update

internet_ml/NLP/no_context/QA.py

@@ -1,3 +1,5 @@
+from typing import Any
+
 import sys
 from pathlib import Path
 
@@ -6,8 +8,10 @@ from transformers import pipeline
 sys.path.append(str(Path(__file__).parent.parent.parent) + "/tools/NLP/data")
 import internet
 
-qa_model = pipeline("question-answering")
+QA_MODEL = pipeline("question-answering")
-question = "Who is Rishi Sunak"
+
-a = str(internet.google(question)[0])
+
-print(qa_model(question=question, context=a))
+def answer(query: str) -> Any:
-## {'answer': 'İstanbul', 'end': 39, 'score': 0.953, 'start': 31}
+    global QA_MODEL
+    results = internet.google(query)
+    return (QA_MODEL(question=query, context=str(results[0])), results[1])

internet_ml/NLP/no_context/test.py

@@ -1,4 +0,0 @@
-import sys
-from pathlib import Path
-
-print()

internet_ml/tools/NLP/data/internet.py

@@ -81,6 +81,7 @@ URL_EXTRACTOR = URLExtract()
 
 
 def google(query: str) -> tuple[list[str], list[str]]:
+    global URL_EXTRACTOR
     if "Thamognya" in query or "thamognya" in query:
         return (["The smartest person in the world"], ["I decided it"])
     links_in_text: list[str] = URL_EXTRACTOR.find_urls(query)

poetry.lock

@@ -153,6 +153,18 @@ files = [
 [package.dependencies]
 frozenlist = ">=1.1.0"
 
+[[package]]
+name = "anyascii"
+version = "0.3.1"
+description = "Unicode to ASCII transliteration"
+category = "main"
+optional = false
+python-versions = ">=3.3"
+files = [
+    {file = "anyascii-0.3.1-py3-none-any.whl", hash = "sha256:8707d3185017435933360462a65e2c70a4818490745804f38a5ca55e59eb56a0"},
+    {file = "anyascii-0.3.1.tar.gz", hash = "sha256:dedf57728206e286c91eed7c759505a5e45c8cd01367dd40c2f7248bb15c11f6"},
+]
+
 [[package]]
 name = "astroid"
 version = "2.12.13"
@@ -226,6 +238,25 @@ test = ["beautifulsoup4 (>=4.8.0)", "coverage (>=4.5.4)", "fixtures (>=3.0.0)",
 toml = ["toml"]
 yaml = ["PyYAML"]
 
+[[package]]
+name = "beautifulsoup4"
+version = "4.11.1"
+description = "Screen-scraping library"
+category = "main"
+optional = false
+python-versions = ">=3.6.0"
+files = [
+    {file = "beautifulsoup4-4.11.1-py3-none-any.whl", hash = "sha256:58d5c3d29f5a36ffeb94f02f0d786cd53014cf9b3b3951d42e0080d8a9498d30"},
+    {file = "beautifulsoup4-4.11.1.tar.gz", hash = "sha256:ad9aa55b65ef2808eb405f46cf74df7fcb7044d5cbc26487f96eb2ef2e436693"},
+]
+
+[package.dependencies]
+soupsieve = ">1.2"
+
+[package.extras]
+html5lib = ["html5lib"]
+lxml = ["lxml"]
+
 [[package]]
 name = "black"
 version = "23.1a1"
@@ -261,6 +292,59 @@ d = ["aiohttp (>=3.7.4)"]
 jupyter = ["ipython (>=7.8.0)", "tokenize-rt (>=3.2.0)"]
 uvloop = ["uvloop (>=0.15.2)"]
 
+[[package]]
+name = "blis"
+version = "0.7.9"
+description = "The Blis BLAS-like linear algebra library, as a self-contained C-extension."
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+    {file = "blis-0.7.9-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:b3ea73707a7938304c08363a0b990600e579bfb52dece7c674eafac4bf2df9f7"},
+    {file = "blis-0.7.9-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e85993364cae82707bfe7e637bee64ec96e232af31301e5c81a351778cb394b9"},
+    {file = "blis-0.7.9-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d205a7e69523e2bacdd67ea906b82b84034067e0de83b33bd83eb96b9e844ae3"},
+    {file = "blis-0.7.9-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b9737035636452fb6d08e7ab79e5a9904be18a0736868a129179cd9f9ab59825"},
+    {file = "blis-0.7.9-cp310-cp310-win_amd64.whl", hash = "sha256:d3882b4f44a33367812b5e287c0690027092830ffb1cce124b02f64e761819a4"},
+    {file = "blis-0.7.9-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3dbb44311029263a6f65ed55a35f970aeb1d20b18bfac4c025de5aadf7889a8c"},
+    {file = "blis-0.7.9-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:6fd5941bd5a21082b19d1dd0f6d62cd35609c25eb769aa3457d9877ef2ce37a9"},
+    {file = "blis-0.7.9-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:97ad55e9ef36e4ff06b35802d0cf7bfc56f9697c6bc9427f59c90956bb98377d"},
+    {file = "blis-0.7.9-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f7b6315d7b1ac5546bc0350f5f8d7cc064438d23db19a5c21aaa6ae7d93c1ab5"},
+    {file = "blis-0.7.9-cp311-cp311-win_amd64.whl", hash = "sha256:5fd46c649acd1920482b4f5556d1c88693cba9bf6a494a020b00f14b42e1132f"},
+    {file = "blis-0.7.9-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:db2959560dcb34e912dad0e0d091f19b05b61363bac15d78307c01334a4e5d9d"},
+    {file = "blis-0.7.9-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c0521231bc95ab522f280da3bbb096299c910a62cac2376d48d4a1d403c54393"},
+    {file = "blis-0.7.9-cp36-cp36m-win_amd64.whl", hash = "sha256:d811e88480203d75e6e959f313fdbf3326393b4e2b317067d952347f5c56216e"},
+    {file = "blis-0.7.9-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:5cb1db88ab629ccb39eac110b742b98e3511d48ce9caa82ca32609d9169a9c9c"},
+    {file = "blis-0.7.9-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c399a03de4059bf8e700b921f9ff5d72b2a86673616c40db40cd0592051bdd07"},
+    {file = "blis-0.7.9-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d4eb70a79562a211bd2e6b6db63f1e2eed32c0ab3e9ef921d86f657ae8375845"},
+    {file = "blis-0.7.9-cp37-cp37m-win_amd64.whl", hash = "sha256:3e3f95e035c7456a1f5f3b5a3cfe708483a00335a3a8ad2211d57ba4d5f749a5"},
+    {file = "blis-0.7.9-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:179037cb5e6744c2e93b6b5facc6e4a0073776d514933c3db1e1f064a3253425"},
+    {file = "blis-0.7.9-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:d0e82a6e0337d5231129a4e8b36978fa7b973ad3bb0257fd8e3714a9b35ceffd"},
+    {file = "blis-0.7.9-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6d12475e588a322e66a18346a3faa9eb92523504042e665c193d1b9b0b3f0482"},
+    {file = "blis-0.7.9-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4d5755ef37a573647be62684ca1545698879d07321f1e5b89a4fd669ce355eb0"},
+    {file = "blis-0.7.9-cp38-cp38-win_amd64.whl", hash = "sha256:b8a1fcd2eb267301ab13e1e4209c165d172cdf9c0c9e08186a9e234bf91daa16"},
+    {file = "blis-0.7.9-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8275f6b6eee714b85f00bf882720f508ed6a60974bcde489715d37fd35529da8"},
+    {file = "blis-0.7.9-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:7417667c221e29fe8662c3b2ff9bc201c6a5214bbb5eb6cc290484868802258d"},
+    {file = "blis-0.7.9-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b5f4691bf62013eccc167c38a85c09a0bf0c6e3e80d4c2229cdf2668c1124eb0"},
+    {file = "blis-0.7.9-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f5cec812ee47b29107eb36af9b457be7191163eab65d61775ed63538232c59d5"},
+    {file = "blis-0.7.9-cp39-cp39-win_amd64.whl", hash = "sha256:d81c3f627d33545fc25c9dcb5fee66c476d89288a27d63ac16ea63453401ffd5"},
+    {file = "blis-0.7.9.tar.gz", hash = "sha256:29ef4c25007785a90ffc2f0ab3d3bd3b75cd2d7856a9a482b7d0dac8d511a09d"},
+]
+
+[package.dependencies]
+numpy = ">=1.15.0"
+
+[[package]]
+name = "catalogue"
+version = "2.0.8"
+description = "Super lightweight function registries for your library"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "catalogue-2.0.8-py3-none-any.whl", hash = "sha256:2d786e229d8d202b4f8a2a059858e45a2331201d831e39746732daa704b99f69"},
+    {file = "catalogue-2.0.8.tar.gz", hash = "sha256:b325c77659208bfb6af1b0d93b1a1aa4112e1bb29a4c5ced816758a722f0e388"},
+]
+
 [[package]]
 name = "certifi"
 version = "2022.12.7"
@@ -342,6 +426,36 @@ files = [
 [package.extras]
 test = ["flake8 (==3.7.8)", "hypothesis (==3.55.3)"]
 
+[[package]]
+name = "confection"
+version = "0.0.3"
+description = "The sweetest config system for Python"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "confection-0.0.3-py3-none-any.whl", hash = "sha256:51af839c1240430421da2b248541ebc95f9d0ee385bcafa768b8acdbd2b0111d"},
+    {file = "confection-0.0.3.tar.gz", hash = "sha256:4fec47190057c43c9acbecb8b1b87a9bf31c469caa0d6888a5b9384432fdba5a"},
+]
+
+[package.dependencies]
+pydantic = ">=1.7.4,<1.8 || >1.8,<1.8.1 || >1.8.1,<1.11.0"
+srsly = ">=2.4.0,<3.0.0"
+
+[[package]]
+name = "contractions"
+version = "0.1.73"
+description = "Fixes contractions such as `you're` to you `are`"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+    {file = "contractions-0.1.73-py2.py3-none-any.whl", hash = "sha256:398cee3b69c37307a50dce4930d961a0f42b48fdae9562df73bed5683008d3bc"},
+]
+
+[package.dependencies]
+textsearch = ">=0.0.21"
+
 [[package]]
 name = "coverage"
 version = "7.0.1"
@@ -424,6 +538,44 @@ files = [
 [package.dependencies]
 coverage = "*"
 
+[[package]]
+name = "cymem"
+version = "2.0.7"
+description = "Manage calls to calloc/free through Cython"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+    {file = "cymem-2.0.7-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:4981fc9182cc1fe54bfedf5f73bfec3ce0c27582d9be71e130c46e35958beef0"},
+    {file = "cymem-2.0.7-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:42aedfd2e77aa0518a24a2a60a2147308903abc8b13c84504af58539c39e52a3"},
+    {file = "cymem-2.0.7-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c183257dc5ab237b664f64156c743e788f562417c74ea58c5a3939fe2d48d6f6"},
+    {file = "cymem-2.0.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d18250f97eeb13af2e8b19d3cefe4bf743b963d93320b0a2e729771410fd8cf4"},
+    {file = "cymem-2.0.7-cp310-cp310-win_amd64.whl", hash = "sha256:864701e626b65eb2256060564ed8eb034ebb0a8f14ce3fbef337e88352cdee9f"},
+    {file = "cymem-2.0.7-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:314273be1f143da674388e0a125d409e2721fbf669c380ae27c5cbae4011e26d"},
+    {file = "cymem-2.0.7-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:df543a36e7000808fe0a03d92fd6cd8bf23fa8737c3f7ae791a5386de797bf79"},
+    {file = "cymem-2.0.7-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9e5e1b7de7952d89508d07601b9e95b2244e70d7ef60fbc161b3ad68f22815f8"},
+    {file = "cymem-2.0.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2aa33f1dbd7ceda37970e174c38fd1cf106817a261aa58521ba9918156868231"},
+    {file = "cymem-2.0.7-cp311-cp311-win_amd64.whl", hash = "sha256:10178e402bb512b2686b8c2f41f930111e597237ca8f85cb583ea93822ef798d"},
+    {file = "cymem-2.0.7-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a2971b7da5aa2e65d8fbbe9f2acfc19ff8e73f1896e3d6e1223cc9bf275a0207"},
+    {file = "cymem-2.0.7-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:85359ab7b490e6c897c04863704481600bd45188a0e2ca7375eb5db193e13cb7"},
+    {file = "cymem-2.0.7-cp36-cp36m-win_amd64.whl", hash = "sha256:0ac45088abffbae9b7db2c597f098de51b7e3c1023cb314e55c0f7f08440cf66"},
+    {file = "cymem-2.0.7-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:26e5d5c6958855d2fe3d5629afe85a6aae5531abaa76f4bc21b9abf9caaccdfe"},
+    {file = "cymem-2.0.7-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:011039e12d3144ac1bf3a6b38f5722b817f0d6487c8184e88c891b360b69f533"},
+    {file = "cymem-2.0.7-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6f9e63e5ad4ed6ffa21fd8db1c03b05be3fea2f32e32fdace67a840ea2702c3d"},
+    {file = "cymem-2.0.7-cp37-cp37m-win_amd64.whl", hash = "sha256:5ea6b027fdad0c3e9a4f1b94d28d213be08c466a60c72c633eb9db76cf30e53a"},
+    {file = "cymem-2.0.7-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:4302df5793a320c4f4a263c7785d2fa7f29928d72cb83ebeb34d64a610f8d819"},
+    {file = "cymem-2.0.7-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:24b779046484674c054af1e779c68cb224dc9694200ac13b22129d7fb7e99e6d"},
+    {file = "cymem-2.0.7-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6c50794c612801ed8b599cd4af1ed810a0d39011711c8224f93e1153c00e08d1"},
+    {file = "cymem-2.0.7-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a9525ad563b36dc1e30889d0087a0daa67dd7bb7d3e1530c4b61cd65cc756a5b"},
+    {file = "cymem-2.0.7-cp38-cp38-win_amd64.whl", hash = "sha256:48b98da6b906fe976865263e27734ebc64f972a978a999d447ad6c83334e3f90"},
+    {file = "cymem-2.0.7-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:e156788d32ad8f7141330913c5d5d2aa67182fca8f15ae22645e9f379abe8a4c"},
+    {file = "cymem-2.0.7-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3da89464021fe669932fce1578343fcaf701e47e3206f50d320f4f21e6683ca5"},
+    {file = "cymem-2.0.7-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4f359cab9f16e25b3098f816c40acbf1697a3b614a8d02c56e6ebcb9c89a06b3"},
+    {file = "cymem-2.0.7-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f165d7bce55d6730930e29d8294569788aa127f1be8d1642d9550ed96223cb37"},
+    {file = "cymem-2.0.7-cp39-cp39-win_amd64.whl", hash = "sha256:59a09cf0e71b1b88bfa0de544b801585d81d06ea123c1725e7c5da05b7ca0d20"},
+    {file = "cymem-2.0.7.tar.gz", hash = "sha256:e6034badb5dd4e10344211c81f16505a55553a7164adc314c75bd80cf07e57a8"},
+]
+
 [[package]]
 name = "darglint"
 version = "1.8.1"
@@ -875,7 +1027,7 @@ requirements-deprecated-finder = ["pip-api", "pipreqs"]
 name = "jinja2"
 version = "3.1.2"
 description = "A very fast and expressive template engine."
-category = "dev"
+category = "main"
 optional = false
 python-versions = ">=3.7"
 files = [
@@ -889,6 +1041,33 @@ MarkupSafe = ">=2.0"
 [package.extras]
 i18n = ["Babel (>=2.7)"]
 
+[[package]]
+name = "joblib"
+version = "1.2.0"
+description = "Lightweight pipelining with Python functions"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "joblib-1.2.0-py3-none-any.whl", hash = "sha256:091138ed78f800342968c523bdde947e7a305b8594b910a0fea2ab83c3c6d385"},
+    {file = "joblib-1.2.0.tar.gz", hash = "sha256:e1cee4a79e4af22881164f218d4311f60074197fb707e082e803b61f6d137018"},
+]
+
+[[package]]
+name = "langcodes"
+version = "3.3.0"
+description = "Tools for labeling human languages with IETF language tags"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "langcodes-3.3.0-py3-none-any.whl", hash = "sha256:4d89fc9acb6e9c8fdef70bcdf376113a3db09b67285d9e1d534de6d8818e7e69"},
+    {file = "langcodes-3.3.0.tar.gz", hash = "sha256:794d07d5a28781231ac335a1561b8442f8648ca07cd518310aeb45d6f0807ef6"},
+]
+
+[package.extras]
+data = ["language-data (>=1.1,<2.0)"]
+
 [[package]]
 name = "lazy-object-proxy"
 version = "1.8.0"
@@ -937,7 +1116,7 @@ testing = ["coverage", "pyyaml"]
 name = "markupsafe"
 version = "2.1.1"
 description = "Safely add untrusted strings to HTML/XML markup."
-category = "dev"
+category = "main"
 optional = false
 python-versions = ">=3.7"
 files = [
@@ -1146,6 +1325,44 @@ files = [
 [package.dependencies]
 dill = ">=0.3.6"
 
