Created
June 25, 2019 18:39
-
-
Save waqaskhan409/1b0fd729d7f8ed305f33835145ca680e to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from __future__ import print_function | |
| from googleapiclient.discovery import build | |
| from googleapiclient.http import MediaIoBaseDownload | |
| from httplib2 import Http | |
| from oauth2client import file, client, tools | |
| import http | |
| import io | |
| import pandas | |
| from sklearn.cross_validation import train_test_split | |
| import threading as thr | |
| # If modifying these scopes, delete the file token.json. | |
| SCOPES = 'https://www.googleapis.com/auth/drive' | |
| # def main(fileId,fileName): | |
| # """Shows basic usage of the Drive v3 API. | |
| # Prints the names and ids of the first 10 files the user has access to. | |
| # """ | |
| # store = file.Storage('token.json') | |
| # creds = store.get() | |
| # if not creds or creds.invalid: | |
| # flow = client.flow_from_clientsecrets('credentials.json', SCOPES) | |
| # creds = tools.run_flow(flow, store) | |
| # service = build('drive', 'v3', http=creds.authorize(Http())) | |
| # | |
| # # Call the Drive v3 API | |
| # results = service.files().list( | |
| # pageSize=10, fields="nextPageToken, files(id, name)").execute() | |
| # items = results.get('files', []) | |
| # | |
| # if not items: | |
| # print('No files found.') | |
| # else: | |
| # file_id = fileId | |
| # request = service.files().get_media(fileId=file_id) | |
| # fh = io.BytesIO() | |
| # downloader = MediaIoBaseDownload(fh, request) | |
| # done = False | |
| # while done is False: | |
| # status, done = downloader.next_chunk() | |
| # print ("Download %d%%." % int(status.progress() * 100)) | |
| # with io.open(fileName , 'wb') as f: | |
| # fh.seek(0) | |
| # f.write(fh.read()) | |
| def downloadFile(fileId, fileName): | |
| store = file.Storage('token.json') | |
| creds = store.get() | |
| if not creds or creds.invalid: | |
| flow = client.flow_from_clientsecrets('credentials.json', SCOPES) | |
| creds = tools.run_flow(flow, store) | |
| service = build('drive', 'v3', http=creds.authorize(Http())) | |
| file_id = fileId | |
| request = service.files().get_media(fileId=file_id) | |
| fh = io.BytesIO() | |
| downloader = MediaIoBaseDownload(fh, request) | |
| done = False | |
| while done is False: | |
| status, done = downloader.next_chunk() | |
| print ("Download %d%%." % int(status.progress() * 100)) | |
| with io.open(fileName , 'wb') as f: | |
| fh.seek(0) | |
| f.write(fh.read()) | |
| pass | |
| def definingPath(dataset , pathVar): | |
| path = "E:\\fileMachineLearning\\OrganizeDatasetWateremlon\\" | |
| path = path + pathVar | |
| surface = dataset['Watermelon surface'] | |
| top = dataset['Watermelon top side'] | |
| inner = dataset['Watermelon inner side'] | |
| bot = dataset['Watermelon bottom side'] | |
| print(len(surface)) | |
| # print(surface.values[0]) | |
| for i in range( len(dataset)): | |
| print(i) | |
| leftSideS ,rightSideS = surface.values[i].split("id=") | |
| leftSideI ,rightSideI = inner.values[i].split("id=") | |
| leftSideT ,rightSideT = top.values[i].split("id=") | |
| leftSideB ,rightSideB = bot.values[i].split("id=") | |
| downloadFile(rightSideS , path +"S"+ str(i+1) + ".jpg") | |
| downloadFile(rightSideI , path +"I"+ str(i+1) + ".jpg") | |
| downloadFile(rightSideT , path +"T"+ str(i+1) + ".jpg") | |
| downloadFile(rightSideB , path +"B"+ str(i+1) + ".jpg") | |
| # t1 = thr.Thread(target = downloadFile , args=(rightSideS , path +"S"+ str(i+1) + ".jpg")) | |
| # t2 = thr.Thread(target = downloadFile , args=(rightSideI , path +"I"+ str(i+1) + ".jpg")) | |
| # t3 = thr.Thread(target = downloadFile , args=(rightSideT , path +"T"+ str(i+1) + ".jpg")) | |
| # t4 = thr.Thread(target = downloadFile , args=(rightSideB , path +"B"+ str(i+1) + ".jpg")) | |
| # t1.start() | |
| # t2.start() | |
| # t3.start() | |
| # t4.start() | |
| # downloadFile(rightSideS , path +"S"+ str(i+1) + ".jpg") | |
| # downloadFile(rightSideI , path +"I"+ str(i+1) + ".jpg") | |
| # downloadFile(rightSideT , path +"T"+ str(i+1) + ".jpg") | |
| # downloadFile(rightSideB , path +"B"+ str(i+1) + ".jpg") | |
| def arrangingDataSet(): | |
| dataset = pandas.read_csv('e:sampleWatermelon.csv') | |
| surface = dataset['Watermelon surface'] | |
| top = dataset['Watermelon top side'] | |
| inner = dataset['Watermelon inner side'] | |
| bot = dataset['Watermelon bottom side'] | |
| path = "E:\\fileMachineLearning\\DataSetWatermelon\\" | |
| print(len(surface)) | |
| fileName = dataset.values[0] | |
| for i in range(len(dataset)): | |
| leftSideS ,rightSideS = surface[i].split("id=") | |
| leftSideI ,rightSideI = inner[i].split("id=") | |
| leftSideT ,rightSideT = top[i].split("id=") | |
| leftSideB ,rightSideB = bot[i].split("id=") | |
| pathS = path + "Surface\\" | |
| pathT = path + "Top\\" | |
| pathI = path + "Inner\\" | |
| pathB = path + "Bottom\\" | |
| fileName = dataset.values[i] | |
| newFileName = str(i+1) +","+ str(fileName[5]) +","+ str(fileName[6]) +","+ str(fileName[7]) +","+ str(fileName[8]) +","+ str(fileName[9]) +","+ str(fileName[10]) + "," + str(fileName[11]) + ".jpg" | |
| main(rightSideS , pathS + newFileName) | |
| main(rightSideI , pathI + newFileName) | |
| main(rightSideT , pathT + newFileName) | |
| main(rightSideB , pathB + newFileName) | |
| if __name__ == '__main__' : | |
| dataset = pandas.read_csv('e:updateWatermelon.csv') | |
| # verySweetWaterMelon = dataset[dataset['Watermelon sweetness level'] > 8] | |
| # definingPath(verySweetWaterMelon , 'sweet\\Training\\verySweet\\verySweet') | |
| # t1 = thr.Thread(target = definingPath , args=(sweetWaterMelon , 'sweet\\Training\\verySweet\\verySweet')) | |
| # sweetWaterMelon = dataset[dataset['Watermelon sweetness level'] < 9] | |
| # sweetWaterMelon = sweetWaterMelon[sweetWaterMelon['Watermelon sweetness level'] > 5 ] | |
| # print(len(sweetWaterMelon)) | |
| # definingPath(sweetWaterMelon , 'sweet\\Training\\sweet\\sweet') | |
| # t2 = thr.Thread(target = definingPath , args=(sweetWaterMelon , 'sweet\\Training\\sweet\\sweet')) | |
| # notSweetWaterMelon = dataset[dataset['Watermelon sweetness level'] < 6] | |
| # notSweetWaterMelon = notSweetWaterMelon[notSweetWaterMelon['Watermelon sweetness level'] > 3 ] | |
| # print(len(notSweetWaterMelon)) | |
| # definingPath(notSweetWaterMelon , 'sweet\\Training\\notSweet\\notSweet') | |
| # t3 = thr.Thread(target = definingPath , args=(sweetWaterMelon , 'sweet\\Training\\notSweet\\notSweet')) | |
| # | |
| # badWaterMelon = dataset[dataset['Watermelon sweetness level'] < 4] | |
| # print(len(badWaterMelon)) | |
| # definingPath(badWaterMelon , 'sweet\\Training\\bad\\bad') | |
| # t40 = thr.Thread(target = definingPath , args=(sweetWaterMelon , 'sweet\\Training\\bad\\bad')) | |
| # | |
| # rippedWaterMelon = dataset[dataset['Watermelon ripeness level'] > 4] | |
| # print(len(rippedWaterMelon)) | |
| # definingPath(rippedWaterMelon , 'Ripe\\Train\\Riped\\riped') | |
| # t41 = thr.Thread(target = definingPath , args=(sweetWaterMelon , 'sweet\\Training\\Riped\\riped')) | |
| # | |
| # unRippedWaterMelon = dataset[dataset['Watermelon ripeness level'] < 5] | |
| # print(len(unRippedWaterMelon)) | |
| # definingPath(unRippedWaterMelon , 'Ripe\\Train\\unRiped\\unRiped') | |
| # t42 = thr.Thread(target = definingPath , args=(sweetWaterMelon , 'sweet\\Training\\unRiped\\unRiped')) | |
| # | |
| # affectedBySurface = dataset[dataset['Watermelon surface color'] == 'yellow (Affected)'] | |
| # definingPath(affectedBySurface , 'Affected\\Training\\Affected\\Affected0') | |
| # print(len(affectedBySurface)) | |
| # print(affectedBySurface.values[1]) | |
| # t50 = thr.Thread(target = definingPath , args=(sweetWaterMelon , 'sweet\\Training\\Affected\\Affected0')) | |
| # | |
| # affectedByCondition = dataset[dataset['Watermelon condition'] == 'bad'] | |
| # print(len(affectedByCondition)) | |
| # definingPath(affectedByCondition , 'Affected\\Training\\Affected\\Affected1') | |
| # t51 = thr.Thread(target = definingPath , args=(sweetWaterMelon , 'sweet\\Training\\Affected\\Affected1')) | |
| # | |
| # unAffectedBySurface = dataset[dataset['Watermelon surface color'] != 'yellow (Affected)'] | |
| # # definingPath(unAffectedBySurface , 'Affected\\Training\\notAffected\\notAffected0') | |
| # t60 = thr.Thread(target = definingPath , args=(sweetWaterMelon , 'sweet\\Training\\notAffected\\notAffected0')) | |
| # | |
| # unAffectedByCondition = dataset[dataset['Watermelon condition'] != 'bad'] | |
| # # definingPath(unAffectedByCondition , 'Affected\\Training\\notAffected\\notAffected1') | |
| # t61 = thr.Thread(target = definingPath , args=(sweetWaterMelon , 'sweet\\Training\\notAffected\\notAffected1')) | |
| # | |
| # t1.start() | |
| # t2.start() | |
| # t3.start() | |
| # t40.start() | |
| # t41.start() | |
| # t42.start() | |
| # | |
| # t50.start() | |
| # t51.start() | |
| # t60.start() | |
| # t61.start() | |
| # (trainVerySweetWaterMelon , testVerySweetWaterMelon) , (trainSweetWaterMelon,testSweetWaterMelon) , | |
| # (trainNotSweetWaterMelon,testNotSweetWaterMelon) , (trainBadWaterMelon,testBadWaterMelon) = train_test_split(verySweetWaterMelon , sweetWaterMelon , notSweetWaterMelon , badWaterMelon); | |
| # affectedWaterMelon = affectedWaterMelon + dataset[dataset['Watermelon surface color'] == 'yellow (Affected)'] | |
| # print(sweetWaterMelon) | |
| # url = '1h-Xbt-PRUJZYZlgW-PmAUzqO8MvuE0TZ' | |
| # # print(rightSide) | |
| # downloadFile(url , "E:\\fileMachineLearning\\DataSetWatermelon\\Surface\\top.jpg") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment