idramalab / lambretta Goto Github PK

    for item in splitter:
        addedawk+='/'+item+'/'
        if cc<len(splitter):#for the last item we don't need && 
            addedawk+=' && '
    addedawk+="' "+awk_source_path+" > cmdtmp";
    cmd=awkroot+addedawk
    print("Running for query :  ",querystring," command ",cmd)

        result=awk_query(query)
        with open(awk_output_export_path,"a+") as of:
            json.dump({"keyword":query,"data":results},of)
            of.write("\n")
    except Exception as err:
        ff=open("awkerrors_test.txt","a+")
        ff.write("quer"+querystring+" Error : "+str(err))

xx=open("candidates_test.txt")

xx=open("candidate_queries.txt")

 json.dump({"keyword":query,"data":results},of)

{"keyword": "value", "data": null}
{"keyword": "value", "data": null}
{"keyword": "value", "data": null}
{"keyword": "value", "data": null}

awk_output_export_path="/data/ppaudeldata/VoterFraud/awk_output_test.json"

xx=open("candidates_test.txt")
search=[]
for x in xx:
    x=x.rstrip()
    search.append(x)

 raw_cleaned_claim.append(item.strip())
 cleaned_tweet=' '.join(raw_cleaned_tweet).strip()

        # Creating spanning subset
        left_join = sorted_data[0:int(0.2*len(sorted_data))]
        right_join = sorted_data[-int(0.2*len(sorted_data)):]
        mid = int(len(sorted_data)*0.5)
       # total 👇 👇👇
        mid_join = sorted_data[mid-(int(total*0.1)):mid+(int(total*0.1))]
        # Sliced data is spanning subset discussed in the paper
        sliced_data = left_join+mid+right_join
        texts = []

for x in xx:
    try:
        x = x.rstrip()
        jsx = json.loads(x)
        query = jsx["keyword"]
        query_split = query.split(" ")
        query = ' '.join(query_split)
        print("Working on ... ", query)
        data = jsx["data"]
        if len(data) == 0: # <- error on this line

'''
Create TF-IDF vectorizer 
'''
#First, generate the document by accumulating all the claims 
docs=[]
for item in jsx:
    tr4w = TextRank4Keyword()
    claim=item["claim"]
    docs.append(jsx["claim"])
cv=CountVectorizer()
word_count_vector=cv.fit_transform(docs)
tfidf_transformer=TfidfTransformer(smooth_idf=True,use_idf=True)
tfidf_transformer.fit(word_count_vector)
def sort_coo(coo_matrix):
    tuples = zip(coo_matrix.col, coo_matrix.data)
    return sorted(tuples, key=lambda x: (x[1], x[0]), reverse=True)
feature_names=cv.get_feature_names()

import pandas as pd

df = pd.read_csv('data_source/data_source.csv', nrows=50)

df.to_csv('data_source/MOD_data_source.csv', index=False)