diff --git a/web/tests/test_data/alphabet_output.json b/web/tests/test_data/alphabet_output.json index d4d6484..546570e 100644 --- a/web/tests/test_data/alphabet_output.json +++ b/web/tests/test_data/alphabet_output.json @@ -1,11 +1,12 @@ { "cset_id": 796, "country": "United States", + "permid": "5030853586", + "website": "https://abc.xyz/", "description": "Alphabet is a holding company that provides projects with resources, freedom, and focus to make their ideas happen.", "description_source": "crunchbase", "description_link": "https://www.crunchbase.com/organization/alphabet", "description_retrieval_date": "2024-05-16", - "website": "https://abc.xyz/", "crunchbase": { "text": "096694c6-bcd2-a975-b95c-fab77c81d915", "url": "https://www.crunchbase.com/organization/alphabet" @@ -41,7 +42,6 @@ "continent": "North America", "local_logo": "alphabet.png", "aliases": "Alphabet; Alphabet Inc", - "permid": "5030853586", "permid_links": [ { "text": "5030853586", @@ -127,7 +127,6 @@ "articles": { "all_publications": { "counts": [ - 0, 2, 6, 24, @@ -137,6 +136,7 @@ 157, 134, 159, + 0, 0 ], "total": 768, @@ -144,7 +144,6 @@ }, "ai_publications": { "counts": [ - 0, 1, 2, 1, @@ -154,6 +153,7 @@ 29, 31, 29, + 0, 0 ], "total": 136, @@ -161,12 +161,28 @@ }, "ai_publications_growth": { "counts": [], - "isTopResearch": false, - "total": 22.669220945083016 + "total": 20.518683310674415, + "isTopResearch": false }, - "ai_pubs_top_conf": { + "highly_cited_ai_pubs": { "counts": [ + 1, 0, + 0, + 1, + 4, + 4, + 6, + 5, + 10, + 0, + 0 + ], + "total": 31, + "isTopResearch": false + }, + "ai_pubs_top_conf": { + "counts": [ 0, 1, 0, @@ -176,19 +192,14 @@ 11, 11, 4, + 0, 0 ], "total": 32, "isTopResearch": false }, - "ai_pubs_percent": { - "counts": [], - "total": 17.7, - "isTopResearch": false - }, "ai_citation_counts": { "counts": [ - 0, 0, 1, 15, @@ -198,14 +209,14 @@ 1357, 2039, 1820, - 39 + 39, + 0 ], "total": 6087, "isTopResearch": false }, "cv_citation_counts": { "counts": [ - 0, 0, 1, 15, @@ -215,14 +226,14 @@ 1357, 2039, 1820, - 39 + 39, + 0 ], "total": 6087, "isTopResearch": false }, "nlp_citation_counts": { "counts": [ - 0, 0, 1, 15, @@ -232,14 +243,14 @@ 1357, 2039, 1820, - 39 + 39, + 0 ], "total": 6087, "isTopResearch": false }, "robotics_citation_counts": { "counts": [ - 0, 0, 1, 15, @@ -249,50 +260,14 @@ 1357, 2039, 1820, - 39 - ], - "total": 6087, - "isTopResearch": false - }, - "ai_citations_per_article": { - "counts": [ - 0, - 0.0, - 0.5, - 15.0, - 6.428571428571429, - 12.777777777777779, - 30.055555555555557, - 46.793103448275865, - 65.7741935483871, - 62.758620689655174, + 39, 0 ], - "total": 44.75735294117647, + "total": 6087, "isTopResearch": false }, - "highly_cited_ai_pubs": { - "counts": [ - 0, - 1, - 0, - 0, - 1, - 4, - 4, - 6, - 5, - 10, - 0 - ], - "isTopResearch": false, - "total": 31 - }, "cv_publications": { - "citations_per_article": 89.51470588235294, - "growth": 63.16, "counts": [ - 0, 1, 0, 0, @@ -302,14 +277,15 @@ 13, 19, 21, + 0, 0 ], "total": 68, - "isTopResearch": true + "isTopResearch": true, + "growth": 72.23, + "citations_per_article": 89.51470588235294 }, "nlp_publications": { - "citations_per_article": 6087.0, - "growth": -100.0, "counts": [ 0, 0, @@ -317,20 +293,19 @@ 0, 0, 0, - 0, 1, 0, 0, + 0, 0 ], "total": 1, - "isTopResearch": true + "isTopResearch": true, + "growth": -100.0, + "citations_per_article": 6087.0 }, "robotics_publications": { - "citations_per_article": 196.3548387096774, - "growth": 11.11, "counts": [ - 0, 1, 0, 0, @@ -340,16 +315,40 @@ 6, 5, 10, + 0, 0 ], "total": 31, - "isTopResearch": true + "isTopResearch": true, + "growth": 44.44, + "citations_per_article": 196.3548387096774 + }, + "ai_citations_per_article": { + "counts": [ + 0.0, + 0.5, + 15.0, + 6.428571428571429, + 12.777777777777779, + 30.055555555555557, + 46.793103448275865, + 65.7741935483871, + 62.758620689655174, + 0, + 0 + ], + "total": 44.75735294117647, + "isTopResearch": false + }, + "ai_pubs_percent": { + "counts": [], + "total": 17.7, + "isTopResearch": false } }, "patents": { "ai_patents": { "counts": [ - 22, 25, 61, 99, @@ -359,24 +358,24 @@ 198, 64, 0, + 0, 0 ], - "total": 968, + "total": 946, "table": null }, "ai_patents_growth": { "counts": [], - "table": null, - "total": 12.192163477671421 + "total": 27.50449073029718, + "table": null }, "ai_patents_grants": { "counts": [], - "table": null, - "total": 1634 + "total": 1515, + "table": null }, "all_patents": { "counts": [ - 220, 250, 610, 990, @@ -386,14 +385,14 @@ 1980, 640, 0, + 0, 0 ], - "table": null, - "total": 9680 + "total": 9460, + "table": null }, "Physical_Sciences_and_Engineering": { "counts": [ - 1, 1, 2, 1, @@ -403,15 +402,15 @@ 0, 0, 0, + 0, 0 ], + "total": 7, "growth": -100.0, - "total": 8, "table": null }, "Life_Sciences": { "counts": [ - 3, 0, 6, 13, @@ -421,15 +420,15 @@ 27, 5, 0, + 0, 0 ], - "growth": 23.61, - "total": 112, + "total": 109, + "growth": 14.26, "table": "industry" }, "Security__eg_cybersecurity": { "counts": [ - 1, 1, 3, 1, @@ -439,15 +438,15 @@ 4, 0, 0, + 0, 0 ], + "total": 16, "growth": 38.89, - "total": 17, "table": null }, "Transportation": { "counts": [ - 13, 15, 17, 25, @@ -457,15 +456,15 @@ 29, 8, 0, + 0, 0 ], - "growth": -14.75, - "total": 267, + "total": 254, + "growth": 35.25, "table": "industry" }, "Industrial_and_Manufacturing": { "counts": [ - 0, 1, 6, 10, @@ -475,10 +474,11 @@ 21, 3, 0, + 0, 0 ], - "growth": 17.85, "total": 93, + "growth": 44.08, "table": "industry" }, "Education": { @@ -486,17 +486,17 @@ 0, 0, 0, - 0, 1, 3, 1, 1, 0, 0, + 0, 0 ], - "growth": 44.44, "total": 6, + "growth": 66.67, "table": null }, "Document_Mgt_and_Publishing": { @@ -513,13 +513,12 @@ 0, 0 ], - "growth": null, "total": 0, + "growth": null, "table": null }, "Military": { "counts": [ - 0, 0, 1, 0, @@ -529,15 +528,15 @@ 0, 0, 0, + 0, 0 ], - "growth": -100.0, "total": 2, + "growth": null, "table": null }, "Agricultural": { "counts": [ - 0, 0, 0, 2, @@ -547,10 +546,11 @@ 10, 1, 0, + 0, 0 ], - "growth": 114.44, "total": 23, + "growth": 36.67, "table": null }, "Computing_in_Government": { @@ -562,18 +562,17 @@ 0, 0, 0, - 0, 1, 0, + 0, 0 ], - "growth": null, "total": 1, + "growth": null, "table": null }, "Personal_Devices_and_Computing": { "counts": [ - 3, 2, 17, 25, @@ -583,15 +582,15 @@ 43, 6, 0, + 0, 0 ], - "growth": 12.98, - "total": 203, + "total": 200, + "growth": 17.15, "table": "industry" }, "Banking_and_Finance": { "counts": [ - 1, 1, 2, 1, @@ -601,15 +600,15 @@ 0, 1, 0, + 0, 0 ], - "growth": 16.67, - "total": 12, + "total": 11, + "growth": 50.0, "table": null }, "Telecommunications": { "counts": [ - 6, 3, 12, 11, @@ -619,10 +618,11 @@ 23, 5, 0, + 0, 0 ], - "growth": 15.83, - "total": 114, + "total": 108, + "growth": 19.22, "table": "industry" }, "Networks__eg_social_IOT_etc": { @@ -639,13 +639,12 @@ 0, 0 ], - "growth": null, "total": 0, + "growth": null, "table": null }, "Business": { "counts": [ - 0, 4, 3, 4, @@ -655,15 +654,15 @@ 11, 2, 0, + 0, 0 ], - "growth": 31.93, "total": 46, + "growth": 31.93, "table": null }, "Energy_Management": { "counts": [ - 2, 0, 1, 0, @@ -673,15 +672,15 @@ 2, 0, 0, + 0, 0 ], - "growth": -50.0, - "total": 8, + "total": 6, + "growth": -100.0, "table": null }, "Entertainment": { "counts": [ - 1, 0, 1, 3, @@ -691,15 +690,15 @@ 0, 0, 0, + 0, 0 ], - "growth": -50.0, - "total": 10, + "total": 9, + "growth": -27.78, "table": null }, "Nanotechnology": { "counts": [ - 0, 0, 1, 0, @@ -709,15 +708,15 @@ 0, 0, 0, + 0, 0 ], - "growth": null, "total": 1, + "growth": null, "table": null }, "Semiconductors": { "counts": [ - 0, 0, 2, 0, @@ -727,15 +726,15 @@ 0, 0, 0, + 0, 0 ], - "growth": -50.0, "total": 4, + "growth": 0.0, "table": null }, "Language_Processing": { "counts": [ - 1, 0, 2, 3, @@ -745,15 +744,15 @@ 0, 0, 0, + 0, 0 ], - "growth": -87.5, - "total": 11, + "total": 10, + "growth": -47.22, "table": null }, "Speech_Processing": { "counts": [ - 0, 0, 4, 5, @@ -763,15 +762,15 @@ 6, 2, 0, + 0, 0 ], - "growth": 26.11, "total": 29, + "growth": 6.11, "table": null }, "Knowledge_Representation": { "counts": [ - 2, 2, 2, 1, @@ -781,15 +780,15 @@ 3, 1, 0, + 0, 0 ], - "growth": 2.62, - "total": 27, + "total": 25, + "growth": 121.67, "table": null }, "Planning_and_Scheduling": { "counts": [ - 0, 2, 3, 3, @@ -799,15 +798,15 @@ 9, 2, 0, + 0, 0 ], - "growth": 36.67, "total": 37, + "growth": 47.78, "table": "application" }, "Control": { "counts": [ - 14, 15, 18, 37, @@ -817,10 +816,11 @@ 31, 10, 0, + 0, 0 ], - "growth": -17.95, - "total": 317, + "total": 303, + "growth": 22.49, "table": "application" }, "Distributed_AI": { @@ -828,22 +828,21 @@ 0, 0, 0, - 0, 2, 2, 2, 1, 0, 0, + 0, 0 ], - "growth": -16.67, "total": 7, + "growth": 0.0, "table": null }, "Robotics": { "counts": [ - 0, 2, 2, 2, @@ -853,15 +852,15 @@ 0, 0, 0, + 0, 0 ], - "growth": -87.5, "total": 16, + "growth": 41.67, "table": null }, "Computer_Vision": { "counts": [ - 10, 9, 8, 26, @@ -871,15 +870,15 @@ 61, 19, 0, + 0, 0 ], - "growth": 21.13, - "total": 315, + "total": 305, + "growth": 48.49, "table": "application" }, "Analytics_and_Algorithms": { "counts": [ - 3, 0, 3, 11, @@ -889,15 +888,15 @@ 15, 4, 0, + 0, 0 ], - "growth": 10.53, - "total": 78, + "total": 75, + "growth": 22.14, "table": "application" }, "Measuring_and_Testing": { "counts": [ - 9, 5, 7, 13, @@ -907,16 +906,17 @@ 27, 7, 0, + 0, 0 ], - "growth": 0.28, - "total": 153, + "total": 144, + "growth": 39.51, "table": "application" }, "ai_patents_percent": { "counts": [], - "table": null, - "total": 10.0 + "total": 10.0, + "table": null } }, "other_metrics": { @@ -929,4 +929,4 @@ "total": 213 } } -} +} \ No newline at end of file diff --git a/web/tests/test_data/hugging_face_input.json b/web/tests/test_data/hugging_face_input.json deleted file mode 100644 index c19c02e..0000000 --- a/web/tests/test_data/hugging_face_input.json +++ /dev/null @@ -1,860 +0,0 @@ -{ - "cset_id": 1425, - "country": "usa", - "aliases": [ - { - "alias_language": "en", - "alias": "Hugging Face, Inc." - }, - { - "alias_language": "en", - "alias": "Hugging Face Inc" - } - ], - "parent": [], - "children": [], - "non_agg_children": [], - "permid": "5063742076", - "child_permid": [], - "description": "Hugging Face, Inc. is a French-American company based in New York City that develops computation tools for building applications using machine learning. It is most notable for its transformers library built for natural language processing applications and its platform that allows users to share machine learning models and datasets and showcase their work.", - "description_source": "wikipedia", - "description_link": "https://en.wikipedia.org/wiki/Hugging_Face", - "description_retrieval_date": "2024-05-23", - "website": "https://huggingface.co/", - "market": [], - "crunchbase": { - "crunchbase_uuid": "b7947f18-b199-45ac-b7da-66f5c52fcfbc", - "crunchbase_url": "https://www.crunchbase.com/organization/hugging-face" - }, - "child_crunchbase": [], - "linkedin": [ - "https://www.linkedin.com/company/huggingface" - ], - "in_sandp_500": false, - "in_global_big_tech": false, - "in_gen_ai": false, - "ai_pubs": 18, - "cv_pubs": 1, - "nlp_pubs": 15, - "robotics_pubs": 0, - "ai_pubs_by_year": [ - { - "year": 2018, - "num_papers": 2 - }, - { - "year": 2019, - "num_papers": 1 - }, - { - "year": 2020, - "num_papers": 2 - }, - { - "year": 2021, - "num_papers": 5 - }, - { - "year": 2022, - "num_papers": 8 - } - ], - "cv_pubs_by_year": [ - { - "year": 2018, - "num_papers": 0 - }, - { - "year": 2019, - "num_papers": 0 - }, - { - "year": 2020, - "num_papers": 0 - }, - { - "year": 2021, - "num_papers": 0 - }, - { - "year": 2022, - "num_papers": 1 - } - ], - "nlp_pubs_by_year": [ - { - "year": 2018, - "num_papers": 2 - }, - { - "year": 2019, - "num_papers": 1 - }, - { - "year": 2020, - "num_papers": 2 - }, - { - "year": 2021, - "num_papers": 5 - }, - { - "year": 2022, - "num_papers": 5 - } - ], - "robotics_pubs_by_year": [ - { - "year": 2018, - "num_papers": 0 - }, - { - "year": 2019, - "num_papers": 0 - }, - { - "year": 2020, - "num_papers": 0 - }, - { - "year": 2021, - "num_papers": 0 - }, - { - "year": 2022, - "num_papers": 0 - } - ], - "highly_cited_ai_pubs_by_year": [ - { - "year": 2014, - "num_papers": 1 - }, - { - "year": 2015, - "num_papers": 0 - }, - { - "year": 2016, - "num_papers": 0 - }, - { - "year": 2017, - "num_papers": 1 - }, - { - "year": 2018, - "num_papers": 4 - }, - { - "year": 2019, - "num_papers": 4 - }, - { - "year": 2020, - "num_papers": 6 - }, - { - "year": 2021, - "num_papers": 5 - }, - { - "year": 2022, - "num_papers": 10 - } - ], - "ai_pubs_in_top_conferences": 13, - "ai_pubs_in_top_conferences_by_year": [ - { - "year": 2018, - "num_papers": 2 - }, - { - "year": 2019, - "num_papers": 1 - }, - { - "year": 2021, - "num_papers": 3 - }, - { - "year": 2022, - "num_papers": 7 - } - ], - "all_pubs": 22, - "all_pubs_by_year": [ - { - "year": 2018, - "num_papers": 2 - }, - { - "year": 2019, - "num_papers": 1 - }, - { - "year": 2020, - "num_papers": 2 - }, - { - "year": 2021, - "num_papers": 5 - }, - { - "year": 2022, - "num_papers": 13 - } - ], - "short_description": "Hugging Face allows users to build, train, and deploy art models using the reference open source in machine learning.", - "logo_url": "https://res.cloudinary.com/crunchbase-production/image/upload/v1505375959/urhmulzddqdfmlzpk2vn.png", - "stage": "Growth", - "tt1_jobs": 72, - "ai_jobs": 37, - "ai_citation_count_by_year": [ - { - "year": 2019, - "num_papers": 56 - }, - { - "year": 2020, - "num_papers": 361 - }, - { - "year": 2021, - "num_papers": 1467 - }, - { - "year": 2022, - "num_papers": 1086 - }, - { - "year": 2023, - "num_papers": 23 - } - ], - "cv_citation_count_by_year": [ - { - "year": 2019, - "num_papers": 56 - }, - { - "year": 2020, - "num_papers": 361 - }, - { - "year": 2021, - "num_papers": 1467 - }, - { - "year": 2022, - "num_papers": 1086 - }, - { - "year": 2023, - "num_papers": 23 - } - ], - "nlp_citation_count_by_year": [ - { - "year": 2019, - "num_papers": 56 - }, - { - "year": 2020, - "num_papers": 361 - }, - { - "year": 2021, - "num_papers": 1467 - }, - { - "year": 2022, - "num_papers": 1086 - }, - { - "year": 2023, - "num_papers": 23 - } - ], - "robotics_citation_count_by_year": [ - { - "year": 2019, - "num_papers": 56 - }, - { - "year": 2020, - "num_papers": 361 - }, - { - "year": 2021, - "num_papers": 1467 - }, - { - "year": 2022, - "num_papers": 1086 - }, - { - "year": 2023, - "num_papers": 23 - } - ], - "fields": [ - { - "field_name": "Language model", - "field_count": 2 - }, - { - "field_name": "Question answering", - "field_count": 1 - }, - { - "field_name": "Inference", - "field_count": 1 - }, - { - "field_name": "Pruning (morphology)", - "field_count": 1 - }, - { - "field_name": "Artificial neural network", - "field_count": 1 - }, - { - "field_name": "Hierarchical database model", - "field_count": 1 - }, - { - "field_name": "Task (computing)", - "field_count": 1 - }, - { - "field_name": "Natural language", - "field_count": 1 - }, - { - "field_name": "Product of experts", - "field_count": 1 - } - ], - "clusters": [ - { - "cluster_id": 1193, - "cluster_count": 6 - }, - { - "cluster_id": 1621, - "cluster_count": 2 - }, - { - "cluster_id": 4358, - "cluster_count": 1 - }, - { - "cluster_id": 16472, - "cluster_count": 1 - }, - { - "cluster_id": 62049, - "cluster_count": 1 - }, - { - "cluster_id": 3527, - "cluster_count": 1 - }, - { - "cluster_id": 11991, - "cluster_count": 1 - } - ], - "company_references": [ - { - "ref_CSET_id": 101, - "referenced_count": 91 - }, - { - "ref_CSET_id": 87, - "referenced_count": 58 - }, - { - "ref_CSET_id": 163, - "referenced_count": 33 - }, - { - "ref_CSET_id": 184, - "referenced_count": 15 - }, - { - "ref_CSET_id": 319, - "referenced_count": 15 - }, - { - "ref_CSET_id": 115, - "referenced_count": 13 - }, - { - "ref_CSET_id": 127, - "referenced_count": 8 - }, - { - "ref_CSET_id": 23, - "referenced_count": 6 - }, - { - "ref_CSET_id": 1425, - "referenced_count": 5 - }, - { - "ref_CSET_id": 6, - "referenced_count": 3 - }, - { - "ref_CSET_id": 209, - "referenced_count": 2 - }, - { - "ref_CSET_id": 219, - "referenced_count": 2 - }, - { - "ref_CSET_id": 1827, - "referenced_count": 2 - }, - { - "ref_CSET_id": 792, - "referenced_count": 2 - }, - { - "ref_CSET_id": 617, - "referenced_count": 1 - }, - { - "ref_CSET_id": 734, - "referenced_count": 1 - }, - { - "ref_CSET_id": 37, - "referenced_count": 1 - }, - { - "ref_CSET_id": 21, - "referenced_count": 1 - }, - { - "ref_CSET_id": 506, - "referenced_count": 1 - }, - { - "ref_CSET_id": 267, - "referenced_count": 1 - }, - { - "ref_CSET_id": 735, - "referenced_count": 1 - }, - { - "ref_CSET_id": 795, - "referenced_count": 1 - }, - { - "ref_CSET_id": 694, - "referenced_count": 1 - }, - { - "ref_CSET_id": 112, - "referenced_count": 1 - }, - { - "ref_CSET_id": 805, - "referenced_count": 1 - }, - { - "ref_CSET_id": 1962, - "referenced_count": 1 - } - ], - "tasks": [ - { - "referent": "natural_language_processing", - "task_count": 4 - }, - { - "referent": "classification_tasks", - "task_count": 3 - }, - { - "referent": "unsupervised_pre_training", - "task_count": 2 - }, - { - "referent": "multi_task_learning", - "task_count": 2 - }, - { - "referent": "language_identification", - "task_count": 1 - }, - { - "referent": "few_shot_learning", - "task_count": 1 - }, - { - "referent": "out_of_distribution_detection", - "task_count": 1 - }, - { - "referent": "continuous_object_recognition", - "task_count": 1 - }, - { - "referent": "inference_attack", - "task_count": 1 - }, - { - "referent": "classification", - "task_count": 1 - }, - { - "referent": "document_classification", - "task_count": 1 - }, - { - "referent": "document_dating", - "task_count": 1 - }, - { - "referent": "identity_recognition", - "task_count": 1 - }, - { - "referent": "relation_classification", - "task_count": 1 - }, - { - "referent": "named_entity_recognition", - "task_count": 1 - }, - { - "referent": "learning_word_embeddings", - "task_count": 1 - }, - { - "referent": "developmental_learning", - "task_count": 1 - } - ], - "methods": [ - { - "referent": "language_models", - "method_count": 4 - }, - { - "referent": "albert", - "method_count": 1 - }, - { - "referent": "bert", - "method_count": 1 - }, - { - "referent": "hierarchical_vae", - "method_count": 1 - }, - { - "referent": "3d_representations", - "method_count": 1 - }, - { - "referent": "recurrent_neural_networks", - "method_count": 1 - }, - { - "referent": "amsbound", - "method_count": 1 - }, - { - "referent": "vqa_models", - "method_count": 1 - }, - { - "referent": "l1_regularization", - "method_count": 1 - }, - { - "referent": "fine_tuning", - "method_count": 1 - }, - { - "referent": "procan", - "method_count": 1 - }, - { - "referent": "statistical_inference", - "method_count": 1 - }, - { - "referent": "natural_language_processing", - "method_count": 1 - } - ], - "ai_patents": 0, - "all_patents": 0, - "Physical_Sciences_and_Engineering_pats": 0, - "Life_Sciences_pats": 0, - "Security__eg_cybersecurity_pats": 0, - "Transportation_pats": 0, - "Industrial_and_Manufacturing_pats": 0, - "Education_pats": 0, - "Document_Mgt_and_Publishing_pats": 0, - "Military_pats": 0, - "Agricultural_pats": 0, - "Computing_in_Government_pats": 0, - "Personal_Devices_and_Computing_pats": 0, - "Banking_and_Finance_pats": 0, - "Telecommunications_pats": 0, - "Networks__eg_social_IOT_etc_pats": 0, - "Business_pats": 0, - "Energy_Management_pats": 0, - "Entertainment_pats": 0, - "Nanotechnology_pats": 0, - "Semiconductors_pats": 0, - "Language_Processing_pats": 0, - "Speech_Processing_pats": 0, - "Knowledge_Representation_pats": 0, - "Planning_and_Scheduling_pats": 0, - "Control_pats": 0, - "Distributed_AI_pats": 0, - "Robotics_pats": 0, - "Computer_Vision_pats": 0, - "Analytics_and_Algorithms_pats": 0, - "Measuring_and_Testing_pats": 0, - "Logic_Programming_pats": 0, - "Fuzzy_Logic_pats": 0, - "Probabilistic_Reasoning_pats": 0, - "Ontology_Engineering_pats": 0, - "Machine_Learning_pats": 0, - "Search_Methods_pats": 0, - "ai_patents_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "all_patents_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Physical_Sciences_and_Engineering_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Life_Sciences_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Security__eg_cybersecurity_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Transportation_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Industrial_and_Manufacturing_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Education_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Document_Mgt_and_Publishing_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Military_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Agricultural_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Computing_in_Government_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Personal_Devices_and_Computing_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Banking_and_Finance_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Telecommunications_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Networks__eg_social_IOT_etc_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Business_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Energy_Management_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Entertainment_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Nanotechnology_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Semiconductors_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Language_Processing_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Speech_Processing_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Knowledge_Representation_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Planning_and_Scheduling_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Control_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Distributed_AI_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Robotics_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Computer_Vision_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Analytics_and_Algorithms_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Measuring_and_Testing_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Logic_Programming_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Fuzzy_Logic_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Probabilistic_Reasoning_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Ontology_Engineering_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Machine_Learning_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "Search_Methods_pats_by_year": [ - { - "priority_year": null, - "num_patents": null - } - ], - "name": "Hugging Face", - "patent_name": "hugging face" -} diff --git a/web/tests/test_data/hugging_face_output.json b/web/tests/test_data/hugging_face_output.json deleted file mode 100644 index 4efab46..0000000 --- a/web/tests/test_data/hugging_face_output.json +++ /dev/null @@ -1,886 +0,0 @@ -{ - "cset_id": 1425, - "country": "United States", - "description": "Hugging Face, Inc. is a French-American company based in New York City that develops computation tools for building applications using machine learning. It is most notable for its transformers library built for natural language processing applications and its platform that allows users to share machine learning models and datasets and showcase their work.", - "description_source": "wikipedia", - "description_link": "https://en.wikipedia.org/wiki/Hugging_Face", - "description_retrieval_date": "2024-05-23", - "website": "https://huggingface.co/", - "crunchbase": { - "text": "b7947f18-b199-45ac-b7da-66f5c52fcfbc", - "url": "https://www.crunchbase.com/organization/hugging-face" - }, - "child_crunchbase": [], - "linkedin": [ - "https://www.linkedin.com/company/huggingface" - ], - "stage": "Growth", - "name": "Hugging Face", - "patent_name": "hugging face", - "continent": "North America", - "local_logo": "hugging_face.png", - "aliases": "Hugging Face; Hugging Face Inc; Hugging Face, Inc", - "permid": "5063742076", - "permid_links": [ - { - "text": "5063742076", - "url": "https://permid.org/1-5063742076" - } - ], - "parent_info": null, - "agg_child_info": null, - "unagg_child_info": null, - "market": [], - "groups": { - "sp500": false, - "globalBigTech": false, - "genAI": false - }, - "company_references": [ - { - "ref_CSET_id": 101, - "referenced_count": 91 - }, - { - "ref_CSET_id": 87, - "referenced_count": 58 - }, - { - "ref_CSET_id": 163, - "referenced_count": 33 - }, - { - "ref_CSET_id": 184, - "referenced_count": 15 - }, - { - "ref_CSET_id": 319, - "referenced_count": 15 - }, - { - "ref_CSET_id": 115, - "referenced_count": 13 - }, - { - "ref_CSET_id": 127, - "referenced_count": 8 - }, - { - "ref_CSET_id": 23, - "referenced_count": 6 - }, - { - "ref_CSET_id": 1425, - "referenced_count": 5 - }, - { - "ref_CSET_id": 6, - "referenced_count": 3 - } - ], - "articles": { - "all_publications": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 2, - 1, - 2, - 5, - 13, - 0 - ], - "total": 23, - "isTopResearch": false - }, - "ai_publications": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 2, - 1, - 2, - 5, - 8, - 0 - ], - "total": 18, - "isTopResearch": false - }, - "ai_publications_growth": { - "counts": [], - "total": 66.66666666666667, - "isTopResearch": false - }, - "ai_pubs_top_conf": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 2, - 1, - 0, - 3, - 7, - 0 - ], - "total": 13, - "isTopResearch": false - }, - "ai_pubs_percent": { - "counts": [], - "total": 78.3, - "isTopResearch": false - }, - "ai_citation_counts": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 56, - 361, - 1467, - 1086, - 23 - ], - "total": 2993, - "isTopResearch": false - }, - "cv_citation_counts": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 56, - 361, - 1467, - 1086, - 23 - ], - "total": 2993, - "isTopResearch": false - }, - "nlp_citation_counts": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 56, - 361, - 1467, - 1086, - 23 - ], - "total": 2993, - "isTopResearch": false - }, - "robotics_citation_counts": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 56, - 361, - 1467, - 1086, - 23 - ], - "total": 2993, - "isTopResearch": false - }, - "ai_citations_per_article": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0.0, - 56.0, - 180.5, - 293.4, - 135.75, - 0 - ], - "total": 166.27777777777777, - "isTopResearch": false - }, - "highly_cited_ai_pubs": { - "counts": [ - 0, - 1, - 0, - 0, - 1, - 4, - 4, - 6, - 5, - 10, - 0 - ], - "isTopResearch": false, - "total": 31 - }, - "cv_publications": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 1, - 0 - ], - "total": 1, - "growth": null, - "citations_per_article": 2993.0, - "isTopResearch": true - }, - "nlp_publications": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 2, - 1, - 2, - 5, - 5, - 0 - ], - "total": 15, - "growth": 66.67, - "citations_per_article": 199.53333333333333, - "isTopResearch": true - }, - "robotics_publications": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "citations_per_article": 0, - "isTopResearch": true - } - }, - "patents": { - "ai_patents": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "table": null - }, - "ai_patents_growth": { - "counts": [], - "table": null, - "total": null - }, - "ai_patents_grants": { - "counts": [], - "table": null, - "total": 0 - }, - "all_patents": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "table": null, - "total": 0 - }, - "Physical_Sciences_and_Engineering": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": "industry" - }, - "Life_Sciences": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": "industry" - }, - "Security__eg_cybersecurity": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": "industry" - }, - "Transportation": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": "industry" - }, - "Industrial_and_Manufacturing": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": "industry" - }, - "Education": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Document_Mgt_and_Publishing": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Military": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Agricultural": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Computing_in_Government": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Personal_Devices_and_Computing": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Banking_and_Finance": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Telecommunications": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Networks__eg_social_IOT_etc": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Business": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Energy_Management": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Entertainment": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Nanotechnology": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Semiconductors": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Language_Processing": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": "application" - }, - "Speech_Processing": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": "application" - }, - "Knowledge_Representation": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": "application" - }, - "Planning_and_Scheduling": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": "application" - }, - "Control": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": "application" - }, - "Distributed_AI": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Robotics": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Computer_Vision": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Analytics_and_Algorithms": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "Measuring_and_Testing": { - "counts": [ - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0, - 0 - ], - "total": 0, - "growth": null, - "table": null - }, - "ai_patents_percent": { - "counts": [], - "table": null, - "total": 0 - } - }, - "other_metrics": { - "tt1_jobs": { - "counts": null, - "total": 72 - }, - "ai_jobs": { - "counts": null, - "total": 37 - } - } -} diff --git a/web/tests/test_retrieve_data.py b/web/tests/test_retrieve_data.py index 0ab45cd..a34f607 100644 --- a/web/tests/test_retrieve_data.py +++ b/web/tests/test_retrieve_data.py @@ -152,9 +152,6 @@ def test_get_yearly_counts(self): def test_alphabet(self): self.run_clean_row_test("alphabet") - def test_hugging_face(self): - self.run_clean_row_test("hugging_face") - def run_clean_row_test(self, company): market_key_to_link = {} with open(EXCHANGE_LINK_FI) as f: @@ -174,7 +171,7 @@ def run_clean_row_test(self, company): def test_get_growth(self): self.assertEqual(18.333333333333336, get_growth([0, 1, 2, 1, 0, 5, 6, 7, 8, 9])) - self.assertEqual(-40.0, get_growth([0, 1, 2, 1, 0, 5, 6, 7, 8, 9], is_patents=True)) + self.assertEqual(-16.666666666666668, get_growth([0, 1, 2, 1, 0, 5, 6, 7, 8, 9], is_patents=True)) def test_get_average_group_data(self): with open(os.path.join(self.DATA_DIR, "get_average_group_data_input.json")) as f: