In [2]:
%matplotlib inline
import pandas as pd

In [2]:
alleged_doe_contracts_FY2018 = pd.read_csv('/Users/mbaumer/Downloads/FY2018_DOE_Contracts_Full_20181212_newsite.csv')


/Users/mbaumer/anaconda2/lib/python2.7/site-packages/IPython/core/interactiveshell.py:2718: DtypeWarning: Columns (26,28,33,34,39,57,109,110,138) have mixed types. Specify dtype option on import or set low_memory=False.
  interactivity=interactivity, compiler=compiler, result=result)

In [3]:
len(alleged_doe_contracts_FY2018)


Out[3]:
10932

In [4]:
print alleged_doe_contracts_FY2018.columns


Index([u'award_id_piid', u'modification_number', u'transaction_number',
       u'parent_award_agency_id', u'parent_award_agency_name',
       u'parent_award_id', u'parent_award_modification_number',
       u'federal_action_obligation', u'total_dollars_obligated',
       u'base_and_exercised_options_value',
       ...
       u'native_hawaiian_servicing_institution', u'school_of_forestry',
       u'veterinary_college', u'dot_certified_disadvantage',
       u'self_certified_small_disadvantaged_business',
       u'small_disadvantaged_business', u'c8a_program_participant',
       u'historically_underutilized_business_zone_hubzone_firm',
       u'sba_certified_8a_joint_venture', u'last_modified_date'],
      dtype='object', length=261)

In [12]:
office_names = alleged_doe_contracts_FY2018['funding_office_name']

In [14]:
science_offices = ['SCIENCE','SC OAK RIDGE OFFICE','SC CHICAGO SERVICE CENTER']

In [19]:
name_list = []
for office_name in office_names:
    if ('SC' in office_name) | ('SCIENCE' in office_name): name_list.append(office_name)
pd.Series(name_list).drop_duplicates()


Out[19]:
0                        SCIENCE
1            SC OAK RIDGE OFFICE
66     SC CHICAGO SERVICE CENTER
153            F1ATCY USCYBERCOM
201    NAVAL POSTGRADUATE SCHOOL
dtype: object

NSF Grants


In [20]:
nsf_grants_2018 = pd.read_csv('/Users/mbaumer/Downloads/FY2018_NSF_Assistance_Full_20181212_newsite.csv')


/Users/mbaumer/anaconda2/lib/python2.7/site-packages/IPython/core/interactiveshell.py:2718: DtypeWarning: Columns (33,45,65,66) have mixed types. Specify dtype option on import or set low_memory=False.
  interactivity=interactivity, compiler=compiler, result=result)

In [74]:
nsf_grants_2018.columns


Out[74]:
Index([u'award_id_fain', u'modification_number', u'award_id_uri',
       u'sai_number', u'federal_action_obligation',
       u'non_federal_funding_amount', u'total_funding_amount',
       u'face_value_of_loan', u'original_subsidy_cost', u'total_subsidy_cost',
       u'total_loan_value', u'action_date',
       u'period_of_performance_start_date',
       u'period_of_performance_current_end_date', u'awarding_agency_code',
       u'awarding_agency_name', u'awarding_sub_agency_code',
       u'awarding_sub_agency_name', u'awarding_office_code',
       u'awarding_office_name', u'funding_agency_code', u'funding_agency_name',
       u'funding_sub_agency_code', u'funding_sub_agency_name',
       u'funding_office_code', u'funding_office_name', u'recipient_duns',
       u'recipient_name', u'recipient_parent_name', u'recipient_parent_duns',
       u'recipient_country_code', u'recipient_country_name',
       u'recipient_address_line_1', u'recipient_address_line_2',
       u'recipient_city_code', u'recipient_city_name',
       u'recipient_county_code', u'recipient_county_name',
       u'recipient_state_code', u'recipient_state_name', u'recipient_zip_code',
       u'recipient_zip_last_4_code', u'recipient_congressional_district',
       u'recipient_foreign_city_name', u'recipient_foreign_province_name',
       u'recipient_foreign_postal_code',
       u'primary_place_of_performance_country_code',
       u'primary_place_of_performance_country_name',
       u'primary_place_of_performance_code',
       u'primary_place_of_performance_city_name',
       u'primary_place_of_performance_county_code',
       u'primary_place_of_performance_county_name',
       u'primary_place_of_performance_state_name',
       u'primary_place_of_performance_zip_4',
       u'primary_place_of_performance_congressional_district',
       u'primary_place_of_performance_foreign_location', u'cfda_number',
       u'cfda_title', u'assistance_type_code', u'assistance_type_description',
       u'award_description', u'business_funds_indicator_code',
       u'business_funds_indicator_description', u'business_types_code',
       u'business_types_description', u'correction_delete_indicator_code',
       u'correction_delete_indicator_description', u'action_type_code',
       u'action_type_description', u'record_type_code',
       u'record_type_description', u'last_modified_date'],
      dtype='object')

In [90]:
nsf_grants_2018['cfda_title']


Out[90]:
0                           EDUCATION AND HUMAN RESOURCES
1                      MATHEMATICAL AND PHYSICAL SCIENCES
2                                      ENGINEERING GRANTS
3                                             GEOSCIENCES
4                      MATHEMATICAL AND PHYSICAL SCIENCES
5                                      ENGINEERING GRANTS
6                                      ENGINEERING GRANTS
7                                     BIOLOGICAL SCIENCES
8                                      ENGINEERING GRANTS
9        COMPUTER AND INFORMATION SCIENCE AND ENGINEERING
10                                     ENGINEERING GRANTS
11                          EDUCATION AND HUMAN RESOURCES
12                     MATHEMATICAL AND PHYSICAL SCIENCES
13                     MATHEMATICAL AND PHYSICAL SCIENCES
14       COMPUTER AND INFORMATION SCIENCE AND ENGINEERING
15                                     ENGINEERING GRANTS
16                     MATHEMATICAL AND PHYSICAL SCIENCES
17                                     ENGINEERING GRANTS
18                          EDUCATION AND HUMAN RESOURCES
19                     MATHEMATICAL AND PHYSICAL SCIENCES
20                                            GEOSCIENCES
21                     MATHEMATICAL AND PHYSICAL SCIENCES
22       COMPUTER AND INFORMATION SCIENCE AND ENGINEERING
23                                     ENGINEERING GRANTS
24                                            GEOSCIENCES
25                                     ENGINEERING GRANTS
26                                         POLAR PROGRAMS
27       COMPUTER AND INFORMATION SCIENCE AND ENGINEERING
28                                            GEOSCIENCES
29                                     ENGINEERING GRANTS
                               ...                       
25602    COMPUTER AND INFORMATION SCIENCE AND ENGINEERING
25603                       EDUCATION AND HUMAN RESOURCES
25604                       EDUCATION AND HUMAN RESOURCES
25605                       EDUCATION AND HUMAN RESOURCES
25606                  MATHEMATICAL AND PHYSICAL SCIENCES
25607                  MATHEMATICAL AND PHYSICAL SCIENCES
25608                                 BIOLOGICAL SCIENCES
25609                                 BIOLOGICAL SCIENCES
25610                       EDUCATION AND HUMAN RESOURCES
25611    COMPUTER AND INFORMATION SCIENCE AND ENGINEERING
25612    COMPUTER AND INFORMATION SCIENCE AND ENGINEERING
25613    COMPUTER AND INFORMATION SCIENCE AND ENGINEERING
25614     OFFICE OF INTERNATIONAL SCIENCE AND ENGINEERING
25615                                 BIOLOGICAL SCIENCES
25616                  MATHEMATICAL AND PHYSICAL SCIENCES
25617                                         GEOSCIENCES
25618                                         GEOSCIENCES
25619                                  ENGINEERING GRANTS
25620                                 BIOLOGICAL SCIENCES
25621                                  ENGINEERING GRANTS
25622                                         GEOSCIENCES
25623                                         GEOSCIENCES
25624                  MATHEMATICAL AND PHYSICAL SCIENCES
25625                                 BIOLOGICAL SCIENCES
25626    COMPUTER AND INFORMATION SCIENCE AND ENGINEERING
25627                                 BIOLOGICAL SCIENCES
25628                                         GEOSCIENCES
25629                                         GEOSCIENCES
25630                                 BIOLOGICAL SCIENCES
25631                  MATHEMATICAL AND PHYSICAL SCIENCES
Name: cfda_title, Length: 25632, dtype: object

DOE Grants


In [22]:
alleged_doe_grants_FY2018 = pd.read_csv('/Users/mbaumer/Downloads/FY2018_DOE_Assistance_Full_20181212_newsite.csv')

In [29]:
alleged_doe_grants_FY2018.columns


Out[29]:
Index([u'award_id_fain', u'modification_number', u'award_id_uri',
       u'sai_number', u'federal_action_obligation',
       u'non_federal_funding_amount', u'total_funding_amount',
       u'face_value_of_loan', u'original_subsidy_cost', u'total_subsidy_cost',
       u'total_loan_value', u'action_date',
       u'period_of_performance_start_date',
       u'period_of_performance_current_end_date', u'awarding_agency_code',
       u'awarding_agency_name', u'awarding_sub_agency_code',
       u'awarding_sub_agency_name', u'awarding_office_code',
       u'awarding_office_name', u'funding_agency_code', u'funding_agency_name',
       u'funding_sub_agency_code', u'funding_sub_agency_name',
       u'funding_office_code', u'funding_office_name', u'recipient_duns',
       u'recipient_name', u'recipient_parent_name', u'recipient_parent_duns',
       u'recipient_country_code', u'recipient_country_name',
       u'recipient_address_line_1', u'recipient_address_line_2',
       u'recipient_city_code', u'recipient_city_name',
       u'recipient_county_code', u'recipient_county_name',
       u'recipient_state_code', u'recipient_state_name', u'recipient_zip_code',
       u'recipient_zip_last_4_code', u'recipient_congressional_district',
       u'recipient_foreign_city_name', u'recipient_foreign_province_name',
       u'recipient_foreign_postal_code',
       u'primary_place_of_performance_country_code',
       u'primary_place_of_performance_country_name',
       u'primary_place_of_performance_code',
       u'primary_place_of_performance_city_name',
       u'primary_place_of_performance_county_code',
       u'primary_place_of_performance_county_name',
       u'primary_place_of_performance_state_name',
       u'primary_place_of_performance_zip_4',
       u'primary_place_of_performance_congressional_district',
       u'primary_place_of_performance_foreign_location', u'cfda_number',
       u'cfda_title', u'assistance_type_code', u'assistance_type_description',
       u'award_description', u'business_funds_indicator_code',
       u'business_funds_indicator_description', u'business_types_code',
       u'business_types_description', u'correction_delete_indicator_code',
       u'correction_delete_indicator_description', u'action_type_code',
       u'action_type_description', u'record_type_code',
       u'record_type_description', u'last_modified_date'],
      dtype='object')

In [33]:
alleged_doe_grants_FY2018[alleged_doe_grants_FY2018['recipient_name'] == 'WASHINGTON UNIVERSITY IN ST. LOUIS']['award_description']


Out[33]:
8365    CORROSION-RESISTANT NON-CARBON ELECTROCATALYST...
Name: award_description, dtype: object

In [34]:
sc_website_doe_grants = pd.read_excel('/Users/mbaumer/Downloads/DOE-SC_Grants_FY2018.xlsx')

In [37]:
sc_website_doe_grants


Out[37]:
Institution City State Country Zipcode Congressional District Award Number Principlal Investigator Awarded Amount Action Type Title Award Type Org. Code Program Office Division Program Area/Topic - Subtopic Current Project Period Project End Date Institution Type
0 Abilene Christian University Abilene TX United States 79699-9103 TX-19 DE-FG02-03ER41243 Isenhower, Larry 50000.0 Supplemental The Spin and Anti‐Quark Structure of the... Grant SC-26.1 Nuclear Physics (NP) Physics Research Medium Energy Nuclear Physics 05/15/2017 - 05/14/2020 2020-05-14 Private Institution of Higher Education
1 Abilene Christian University Abilene TX United States 79699-9103 TX-19 DE-FG02-03ER41243 Isenhower, Larry 0.0 Continuation The Spin and Anti‐Quark Structure of the... Grant SC-26.1 Nuclear Physics (NP) Physics Research Medium Energy Nuclear Physics 05/15/2017 - 05/14/2020 2020-05-14 Private Institution of Higher Education
2 Advanced Research Corporation Saint Paul MN United States 55110-7626 MN-04 DE-SC0019471 Keesee, Amy 149920.0 New Micro Faraday Cup for Low Energy Ion Detection... Grant SC-24.1 Fusion Energy Sciences (FES) Facilities, Operations, and Projects Discovery Plasma Science: Measurement Innovation 09/01/2018 - 08/31/2019 2019-08-31 Small Business
3 Air Force Life Cycle Management Center Hanscom AFB MA United States 01731-2800 MA-05 DE-SC0012361 Dauler, Eric 0.0 No Cost Extension Center for Excitonics - MIT Lincoln Laboratory Interagency Agreement SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Energy Frontier Research Centers 08/26/2014 - 07/31/2019 2019-07-31 Other Federal Agency
4 American Physical Society College Park MD United States 20740-3840 MD-05 DE-SC0011076 Hodapp, Theodore 0.0 Continuation APS Conferences for Undergraduate Women in Phy... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Experimental Condensed Matter Physics 05/02/2017 - 05/01/2020 2020-05-01 Nonprofit with 501C3 IRS status (other than In...
5 American Physical Society College Park MD United States 20740-3840 MD-05 DE-SC0018365 Kirby, Kate 0.0 Continuation Workshop on Energy Research Opportunities for ... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Experimental Condensed Matter Physics 09/15/2017 - 09/14/2020 2020-09-14 Nonprofit with 501C3 IRS status (other than In...
6 Arizona State University Tempe AZ United States 85287-6011 AZ-09 DE-SC0019307 Shirzaei, Manoochehr 997084.0 New Physics-based Operational Induced Earthquake F... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Geosciences Research 09/01/2018 - 08/31/2021 2021-08-31 Public/State Controlled Institution of Higher ...
7 Arizona State University Tempe AZ United States 85287-6011 AZ-09 DE-SC0019208 Redding, Kevin 9990.0 New Joint conference support (ISPP and ICMP) Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Photosynthetic Systems 08/01/2018 - 07/31/2019 2019-07-31 Public/State Controlled Institution of Higher ...
8 Arizona State University Tempe AZ United States 85287-6011 AZ-09 DE-SC0019457 Fromme, Petra 165654.0 New Collaborative Project: Regulation of Sustaine... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Photosynthetic Systems 09/15/2018 - 09/14/2021 2021-09-14 Public/State Controlled Institution of Higher ...
9 Arizona State University Tempe AZ United States 85287-6011 AZ-09 DE-SC0019470 Vachaspati, Tanmay 265000.0 New Theoretical Research at the High Energy Fronti... Grant SC-25.1 High Energy Physics (HEP) Research & Technology Theoretical High Energy Physics 05/01/2018 - 04/30/2022 2022-04-30 Public/State Controlled Institution of Higher ...
10 Arizona State University Tempe AZ United States 85287-6011 AZ-09 DE-SC0019309 Alarcon, Ricardo 424000.0 New Experiments in Fundamental Neutron Physics Grant SC-26.1 Nuclear Physics (NP) Physics Research Fundamental Symmetries 08/15/2018 - 08/14/2021 2021-08-14 Public/State Controlled Institution of Higher ...
11 Arizona State University Tempe AZ United States 85287-6011 AZ-09 DE-SC0002423 Wachter, Rebekka 600000.0 Renewal Structure and Function of Rubisco Activase Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Photosynthetic Systems 09/15/2018 - 09/14/2021 2021-09-14 Public/State Controlled Institution of Higher ...
12 Arizona State University Tempe AZ United States 85287-6011 AZ-09 DE-SC0008677 Sieradzki, Karl 428586.0 Renewal Dynamic Fracture in Dealloying Induced Stress ... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Mechanical Behavior and Radiation Effects 08/15/2018 - 08/14/2021 2021-08-14 Public/State Controlled Institution of Higher ...
13 Arizona State University Tempe AZ United States 85287-6011 AZ-09 DE-SC0015641 Matyushov, Dmitry 276608.0 Renewal Theories of homogeneous and electrochemical el... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Solar Photochemistry 06/01/2018 - 05/31/2021 2021-05-31 Public/State Controlled Institution of Higher ...
14 Arizona State University Tempe AZ United States 85287-6011 AZ-09 DE-FG02-03ER15393 Gust, Devens 0.0 Continuation SUPRAMOLECULAR STRUCTURES FOR PHOTOCHEMICAL EN... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Solar Photochemistry 02/15/2017 - 02/14/2020 2020-02-14 Public/State Controlled Institution of Higher ...
15 Arizona State University Tempe AZ United States 85287-6011 AZ-09 DE-SC0010575 Redding, Kevin 372954.0 Continuation The Type I Homodimer Reaction Center in Heliob... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Photosynthetic Systems 09/01/2016 - 08/31/2019 2019-08-31 Public/State Controlled Institution of Higher ...
16 Arizona State University Tempe AZ United States 85287-6011 AZ-09 DE-SC0004954 Crozier, Peter 0.0 Continuation Development and Application of In Situ Nanocha... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Electron and Scanning Probe Microscopies 07/15/2016 - 07/14/2019 2019-07-14 Public/State Controlled Institution of Higher ...
17 Arizona State University Tempe AZ United States 85287-6011 AZ-09 DE-SC0016353 Yan, Hao 0.0 Continuation DNA nanostructure directed designer excitonic ... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Biomolecular Materials 08/15/2016 - 06/14/2019 2019-06-14 Public/State Controlled Institution of Higher ...
18 Arizona State University Tempe AZ United States 85287-6011 AZ-09 DE-SC0018241 Steimle, Timothy 0.0 Continuation Characterization of Gas-phase Uranium and Thor... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Heavy Element Chemistry 08/01/2017 - 07/31/2020 2020-07-31 Public/State Controlled Institution of Higher ...
19 Aspen Center for Physics Aspen CO United States 81611-1197 CO-03 DE-SC0018415 Si, Qimiao 20000.0 New High Temperature Superconductivity - Unifying ... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Theoretical Condensed Matter Physics 01/15/2018 - 01/14/2019 2019-01-14 Nonprofit with 501C3 IRS status (other than In...
20 Aspen Global Change Institute Basalt CO United States 81621-8379 CO-03 DE-SC0019428 Arnott, James 26866.0 New 2018 Interdisciplinary Science Workshop on 'Wh... Grant SC-23.1 Biological & Environmental Research (BER) Climate and Environmental Science Regional and Global Climate Modeling 09/01/2018 - 08/31/2019 2019-08-31 Nonprofit with 501C3 IRS status (other than In...
21 Atmospheric and Environmental Research, Inc. Lexington MA United States 02421-3126 MA-05 DE-SC0016530 Mlawer, Eli 0.0 Continuation Collaborative Research: Collaborative Research... Cooperative Agreement SC-23.1 Biological & Environmental Research (BER) Climate and Environmental Science Earth System Modeling 09/01/2016 - 08/31/2019 2019-08-31 For-Profit Organization (Other than Small Busi...
22 Atmospheric and Environmental Research, Inc. Lexington MA United States 02421-3126 MA-05 DE-SC0018296 Mlawer, Eli 0.0 Continuation Climate-Relevant Gas Absorption Properties fro... Grant SC-23.1 Biological & Environmental Research (BER) Climate and Environmental Science Atmospheric System Research 09/15/2017 - 09/14/2020 2020-09-14 For-Profit Organization (Other than Small Busi...
23 Auburn University Auburn University AL United States 36849-5131 AL-03 DE-SC0019176 Thomas, Edward 1499993.0 New Magnetized Plasma Research Laboratory as a DOE... Cooperative Agreement SC-24.2 Fusion Energy Sciences (FES) Research Discovery Plasma Science: Plasma Science Front... 09/01/2018 - 08/31/2021 2021-08-31 Public/State Controlled Institution of Higher ...
24 Auburn University Auburn University AL United States 36849-5131 AL-03 DE-SC0019177 Gorden, Anne 419659.0 New Tailoring Redox Active Ligands for Probing the... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Heavy Element Chemistry 09/01/2018 - 08/31/2021 2021-08-31 Public/State Controlled Institution of Higher ...
25 Auburn University Auburn University AL United States 36849-5131 AL-03 DE-SC0019181 Wang, Jin 1100000.0 New Harnessing methanotroph-photoautotroph interac... Grant SC-23.2 Biological & Environmental Research (BER) Biological Systems Science Foundational Genomics Research 09/01/2018 - 08/31/2021 2021-08-31 Public/State Controlled Institution of Higher ...
26 Auburn University Auburn University AL United States 36849-5131 AL-03 DE-FG02-03ER54692 Hanson, James 300000.0 Renewal Three-dimensional Equilibrium Reconstruction a... Grant SC-24.2 Fusion Energy Sciences (FES) Research Burning Plasma Science: Foundations: Theory & ... 11/01/2017 - 10/31/2020 2020-10-31 Public/State Controlled Institution of Higher ...
27 Auburn University Auburn University AL United States 36849-5131 AL-03 DE-SC0014529 Maurer, David 600000.0 Renewal Three Dimensional Equilibrium Stability & Its ... Grant SC-24.2 Fusion Energy Sciences (FES) Research Burning Plasma Science: Long Pulse: Stellarators 08/15/2018 - 08/14/2021 2021-08-14 Public/State Controlled Institution of Higher ...
28 Auburn University Auburn University AL United States 36849-5131 AL-03 DE-SC0014196 Guazzotto, Luca 325000.0 Renewal Two-Fluid and Kinetic Effects on Equilibrium, ... Grant SC-24.2 Fusion Energy Sciences (FES) Research Burning Plasma Science: Foundations: Theory & ... 07/01/2018 - 06/30/2021 2021-06-30 Public/State Controlled Institution of Higher ...
