os.listdir('all_new_datasets/')

os.listdir('all_new_datasets/AESLC-master/')

aeslc = pd.read_csv('all_new_datasets/AESLC-master/AESLC (train+dev+test).csv') aeslc.head()

aeslc.loc[4, 'Text']

os.listdir('all_new_datasets/AMI/')

os.listdir('all_new_datasets/argument-dialogue-summary/')

arg_dial_summ = pd.read_csv('all_new_datasets/argument-dialogue-summary/AllDialogs_phase1_Formatted_ALL.csv') arg_dial_summ.head()

arg_dial_summ.loc[0, 'Dialog']

arg_dial_summ.loc[0, 'Summary']

os.listdir('all_new_datasets/argument-facet-similarity/')

argpairs = pd.read_csv('all_new_datasets/argument-facet-similarity/ArgPairs_ALL.csv') argpairs.head()

argpairs.loc[1, 'sentence_2']

argpairs.loc[1, 'sentence_1']

argpairs['regression_label'].plot.kde()

argquality = pd.read_csv('all_new_datasets/argument-facet-similarity/ArgQuality_ALL.csv') argquality.head()

argquality.loc[0, 'sentence']

argquality['scale2_1_Count'].plot.kde()

argquality['scale3_Count'].plot.kde()

os.listdir('all_new_datasets/Artwalk/')

dyad_dial = pd.read_csv('all_new_datasets/Artwalk/Dyad Dialogues ALL.csv') dyad_dial.head()

dyad_dial[dyad_dial['Filename']=='Dyad 10.docx']

dyad_info = pd.read_csv('all_new_datasets/Artwalk/Dyad Info ALL.csv') dyad_info.head()

artwalk_addi_info = pd.read_excel('all_new_datasets/Artwalk/Artwalk.Additional.Info.xlsx') artwalk_addi_info.head()

artwalk_addi_info.info()

os.listdir('all_new_datasets/arxiv-dataset/')

arxiv_data = pd.read_csv('all_new_datasets/arxiv-dataset/sections_ALL.csv', nrows=1000) arxiv_data.head()

arxiv_data.loc[0, 'article_text']

arxiv_data.loc[0, 'abstract_text']

arxiv_data.loc[0, 'section_names']

arxiv_data.loc[0, 'sections']

os.listdir('all_new_datasets/auto-hMDS-master/')

auto_hmds = pd.read_pickle('all_new_datasets/auto-hMDS-master/reference_text_and_sentence_urls_ALL.pkl') auto_hmds.head()

tmp_df = auto_hmds[auto_hmds['Folder-name']=='100062_800724450_Super Mario 64'] for i in range(len(tmp_df)): print(tmp_df.loc[i, 'Text'])

os.listdir('all_new_datasets/AVDIAR_All/')