lœ: vÓÜ
7‰7>‰>˜ Ü O‰O˜C °DÕ H‰HÐ.¨s¨e°4¸°uÐ 
‡ww‡~~ˆä—77—<< ¨&Ó1ˆÜ
7‰7>‰>˜ ˆ.:Ø
ˆ ð
+6×*;Ñ*;Ó*=ó hÑ &ˆ°8Ó<ˆŸŸ¤jÐ2BÓCˆJÜ K‰K˜
¨TÕ œbŸg™gŸn™n¨ZÔ
Ü!#§¡¨JÓ!7ò(IÜ%'§W¡W§\¡\°*¸iÓ%H—w‘w—~‘~ nÕŸ  N°JÔ" a™
ð 
Ð+¨J¨<°}ÀZÀLÐPTÐU_ÐT`Ð Ð5Ð6FÐ5GÐGeÐ hô ÐVr8có
|j«}tjj||«}tjj |«r|S|j «}tj |«D}|j «|k(sTtjj|«dj «tjj|«dk(sŒjtjj||«cSy)Nr)Ústripr,rrUr-rSrRr@)Ú
folder_sumberÚnama_file_targetÚ
path_langsungÚ target_lowerrXs rÚcari_gambar_fleksibelr}ÚØÜ—GG—L‘L Ð0@ÓA€MÜ ‡ww‡~~Ðà#×+€LÜ
Z‰Z˜
Ó
2ˆØ
G‰G‹I˜Ò —77×# & )×1´R·W±W×5EÑ5EÀlÓ5SÐTUÑ5VÓ—77—<< 
¨qÓ  r8có´tjd«tjj dd«}tjj dd«}tjj |«stj
d|d«yt|dd¬ «5}tj|«}ddd«d
}D}|jd «}|jd d
«j«}|sŒ7|tvsŒ@t|}tjj t|«} tj| d¬«t||«}
|
sŒ“tjj!|
«} t#j$|
tjj | | ««|dz
}Œìtjd|dtd«y#1swYŒxYw)Nz9--- TAHAP 3: Menggabungkan Dataset 3 berdasarkan JSON ---Ú dataset_3r_z desc.jsonz [SKIP] z% tidak ditemukan. Dataset 3 dilewati.r<zutf-8)ÚencodingrÚ
image_nameÚlabelr(Tr:rcz [OK] Berhasil merutekan z gambar dari dataset_3 ke 'ú')rrr,rrUr-rÚopenÚjsonÚloadÚgetrxÚPEMETAAN_KATEGORIrdrAr}Úbasenamer.rh) Ú folder_dataÚ file_jsonrXÚ
data_labelÚberhasilÚitemrrÚnama_folder_targetÚ
folder_tujuanÚ path_sumberÚ nama_aslis rÚgabungkan_dataset_3r“èso܇H
—''—,,˜{¨FÓ3€KÜ ˜[¨+Ó6€Iä
7‰7>‰>˜  i  ˜{Ð*OÐä
ˆi˜ wÔ /ð"°1Ü—YY˜q“\ˆ
÷€HØò
ˆØ—XX˜+ˆ
ؘ "Ó-ˆâ ˜%Ô#4Ò4Ü!2°5Ñ!9Ð ÜŸG™GŸL™L¬Ð5GÓHˆMÜ K‰K˜
°Õ  ¸ZÓHˆKÚÜŸG™G×,¨[Ó9 Ü ˜K¬¯©¯©°mÀYÓ)OÔ˜A‘
ð
ô‡H)¨(¨Ð3NÌzÈlÐZ[Ð
]÷'"ús ÂG
Ç
Gc
óÖtjd«tt«}d}tj
j
t«rt jt«D]v\}}}|D]k}||vsŒtj
j||«} t j|«tjd|«|j|«|dz
}ŒmŒxtjd|«|rBtjd t|«d
«|D]}tjd |«Œyy#t$r&}tjd|d|d«Yd}~Œ÷d}~wwxYw) Nz*--- TAHAP 4: Menghapus File Bermasalah ---rz