In [1]:
import pandas as pd
import sqlalchemy
import multiprocessing
import numpy as np

In [3]:
data = pd.read_excel('data/Budget-2018-19_Corrected.xlsx')

In [4]:
data.head()


Out[4]:
BUDGET 2018-19 Unnamed: 1 Unnamed: 2 Unnamed: 3 Unnamed: 4 Unnamed: 5 Unnamed: 6 Unnamed: 7 Unnamed: 8 Unnamed: 9
0 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
1 # GRANT NUMBER BUDGET ENTITY HEAD OF ACCOUNT HEAD DESCRIPTION HEAD DESCRIPTION ASSAMESE ACTUALS 2016-17 BUDGET 2017-18 REVISED 2017-18 BUDGET 2018-19
2 1 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-01-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 747.15 342.13 342.13 786.056
3 2 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-02-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0 484.113 484.113 86.0831
4 3 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-05-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0 4 4 4

In [5]:
data.columns = data.iloc[1]

In [6]:
data.drop([0,1], axis=0, inplace=True)
data.head()


Out[6]:
1 # GRANT NUMBER BUDGET ENTITY HEAD OF ACCOUNT HEAD DESCRIPTION HEAD DESCRIPTION ASSAMESE ACTUALS 2016-17 BUDGET 2017-18 REVISED 2017-18 BUDGET 2018-19
2 1 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-01-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 747.15 342.13 342.13 786.056
3 2 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-02-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0 484.113 484.113 86.0831
4 3 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-05-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0 4 4 4
5 4 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-08-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0 6 6 6
6 5 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-12-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0 0.01 0.01 0.01

In [7]:
data.columns


Out[7]:
Index(['#', 'GRANT NUMBER', 'BUDGET ENTITY', 'HEAD OF ACCOUNT',
       'HEAD DESCRIPTION', 'HEAD DESCRIPTION ASSAMESE', 'ACTUALS 2016-17',
       'BUDGET 2017-18', 'REVISED 2017-18', 'BUDGET 2018-19'],
      dtype='object', name=1)

In [8]:
data['HEAD OF ACCOUNT'].head()


Out[8]:
2    2051-00-102-0000-000-01-01-EE-GA-C
3    2051-00-102-0000-000-01-02-EE-GA-C
4    2051-00-102-0000-000-01-05-EE-GA-C
5    2051-00-102-0000-000-01-08-EE-GA-C
6    2051-00-102-0000-000-01-12-EE-GA-C
Name: HEAD OF ACCOUNT, dtype: object

In [8]:
# Scheme Names
schemes = {'CSS': 'Centrally Sponsored Scheme',
          'EAP': 'Externally Aided Projects',
          'EAP-SS': 'Externally Aided Projects-State Share',
          'EE-CS': 'Establishment Expenditure-Central Share',
          'EE-SS': 'Establishmet Expenditure-State Share',
          'EE': 'Establishmet Expenditure',
          'Plan': 'Plan',
          'RIDF-LS': 'Rural Infrastructure Development fund-Loan Share',
          'RIDF-SS': 'Rural Infrastructure Development fund-State Share',
          'SOPD EE-SSA': 'Establishment Expenditure-Six Schedule Area',
          'SOPD-G': 'State Own Priority Scheme-General',
          'SOPD-GSP': 'State Own Priority Scheme-GOI Special Scheme',
          'SOPD-ODS': 'State Own Priority Scheme-Other Development Scheme',
          'SOPD-SCSP': 'State Own Priority Scheme-SCSP',
          'SOPD-SCSP SS': 'State Own Priority Scheme-SCSP State Share',
          'SOPD-SS': 'State Own Priority Scheme-State Share',
          'SOPD-TSP': 'State Own Priority Scheme-TSP',
          'TG-AC': 'Transfer Grants to Autonomous Councils',
          'TG-DC': 'Transfer Grants to Development Councils',
          'TG-EI': 'Transfer Grants to Educational Institutions',
          'TG-FFC': 'Transfer Grants to Finance Commission Grants',
          'TG-IB': 'Transfer Grants to Individual Benefeciaries',
          'TG-PRI': 'Transfer Grants to Panchayat Raj Institutions',
          'TG-SFC': 'Transfer Grants to State Finance Commission Grants',
          'TG-SSA': 'Transfer Grants to Sixth Schedule Areas',
          'TG-UL': 'Transfer Grants to Urban Local Bodies'}

In [9]:
# Sixth Schedule Area
codes_for_areas = {'GA': 'General Area',
                   'KN': 'Karbi Anglong Non-entrusted',
                   'NN': 'North Cachar Non-entrusted',
                   'BN': 'Bodoland Non-entrusted',
                   'KE': 'Karbi Anglong Entrusted',
                   'NE': 'North Cachar Entrusted',
                   'BE': 'Bodoland Entrusted'}

