From 2f2e961ba364e87537c0e68854b4246c089a3022 Mon Sep 17 00:00:00 2001
From: s495728 <serkan@st.amu.edu.pl>
Date: Thu, 2 May 2024 23:29:00 +0200
Subject: [PATCH] Add dataManager

---
 .gitignore     |  2 ++
 DataManager.py | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 DataManager.py

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..6f951ce
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+data
+archive.zip
\ No newline at end of file
diff --git a/DataManager.py b/DataManager.py
new file mode 100644
index 0000000..d837ec8
--- /dev/null
+++ b/DataManager.py
@@ -0,0 +1,55 @@
+import glob
+import shutil
+import cv2
+from zipfile import ZipFile
+import os
+import wget
+
+mainPath="data/"
+pathToTrainAndValidDate = mainPath + "%s/**/*.*"
+pathToTestDataset = mainPath + "/test"
+originalDatasetName = "original dataset"
+
+class DataManager:
+
+    def downloadData(self):
+        if not os.path.isfile("archive.zip"):
+            wget.download("https://storage.googleapis.com/kaggle-data-sets/78313/182633/bundle/archive.zip?X-Goog-Algorithm=GOOG4-RSA-SHA256&X-Goog-Credential=gcp-kaggle-com%40kaggle-161607.iam.gserviceaccount.com%2F20240502%2Fauto%2Fstorage%2Fgoog4_request&X-Goog-Date=20240502T181500Z&X-Goog-Expires=259200&X-Goog-SignedHeaders=host&X-Goog-Signature=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")
+
+    def unzipData(self, fileName, pathToExtract):
+        if not os.path.exists(mainPath):
+            os.makedirs("data")    
+        ZipFile(fileName).extractall(mainPath + pathToExtract)
+        shutil.move("data/original dataset/test/test", "data", copy_function = shutil.copytree)
+        shutil.move("data/original dataset/New Plant Diseases Dataset(Augmented)/New Plant Diseases Dataset(Augmented)/train", "data/original dataset/train", copy_function = shutil.copytree)
+        shutil.move("data/original dataset/New Plant Diseases Dataset(Augmented)/New Plant Diseases Dataset(Augmented)/valid", "data/original dataset/valid", copy_function = shutil.copytree)
+        shutil.rmtree("data/original dataset/New Plant Diseases Dataset(Augmented)")
+        shutil.rmtree("data/Detection-of-plant-diseases/data/original dataset/test")
+
+    def writeImageToGivenPath(self, image, path):
+        os.makedirs(path.rsplit('/', 1)[0], exist_ok=True)
+        cv2.imwrite(path, image)
+
+    def resizeDataset(self, soruceDatasetName, width, height):
+        if not os.path.exists(mainPath + "resized dataset"):
+            for file in glob.glob(pathToTrainAndValidDate % soruceDatasetName, recursive=True):
+                pathToFile = file.replace("\\","/")
+                image = cv2.imread(pathToFile)
+                image = cv2.resize(image, (width, height))
+                newPath = pathToFile.replace(soruceDatasetName,"resized dataset")
+                self.writeImageToGivenPath(image,newPath)
+
+    def sobelx(self, soruceDatasetName):
+        if not os.path.exists(mainPath + "sobel dataset"):
+            for file in glob.glob(pathToTrainAndValidDate % soruceDatasetName, recursive=True):
+                pathToFile = file.replace("\\","/")
+                image = cv2.imread(pathToFile)
+                sobel = cv2.Sobel(image,cv2.CV_64F,1,0,ksize=5) 
+                newPath = pathToFile.replace(soruceDatasetName,"sobel dataset")
+                self.writeImageToGivenPath(sobel,newPath)
+
+dataManager = DataManager()
+dataManager.downloadData()
+dataManager.unzipData("archive.zip","original dataset")
+dataManager.resizeDataset("original dataset", 64, 64)
+dataManager.sobelx("resized dataset")
\ No newline at end of file