from tqdm import tqdm

read_csv = pd.read_csv('count_data.csv')


long_sentences = []
short_sentences= []
u_cause =[]
subcategory =[]
category =[]
p_1 =[]
s_1 =[]
u_1 =[]
l_1 =[]
opened_by =[]
sys_created_by =[]
u_business_service=[]
u_vendor =[]
u_assignment_group = []
labels =[]
read_csv = data_loads
for m in tqdm(range(len(read_csv))):
    if str(read_csv.iloc[m]['description']).lower()!='nan' and str(read_csv.iloc[m]['short_description']).lower()!='nan' and str(read_csv.iloc[m]['l1label']).lower()!='nan' and str(read_csv.iloc[m]['assignment_group']).lower()!='nan':
        if int(read_csv.iloc[m]['count'])>=100:


            long_sentences.append(str(read_csv.iloc[m]['description']))
            short_sentences.append(str(read_csv.iloc[m]['short_description']))

            labels.append(int(read_csv.iloc[m]['l1label']))
            u_cause.append(int(read_csv.iloc[m]['u_cause']))
            subcategory.append((int(read_csv.iloc[m]['subcategory'])))
            category.append((int(read_csv.iloc[m]['category'])))
            p_1.append((int(read_csv.iloc[m]['priority'])))
            s_1.append((int(read_csv.iloc[m]['severity'])))
            u_1.append((int(read_csv.iloc[m]['urgency'])))
            l_1.append((int(read_csv.iloc[m]['location'])))
            opened_by.append((int(read_csv.iloc[m]['opened_by'])))
            sys_created_by.append((int(read_csv.iloc[m]['sys_created_by'])))
            u_business_service.append((int(read_csv.iloc[m]['u_business_service'])))
            u_vendor.append((int(read_csv.iloc[m]['u_vendor'])))
            u_assignment_group.append((int(read_csv.iloc[m]['assignment_group'])))