From 3615b054f01c74e03f7c4d6d9b80ae655ac63d34 Mon Sep 17 00:00:00 2001 From: Mark Eaton Date: Sun, 20 Jul 2025 01:55:49 -0400 Subject: [PATCH] add names count, blacken --- parse.py | 73 ++++++++++++++++++++++++++++++++++++++++++++++---------- uv.lock | 53 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 113 insertions(+), 13 deletions(-) diff --git a/parse.py b/parse.py index 3b04451..dda63e0 100644 --- a/parse.py +++ b/parse.py @@ -6,16 +6,52 @@ import numpy as np from collections import Counter from pprint import pprint -stop_words = ['of', 'and', 'the', 'we', 'in', 'to', 'what', 'a', 'on', 'an', - 'do', 'for', 'with', 'is', 'it', 'that', 'this', 'as', 'by', - 'are', 'using', 'from', 'how', 'has', 'be', 'or', 'can', 'our', - 'at', 'why', 'when', 'introduction', 'your', 'through'] -file_path = 'data.csv' +stop_words = [ + "of", + "and", + "the", + "we", + "in", + "to", + "what", + "a", + "on", + "an", + "do", + "for", + "with", + "is", + "it", + "that", + "this", + "as", + "by", + "are", + "using", + "from", + "how", + "has", + "be", + "or", + "can", + "our", + "at", + "why", + "when", + "introduction", + "your", + "through", + "et", + "al.", + "&", + "", +] +file_path = "data.csv" data = [] def parse_csv(file_path): - with open(file_path, 'r') as file: + with open(file_path, "r") as file: reader = csv.reader(file) for row in reader: data.append(row) @@ -35,10 +71,10 @@ def extract_title_keywords(data): title_keywords = [] re_words = [] for row in data: - raw_words = row[2].split(' ') + raw_words = row[2].split(" ") row_words = [] for word in raw_words: - re_word = re.sub(r'[^a-zA-Z\-]', '', word.lower()) + re_word = re.sub(r"[^a-zA-Z\-]", "", word.lower()) if re_word not in stop_words: re_words.append(re_word) row_words.append(re_word) @@ -50,22 +86,33 @@ def print_title_keywords(data): title_keywords = extract_title_keywords(data) title_keywords = [word[0] for word in title_keywords] count_title_words = Counter(title_keywords).most_common(20) - pprint(count_title_words) + pprint(count_title_words) def histogram(data): - dates = [] + dates = [] for row in data: dates.append(int(row[4])) - years = range(min(dates), max(dates)+2) + years = range(min(dates), max(dates) + 2) plt.hist(dates, bins=years) plt.show() -if __name__ == '__main__': +def names(data): + names = [] + for row in data: + name_parts = row[1].split(" ") + for name in name_parts: + if name not in stop_words: + names.append(name) + count_names = Counter(names).most_common(20) + pprint(count_names) + + +if __name__ == "__main__": parse_csv(file_path) data = data[1:] extract_journal_titles(data) print_title_keywords(data) - dash_viz(data) + names(data) histogram(data) diff --git a/uv.lock b/uv.lock index 69c2078..3d3a300 100644 --- a/uv.lock +++ b/uv.lock @@ -7,6 +7,7 @@ name = "1article" version = "0.1.0" source = { virtual = "." } dependencies = [ + { name = "black" }, { name = "dash" }, { name = "dash-cytoscape" }, { name = "matplotlib" }, @@ -15,12 +16,37 @@ dependencies = [ [package.metadata] requires-dist = [ + { name = "black", specifier = ">=25.1.0" }, { name = "dash", specifier = ">=3.1.1" }, { name = "dash-cytoscape", specifier = ">=1.0.2" }, { name = "matplotlib", specifier = ">=3.10.3" }, { name = "pyqt6", specifier = ">=6.9.1" }, ] +[[package]] +name = "black" +version = "25.1.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "click" }, + { name = "mypy-extensions" }, + { name = "packaging" }, + { name = "pathspec" }, + { name = "platformdirs" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/94/49/26a7b0f3f35da4b5a65f081943b7bcd22d7002f5f0fb8098ec1ff21cb6ef/black-25.1.0.tar.gz", hash = "sha256:33496d5cd1222ad73391352b4ae8da15253c5de89b93a80b3e2c8d9a19ec2666", size = 649449, upload-time = "2025-01-29T04:15:40.373Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/83/71/3fe4741df7adf015ad8dfa082dd36c94ca86bb21f25608eb247b4afb15b2/black-25.1.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:4b60580e829091e6f9238c848ea6750efed72140b91b048770b64e74fe04908b", size = 1650988, upload-time = "2025-01-29T05:37:16.707Z" }, + { url = "https://files.pythonhosted.org/packages/13/f3/89aac8a83d73937ccd39bbe8fc6ac8860c11cfa0af5b1c96d081facac844/black-25.1.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:1e2978f6df243b155ef5fa7e558a43037c3079093ed5d10fd84c43900f2d8ecc", size = 1453985, upload-time = "2025-01-29T05:37:18.273Z" }, + { url = "https://files.pythonhosted.org/packages/6f/22/b99efca33f1f3a1d2552c714b1e1b5ae92efac6c43e790ad539a163d1754/black-25.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3b48735872ec535027d979e8dcb20bf4f70b5ac75a8ea99f127c106a7d7aba9f", size = 1783816, upload-time = "2025-01-29T04:18:33.823Z" }, + { url = "https://files.pythonhosted.org/packages/18/7e/a27c3ad3822b6f2e0e00d63d58ff6299a99a5b3aee69fa77cd4b0076b261/black-25.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:ea0213189960bda9cf99be5b8c8ce66bb054af5e9e861249cd23471bd7b0b3ba", size = 1440860, upload-time = "2025-01-29T04:19:12.944Z" }, + { url = "https://files.pythonhosted.org/packages/98/87/0edf98916640efa5d0696e1abb0a8357b52e69e82322628f25bf14d263d1/black-25.1.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:8f0b18a02996a836cc9c9c78e5babec10930862827b1b724ddfe98ccf2f2fe4f", size = 1650673, upload-time = "2025-01-29T05:37:20.574Z" }, + { url = "https://files.pythonhosted.org/packages/52/e5/f7bf17207cf87fa6e9b676576749c6b6ed0d70f179a3d812c997870291c3/black-25.1.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:afebb7098bfbc70037a053b91ae8437c3857482d3a690fefc03e9ff7aa9a5fd3", size = 1453190, upload-time = "2025-01-29T05:37:22.106Z" }, + { url = "https://files.pythonhosted.org/packages/e3/ee/adda3d46d4a9120772fae6de454c8495603c37c4c3b9c60f25b1ab6401fe/black-25.1.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:030b9759066a4ee5e5aca28c3c77f9c64789cdd4de8ac1df642c40b708be6171", size = 1782926, upload-time = "2025-01-29T04:18:58.564Z" }, + { url = "https://files.pythonhosted.org/packages/cc/64/94eb5f45dcb997d2082f097a3944cfc7fe87e071907f677e80788a2d7b7a/black-25.1.0-cp313-cp313-win_amd64.whl", hash = "sha256:a22f402b410566e2d1c950708c77ebf5ebd5d0d88a6a2e87c86d9fb48afa0d18", size = 1442613, upload-time = "2025-01-29T04:19:27.63Z" }, + { url = "https://files.pythonhosted.org/packages/09/71/54e999902aed72baf26bca0d50781b01838251a462612966e9fc4891eadd/black-25.1.0-py3-none-any.whl", hash = "sha256:95e8176dae143ba9097f351d174fdaf0ccd29efb414b362ae3fd72bf0f710717", size = 207646, upload-time = "2025-01-29T04:15:38.082Z" }, +] + [[package]] name = "blinker" version = "1.9.0" @@ -384,6 +410,15 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/1b/92/9a45c91089c3cf690b5badd4be81e392ff086ccca8a1d4e3a08463d8a966/matplotlib-3.10.3-cp313-cp313t-win_amd64.whl", hash = "sha256:4f23ffe95c5667ef8a2b56eea9b53db7f43910fa4a2d5472ae0f72b64deab4d5", size = 8139044, upload-time = "2025-05-08T19:10:44.551Z" }, ] +[[package]] +name = "mypy-extensions" +version = "1.1.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/a2/6e/371856a3fb9d31ca8dac321cda606860fa4548858c0cc45d9d1d4ca2628b/mypy_extensions-1.1.0.tar.gz", hash = "sha256:52e68efc3284861e772bbcd66823fde5ae21fd2fdb51c62a211403730b916558", size = 6343, upload-time = "2025-04-22T14:54:24.164Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/79/7b/2c79738432f5c924bef5071f933bcc9efd0473bac3b4aa584a6f7c1c8df8/mypy_extensions-1.1.0-py3-none-any.whl", hash = "sha256:1be4cccdb0f2482337c4743e60421de3a356cd97508abadd57d47403e94f5505", size = 4963, upload-time = "2025-04-22T14:54:22.983Z" }, +] + [[package]] name = "narwhals" version = "1.47.1" @@ -452,6 +487,15 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/20/12/38679034af332785aac8774540895e234f4d07f7545804097de4b666afd8/packaging-25.0-py3-none-any.whl", hash = "sha256:29572ef2b1f17581046b3a2227d5c611fb25ec70ca1ba8554b24b0e69331a484", size = 66469, upload-time = "2025-04-19T11:48:57.875Z" }, ] +[[package]] +name = "pathspec" +version = "0.12.1" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/ca/bc/f35b8446f4531a7cb215605d100cd88b7ac6f44ab3fc94870c120ab3adbf/pathspec-0.12.1.tar.gz", hash = "sha256:a482d51503a1ab33b1c67a6c3813a26953dbdc71c31dacaef9a838c4e29f5712", size = 51043, upload-time = "2023-12-10T22:30:45Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/cc/20/ff623b09d963f88bfde16306a54e12ee5ea43e9b597108672ff3a408aad6/pathspec-0.12.1-py3-none-any.whl", hash = "sha256:a0d503e138a4c123b27490a4f7beda6a01c6f288df0e4a8b79c7eb0dc7b4cc08", size = 31191, upload-time = "2023-12-10T22:30:43.14Z" }, +] + [[package]] name = "pillow" version = "11.2.1" @@ -493,6 +537,15 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/67/32/32dc030cfa91ca0fc52baebbba2e009bb001122a1daa8b6a79ad830b38d3/pillow-11.2.1-cp313-cp313t-win_arm64.whl", hash = "sha256:225c832a13326e34f212d2072982bb1adb210e0cc0b153e688743018c94a2681", size = 2417234, upload-time = "2025-04-12T17:49:08.399Z" }, ] +[[package]] +name = "platformdirs" +version = "4.3.8" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/fe/8b/3c73abc9c759ecd3f1f7ceff6685840859e8070c4d947c93fae71f6a0bf2/platformdirs-4.3.8.tar.gz", hash = "sha256:3d512d96e16bcb959a814c9f348431070822a6496326a4be0911c40b5a74c2bc", size = 21362, upload-time = "2025-05-07T22:47:42.121Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/fe/39/979e8e21520d4e47a0bbe349e2713c0aac6f3d853d0e5b34d76206c439aa/platformdirs-4.3.8-py3-none-any.whl", hash = "sha256:ff7059bb7eb1179e2685604f4aaf157cfd9535242bd23742eadc3c13542139b4", size = 18567, upload-time = "2025-05-07T22:47:40.376Z" }, +] + [[package]] name = "plotly" version = "6.2.0"