29 Auburn University Auburn University AL United States 36849-5131 AL-03 DE-FG02-00ER54610 Maurer, David 540000.0 Continuation MHD Stability and Equilibrium in a Current-Dri... Grant SC-24.2 Fusion Energy Sciences (FES) Research Burning Plasma Science: Long Pulse: Stellarators 05/16/2016 - 05/15/2019 2019-05-15 Public/State Controlled Institution of Higher ...
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
2815 Woods Hole Oceanographic Institution Woods Hole MA United States 02543-1501 MA-09 DE-SC0019263 Condron, Alan 51832.0 New Assessing global ocean circulation sensitivity... Grant SC-23.1 Biological & Environmental Research (BER) Climate and Environmental Science Earth System Modeling 09/01/2018 - 08/31/2019 2019-08-31 Nonprofit with 501C3 IRS status (other than In...
2816 Woods Hole Oceanographic Institution Woods Hole MA United States 02543-1501 MA-09 DE-SC0019492 Kwon, Young-Oh 880885.0 New The Atlantic Multidecadal Oscillation: Key Dri... Grant SC-23.1 Biological & Environmental Research (BER) Climate and Environmental Science Regional and Global Climate Modeling 09/15/2018 - 09/14/2021 2021-09-14 Nonprofit with 501C3 IRS status (other than In...
2817 Woods Hole Oceanographic Institution Woods Hole MA United States 02543-1501 MA-09 DE-SC0014433 Kwon, Young-Oh 0.0 No Cost Extension Compensation Between Poleward Energy Transport... Grant SC-23.1 Biological & Environmental Research (BER) Climate and Environmental Science Regional and Global Climate Modeling 08/01/2015 - 07/31/2019 2019-07-31 Nonprofit with 501C3 IRS status (other than In...
2818 X Science LLC Plainsboro NJ United States 08536-2483 NJ-12 DE-SC0007979 Maqueda, Ricardo 0.0 Continuation Divertor Studies Using Absolutely Calibrated v... Grant SC-24.2 Fusion Energy Sciences (FES) Research Burning Plasma Science: Foundations: Spherical... 06/01/2016 - 05/31/2019 2019-05-31 Small Business
2819 Xantho Technologies Madison WI United States 53705-3329 WI-02 DE-SC0013918 DEMERS, DIANE 326000.0 Renewal AN ION BEAM PROBE TO ADVANCE UNDERSTANDING OF ... Grant SC-24.2 Fusion Energy Sciences (FES) Research Burning Plasma Science: Long Pulse: Stellarators 07/01/2018 - 06/30/2021 2021-06-30 Small Business
2820 Xantho Technologies Madison WI United States 53705-3329 WI-02 DE-SC0006077 DEMERS, DIANE 0.0 Continuation DEVELOPMENT OF BEAM MEASUREMENTS TO ADVANCE UN... Grant SC-24.2 Fusion Energy Sciences (FES) Research Discovery Plasma Science: Measurement Innovation 07/18/2017 - 07/17/2020 2020-07-17 Small Business
2821 Xantho Technologies Madison WI United States 53705-3329 WI-02 DE-SC0017998 DEMERS, DIANE 0.0 Continuation Neutral Atomic Beam Techniques for Diagnosis o... Grant SC-24.2 Fusion Energy Sciences (FES) Research Discovery Plasma Science: Measurement Innovation 09/01/2017 - 08/31/2019 2019-08-31 Small Business
2822 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0019211 Ahn, Charles 489348.0 New Visualizing Orbital-Selective Spin Polarizatio... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Experimental Condensed Matter Physics 08/01/2018 - 07/31/2021 2021-07-31 Private Institution of Higher Education
2823 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0019406 Tang, Hongxing 1200000.0 New Hybrid quantum systems: spins, photons and sup... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Physical Behavior of Materials 09/15/2018 - 09/14/2021 2021-09-14 Private Institution of Higher Education
2824 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0019061 Fleming, George 49000.0 New Quantum Finite Elements for Nonperturbative Qu... Grant SC-25.1 High Energy Physics (HEP) Research & Technology Theoretical High Energy Physics 06/01/2018 - 03/31/2020 2020-03-31 Private Institution of Higher Education
2825 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0019368 Heeger, Karsten 80000.0 New Collaborative Proposal: R&D Towards CUPID, a T... Grant SC-26.1 Nuclear Physics (NP) Physics Research Research Capital Equipment, Major Items of Equ... 08/15/2018 - 08/14/2019 2019-08-14 Private Institution of Higher Education
2826 Yale University New Haven CT United States 06520-8047 CT-03 DE-FG02-01ER15183 Haller, Gary 367000.0 Renewal ZrO2/MWCNT as Support Platform for Acid and Me... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Catalysis Science 08/01/2018 - 07/31/2020 2020-07-31 Private Institution of Higher Education
2827 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0014476 Cha, Judy 509994.0 Renewal One-dimensional topological nanomaterials and ... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Experimental Condensed Matter Physics 09/01/2018 - 08/31/2021 2021-08-31 Private Institution of Higher Education
2828 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0012654 Heeger, Karsten 450000.0 Renewal Investigation of Neutrino Properties and Funda... Grant SC-26.1 Nuclear Physics (NP) Physics Research Fundamental Symmetries 11/01/2017 - 10/31/2020 2020-10-31 Private Institution of Higher Education