In [30]:
data['HEAD DESCRIPTION'].str.split('$').iloc[10000]


Out[30]:
['Medical and Public Health',
 'Medical Education, Training and Research',
 'Homeopathy',
 'Dr. J.K. Saikia Homeopathic Medical College,',
 'NULL',
 'Office Expenses',
 'Books and Periodicals']

In [11]:
scheme_names = data['HEAD OF ACCOUNT'].apply(lambda x: '-'.join(x.split('-')[7:][:-2])).unique()

In [12]:
scheme_names


Out[12]:
array(['EE', 'SOPD-ODS', 'TG-IB', 'SOPD-G', 'TG-FFC', 'SOPD-SS', 'CSS',
       'EAP', 'EAP-SS', 'TG-SFC', 'SOPD-TSP', 'SOPD-GSP', 'SOPD-SCSP',
       'RIDF-LS', 'RIDF-SS', 'EE-CS', 'TG-UL', 'Plan', 'TG-AC', 'TG-DC',
       'SOPD-SCSP SS', 'EE-SS', 'TG-EI', 'TG-SSA', 'SOPD EE-SSA'],
      dtype=object)

In [13]:
set(scheme_names) - set(schemes.keys())


Out[13]:
set()

In [14]:
data[data['HEAD OF ACCOUNT'].apply(lambda x: '-'.join(x.split('-')[7:][:-2]) in ['Plan'])]


Out[14]:
1 # GRANT NUMBER BUDGET ENTITY HEAD OF ACCOUNT HEAD DESCRIPTION HEAD DESCRIPTION ASSAMESE ACTUALS 2016-17 BUDGET 2017-18 REVISED 2017-18 BUDGET 2018-19
12275 12274 31 - Urban Development ,Town & Country Planning Directorate of Town & Country Planning (R) 2217-03-800-4837-415-35-99-Plan-GA-V Urban Development$Integrated Development of Sm... নগৰ উন্নয়ন$ক্ষুদ্ৰ আৰু মজলীয়া চহৰৰ সংহত উন্নয়ন... 0 0 300 0
15041 15040 42 - Other Social Services Welfare of Minorities Development Department (D) 2250-00-101-1752-000-32-99-Plan-GA-V Other Social Services$NULL$Donations for Chari... অন্যান্য সাধাৰন সেৱা$NULL$দানৰ উদ্দেশ্যে দিয়া ... 0 0 27.5 0

In [15]:
area_codes = data['HEAD OF ACCOUNT'].apply(lambda x: x.split('-')[-2]).unique()
area_codes


Out[15]:
array(['GA', 'KN', 'NN', 'BN', 'KE', 'NE', 'BE'], dtype=object)

In [16]:
set(area_codes) - set(codes_for_areas.keys())


Out[16]:
set()

In [17]:
data['HEAD DESCRIPTION'].apply(lambda x: x.split('-')).iloc[0]


Out[17]:
['Public Service Commission$NULL$State Public Service Commission$NULL$NULL$Salaries$Pay']

In [18]:
data['HEAD OF ACCOUNT'].apply(lambda x: x.split('-')[:7])


Out[18]:
2        [2051, 00, 102, 0000, 000, 01, 01]
3        [2051, 00, 102, 0000, 000, 01, 02]
4        [2051, 00, 102, 0000, 000, 01, 05]
5        [2051, 00, 102, 0000, 000, 01, 08]
6        [2051, 00, 102, 0000, 000, 01, 12]
7        [2051, 00, 102, 0000, 000, 01, 13]
8        [2051, 00, 102, 0000, 000, 03, 00]
9        [2051, 00, 102, 0000, 000, 04, 01]
10       [2051, 00, 102, 0000, 000, 01, 06]
11       [2051, 00, 102, 0000, 000, 01, 07]
12       [2051, 00, 102, 0000, 000, 04, 02]
13       [2051, 00, 102, 0000, 000, 04, 03]
14       [2051, 00, 102, 0000, 000, 04, 04]
15       [2051, 00, 102, 0000, 000, 04, 05]
16       [2051, 00, 102, 0000, 000, 04, 06]
17       [2051, 00, 102, 0000, 000, 04, 07]
18       [2051, 00, 102, 0000, 000, 04, 08]
19       [2051, 00, 102, 0000, 000, 04, 09]
20       [2051, 00, 102, 0000, 000, 04, 10]
21       [2051, 00, 102, 0000, 000, 04, 11]
22       [2051, 00, 102, 0000, 000, 04, 99]
23       [2051, 00, 102, 0000, 000, 05, 01]
24       [2051, 00, 102, 0000, 000, 05, 02]
25       [2051, 00, 102, 0000, 000, 26, 03]
26       [2051, 00, 102, 0000, 000, 15, 01]
27       [2051, 00, 102, 0000, 000, 26, 02]
28       [2051, 00, 102, 0000, 000, 26, 99]
29       [2051, 00, 102, 0000, 000, 02, 04]
30       [2051, 00, 102, 0000, 000, 05, 99]
31       [2051, 00, 102, 0000, 000, 14, 99]
                        ...                
27037    [2210, 01, 001, 0144, 000, 04, 08]
27038    [2202, 80, 003, 0647, 000, 06, 02]
27039    [2202, 80, 003, 0647, 000, 02, 06]
27040    [2202, 80, 003, 0642, 000, 06, 02]
27041    [2202, 80, 003, 0642, 000, 02, 06]
27042    [2202, 03, 103, 4556, 000, 06, 02]
27043    [2202, 03, 103, 4556, 000, 02, 06]
27044    [2202, 03, 103, 0597, 000, 02, 06]
27045    [2202, 02, 109, 0576, 000, 06, 02]
27046    [2202, 01, 104, 0249, 000, 06, 02]
27047    [2029, 00, 101, 0000, 000, 01, 16]
27048    [2029, 00, 001, 0143, 000, 04, 08]
27049    [2217, 03, 001, 0794, 000, 01, 12]
27050    [2401, 00, 113, 1093, 000, 04, 08]
27051    [2401, 00, 109, 1079, 000, 04, 08]
27052    [2401, 00, 001, 1027, 000, 02, 01]
27053    [2401, 00, 001, 1026, 000, 04, 08]
27054    [2401, 00, 001, 0240, 000, 04, 08]
27055    [2202, 02, 109, 0576, 000, 02, 06]
27056    [4702, 00, 800, 0160, 334, 32, 99]
27057    [2225, 02, 800, 2971, 000, 32, 99]
27058    [2225, 02, 800, *BTC, 000, 32, 99]
27059    [2405, 00, 001, 0143, 000, 03, 01]
27060    [2405, 00, 101, 0106, 000, 03, 01]
27061    [2405, 00, 101, 1203, 000, 03, 01]
27062    [2405, 00, 101, 1205, 000, 03, 01]
27063    [2405, 00, 109, 1216, 000, 03, 01]
27064    [2041, 00, 101, 0348, 000, 03, 01]
27065    [3055, 00, 001, 1390, 000, 03, 01]
27066    [2415, 05, 004, 1307, 000, 03, 01]
Name: HEAD OF ACCOUNT, Length: 27065, dtype: object

In [19]:
def decipher_head_of_account(row, scheme_map, area_map, hard_check=True):
    head_of_account = row['HEAD OF ACCOUNT']
    hod_split = head_of_account.split('-')
    desc = row['HEAD DESCRIPTION'].split('$')
    row['Major Head'] = desc[0]
    row['Sub-Major Head'] = desc[1]
    row['Minor Head'] = desc[2]
    row['Sub-Minor Head'] = desc[3]
    row['Detailed Head'] = desc[4]
    row['Object Head'] = desc[5]
    row['Voucher Head'] = desc[6]
    scheme_code = '-'.join(hod_split[7:-2])
    area_code = hod_split[-2]
    if hard_check:
        row['Scheme'] = scheme_map[scheme_code]
        row['Area'] = area_map[area_code]
    else:
        if scheme_code in scheme_map:
            row['Scheme'] = scheme_map[scheme_code]
        else:
            row['Scheme'] = scheme_code
        if area_code in area_map:
            row['Area'] = area_map[area_code]
        else:
            row['Area'] = area_code
    row['Voted/Charged'] = 'Charged' if hod_split[-1] == 'C' else 'Voted'
    return row

In [20]:
# multiprocessing for some speed boost
def _apply_df(args):
    df, func, kwargs = args
    return df.apply(func, **kwargs)

def apply_by_multiprocessing(df, func, **kwargs):
    workers = kwargs.pop('workers')
    pool = multiprocessing.Pool(processes=workers)
    result = pool.map(_apply_df, [(d, func, kwargs)
            for d in np.array_split(df, workers)])
    pool.close()
    return pd.concat(list(result))

In [21]:
assam_processed_data = apply_by_multiprocessing(data, decipher_head_of_account, args=[schemes, codes_for_areas], axis=1, workers=4)

In [22]:
# %timeit apply_by_multiprocessing(data, decipher_head_of_account, args=[schemes, codes_for_areas], axis=1, workers=4)
# 30.8 s ± 1.1 s per loop (mean ± std. dev. of 7 runs, 1 loop each)

In [23]:
# %timeit data.apply(decipher_head_of_account, axis=1, args=[schemes, codes_for_areas])
# 1min 52s ± 1.28 s per loop (mean ± std. dev. of 7 runs, 1 loop each)

