csvFile.py

from cassandra.cluster import Cluster
import csv
# 1. Import csv library

import pandas as pd

if __name__ == "__main__":
    cluster = Cluster(['rio.pdf.com'],port=9042)
    session = cluster.connect('system_schema',wait_for_all_pools=True)
    session.execute('USE system_schema')
    rows = session.execute("SELECT column_name FROM system_schema.columns WHERE keyspace_name = 'fdc_13407_cass' AND table_name = 'treateddata';")
    columns = []
    for row in rows:
        columns.append(row.column_name)
    header = ['fdccontextid',
             'indicatorid',
             'agg_key', 
             'anomaly_index', 
             'anomalyindexalarmlevel',  
             'spcalarmlevel', 
             'sum_key', 
             'td_dcqv', 
             'value'
             ]

    #data = session.execute("SELECT * FROM fdc_13407_cass.treateddata WHERE fdccontextid = 903146;")
    data = session.execute("SELECT * FROM fdc_treateddata_cass.treateddata LIMIT 10000;")
    # 2. Define a filename and Open the file using open()
    data = pd.DataFrame(data, columns=header)
    data.to_csv('Treateddata.csv', index=False)


    '''
    filename = 'Treateddata.csv'
    with open(filename, 'w', newline="") as file:

        csvwriter = csv.writer(file) # 3. create a csvwriter object
        csvwriter.writerow(header) # 4. write the header
        csvwriter.writerows(data) # 5. write the rest of the data

    
    rows = []
    with open("Treateddata.csv", 'r') as file:
        csvreader = csv.reader(file)
        header = next(csvreader)
        for row in csvreader:
            rows.append(row)
    
    #print(header)
    #print(rows)
    '''

    data= pd.read_csv("Treateddata.csv")
    print(data.columns)
    print(data.indicatorid)








        # https://www.analyticsvidhya.com/blog/2021/08/python-tutorial-working-with-csv-file-for-data-science/