SPB Git

spb/firc0001_uqo

Public
13.3 KB · 937 lines json
1{2  "extracted_sections": [3    [4      "section_id",5      "VARCHAR"6    ],7    [8      "accession_number",9      "VARCHAR"10    ],11    [12      "backend",13      "VARCHAR"14    ],15    [16      "n_mentions",17      "INTEGER"18    ],19    [20      "extracted_at",21      "TIMESTAMP"22    ]23  ],24  "project_mentions": [25    [26      "mention_id",27      "VARCHAR"28    ],29    [30      "accession_number",31      "VARCHAR"32    ],33    [34      "cik",35      "VARCHAR"36    ],37    [38      "section_id",39      "VARCHAR"40    ],41    [42      "section_name",43      "VARCHAR"44    ],45    [46      "project_name",47      "VARCHAR"48    ],49    [50      "project_type",51      "VARCHAR"52    ],53    [54      "description",55      "VARCHAR"56    ],57    [58      "objective",59      "VARCHAR"60    ],61    [62      "amount_usd",63      "DOUBLE"64    ],65    [66      "amount_raw",67      "VARCHAR"68    ],69    [70      "locations",71      "VARCHAR[]"72    ],73    [74      "technologies",75      "VARCHAR[]"76    ],77    [78      "partners",79      "VARCHAR[]"80    ],81    [82      "suppliers",83      "VARCHAR[]"84    ],85    [86      "benefits",87      "VARCHAR[]"88    ],89    [90      "risks",91      "VARCHAR[]"92    ],93    [94      "years",95      "INTEGER[]"96    ],97    [98      "status",99      "VARCHAR"100    ],101    [102      "confidence",103      "DOUBLE"104    ],105    [106      "backend",107      "VARCHAR"108    ],109    [110      "ticker",111      "VARCHAR"112    ],113    [114      "company_name",115      "VARCHAR"116    ],117    [118      "form_type",119      "VARCHAR"120    ],121    [122      "filing_date",123      "DATE"124    ],125    [126      "fiscal_year",127      "INTEGER"128    ],129    [130      "sector",131      "VARCHAR"132    ]133  ],134  "projects": [135    [136      "project_id",137      "VARCHAR"138    ],139    [140      "cik",141      "VARCHAR"142    ],143    [144      "ticker",145      "VARCHAR"146    ],147    [148      "company_name",149      "VARCHAR"150    ],151    [152      "sector",153      "VARCHAR"154    ],155    [156      "project_type",157      "VARCHAR"158    ],159    [160      "project_name",161      "VARCHAR"162    ],163    [164      "canonical_location",165      "VARCHAR"166    ],167    [168      "technologies",169      "VARCHAR[]"170    ],171    [172      "status",173      "VARCHAR"174    ],175    [176      "total_amount_usd",177      "DOUBLE"178    ],179    [180      "n_mentions",181      "INTEGER"182    ],183    [184      "n_filings",185      "INTEGER"186    ],187    [188      "first_seen",189      "DATE"190    ],191    [192      "last_seen",193      "DATE"194    ],195    [196      "first_year",197      "INTEGER"198    ],199    [200      "last_year",201      "INTEGER"202    ],203    [204      "avg_confidence",205      "DOUBLE"206    ],207    [208      "description",209      "VARCHAR"210    ]211  ],212  "project_timeline": [213    [214      "project_id",215      "VARCHAR"216    ],217    [218      "accession_number",219      "VARCHAR"220    ],221    [222      "filing_date",223      "DATE"224    ],225    [226      "form_type",227      "VARCHAR"228    ],229    [230      "status",231      "VARCHAR"232    ],233    [234      "amount_usd",235      "DOUBLE"236    ],237    [238      "confidence",239      "DOUBLE"240    ],241    [242      "snippet",243      "VARCHAR"244    ]245  ],246  "spid_sections": [247    [248      "section_id",249      "VARCHAR"250    ],251    [252      "accession_number",253      "VARCHAR"254    ],255    [256      "section_name",257      "VARCHAR"258    ],259    [260      "item_number",261      "VARCHAR"262    ],263    [264      "text",265      "VARCHAR"266    ],267    [268      "word_count",269      "INTEGER"270    ]271  ],272  "v_sections": [273    [274      "section_id",275      "VARCHAR"276    ],277    [278      "accession_number",279      "VARCHAR"280    ],281    [282      "section_name",283      "VARCHAR"284    ],285    [286      "item_number",287      "VARCHAR"288    ],289    [290      "text",291      "VARCHAR"292    ],293    [294      "word_count",295      "INTEGER"296    ],297    [298      "cik",299      "VARCHAR"300    ],301    [302      "ticker",303      "VARCHAR"304    ],305    [306      "filing_company",307      "VARCHAR"308    ],309    [310      "form_type",311      "VARCHAR"312    ],313    [314      "filing_date",315      "DATE"316    ],317    [318      "fiscal_year",319      "INTEGER"320    ],321    [322      "company_name",323      "VARCHAR"324    ],325    [326      "sector",327      "VARCHAR"328    ],329    [330      "sub_industry",331      "VARCHAR"332    ],333    [334      "sic_code",335      "VARCHAR"336    ],337    [338      "state",339      "VARCHAR"340    ]341  ],342  "src_filings": [343    [344      "accession_number",345      "VARCHAR"346    ],347    [348      "cik",349      "VARCHAR"350    ],351    [352      "ticker",353      "VARCHAR"354    ],355    [356      "company_name",357      "VARCHAR"358    ],359    [360      "form_type",361      "VARCHAR"362    ],363    [364      "filing_date",365      "DATE"366    ],367    [368      "report_date",369      "DATE"370    ],371    [372      "fiscal_year",373      "INTEGER"374    ],375    [376      "fiscal_quarter",377      "INTEGER"378    ],379    [380      "sec_url",381      "VARCHAR"382    ],383    [384      "local_path",385      "VARCHAR"386    ],387    [388      "primary_document",389      "VARCHAR"390    ],391    [392      "file_size_bytes",393      "BIGINT"394    ],395    [396      "download_status",397      "VARCHAR"398    ],399    [400      "parse_status",401      "VARCHAR"402    ],403    [404      "created_at",405      "TIMESTAMP"406    ],407    [408      "updated_at",409      "TIMESTAMP"410    ]411  ],412  "src_sections": [413    [414      "section_id",415      "VARCHAR"416    ],417    [418      "accession_number",419      "VARCHAR"420    ],421    [422      "section_name",423      "VARCHAR"424    ],425    [426      "item_number",427      "VARCHAR"428    ],429    [430      "section_order",431      "INTEGER"432    ],433    [434      "text",435      "VARCHAR"436    ],437    [438      "word_count",439      "INTEGER"440    ],441    [442      "char_count",443      "INTEGER"444    ],445    [446      "created_at",447      "TIMESTAMP"448    ]449  ],450  "src_companies": [451    [452      "cik",453      "VARCHAR"454    ],455    [456      "ticker",457      "VARCHAR"458    ],459    [460      "company_name",461      "VARCHAR"462    ],463    [464      "sector",465      "VARCHAR"466    ],467    [468      "sub_industry",469      "VARCHAR"470    ],471    [472      "sic_code",473      "VARCHAR"474    ],475    [476      "state",477      "VARCHAR"478    ],479    [480      "date_added",481      "DATE"482    ],483    [484      "created_at",485      "TIMESTAMP"486    ],487    [488      "updated_at",489      "TIMESTAMP"490    ],491    [492      "in_sp500",493      "BOOLEAN"494    ],495    [496      "in_russell3000",497      "BOOLEAN"498    ],499    [500      "sic_description",501      "VARCHAR"502    ],503    [504      "state_of_incorporation",505      "VARCHAR"506    ],507    [508      "exchange",509      "VARCHAR"510    ],511    [512      "fiscal_year_end",513      "VARCHAR"514    ],515    [516      "russell_weight_pct",517      "DOUBLE"518    ],519    [520      "shard_node",521      "VARCHAR"522    ]523  ],524  "views": [525    [526      "src_companies",527      "CREATE VIEW src_companies AS SELECT * FROM read_parquet('/Users/simon-pierreboucher/UQO_RESEARCH_DB/data/parquet/companies/companies.parquet');"528    ],529    [530      "src_filings",531      "CREATE VIEW src_filings AS SELECT * FROM read_parquet('/Users/simon-pierreboucher/UQO_RESEARCH_DB/data/parquet/filings/filings.parquet');"532    ],533    [534      "src_sections",535      "CREATE VIEW src_sections AS SELECT * FROM read_parquet('/Users/simon-pierreboucher/UQO_RESEARCH_DB/data/parquet/filing_sections/filing_sections.parquet');"536    ],537    [538      "v_sections",539      "CREATE VIEW v_sections AS WITH parsed AS (SELECT s.section_id, s.accession_number, s.section_name, s.item_number, s.\"text\", s.word_count, f.form_type FROM src_sections AS s INNER JOIN src_filings AS f USING (accession_number) WHERE (NOT ((f.form_type = '10-K') AND (s.accession_number = ANY(SELECT DISTINCT accession_number FROM spid_sections))))), all_sec AS ((SELECT section_id, accession_number, section_name, item_number, \"text\", word_count FROM parsed WHERE (((form_type = '10-K') AND (section_name IN ('business', 'risk_factors', 'properties', 'md_and_a', 'quantitative_disclosures'))) OR (NOT (form_type IN ('10-K'))))) UNION ALL (SELECT section_id, accession_number, section_name, item_number, \"text\", word_count FROM spid_sections)) SELECT s.section_id, s.accession_number, s.section_name, s.item_number, s.\"text\", s.word_count, f.cik, f.ticker, f.company_name AS filing_company, f.form_type, CAST(f.filing_date AS DATE) AS filing_date, f.fiscal_year, co.company_name AS company_name, co.sector, co.sub_industry, co.sic_code, co.state FROM all_sec AS s INNER JOIN src_filings AS f USING (accession_number) LEFT JOIN src_companies AS co ON ((f.cik = co.cik));"540    ]541  ],542  "counts": {543    "extracted_sections": 1123098,544    "project_mentions": 308065,545    "projects": 121099,546    "project_timeline": 308065,547    "spid_sections": 27164548  },549  "ledger_words": [550    1123098,551    3605932059552  ],553  "parquet_files": [554    1342283,555    29.13085581556  ],557  "edgar_filings": [558    [559      "accession_number",560      "VARCHAR"561    ],562    [563      "cik",564      "VARCHAR"565    ],566    [567      "ticker",568      "VARCHAR"569    ],570    [571      "company_name",572      "VARCHAR"573    ],574    [575      "form_type",576      "VARCHAR"577    ],578    [579      "filing_date",580      "DATE"581    ],582    [583      "report_date",584      "DATE"585    ],586    [587      "fiscal_year",588      "INTEGER"589    ],590    [591      "fiscal_quarter",592      "INTEGER"593    ],594    [595      "sec_url",596      "VARCHAR"597    ],598    [599      "local_path",600      "VARCHAR"601    ],602    [603      "primary_document",604      "VARCHAR"605    ],606    [607      "file_size_bytes",608      "BIGINT"609    ],610    [611      "download_status",612      "VARCHAR"613    ],614    [615      "parse_status",616      "VARCHAR"617    ],618    [619      "created_at",620      "TIMESTAMP"621    ],622    [623      "updated_at",624      "TIMESTAMP"625    ]626  ],627  "edgar_filing_sections": [628    [629      "section_id",630      "VARCHAR"631    ],632    [633      "accession_number",634      "VARCHAR"635    ],636    [637      "section_name",638      "VARCHAR"639    ],640    [641      "item_number",642      "VARCHAR"643    ],644    [645      "section_order",646      "INTEGER"647    ],648    [649      "text",650      "VARCHAR"651    ],652    [653      "word_count",654      "INTEGER"655    ],656    [657      "char_count",658      "INTEGER"659    ],660    [661      "created_at",662      "TIMESTAMP"663    ]664  ],665  "edgar_companies": [666    [667      "cik",668      "VARCHAR"669    ],670    [671      "ticker",672      "VARCHAR"673    ],674    [675      "company_name",676      "VARCHAR"677    ],678    [679      "sector",680      "VARCHAR"681    ],682    [683      "sub_industry",684      "VARCHAR"685    ],686    [687      "sic_code",688      "VARCHAR"689    ],690    [691      "state",692      "VARCHAR"693    ],694    [695      "date_added",696      "DATE"697    ],698    [699      "created_at",700      "TIMESTAMP"701    ],702    [703      "updated_at",704      "TIMESTAMP"705    ],706    [707      "in_sp500",708      "BOOLEAN"709    ],710    [711      "in_russell3000",712      "BOOLEAN"713    ],714    [715      "sic_description",716      "VARCHAR"717    ],718    [719      "state_of_incorporation",720      "VARCHAR"721    ],722    [723      "exchange",724      "VARCHAR"725    ],726    [727      "fiscal_year_end",728      "VARCHAR"729    ],730    [731      "russell_weight_pct",732      "DOUBLE"733    ],734    [735      "shard_node",736      "VARCHAR"737    ]738  ],739  "edgar_annual_panel": [740    [741      "cik",742      "VARCHAR"743    ],744    [745      "ticker",746      "VARCHAR"747    ],748    [749      "fiscal_year",750      "INTEGER"751    ],752    [753      "filing_count",754      "BIGINT"755    ],756    [757      "total_chunks",758      "BIGINT"759    ],760    [761      "ai_adoption_mean",762      "DOUBLE"763    ],764    [765      "ai_adoption_max",766      "DOUBLE"767    ],768    [769      "ai_adoption_std",770      "DOUBLE"771    ],772    [773      "ai_adoption_top5pct",774      "DOUBLE"775    ],776    [777      "ai_adoption_wmean",778      "DOUBLE"779    ],780    [781      "ai_disruption_risk_mean",782      "DOUBLE"783    ],784    [785      "ai_disruption_risk_max",786      "DOUBLE"787    ],788    [789      "ai_disruption_risk_std",790      "DOUBLE"791    ],792    [793      "ai_disruption_risk_top5pct",794      "DOUBLE"795    ],796    [797      "ai_disruption_risk_wmean",798      "DOUBLE"799    ],800    [801      "ai_infrastructure_mean",802      "DOUBLE"803    ],804    [805      "ai_infrastructure_max",806      "DOUBLE"807    ],808    [809      "ai_infrastructure_std",810      "DOUBLE"811    ],812    [813      "ai_infrastructure_top5pct",814      "DOUBLE"815    ],816    [817      "ai_infrastructure_wmean",818      "DOUBLE"819    ],820    [821      "esg_commitment_mean",822      "DOUBLE"823    ],824    [825      "esg_commitment_max",826      "DOUBLE"827    ],828    [829      "esg_commitment_std",830      "DOUBLE"831    ],832    [833      "esg_commitment_top5pct",834      "DOUBLE"835    ],836    [837      "esg_commitment_wmean",838      "DOUBLE"839    ],840    [841      "climate_risk_mean",842      "DOUBLE"843    ],844    [845      "climate_risk_max",846      "DOUBLE"847    ],848    [849      "climate_risk_std",850      "DOUBLE"851    ],852    [853      "climate_risk_top5pct",854      "DOUBLE"855    ],856    [857      "climate_risk_wmean",858      "DOUBLE"859    ],860    [861      "cybersecurity_mean",862      "DOUBLE"863    ],864    [865      "cybersecurity_max",866      "DOUBLE"867    ],868    [869      "cybersecurity_std",870      "DOUBLE"871    ],872    [873      "cybersecurity_top5pct",874      "DOUBLE"875    ],876    [877      "cybersecurity_wmean",878      "DOUBLE"879    ],880    [881      "automation_labor_mean",882      "DOUBLE"883    ],884    [885      "automation_labor_max",886      "DOUBLE"887    ],888    [889      "automation_labor_std",890      "DOUBLE"891    ],892    [893      "automation_labor_top5pct",894      "DOUBLE"895    ],896    [897      "automation_labor_wmean",898      "DOUBLE"899    ],900    [901      "macro_risk_mean",902      "DOUBLE"903    ],904    [905      "macro_risk_max",906      "DOUBLE"907    ],908    [909      "macro_risk_std",910      "DOUBLE"911    ],912    [913      "macro_risk_top5pct",914      "DOUBLE"915    ],916    [917      "macro_risk_wmean",918      "DOUBLE"919    ]920  ],921  "edgar_tables": [922    "anchor_embeddings",923    "annual_final",924    "annual_panel",925    "chunk_scores",926    "companies",927    "embeddings_metadata",928    "filings",929    "filing_chunks",930    "filing_scores",931    "filing_sections",932    "processing_log",933    "quarterly_final",934    "quarterly_panel"935  ],936  "temp_ok": true937}
Files · 0dcfa9e5de7aac7ee1626d07548d59e37962b02d
Menu

Theme