In [24]:
assam_processed_data


Out[24]:
1 # GRANT NUMBER BUDGET ENTITY HEAD OF ACCOUNT HEAD DESCRIPTION HEAD DESCRIPTION ASSAMESE ACTUALS 2016-17 BUDGET 2017-18 REVISED 2017-18 BUDGET 2018-19 Major Head Sub-Major Head Minor Head Sub-Minor Head Detailed Head Object Head Voucher Head Scheme Area Voted/Charged
2 1 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-01-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 747.15 342.12950 342.12950 786.05600 Public Service Commission NULL State Public Service Commission NULL NULL Salaries Pay Establishmet Expenditure General Area Charged
3 2 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-02-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 484.11325 484.11325 86.08314 Public Service Commission NULL State Public Service Commission NULL NULL Salaries Dearness Allowance Establishmet Expenditure General Area Charged
4 3 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-05-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 4.00000 4.00000 4.00000 Public Service Commission NULL State Public Service Commission NULL NULL Salaries Leave Travel Concession Establishmet Expenditure General Area Charged
5 4 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-08-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 6.00000 6.00000 6.00000 Public Service Commission NULL State Public Service Commission NULL NULL Salaries Medical Reimbursement Establishmet Expenditure General Area Charged
6 5 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-12-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 0.01000 0.01000 0.01000 Public Service Commission NULL State Public Service Commission NULL NULL Salaries Arrear Salary/DA Establishmet Expenditure General Area Charged
7 6 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-13-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 0.01000 0.01000 0.01000 Public Service Commission NULL State Public Service Commission NULL NULL Salaries Pay Revision Arrear Establishmet Expenditure General Area Charged
8 7 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-03-00-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 3.82 7.35000 7.35000 0.00000 Public Service Commission NULL State Public Service Commission NULL NULL Travel Expenses NULL Establishmet Expenditure General Area Charged
9 8 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-04-01-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 0.01000 0.01000 2.00000 Public Service Commission NULL State Public Service Commission NULL NULL Office Expenses Postage Stamp Establishmet Expenditure General Area Charged
10 9 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-06-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 12.40800 12.40800 13.39200 Public Service Commission NULL State Public Service Commission NULL NULL Salaries Medical Allowance Establishmet Expenditure General Area Charged
11 10 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-01-07-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 51.32000 51.32000 56.52149 Public Service Commission NULL State Public Service Commission NULL NULL Salaries House Rent Allowance Establishmet Expenditure General Area Charged
12 11 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-04-02-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 5.00000 5.00000 5.00000 Public Service Commission NULL State Public Service Commission NULL NULL Office Expenses Telephone Charge Establishmet Expenditure General Area Charged
13 12 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-04-03-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 20.00000 20.00000 22.00000 Public Service Commission NULL State Public Service Commission NULL NULL Office Expenses Electricity and Water Charge Establishmet Expenditure General Area Charged
14 13 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-04-04-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 18.00000 18.00000 22.00000 Public Service Commission NULL State Public Service Commission NULL NULL Office Expenses Office Equipments including Computers & Access... Establishmet Expenditure General Area Charged
15 14 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-04-05-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 6.50000 6.50000 7.50000 Public Service Commission NULL State Public Service Commission NULL NULL Office Expenses Stationery and Printing of Forms Establishmet Expenditure General Area Charged
16 15 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-04-06-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 15.00000 15.00000 16.00000 Public Service Commission NULL State Public Service Commission NULL NULL Office Expenses Furniture Establishmet Expenditure General Area Charged
17 16 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-04-07-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 1.00000 1.00000 1.00000 Public Service Commission NULL State Public Service Commission NULL NULL Office Expenses Liveries Establishmet Expenditure General Area Charged
18 17 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-04-08-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 30.00000 30.00000 4.00000 Public Service Commission NULL State Public Service Commission NULL NULL Office Expenses Maintenance of Vehicles Establishmet Expenditure General Area Charged
19 18 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-04-09-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 17.00000 17.00000 8.00000 Public Service Commission NULL State Public Service Commission NULL NULL Office Expenses Petrol, Oil and Lubricants (POL) Establishmet Expenditure General Area Charged
20 19 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-04-10-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 2.00000 2.00000 2.00000 Public Service Commission NULL State Public Service Commission NULL NULL Office Expenses Books and Periodicals Establishmet Expenditure General Area Charged
21 20 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-04-11-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 3.00000 3.00000 5.00000 Public Service Commission NULL State Public Service Commission NULL NULL Office Expenses Refreshment Expenses Establishmet Expenditure General Area Charged
22 21 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-04-99-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 82.74 26.00000 26.00000 0.00000 Public Service Commission NULL State Public Service Commission NULL NULL Office Expenses Others Establishmet Expenditure General Area Charged
23 22 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-05-01-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 300.00000 300.00000 350.00000 Public Service Commission NULL State Public Service Commission NULL NULL Payment for Professional and Special Services Remuneration for Professional Services Establishmet Expenditure General Area Charged
24 23 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-05-02-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 20.00000 20.00000 22.00000 Public Service Commission NULL State Public Service Commission NULL NULL Payment for Professional and Special Services Legal Service Establishmet Expenditure General Area Charged
25 24 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-26-03-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 10.00000 10.00000 10.00000 Public Service Commission NULL State Public Service Commission NULL NULL Other Charges Training Establishmet Expenditure General Area Charged
26 25 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-15-01-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 1.81 6.50000 6.50000 7.00000 Public Service Commission NULL State Public Service Commission NULL NULL Machinery and Equipment / Tools & Plants Machinery and Equipment Establishmet Expenditure General Area Charged
27 26 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-26-02-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 1.50000 1.50000 2.00000 Public Service Commission NULL State Public Service Commission NULL NULL Other Charges Disaster management Establishmet Expenditure General Area Charged
28 27 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-26-99-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 0.00000 0.01000 0.00000 Public Service Commission NULL State Public Service Commission NULL NULL Other Charges Others Establishmet Expenditure General Area Charged
29 28 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-02-04-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 5.46000 5.46000 7.02000 Public Service Commission NULL State Public Service Commission NULL NULL Wages Bungalow Peon Establishmet Expenditure General Area Charged
30 29 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-05-99-EE-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 124.40 0.00000 0.01000 0.00000 Public Service Commission NULL State Public Service Commission NULL NULL Payment for Professional and Special Services Others Establishmet Expenditure General Area Charged
31 30 C1 - Public Service Commission Assam Public Service Commission (R) 2051-00-102-0000-000-14-99-SOPD-ODS-GA-C Public Service Commission$NULL$State Public Se... লোক সেৱা আয়োগ$NULL$ৰাজ্যিক লোক সেৱা আয়োগ$NULL$... 0.00 25.00000 25.00000 0.00000 Public Service Commission NULL State Public Service Commission NULL NULL Minor Works Other State Own Priority Scheme-Other Development Sc... General Area Charged
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
27037 27036 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2210-01-001-0144-000-04-08-EE-BE-V Medical and Public Health$Urban Health Servic... চিকিৎসা আৰু জনস্বাস্থ্য$নগৰীয়া স্বাস্থ্য সেৱা ... 0.00 0.00000 0.00000 0.50000 Medical and Public Health Urban Health Services-Allopathy Direction and Administration District Establishment NULL Office Expenses Maintenance of Vehicles Establishmet Expenditure Bodoland Entrusted Voted
27038 27037 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2202-80-003-0647-000-06-02-EE-BE-V General Education$General$Training$Provinciali... সাধাৰণ শিক্ষা$সাধাৰণ$প্ৰশিক্ষণ$NULL$NULL$ভাড়া... 0.00 0.00000 0.00000 0.12000 General Education General Training Provincialised B.T. College NULL Rents, Rates & Taxes / Royalty Rates &Taxes Establishmet Expenditure Bodoland Entrusted Voted
27039 27038 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2202-80-003-0647-000-02-06-EE-BE-V General Education$General$Training$Provinciali... সাধাৰণ শিক্ষা$সাধাৰণ$প্ৰশিক্ষণ$NULL$NULL$মজুৰি... 0.00 0.00000 0.00000 0.12000 General Education General Training Provincialised B.T. College NULL Wages Part Time Sweeper Establishmet Expenditure Bodoland Entrusted Voted
27040 27039 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2202-80-003-0642-000-06-02-EE-BE-V General Education$General$Training$Primary Tea... সাধাৰণ শিক্ষা$সাধাৰণ$প্ৰশিক্ষণ$NULL$NULL$ভাড়া... 0.00 0.00000 0.00000 0.10000 General Education General Training Primary Teachers Training School NULL Rents, Rates & Taxes / Royalty Rates &Taxes Establishmet Expenditure Bodoland Entrusted Voted
27041 27040 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2202-80-003-0642-000-02-06-EE-BE-V General Education$General$Training$Primary Tea... সাধাৰণ শিক্ষা$সাধাৰণ$প্ৰশিক্ষণ$NULL$NULL$মজুৰি... 0.00 0.00000 0.00000 0.12000 General Education General Training Primary Teachers Training School NULL Wages Part Time Sweeper Establishmet Expenditure Bodoland Entrusted Voted
27042 27041 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2202-03-103-4556-000-06-02-EE-BE-V General Education$University and Higher Educat... সাধাৰণ শিক্ষা$বিশ্ববিদ্যালয় আৰু উচ্চ শিক্ষা$চৰ... 0.00 0.00000 0.00000 4.75000 General Education University and Higher Education Government Colleges and Institutes Provincialised Teachers/ Employees serving in ... NULL Rents, Rates & Taxes / Royalty Rates &Taxes Establishmet Expenditure Bodoland Entrusted Voted
27043 27042 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2202-03-103-4556-000-02-06-EE-BE-V General Education$University and Higher Educat... সাধাৰণ শিক্ষা$বিশ্ববিদ্যালয় আৰু উচ্চ শিক্ষা$চৰ... 0.00 0.00000 0.00000 1.00000 General Education University and Higher Education Government Colleges and Institutes Provincialised Teachers/ Employees serving in ... NULL Wages Part Time Sweeper Establishmet Expenditure Bodoland Entrusted Voted
27044 27043 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2202-03-103-0597-000-02-06-EE-BE-V General Education$University and Higher Educat... সাধাৰণ শিক্ষা$বিশ্ববিদ্যালয় আৰু উচ্চ শিক্ষা$চৰ... 0.00 0.00000 0.00000 0.36000 General Education University and Higher Education Government Colleges and Institutes Government Art College NULL Wages Part Time Sweeper Establishmet Expenditure Bodoland Entrusted Voted
27045 27044 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2202-02-109-0576-000-06-02-EE-BE-V General Education$Secondary Education$Governme... সাধাৰণ শিক্ষা$মাধ্যমিক শিক্ষা$চৰকাৰী মাধ্যমিক ... 0.00 0.00000 0.00000 0.24000 General Education Secondary Education Government Secondary Schools Secondary School for Boys NULL Rents, Rates & Taxes / Royalty Rates &Taxes Establishmet Expenditure Bodoland Entrusted Voted
27046 27045 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2202-01-104-0249-000-06-02-EE-BE-V General Education$Elementary Education$Inspect... সাধাৰণ শিক্ষা$ প্ৰাথমিক শিক্ষা$পৰিদৰ্শন$NULL$N... 0.00 0.00000 0.00000 1.25000 General Education Elementary Education Inspection Sub-Divisional Office NULL Rents, Rates & Taxes / Royalty Rates &Taxes Establishmet Expenditure Bodoland Entrusted Voted
27047 27046 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2029-00-101-0000-000-01-16-EE-BE-V Land Revenue$NULL$Collection Charges$NULL$NULL... ভুমি ৰাজহ$NULL$কৰ সংগ্ৰহৰ বাবে লোৱা মূল্য$NULL... 0.00 0.00000 0.00000 1.11000 Land Revenue NULL Collection Charges NULL NULL Salaries Fixed Pay Establishmet Expenditure Bodoland Entrusted Voted
27048 27047 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2029-00-001-0143-000-04-08-EE-BE-V Land Revenue$NULL$Direction and Administration... ভুমি ৰাজহ$NULL$নিৰ্দেশনা আৰু প্ৰশাসন$NULL$NULL... 0.00 0.00000 0.00000 0.20000 Land Revenue NULL Direction and Administration District Administration NULL Office Expenses Maintenance of Vehicles Establishmet Expenditure Bodoland Entrusted Voted
27049 27048 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2217-03-001-0794-000-01-12-EE-BE-V Urban Development$Integrated Development of Sm... নগৰ উন্নয়ন$ক্ষুদ্ৰ আৰু মজলীয়া চহৰৰ সংহত উন্নয়ন... 0.00 0.00000 0.00000 2.97000 Urban Development Integrated Development of Small and Medium Towns Direction and Administration Planning Wing NULL Salaries Arrear Salary/DA Establishmet Expenditure Bodoland Entrusted Voted
27050 27049 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2401-00-113-1093-000-04-08-EE-BE-V Crop Husbandary - Horticulture$NULL$Agricultur... শস্য প্ৰতিপালন$NULL$কৃষি অভিযান্ত্ৰিক$NULL$NUL... 0.00 0.00000 0.00000 0.10000 Crop Husbandary - Horticulture NULL Agricultural Engineering Agriculture Service Centres NULL Office Expenses Maintenance of Vehicles Establishmet Expenditure Bodoland Entrusted Voted
27051 27050 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2401-00-109-1079-000-04-08-EE-BE-V Crop Husbandary - Horticulture$NULL$Extension ... শস্য প্ৰতিপালন$NULL$সম্প্ৰসাৰণ আৰু কৃষকৰ প্ৰশি... 0.00 0.00000 0.00000 0.10000 Crop Husbandary - Horticulture NULL Extension and Farmers Training NAEP-III (Mission Double Cropping) NULL Office Expenses Maintenance of Vehicles Establishmet Expenditure Bodoland Entrusted Voted
27052 27051 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2401-00-001-1027-000-02-01-EE-BE-V Crop Husbandary - Horticulture$NULL$Direction ... শস্য প্ৰতিপালন$NULL$নিৰ্দেশনা আৰু প্ৰশাসন$NULL... 0.00 0.00000 0.00000 0.72000 Crop Husbandary - Horticulture NULL Direction and Administration Field trial stations & Cell NULL Wages Wages to Casual Employees Establishmet Expenditure Bodoland Entrusted Voted
27053 27052 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2401-00-001-1026-000-04-08-EE-BE-V Crop Husbandary - Horticulture$NULL$Direction ... শস্য প্ৰতিপালন$NULL$নিৰ্দেশনা আৰু প্ৰশাসন$NULL... 0.00 0.00000 0.00000 0.10000 Crop Husbandary - Horticulture NULL Direction and Administration Intensive Agriculture Extention Schemes NULL Office Expenses Maintenance of Vehicles Establishmet Expenditure Bodoland Entrusted Voted
27054 27053 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2401-00-001-0240-000-04-08-EE-BE-V Crop Husbandary - Horticulture$NULL$Direction ... শস্য প্ৰতিপালন$NULL$নিৰ্দেশনা আৰু প্ৰশাসন$NULL... 0.00 0.00000 0.00000 3.00000 Crop Husbandary - Horticulture NULL Direction and Administration Subordinate Establishment NULL Office Expenses Maintenance of Vehicles Establishmet Expenditure Bodoland Entrusted Voted
27055 27054 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2202-02-109-0576-000-02-06-EE-BE-V General Education$Secondary Education$Governme... সাধাৰণ শিক্ষা$মাধ্যমিক শিক্ষা$চৰকাৰী মাধ্যমিক ... 0.00 0.00000 0.00000 0.60000 General Education Secondary Education Government Secondary Schools Secondary School for Boys NULL Wages Part Time Sweeper Establishmet Expenditure Bodoland Entrusted Voted
27056 27055 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 4702-00-800-0160-334-32-99-CSS-BE-V Capital Outlay on Minor Irrigation$NULL$Other ... ক্ষুদ্ৰ জলসিঞ্চনৰ বাবে মূলধনী ব্যয়$NULL$অন্যান... 0.00 0.00000 9809.62000 0.00000 Capital Outlay on Minor Irrigation NULL Other Expenditure Flood Project Central Assistance to AIBP Grants-in-aid General (Non-Salary) Others Centrally Sponsored Scheme Bodoland Entrusted Voted
27057 27056 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2225-02-800-2971-000-32-99-SOPD-ODS-BE-V Welfare of Scheduled Caste, Scheduled Tribes$W... অনুসুচিত জাতি, অনুসুচিত জন-জাতি আৰু অন্যান্য প... 0.00 0.00000 0.00000 1500.00000 Welfare of Scheduled Caste, Scheduled Tribes Welfare of Scheduled Tribes Other Expenditure Administrative Grants in BTC NULL Grants-in-aid General (Non-Salary) Others State Own Priority Scheme-Other Development Sc... Bodoland Entrusted Voted
27058 27057 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2225-02-800-*BTC-000-32-99-TG-AC-BE-V Welfare of Scheduled Caste, Scheduled Tribes$W... অনুসুচিত জাতি, অনুসুচিত জন-জাতি আৰু অন্যান্য প... 0.00 0.00000 0.00000 30000.00000 Welfare of Scheduled Caste, Scheduled Tribes Welfare of Scheduled Tribes Other Expenditure Special Grants to Bodoland Autonomous Council NULL Grants-in-aid General (Non-Salary) Others Transfer Grants to Autonomous Councils Bodoland Entrusted Voted
27059 27058 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2405-00-001-0143-000-03-01-EE-BE-V Fisheries$NULL$Direction and Administration$Di... মীন পালন$NULL$ নিৰ্দেশনা আৰু প্ৰশাসন$NULL$NULL... 0.00 0.00000 0.00000 0.46000 Fisheries NULL Direction and Administration District Administration NULL Travel Expenses Regular Establishmet Expenditure Bodoland Entrusted Voted
27060 27059 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2405-00-101-0106-000-03-01-EE-BE-V Fisheries$NULL$Inland Fisheries$Applied Nutrit... মীন পালন$NULL$আভ্যন্তৰীন মীন পালন$NULL$NULL$ ভ... 0.00 0.00000 0.00000 0.18000 Fisheries NULL Inland Fisheries Applied Nutrition Programme NULL Travel Expenses Regular Establishmet Expenditure Bodoland Entrusted Voted
27061 27060 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2405-00-101-1203-000-03-01-EE-BE-V Fisheries$NULL$Inland Fisheries$Fish and Fish ... মীন পালন$NULL$আভ্যন্তৰীন মীন পালন$$NULL$ ভ্ৰমণ... 0.00 0.00000 0.00000 0.17000 Fisheries NULL Inland Fisheries Fish and Fish seed Farming NULL Travel Expenses Regular Establishmet Expenditure Bodoland Entrusted Voted
27062 27061 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2405-00-101-1205-000-03-01-EE-BE-V Fisheries$NULL$Inland Fisheries$National Fish ... মীন পালন$NULL$আভ্যন্তৰীন মীন পালন$NULL$NULL$ ভ... 0.00 0.00000 0.00000 0.08000 Fisheries NULL Inland Fisheries National Fish Seed Farm NULL Travel Expenses Regular Establishmet Expenditure Bodoland Entrusted Voted
27063 27062 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2405-00-109-1216-000-03-01-EE-BE-V Fisheries$NULL$Extension and Training$Fisherie... মীন পালন$NULL$সম্প্ৰসাৰণ আৰু প্ৰশিক্ষণ$NULL$NU... 0.00 0.00000 0.00000 0.25000 Fisheries NULL Extension and Training Fisheries Extension service NULL Travel Expenses Regular Establishmet Expenditure Bodoland Entrusted Voted
27064 27063 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2041-00-101-0348-000-03-01-EE-BE-V Taxes on Vehicles$NULL$Collection Charges$Comm... যান বাহনৰ ওপৰত কৰ$NULL$কৰ সংগ্ৰহৰ লোৱা মূল্য$N... 0.00 0.00000 0.00000 0.90000 Taxes on Vehicles NULL Collection Charges Commissioner of Transport NULL Travel Expenses Regular Establishmet Expenditure Bodoland Entrusted Voted
27065 27064 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 3055-00-001-1390-000-03-01-EE-BE-V Road Transport$NULL$Direction and Administrati... পথ পৰিবহন$NULL$নিৰ্দেশনা আৰু প্ৰশাসন$NULL$NULL... 0.00 0.00000 0.00000 0.35000 Road Transport NULL Direction and Administration Road Safety staff NULL Travel Expenses Regular Establishmet Expenditure Bodoland Entrusted Voted
27066 27065 78 - Bodoland Territorial Council Bodo Land Territorial Council (R) 2415-05-004-1307-000-03-01-EE-BE-V Agricultural Research and Education$Fisheries$... কৃষি গৱেষনা আৰু শিক্ষা$মৎস$গবেষণা$$NULL$ ভ্ৰমণ... 0.00 0.00000 0.00000 0.08000 Agricultural Research and Education Fisheries Research Survey of FIisheries and Collection of Statistics NULL Travel Expenses Regular Establishmet Expenditure Bodoland Entrusted Voted

27065 rows × 20 columns


In [25]:
assam_processed_data.columns


Out[25]:
Index(['#', 'GRANT NUMBER', 'BUDGET ENTITY', 'HEAD OF ACCOUNT',
       'HEAD DESCRIPTION', 'HEAD DESCRIPTION ASSAMESE', 'ACTUALS 2016-17',
       'BUDGET 2017-18', 'REVISED 2017-18', 'BUDGET 2018-19', 'Major Head',
       'Sub-Major Head', 'Minor Head', 'Sub-Minor Head', 'Detailed Head',
       'Object Head', 'Voucher Head', 'Scheme', 'Area', 'Voted/Charged'],
      dtype='object', name=1)

In [26]:
cols = ['#', 'GRANT NUMBER', 'BUDGET ENTITY', 'HEAD OF ACCOUNT',
       'HEAD DESCRIPTION', 'HEAD DESCRIPTION ASSAMESE', 'Major Head',
       'Sub-Major Head', 'Minor Head', 'Sub-Minor Head', 'Detailed Head',
       'Object Head', 'Voucher Head', 'Scheme', 'Area', 'Voted/Charged',
       'ACTUALS 2016-17', 'BUDGET 2017-18', 'REVISED 2017-18', 'BUDGET 2018-19']

In [27]:
assam_processed_data.to_csv('assam_processed_data.csv', columns=cols, index=False)

In [28]:
def save_to_sqlite(o, combined_data):
    '''
    Save the combined data to sqlite file.
    Args:
        o (str): output file name.
    Return:
        True if sqlite file saved else raise error.
    '''
    engine = sqlalchemy.create_engine('sqlite:///{}'.format(o))
    combined_data.to_sql(name='budget_2018_19', if_exists='replace', con=engine, chunksize=10000)
    return True

In [29]:
save_to_sqlite('assam_budget.sqlite', assam_processed_data)


Out[29]:
True

In [ ]: