Import CSV in Postgress using Python Panda , compare two csv files and compare two db table using python

import pandas as pd from sqlalchemy import create_engine import psycopg2 import csv def importCSV(): engine = create_engine('postgresql://credr:credr@localhost/credr_db1') df = pd.read_csv('/Users/ranvijay/Desktop/data_sanity_21082015/Katta_data.csv') df.to_sql('data_anlytics', engine, if_exists='replace') df = pd.read_csv('/Users/ranvijay/Desktop/data_sanity_21082015/Data_sanity_21082015.csv') df.to_sql('data_bd', engine, if_exists='replace') # df = pd.read_csv('/Users/ranvijay/Downloads/BikeSheet.csv') # df.to_sql('bikesheet_dump', engine, if_exists='replace') def comapre_two_table(): # execute our Query conn_string = "host='localhost' dbname='credr_db1' user='credr' password='credr'" # print the connection string we will use to connect print "Connecting to database\n ->%s" % (conn_string) # get a connection, if a connect cannot be made an exception will be raised here conn = psycopg2.connect(conn_string) # conn.cursor will return a cursor object, you can use this cursor to perform queries print "year mismatch" cursor = conn.cursor() cursor.execute("SELECT * FROM bikesheet_dump WHERE year_of_mfg != year_of_mfg_new AND (remarks !~ '.*SKIPYEAR.*' OR remarks IS NULL)") records = cursor.fetchall() for record in records: print record print "make model variant mismatch" cursor = conn.cursor() cursor.execute("select * from bikesheet_dump where upper(COALESCE(bike_make_new,'NA')||COALESCE(bike_model_new,'NA')||COALESCE(bike_variant_new,'NA')) not in (select upper(COALESCE(make,'NA')||COALESCE(model,'NA')||COALESCE(variant,'NA')) from models_dump)") records = cursor.fetchall() for record in records: print record def parse_csv(): print("please wait......") fieldnames = ['bike_make','bike_model','bike_variant','year_of_mfg','cc','','bike_make_new','bike_model_new','bike_variant_new','year_of_mfg_new','cc_new','model_id'] outFile = open('/Users/ranvijay/Desktop/data_sanity_21082015/new_sanitized_file.csv', "wt") writer = csv.DictWriter(outFile, fieldnames = fieldnames) headers = {} for headerName in fieldnames: headers[headerName] = headerName writer.writerow(headers) with open('/Users/ranvijay/Desktop/data_sanity_21082015/data_sanity123.csv', 'rU') as csvfile: reader = csv.DictReader(csvfile) parsedata=[] for row in reader: with open('/Users/ranvijay/Desktop/data_sanity_21082015/Katta_data1.csv', 'rU') as csvfile1: reader1 = csv.DictReader(csvfile1) dataRow = {} for row1 in reader1: if str(row['bike_make_new'])== str(row1['make']) and str(row['bike_model_new'])== str(row1['model']) and str(row['bike_variant_new'])== str(row1['variant']): dataRow['bike_make']=str(row['bike_make']) dataRow['bike_model']=str(row['bike_model']) dataRow['bike_variant']=str(row['bike_variant']) dataRow['year_of_mfg']=str(row['year_of_mfg']) dataRow['cc']=str(row['cc']) dataRow['bike_make_new']=str(row['bike_make_new']) dataRow['bike_model_new']=str(row['bike_model_new']) dataRow['bike_variant_new']=str(row['bike_variant_new']) dataRow['year_of_mfg_new']=str(row['year_of_mfg_new']) dataRow['cc_new']=str(row['cc_new']) dataRow['model_id']= str(row1['modelID']) else: dataRow['bike_make']=str(row['bike_make']) dataRow['bike_model']=str(row['bike_model']) dataRow['bike_variant']=str(row['bike_variant']) dataRow['year_of_mfg']=str(row['year_of_mfg']) dataRow['cc']=str(row['cc']) dataRow['bike_make_new']=str(row['bike_make_new']) dataRow['bike_model_new']=str(row['bike_model_new']) dataRow['bike_variant_new']=str(row['bike_variant_new']) dataRow['year_of_mfg_new']=str(row['year_of_mfg_new']) dataRow['cc_new']=str(row['cc_new']) parsedata.append(dataRow) writer.writerows(parsedata) outFile.close() if __name__ == '__main__': parse_csv() #importCSV(); #comapre_two_table()