import pandas as pd


chunksize = 1000
ip_filename = '/home/wolfram/Downloads/DataParserData.csv'
op_filename = 'datafile.csv'
prefix = 'cleansedquery_'

all_keys = set()
first_write = True

def update_values(key_value, all_keys=all_keys):
    missing_keys = all_keys - set(key_value.keys())
    key_value.update({key:0 for key in missing_keys})
    return key_value

for df in pd.read_csv(ip_filename, chunksize=chunksize, usecols=['CleansedQuery']):
    df['keys'] = df.CleansedQuery.apply(lambda x: [y.split(':')[0] for y in x.split(' ')])
    all_keys.update({value for row in df['keys'].values for value in row})
for df in pd.read_csv(ip_filename, chunksize=chunksize):
    df['key_value'] = df.CleansedQuery.apply(lambda x: {y.split(':')[0]: int(y.split(':')[1]) for y in x.split(' ')})
    df['key_value'] = df['key_value'].apply(update_values)
    for key in all_keys:
        df[prefix+key] = df['key_value'].apply(lambda x: x[key])

    df.drop('key_value', inplace=True, axis=1)
#     df.sort_index(axis=1, inplace=True)
    if first_write:
        df.to_csv(open(op_filename, 'w'))
        columns = df.columns
        first_write = False
    else:
        df.loc[: columns].to_csv(open(op_filename, 'a'), header=False)