aniruddha27

# selecting non-empty outputs
df_show2 = pd.DataFrame(columns=df_rule2_all.columns)

for row in range(len(df_rule2_all)):
    
    if len(df_rule2_all.loc[row,'Output'])!=0:
        df_show2 = df_show2.append(df_rule2_all.loc[row,:])

# reset the index
df_show2.reset_index(inplace=True)

aniruddha27

# create a df containing sentence and its output for rule 2
row_list = []

# df2 contains all the sentences from all the speeches
for i in range(len(df2)):
    
    sent = df2.loc[i,'Sent']
    year = df2.loc[i,'Year']
    output = rule2(sent)
    dict1 = {'Year':year,'Sent':sent,'Output':output}

aniruddha27

# create a df containing sentence and its output for rule 2
row_list = []

for i in range(len(df3)):
    
    sent = df3.loc[i,'Sent']
    year = df3.loc[i,'Year']
    # rule
    output = rule2(sent)
    

aniruddha27

# 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

aniruddha27

# selecting non-empty output rows
df_show = pd.DataFrame(columns=df_rule1_all.columns)

for row in range(len(df_rule1_all)):
    
    if len(df_rule1_all.loc[row,'Output'])!=0:
        df_show = df_show.append(df_rule1_all.loc[row,:])

# reset the index
df_show.reset_index(inplace=True)

aniruddha27

# create a dataframe containing sentences
df2 = pd.DataFrame(columns=['Sent','Year','Len'])

row_list = []

for i in range(len(df)):
    for sent in df.loc[i,'sent']:
    
        wordcount = len(sent.split())
        year = df.loc[i,'Year']

aniruddha27

# rule 3 function
def rule3_mod(text):
    
    doc = nlp(text)
    
    sent = []
    
    for token in doc:

        if token.pos_=='ADP':

aniruddha27

# rule 0
def rule0(text, index):
    
    doc = nlp(text)
        
    token = doc[index]
    
    entity = ''
    
    for sub_tok in token.children:

aniruddha27

# rule 3 function
def rule3(text):
    
    doc = nlp(text)
    
    sent = []
    
    for token in doc:

        # look for prepositions

aniruddha27

# rule 1 modified function
def rule1_mod(text):
    
    doc = nlp(text)
    
    sent = []
    
    for token in doc:
        # root word
        if (token.pos_=='VERB'):