2829 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0004168 Harris, John 20000.0 Supplemental Relativistic Heavy Ion Physics Grant SC-26.1 Nuclear Physics (NP) Physics Research Heavy Ion Nuclear Physics 01/01/2016 - 12/31/2018 2018-12-31 Private Institution of Higher Education
2830 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0010699 Hirshfield, Jay NaN Supplemental Advanced Accelerator Physics Studies Grant SC-25.1 High Energy Physics (HEP) Research & Technology Accelerator Research and Development for High ... 09/01/2014 - 08/31/2018 2018-08-31 Private Institution of Higher Education
2831 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0016357 Heeger, Karsten 70000.0 Supplemental PROSPECT: A Precision Reactor Oscillation and ... Grant SC-25.1 High Energy Physics (HEP) Research & Technology Energy Frontier Experimental Research 07/01/2016 - 06/30/2021 2021-06-30 Private Institution of Higher Education
2832 Yale University New Haven CT United States 06520-8047 CT-03 DE-FG02-05ER15646 Brudvig, Gary 0.0 Continuation Structure/Function Studies of Photosystem II Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Photosynthetic Systems 07/01/2017 - 06/30/2020 2020-06-30 Private Institution of Higher Education
2833 Yale University New Haven CT United States 06520-8047 CT-03 DE-FG02-06ER15800 Johnson, Mark 0.0 Continuation UNMASKING THE MECHANICS OF PROTON DEFECT ACCOM... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Chemical Physics Research: Condensed Phase and... 07/01/2017 - 07/31/2019 2019-07-31 Private Institution of Higher Education
2834 Yale University New Haven CT United States 06520-8047 CT-03 DE-FG02-07ER15909 Brudvig, Gary 600000.0 Continuation Photocatalytic Assemblies for Solar Fuel Produ... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Solar Photochemistry 03/01/2017 - 02/29/2020 2020-02-29 Private Institution of Higher Education
2835 Yale University New Haven CT United States 06520-8047 CT-03 DE-FG02-98ER20311 Soll, Dieter 0.0 Continuation Engineering Selenoproteins for Enhanced Hydrog... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Physical Biosciences 09/01/2016 - 08/31/2019 2019-08-31 Private Institution of Higher Education
2836 Yale University New Haven CT United States 06520-8047 CT-03 DE-FG02-91ER40608 Iachello, Francesco 500000.0 Continuation Nuclear Theory (Task A & B) \n\n Grant SC-26.1 Nuclear Physics (NP) Physics Research Nuclear Theory 01/01/2016 - 12/31/2018 2018-12-31 Private Institution of Higher Education
2837 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0004168 Harris, John 1032000.0 Continuation Relativistic Heavy Ion Physics Grant SC-26.1 Nuclear Physics (NP) Physics Research Heavy Ion Nuclear Physics 01/01/2016 - 12/31/2018 2018-12-31 Private Institution of Higher Education
2838 Yale University New Haven CT United States 06520-8047 CT-03 DE-FG02-08ER46482 Glazman, Leonid 0.0 Continuation Non-equilibrium effects in quantum coherent su... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Theoretical Condensed Matter Physics 01/01/2016 - 12/31/2018 2018-12-31 Private Institution of Higher Education
2839 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0004889 Schroers, Jan 0.0 Continuation Effect of Chemical Composition and Fabrication... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Mechanical Behavior and Radiation Effects 09/01/2016 - 05/31/2019 2019-05-31 Private Institution of Higher Education
2840 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0016179 Schwarz, Udo 0.0 Continuation Atomic-scale Surface Studies of Bulk Metallic ... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Electron and Scanning Probe Microscopies 08/15/2016 - 07/14/2019 2019-07-14 Private Institution of Higher Education
2841 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0016357 Heeger, Karsten 550000.0 Continuation PROSPECT: A Precision Reactor Oscillation and ... Grant SC-25.1 High Energy Physics (HEP) Research & Technology Intensity Frontier Experimental Research 07/01/2016 - 06/30/2021 2021-06-30 Private Institution of Higher Education
2842 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0017660 Fleming, Bonnie 1928000.0 Continuation High Energy Physics Grant SC-25.1 High Energy Physics (HEP) Research & Technology Energy Frontier Experimental Research 04/01/2017 - 03/31/2020 2020-03-31 Private Institution of Higher Education
2843 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0010699 Hirshfield, Jay 100000.0 No Cost Extension Advanced Accelerator Physics Studies Grant SC-25.1 High Energy Physics (HEP) Research & Technology Accelerator Research and Development for High ... 09/01/2014 - 06/30/2019 2019-06-30 Private Institution of Higher Education
2844 Yale University New Haven CT United States 06520-8047 CT-03 DE-SC0015749 Fleming, Bonnie 0.0 No Cost Extension Next Generation Noble Liquid Detectors Grant SC-25.1 High Energy Physics (HEP) Research & Technology Detector Research and Development for High Ene... 05/01/2016 - 03/31/2019 2019-03-31 Private Institution of Higher Education

2845 rows × 19 columns


In [41]:
sc_website_doe_grants[sc_website_doe_grants['Institution'] == 'California Institute of Technology']


Out[41]:
Institution City State Country Zipcode Congressional District Award Number Principlal Investigator Awarded Amount Action Type Title Award Type Org. Code Program Office Division Program Area/Topic - Subtopic Current Project Period Project End Date Institution Type
87 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0018655 Kornfield, Julia 283041.0 New Polymer Macrocycles: A novel topology to contr... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Materials Chemistry 07/01/2018 - 06/30/2021 2021-06-30 Private Institution of Higher Education
88 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0019136 Peters, Jonas 550000.0 New Towards Electrocatalytic N2-to-NH3 Conversion ... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Catalysis Science 09/15/2018 - 09/14/2021 2021-09-14 Private Institution of Higher Education
89 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0019166 Nadj-Perge, Stevan 700000.0 New Quantum States in Layered Heterostructures Con... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Theoretical Condensed Matter Physics 09/15/2018 - 09/14/2021 2021-09-14 Private Institution of Higher Education
90 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0019390 Miller, Thomas 555000.0 New Ab initio Molecular Dynamics Beyond Density Fu... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Chemical Physics Research: Computational and T... 09/15/2018 - 09/14/2022 2022-09-14 Private Institution of Higher Education
91 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0018407 Preskill, John 360000.0 New Quantum error correction and spacetime geometry Grant SC-25.1 High Energy Physics (HEP) Research & Technology Computational Research in High Energy Physics 10/01/2017 - 09/30/2019 2019-09-30 Private Institution of Higher Education
92 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0019227 Spiropulu, Maria 310000.0 New Quantum Machine Learning and Quantum Computati... Grant SC-25.1 High Energy Physics (HEP) Research & Technology Computational Research in High Energy Physics 09/01/2018 - 08/31/2020 2020-08-31 Private Institution of Higher Education
93 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0019219 Spiropulu, Maria 490000.0 New Quantum Communication Channels for Fundamental... Grant SC-25.1 High Energy Physics (HEP) Research & Technology Computational Research in High Energy Physics 09/01/2018 - 08/31/2020 2020-08-31 Private Institution of Higher Education
94 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0019085 Simmons-Duffin, David 750000.0 New Precision Computations in Strongly Coupled Con... Grant SC-25.1 High Energy Physics (HEP) Research & Technology Theoretical High Energy Physics 09/01/2018 - 08/31/2023 2023-08-31 Private Institution of Higher Education
95 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-FG02-03ER46055 Fultz, Brent 594996.0 Renewal Inelastic Neutron Scattering Studies of Phonon... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Neutron Scattering 07/15/2018 - 07/14/2021 2021-07-14 Private Institution of Higher Education
96 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0011632 Wise, Mark 650000.0 Renewal Research Accomplishments and Goals of the Theo... Grant SC-25.1 High Energy Physics (HEP) Research & Technology Theoretical High Energy Physics 04/01/2018 - 03/31/2021 2021-03-31 Private Institution of Higher Education
97 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0016945 Greer, Julia 110550.0 Supplemental A Fundamental Study on the Link between Mechan... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Mechanical Behavior and Radiation Effects 12/15/2016 - 03/14/2020 2020-03-14 Private Institution of Higher Education
98 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0004993 Atwater, Harry 7250000.0 Continuation Energy Innovation Hub Renewal - Fuels from Sun... Cooperative Agreement SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Solar Photochemistry 09/30/2015 - 09/29/2020 2020-09-29 Private Institution of Higher Education
99 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0015527 Newman, Harvey 0.0 Continuation SDN- Next Generation Integrated Architecture (... Cooperative Agreement SC-21.1 Advanced Scientific Computing Research (ASCR) Computational Science Research & Partnerships ... Next-Generation Networking for Science 02/15/2016 - 02/14/2019 2019-02-14 Private Institution of Higher Education
100 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0015528 Newman, Harvey 0.0 Continuation SENSE: SDN for End-to-end Networked Science at... Cooperative Agreement SC-21.1 Advanced Scientific Computing Research (ASCR) Computational Science Research & Partnerships ... Next-Generation Networking for Science 02/15/2016 - 02/14/2019 2019-02-14 Private Institution of Higher Education
101 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-FG02-03ER15483 Lewis, Nathan 0.0 Continuation MOLECULAR-LEVEL FUNCTIONALIZATION, ATOMICALLY ... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Solar Photochemistry 02/15/2017 - 02/14/2020 2020-02-14 Private Institution of Higher Education
102 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0002679 Bellan, Josette 0.0 Continuation SISGR: PREDICTIVE LARGE-EDDY SIMULATION OF SUP... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Chemical Physics Research: Gas Phase Chemical ... 11/15/2016 - 11/14/2019 2019-11-14 Private Institution of Higher Education
103 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-FG02-07ER46405 Atwater, Harry 0.0 Continuation PLASMON AND PHOTON EXCITATIONS IN TWO-DIMENSIO... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Physical Behavior of Materials 09/01/2017 - 08/31/2020 2020-08-31 Private Institution of Higher Education
104 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0010533 Hsieh, David 0.0 Continuation Search for Novel Topological Phases in Superco... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Experimental Condensed Matter Physics 05/01/2017 - 04/30/2020 2020-04-30 Private Institution of Higher Education
105 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-FG02-04ER54755 Bellan, Paul 0.0 Continuation Enhancing Fundamental Understanding of Magneti... Grant SC-24.2 Fusion Energy Sciences (FES) Research Diagnostic Development for Fusion and Plasma S... 08/01/2016 - 07/31/2019 2019-07-31 Private Institution of Higher Education
106 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0014866 Rosenbaum, Thomas 0.0 Continuation QUANTUM ORDER AND DISORDER IN MAGNETIC MATERIALS Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Experimental Condensed Matter Physics 02/01/2016 - 01/31/2019 2019-01-31 Private Institution of Higher Education
107 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0016561 Eiler, John 0.0 Continuation Foundations Of Molecular "Isotomics": A First ... Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Photosynthetic Systems 08/01/2016 - 07/31/2019 2019-07-31 Private Institution of Higher Education
108 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0016945 Greer, Julia 0.0 Continuation A Fundamental Study on the Link between Mechan... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Mechanical Behavior and Radiation Effects 12/15/2016 - 03/14/2020 2020-03-14 Private Institution of Higher Education
109 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0018140 Chan, Garnet 0.0 Continuation Condensed phase quantum embedding and quantum ... Grant SC-22.2 Basic Energy Sciences (BES) Materials Sciences & Engineering Theoretical Condensed Matter Physics 08/15/2017 - 05/14/2020 2020-05-14 Private Institution of Higher Education
110 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0016469 Orphan, Victoria 1054362.0 Continuation Identification and ecophysiological understand... Grant SC-23.2 Biological & Environmental Research (BER) Biological Systems Science Foundational Genomics Research 08/15/2016 - 08/14/2019 2019-08-14 Private Institution of Higher Education
111 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0011925 Spiropulu, Maria 2930000.0 Continuation ACCOMPLISHMENTS AND FUTURE GOALS OF THE EXPERI... Grant SC-25.1 High Energy Physics (HEP) Research & Technology Energy Frontier Experimental Research 04/01/2017 - 03/31/2020 2020-03-31 Private Institution of Higher Education
112 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0018126 Golwala, Sunil 0.0 Continuation Broadband Microstrip-Coupled Titanium Nitride ... Grant SC-25.1 High Energy Physics (HEP) Research & Technology Detector Research and Development for High Ene... 05/01/2017 - 03/31/2020 2020-03-31 Private Institution of Higher Education
113 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0018407 Preskill, John 0.0 Continuation Quantum error correction and spacetime geometry Grant SC-25.1 High Energy Physics (HEP) Research & Technology Computational Research in High Energy Physics 10/01/2017 - 09/30/2019 2019-09-30 Private Institution of Higher Education
114 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0010255 Cheung, Clifford 0.0 No Cost Extension The Higgs Frontier Grant SC-25.1 High Energy Physics (HEP) Research & Technology Theoretical High Energy Physics 07/15/2013 - 07/31/2018 2018-07-31 Private Institution of Higher Education
115 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0001293 Nuzzo, Ralph 0.0 No Cost Extension Light-Material Interactions in Energy Conversion Grant SC-22.1 Basic Energy Sciences (BES) Chemical Sciences, Geosciences, & Biosciences Energy Frontier Research Centers 08/01/2014 - 01/31/2019 2019-01-31 Private Institution of Higher Education
116 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0013881 Golwala, Sunil 0.0 No Cost Extension A Massive, Position-Resolving, High-Energy-Res... Grant SC-25.1 High Energy Physics (HEP) Research & Technology Detector Research and Development for High Ene... 05/01/2015 - 04/30/2019 2019-04-30 Private Institution of Higher Education
117 California Institute of Technology Pasadena CA United States 91125-0001 CA-29 DE-SC0006624 Hirata, Christopher -116532.0 Award Revision Cosmological Probes of Fundamental Physics Grant SC-25.1 High Energy Physics (HEP) Research & Technology Theoretical High Energy Physics 07/15/2011 - 06/30/2017 2017-06-30 Private Institution of Higher Education

In [42]:
data1 = pd.read_csv(
        '../data/doe_contracts/2018_DOE_Contracts_Full_20181212_newsite.csv')
data2 = pd.read_csv(
    '../data/doe_contracts/2017_DOE_Contracts_Full_20180115.csv')


/Users/mbaumer/anaconda2/lib/python2.7/site-packages/IPython/core/interactiveshell.py:2718: DtypeWarning: Columns (42,53,66,67,76,96,116,212) have mixed types. Specify dtype option on import or set low_memory=False.
  interactivity=interactivity, compiler=compiler, result=result)

In [45]:
data1.columns


Out[45]:
Index([u'award_id_piid', u'modification_number', u'transaction_number',
       u'parent_award_agency_id', u'parent_award_agency_name',
       u'parent_award_id', u'parent_award_modification_number',
       u'federal_action_obligation', u'total_dollars_obligated',
       u'base_and_exercised_options_value',
       ...
       u'native_hawaiian_servicing_institution', u'school_of_forestry',
       u'veterinary_college', u'dot_certified_disadvantage',
       u'self_certified_small_disadvantaged_business',
       u'small_disadvantaged_business', u'c8a_program_participant',
       u'historically_underutilized_business_zone_hubzone_firm',
       u'sba_certified_8a_joint_venture', u'last_modified_date'],
      dtype='object', length=261)

In [46]:
data2.columns


Out[46]:
Index([u'unique_transaction_id', u'transaction_status', u'dollarsobligated',
       u'baseandexercisedoptionsvalue', u'baseandalloptionsvalue',
       u'maj_agency_cat', u'mod_agency', u'maj_fund_agency_cat',
       u'contractingofficeagencyid', u'contractingofficeid',
       ...
       u'prime_awardee_executive2', u'prime_awardee_executive2_compensation',
       u'prime_awardee_executive3', u'prime_awardee_executive3_compensation',
       u'prime_awardee_executive4', u'prime_awardee_executive4_compensation',
       u'prime_awardee_executive5', u'prime_awardee_executive5_compensation',
       u'interagencycontractingauthority', u'last_modified_date'],
      dtype='object', length=225)

Let's cross-check with a previous year's data, say from 2016


In [3]:
fy2016_old = pd.read_csv('../data/doe_contracts/2016_DOE_Contracts_Full_20180115.csv')
fy2016_new = pd.read_csv('/Users/mbaumer/Downloads/2016_089_Contracts_Full_20181212_1.csv')


/Users/mbaumer/anaconda2/lib/python2.7/site-packages/IPython/core/interactiveshell.py:2718: DtypeWarning: Columns (42,57,63,66,67,76,96,116,212,213,215,217,219,221) have mixed types. Specify dtype option on import or set low_memory=False.
  interactivity=interactivity, compiler=compiler, result=result)
/Users/mbaumer/anaconda2/lib/python2.7/site-packages/IPython/core/interactiveshell.py:2718: DtypeWarning: Columns (1,26,28,33,37,43,47,49,50,57,75,76,109,110,207) have mixed types. Specify dtype option on import or set low_memory=False.
  interactivity=interactivity, compiler=compiler, result=result)

In [4]:
len(fy2016_new)


Out[4]:
12352

In [5]:
len(fy2016_old)


Out[5]:
13051

In [29]:
fy2016_old.columns[80:100]


Out[29]:
Index([u'productorservicecode', u'systemequipmentcode', u'claimantprogramcode',
       u'principalnaicscode', u'informationtechnologycommercialitemcategory',
       u'gfe_gfp', u'useofepadesignatedproducts', u'recoveredmaterialclauses',
       u'seatransportation', u'contractbundling', u'consolidatedcontract',
       u'countryoforigin', u'placeofmanufacture',
       u'manufacturingorganizationtype', u'agencyid', u'piid', u'modnumber',
       u'transactionnumber', u'fiscal_year', u'idvagencyid'],
      dtype='object')

In [35]:
print len(fy2016_new['award_id_piid'].unique())
len(fy2016_old['piid'].unique())


6363
Out[35]:
6667

In [37]:
import numpy as np
len(np.intersect1d(fy2016_new['award_id_piid'].unique(),fy2016_old['piid'].unique()))


Out[37]:
6330

In [ ]: