Skip to content

Instantly share code, notes, and snippets.

@aniruddha27
Last active June 8, 2020 10:36
Show Gist options
  • Save aniruddha27/0c2f90071cdce515c255807179b07a81 to your computer and use it in GitHub Desktop.
Save aniruddha27/0c2f90071cdce515c255807179b07a81 to your computer and use it in GitHub Desktop.
# separate subject, verb and object
verb_dict = dict()
dis_dict = dict()
dis_list = []
# iterating over all the sentences
for i in range(len(df_show)):
# sentence containing the output
sentence = df_show.loc[i,'Sent']
# year of the sentence
year = df_show.loc[i,'Year']
# output of the sentence
output = df_show.loc[i,'Output']
# iterating over all the outputs from the sentence
for sent in output:
# separate subject, verb and object
n1, v, n2 = sent.split()[:1], sent.split()[1], sent.split()[2:]
# append to list, along with the sentence
dis_dict = {'Sent':sentence,'Year':year,'Noun1':n1,'Verb':v,'Noun2':n2}
dis_list.append(dis_dict)
# counting the number of sentences containing the verb
verb = sent.split()[1]
if verb in verb_dict:
verb_dict[verb]+=1
else:
verb_dict[verb]=1
df_sep = pd.DataFrame(dis_list)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment