How to use the deeplabcut.create_training_dataset function in deeplabcut

deeplabcut.extract_outlier_frames(path_config_file,[newvideo],outlieralgorithm='jump',epsilon=0,automatic=True, destfolder=dfolder)
file=os.path.join(cfg['project_path'],'labeled-data',vname,"machinelabels-iter"+ str(cfg['iteration']) + '.h5')

print("RELABELING")
DF=pd.read_hdf(file,'df_with_missing')
DLCscorer=np.unique(DF.columns.get_level_values(0))[0]
DF.columns.set_levels([scorer.replace(DLCscorer,scorer)],level=0,inplace=True)
DF =DF.drop('likelihood',axis=1,level=2)
DF.to_csv(os.path.join(cfg['project_path'],'labeled-data',vname,"CollectedData_" + scorer + ".csv"))
DF.to_hdf(os.path.join(cfg['project_path'],'labeled-data',vname,"CollectedData_" + scorer + '.h5'),'df_with_missing',format='table', mode='w')

print("MERGING")
deeplabcut.merge_datasets(path_config_file)

print("CREATING TRAININGSET")
deeplabcut.create_training_dataset(path_config_file,net_type=net_type,augmenter_type=augmenter_type2)

cfg=deeplabcut.auxiliaryfunctions.read_config(path_config_file)
posefile=os.path.join(cfg['project_path'],'dlc-models/iteration-'+str(cfg['iteration'])+'/'+ cfg['Task'] + cfg['date'] + '-trainset' + str(int(cfg['TrainingFraction'][0] * 100)) + 'shuffle' + str(1),'train/pose_cfg.yaml')
DLC_config=deeplabcut.auxiliaryfunctions.read_plainconfig(posefile)
DLC_config['save_iters']=numiter
DLC_config['display_iters']=1
DLC_config['multi_step']=[[0.001,numiter]]

print("CHANGING training parameters to end quickly!")
deeplabcut.auxiliaryfunctions.write_config(posefile,DLC_config)

print("TRAIN")
deeplabcut.train_network(path_config_file)

try: #you need ffmpeg command line interface
    #subprocess.call(['ffmpeg','-i',video[0],'-ss','00:00:00','-to','00:00:00.4','-c','copy',newvideo])

columnindex = pd.MultiIndex.from_product([[scorer], [bodypart], ['x', 'y']],names=['scorer', 'bodyparts', 'coords'])
        frame = pd.DataFrame(100+np.ones((len(frames),2))*50*index, columns = columnindex, index = [os.path.join('labeled-data',videoname,fn) for fn in frames])
        if index==0:
            dataFrame=frame
        else:
            dataFrame = pd.concat([dataFrame, frame],axis=1)

dataFrame.to_csv(os.path.join(cfg['project_path'],'labeled-data',videoname,"CollectedData_" + scorer + ".csv"))
dataFrame.to_hdf(os.path.join(cfg['project_path'],'labeled-data',videoname,"CollectedData_" + scorer + '.h5'),'df_with_missing',format='table', mode='w')

print("Plot labels...")

deeplabcut.check_labels(path_config_file)

print("CREATING TRAININGSET")
deeplabcut.create_training_dataset(path_config_file)

posefile=os.path.join(cfg['project_path'],'dlc-models/iteration-'+str(cfg['iteration'])+'/'+ cfg['Task'] + cfg['date'] + '-trainset' + str(int(cfg['TrainingFraction'][0] * 100)) + 'shuffle' + str(1),'train/pose_cfg.yaml')

DLC_config=deeplabcut.auxiliaryfunctions.read_plainconfig(posefile)
DLC_config['save_iters']=10
DLC_config['display_iters']=1
DLC_config['multi_step']=[[0.001,10]]

print("CHANGING training parameters to end quickly!")
deeplabcut.auxiliaryfunctions.write_plainconfig(posefile,DLC_config)

print("TRAIN")
deeplabcut.train_network(path_config_file)

print("TRAIN again... different loss?")
deeplabcut.train_network(path_config_file)

file=os.path.join(cfg['project_path'],'labeled-data',vname,"machinelabels-iter"+ str(cfg['iteration']) + '.h5')

print("RELABELING")
DF=pd.read_hdf(file,'df_with_missing')
DLCscorer=np.unique(DF.columns.get_level_values(0))[0]
DF.columns.set_levels([scorer.replace(DLCscorer,scorer)],level=0,inplace=True)
DF =DF.drop('likelihood',axis=1,level=2)
DF.to_csv(os.path.join(cfg['project_path'],'labeled-data',vname,"CollectedData_" + scorer + ".csv"))
DF.to_hdf(os.path.join(cfg['project_path'],'labeled-data',vname,"CollectedData_" + scorer + '.h5'),'df_with_missing',format='table', mode='w')

print("MERGING")
deeplabcut.merge_datasets(path_config_file)

print("CREATING TRAININGSET")
deeplabcut.create_training_dataset(path_config_file)

cfg=read_config(path_config_file)
posefile=os.path.join(cfg['project_path'],'dlc-models/iteration-'+str(cfg['iteration'])+'/'+ cfg['Task'] + cfg['date'] + '-trainset' + str(int(cfg['TrainingFraction'][0] * 100)) + 'shuffle' + str(1),'train/pose_cfg.yaml')
DLC_config=read_config(posefile)
DLC_config['save_iters']=5
DLC_config['display_iters']=1
DLC_config['multi_step']=[[0.05,5]]

print("CHANGING training parameters to end quickly!")
write_config(posefile,DLC_config)

print("TRAIN")
deeplabcut.train_network(path_config_file)


print("ALL DONE!!! - default cases are functional.")

print("Inference with direct cropping")
deeplabcut.analyze_videos(path_config_file,[newvideo2],destfolder=dfolder,cropping=[0,50,0,50],save_as_csv=True)

print("Extracting skeleton distances, filter and plot filtered output")
deeplabcut.analyzeskeleton(path_config_file, [newvideo], save_as_csv=True, destfolder=dfolder)
deeplabcut.filterpredictions(path_config_file,[newvideo])

#deeplabcut.create_labeled_video(path_config_file,[newvideo], destfolder=dfolder,filtered=True)
deeplabcut.create_labeled_video(path_config_file,[newvideo2], destfolder=dfolder,displaycropped=True,filtered=True)
deeplabcut.plot_trajectories(path_config_file,[newvideo2], destfolder=dfolder,filtered=True)

print("CREATING TRAININGSET for shuffle 2")
print("will be used for 3D testscript...")
deeplabcut.create_training_dataset(path_config_file,Shuffles=[2],net_type=net_type,augmenter_type=augmenter_type3)

posefile=os.path.join(cfg['project_path'],'dlc-models/iteration-'+str(cfg['iteration'])+'/'+ cfg['Task'] + cfg['date'] + '-trainset' + str(int(cfg['TrainingFraction'][0] * 100)) + 'shuffle' + str(2),'train/pose_cfg.yaml')

DLC_config=deeplabcut.auxiliaryfunctions.read_plainconfig(posefile)
DLC_config['save_iters']=10
DLC_config['display_iters']=2
DLC_config['multi_step']=[[0.001,10]]

print("CHANGING training parameters to end quickly!")
deeplabcut.auxiliaryfunctions.write_plainconfig(posefile,DLC_config)

print("TRAINING shuffle 2, with smaller allocated memory")
deeplabcut.train_network(path_config_file,shuffle=2,allow_growth=True)

print("ANALYZING some individual frames")
deeplabcut.analyze_time_lapse_frames(path_config_file,os.path.join(cfg['project_path'],'labeled-data/reachingvideo1/'))

The analysis of the video takes 41 seconds (batch size 32) and creating the frames 8 seconds (+ a few seconds for ffmpeg) to create the video.
"""

# Importing the toolbox (takes several seconds)
import deeplabcut
import os
from pathlib import Path

# Loading example data set
path_config_file = os.path.join(os.getcwd(),'openfield-Pranav-2018-10-30/config.yaml')
#deeplabcut.load_demo_data(path_config_file)

#shuffle=11 #>> imageio functions!
shuffle=12

deeplabcut.create_training_dataset(path_config_file,Shuffles=[shuffle])
cfg=deeplabcut.auxiliaryfunctions.read_config(path_config_file)
posefile=os.path.join(cfg['project_path'],'dlc-models/iteration-'+str(cfg['iteration'])+'/'+ cfg['Task'] + cfg['date'] + '-trainset' + str(int(cfg['TrainingFraction'][0] * 100)) + 'shuffle' + str(shuffle),'train/pose_cfg.yaml')

DLC_config=deeplabcut.auxiliaryfunctions.read_plainconfig(posefile)
DLC_config['save_iters']=10
DLC_config['display_iters']=2
DLC_config['multi_step']=[[0.005,15001]]
deeplabcut.auxiliaryfunctions.write_plainconfig(posefile,DLC_config)


print("TRAIN NETWORK")
deeplabcut.train_network(path_config_file, shuffle=shuffle,saveiters=15000,displayiters=1000,max_snapshots_to_keep=15)

print("EVALUATE")
deeplabcut.evaluate_network(path_config_file, Shuffles=[shuffle],plotting=True)

print("CREATING-SOME LABELS FOR THE FRAMES")
frames=os.listdir(os.path.join(cfg['project_path'],'labeled-data',videoname))
#As this next step is manual, we update the labels by putting them on the diagonal (fixed for all frames)
for index,bodypart in enumerate(cfg['bodyparts']):
        columnindex = pd.MultiIndex.from_product([[scorer], [bodypart], ['x', 'y']],names=['scorer', 'bodyparts', 'coords'])
        frame = pd.DataFrame(np.ones((len(frames),2))*50*index, columns = columnindex, index = [os.path.join('labeled-data',videoname,fn) for fn in frames])
        if index==0:
            dataFrame=frame
        else:
            dataFrame = pd.concat([dataFrame, frame],axis=1)

dataFrame.to_csv(os.path.join(cfg['project_path'],'labeled-data',videoname,"CollectedData_" + scorer + ".csv"))
dataFrame.to_hdf(os.path.join(cfg['project_path'],'labeled-data',videoname,"CollectedData_" + scorer + '.h5'),'df_with_missing',format='table', mode='w')

print("CREATING TRAININGSET")
deeplabcut.create_training_dataset(path_config_file)

posefile=os.path.join(cfg['project_path'],'dlc-models/iteration-'+str(cfg['iteration'])+'/'+ cfg['Task'] + cfg['date'] + '-trainset' + str(int(cfg['TrainingFraction'][0] * 100)) + 'shuffle' + str(1),'train/pose_cfg.yaml')
DLC_config=read_config(posefile)
DLC_config['save_iters']=10
DLC_config['display_iters']=2
DLC_config['multi_step']=[[0.001,10]]

print("CHANGING training parameters to end quickly!")
write_config(posefile,DLC_config)

print("TRAIN")
deeplabcut.train_network(path_config_file)

#this is much easier now: deeplabcut.train_network(path_config_file,gputouse=0,max_snapshots_to_keep=None,saveiters=1)

print("EVALUATE")

def create_training_dataset(self,event):
        """
        """
        num_shuffles = self.shuffles.GetValue()
        userfeedback_option = self.userfeedback.GetStringSelection()
        if userfeedback_option=='Yes':
            userfeedback = True
        else:
            userfeedback = False
        trainindex = self.trainingindex.GetValue()

        if self.model_comparison_choice.GetStringSelection() == 'No':
            deeplabcut.create_training_dataset(self.config,num_shuffles,Shuffles=[self.shuffle.GetValue()], userfeedback=userfeedback,net_type=self.net_choice.GetValue(),augmenter_type = self.aug_choice.GetValue())
        if self.model_comparison_choice.GetStringSelection() == 'Yes':
            deeplabcut.create_training_model_comparison(self.config,trainindex=trainindex, num_shuffles=num_shuffles,userfeedback=userfeedback,net_types=self.net_type,augmenter_types=self.aug_type)