+[[package]]
+name = "murmurhash"
+version = "1.0.9"
+description = "Cython bindings for MurmurHash"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "murmurhash-1.0.9-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:697ed01454d92681c7ae26eb1adcdc654b54062bcc59db38ed03cad71b23d449"},
+    {file = "murmurhash-1.0.9-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:5ef31b5c11be2c064dbbdd0e22ab3effa9ceb5b11ae735295c717c120087dd94"},
+    {file = "murmurhash-1.0.9-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d7a2bd203377a31bbb2d83fe3f968756d6c9bbfa36c64c6ebfc3c6494fc680bc"},
+    {file = "murmurhash-1.0.9-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0eb0f8e652431ea238c11bcb671fef5c03aff0544bf7e098df81ea4b6d495405"},
+    {file = "murmurhash-1.0.9-cp310-cp310-win_amd64.whl", hash = "sha256:cf0b3fe54dca598f5b18c9951e70812e070ecb4c0672ad2cc32efde8a33b3df6"},
+    {file = "murmurhash-1.0.9-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5dc41be79ba4d09aab7e9110a8a4d4b37b184b63767b1b247411667cdb1057a3"},
+    {file = "murmurhash-1.0.9-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:c0f84ecdf37c06eda0222f2f9e81c0974e1a7659c35b755ab2fdc642ebd366db"},
+    {file = "murmurhash-1.0.9-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:241693c1c819148eac29d7882739b1099c891f1f7431127b2652c23f81722cec"},
+    {file = "murmurhash-1.0.9-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47f5ca56c430230d3b581dfdbc54eb3ad8b0406dcc9afdd978da2e662c71d370"},
+    {file = "murmurhash-1.0.9-cp311-cp311-win_amd64.whl", hash = "sha256:660ae41fc6609abc05130543011a45b33ca5d8318ae5c70e66bbd351ca936063"},
+    {file = "murmurhash-1.0.9-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:01137d688a6b259bde642513506b062364ea4e1609f886d9bd095c3ae6da0b94"},
+    {file = "murmurhash-1.0.9-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1b70bbf55d89713873a35bd4002bc231d38e530e1051d57ca5d15f96c01fd778"},
+    {file = "murmurhash-1.0.9-cp36-cp36m-win_amd64.whl", hash = "sha256:3e802fa5b0e618ee99e8c114ce99fc91677f14e9de6e18b945d91323a93c84e8"},
+    {file = "murmurhash-1.0.9-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:213d0248e586082e1cab6157d9945b846fd2b6be34357ad5ea0d03a1931d82ba"},
+    {file = "murmurhash-1.0.9-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:94b89d02aeab5e6bad5056f9d08df03ac7cfe06e61ff4b6340feb227fda80ce8"},
+    {file = "murmurhash-1.0.9-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0c2e2ee2d91a87952fe0f80212e86119aa1fd7681f03e6c99b279e50790dc2b3"},
+    {file = "murmurhash-1.0.9-cp37-cp37m-win_amd64.whl", hash = "sha256:8c3d69fb649c77c74a55624ebf7a0df3c81629e6ea6e80048134f015da57b2ea"},
+    {file = "murmurhash-1.0.9-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:ab78675510f83e7a3c6bd0abdc448a9a2b0b385b0d7ee766cbbfc5cc278a3042"},
+    {file = "murmurhash-1.0.9-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:0ac5530c250d2b0073ed058555847c8d88d2d00229e483d45658c13b32398523"},
+    {file = "murmurhash-1.0.9-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69157e8fa6b25c4383645227069f6a1f8738d32ed2a83558961019ca3ebef56a"},
+    {file = "murmurhash-1.0.9-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2aebe2ae016525a662ff772b72a2c9244a673e3215fcd49897f494258b96f3e7"},
+    {file = "murmurhash-1.0.9-cp38-cp38-win_amd64.whl", hash = "sha256:a5952f9c18a717fa17579e27f57bfa619299546011a8378a8f73e14eece332f6"},
+    {file = "murmurhash-1.0.9-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:ef79202feeac68e83971239169a05fa6514ecc2815ce04c8302076d267870f6e"},
+    {file = "murmurhash-1.0.9-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:799fcbca5693ad6a40f565ae6b8e9718e5875a63deddf343825c0f31c32348fa"},
+    {file = "murmurhash-1.0.9-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f9b995bc82eaf9223e045210207b8878fdfe099a788dd8abd708d9ee58459a9d"},
+    {file = "murmurhash-1.0.9-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b129e1c5ebd772e6ff5ef925bcce695df13169bd885337e6074b923ab6edcfc8"},
+    {file = "murmurhash-1.0.9-cp39-cp39-win_amd64.whl", hash = "sha256:379bf6b414bd27dd36772dd1570565a7d69918e980457370838bd514df0d91e9"},
+    {file = "murmurhash-1.0.9.tar.gz", hash = "sha256:fe7a38cb0d3d87c14ec9dddc4932ffe2dbc77d75469ab80fd5014689b0e07b58"},
+]
+
 [[package]]
 name = "mypy"
 version = "0.991"
@@ -1209,6 +1426,32 @@ files = [
     {file = "mypy_extensions-0.4.3.tar.gz", hash = "sha256:2d82818f5bb3e369420cb3c4060a7970edba416647068eb4c5343488a6c604a8"},
 ]
 
+[[package]]
+name = "nltk"
+version = "3.8"
+description = "Natural Language Toolkit"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "nltk-3.8-py3-none-any.whl", hash = "sha256:3306502f487aa9fb0566e23443fa287a85a8d8d0821e2ef1655b4e3f0ea4aeee"},
+    {file = "nltk-3.8.zip", hash = "sha256:74b30826a37d78d53427105bbd037dd880251be269fca64ee530838a46ed55fc"},
+]
+
+[package.dependencies]
+click = "*"
+joblib = "*"
+regex = ">=2021.8.3"
+tqdm = "*"
+
+[package.extras]
+all = ["matplotlib", "numpy", "pyparsing", "python-crfsuite", "requests", "scikit-learn", "scipy", "twython"]
+corenlp = ["requests"]
+machine-learning = ["numpy", "python-crfsuite", "scikit-learn", "scipy"]
+plot = ["matplotlib"]
+tgrep = ["pyparsing"]
+twitter = ["twython"]
+
 [[package]]
 name = "nodeenv"
 version = "1.7.0"
@@ -1402,6 +1645,29 @@ files = [
     {file = "pathspec-0.10.3.tar.gz", hash = "sha256:56200de4077d9d0791465aa9095a01d421861e405b5096955051deefd697d6f6"},
 ]
 
+[[package]]
+name = "pathy"
+version = "0.10.1"
+description = "pathlib.Path subclasses for local and cloud bucket storage"
+category = "main"
+optional = false
+python-versions = ">= 3.6"
+files = [
+    {file = "pathy-0.10.1-py3-none-any.whl", hash = "sha256:a7613ee2d99a0a3300e1d836322e2d947c85449fde59f52906f995dbff67dad4"},
+    {file = "pathy-0.10.1.tar.gz", hash = "sha256:4cd6e71b4cd5ff875cfbb949ad9fa5519d8d1dbe69d5fc1d1b23aa3cb049618b"},
+]
+
+[package.dependencies]
+smart-open = ">=5.2.1,<7.0.0"
+typer = ">=0.3.0,<1.0.0"
+
+[package.extras]
+all = ["azure-storage-blob", "boto3", "google-cloud-storage (>=1.26.0,<2.0.0)", "mock", "pytest", "pytest-coverage", "typer-cli"]
+azure = ["azure-storage-blob"]
+gcs = ["google-cloud-storage (>=1.26.0,<2.0.0)"]
+s3 = ["boto3"]
+test = ["mock", "pytest", "pytest-coverage", "typer-cli"]
+
 [[package]]
 name = "pbr"
 version = "5.11.0"
@@ -1493,7 +1759,7 @@ tests = ["check-manifest", "coverage", "defusedxml", "markdown2", "olefile", "pa
 name = "platformdirs"
 version = "2.6.0"
 description = "A small Python package for determining appropriate platform-specific dirs, e.g. a \"user data dir\"."
-category = "dev"
+category = "main"
 optional = false
 python-versions = ">=3.7"
 files = [
@@ -1540,6 +1806,48 @@ nodeenv = ">=0.11.1"
 pyyaml = ">=5.1"
 virtualenv = ">=20.10.0"
 
+[[package]]
+name = "preshed"
+version = "3.0.8"
+description = "Cython hash table that trusts the keys are pre-hashed"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "preshed-3.0.8-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ea4b6df8ef7af38e864235256793bc3056e9699d991afcf6256fa298858582fc"},
+    {file = "preshed-3.0.8-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8e945fc814bdc29564a2ce137c237b3a9848aa1e76a1160369b6e0d328151fdd"},
+    {file = "preshed-3.0.8-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f9a4833530fe53001c351974e0c8bb660211b8d0358e592af185fec1ae12b2d0"},
+    {file = "preshed-3.0.8-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e1472ee231f323b4f4368b1b5f8f08481ed43af89697d45450c6ae4af46ac08a"},
+    {file = "preshed-3.0.8-cp310-cp310-win_amd64.whl", hash = "sha256:c8a2e2931eea7e500fbf8e014b69022f3fab2e35a70da882e2fc753e5e487ae3"},
+    {file = "preshed-3.0.8-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:0e1bb8701df7861af26a312225bdf7c4822ac06fcf75aeb60fe2b0a20e64c222"},
+    {file = "preshed-3.0.8-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e9aef2b0b7687aecef48b1c6ff657d407ff24e75462877dcb888fa904c4a9c6d"},
+    {file = "preshed-3.0.8-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:854d58a8913ebf3b193b0dc8064155b034e8987de25f26838dfeca09151fda8a"},
+    {file = "preshed-3.0.8-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:135e2ac0db1a3948d6ec295598c7e182b52c394663f2fcfe36a97ae51186be21"},
+    {file = "preshed-3.0.8-cp311-cp311-win_amd64.whl", hash = "sha256:019d8fa4161035811fb2804d03214143298739e162d0ad24e087bd46c50970f5"},
+    {file = "preshed-3.0.8-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6a49ce52856fbb3ef4f1cc744c53f5d7e1ca370b1939620ac2509a6d25e02a50"},
+    {file = "preshed-3.0.8-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fdbc2957b36115a576c515ffe963919f19d2683f3c76c9304ae88ef59f6b5ca6"},
+    {file = "preshed-3.0.8-cp36-cp36m-win_amd64.whl", hash = "sha256:09cc9da2ac1b23010ce7d88a5e20f1033595e6dd80be14318e43b9409f4c7697"},
+    {file = "preshed-3.0.8-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:e19c8069f1a1450f835f23d47724530cf716d581fcafb398f534d044f806b8c2"},
+    {file = "preshed-3.0.8-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:25b5ef5e387a0e17ff41202a8c1816184ab6fb3c0d0b847bf8add0ed5941eb8d"},
+    {file = "preshed-3.0.8-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:53d3e2456a085425c66af7baba62d7eaa24aa5e460e1a9e02c401a2ed59abd7b"},
+    {file = "preshed-3.0.8-cp37-cp37m-win_amd64.whl", hash = "sha256:85e98a618fb36cdcc37501d8b9b8c1246651cc2f2db3a70702832523e0ae12f4"},
+    {file = "preshed-3.0.8-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7f8837bf616335464f3713cbf562a3dcaad22c3ca9193f957018964ef871a68b"},
+    {file = "preshed-3.0.8-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:720593baf2c2e295f855192974799e486da5f50d4548db93c44f5726a43cefb9"},
+    {file = "preshed-3.0.8-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e0ad3d860b9ce88a74cf7414bb4b1c6fd833813e7b818e76f49272c4974b19ce"},
+    {file = "preshed-3.0.8-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fd19d48440b152657966a52e627780c0ddbe9d907b8d7ee4598505e80a3c55c7"},
+    {file = "preshed-3.0.8-cp38-cp38-win_amd64.whl", hash = "sha256:246e7c6890dc7fe9b10f0e31de3346b906e3862b6ef42fcbede37968f46a73bf"},
+    {file = "preshed-3.0.8-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:67643e66691770dc3434b01671648f481e3455209ce953727ef2330b16790aaa"},
+    {file = "preshed-3.0.8-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:0ae25a010c9f551aa2247ee621457f679e07c57fc99d3fd44f84cb40b925f12c"},
+    {file = "preshed-3.0.8-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5a6a7fcf7dd2e7711051b3f0432da9ec9c748954c989f49d2cd8eabf8c2d953e"},
+    {file = "preshed-3.0.8-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5942858170c4f53d9afc6352a86bbc72fc96cc4d8964b6415492114a5920d3ed"},
+    {file = "preshed-3.0.8-cp39-cp39-win_amd64.whl", hash = "sha256:06793022a56782ef51d74f1399925a2ba958e50c5cfbc6fa5b25c4945e158a07"},
+    {file = "preshed-3.0.8.tar.gz", hash = "sha256:6c74c70078809bfddda17be96483c41d06d717934b07cab7921011d81758b357"},
+]
+
+[package.dependencies]
+cymem = ">=2.0.2,<2.1.0"
+murmurhash = ">=0.28.0,<1.1.0"
+
 [[package]]
 name = "psutil"
 version = "5.9.4"
@@ -1579,6 +1887,52 @@ files = [
     {file = "py-1.11.0.tar.gz", hash = "sha256:51c75c4126074b472f746a24399ad32f6053d1b34b68d2fa41e558e6f4a98719"},
 ]
 
+[[package]]
+name = "pyahocorasick"
+version = "1.4.4"
+description = "pyahocorasick is a fast and memory efficient library for exact or approximate multi-pattern string search.  With the \"ahocorasick.Automaton\" class, you can find multiple key string occurrences at once in some input text.  You can use it as a plain dict-like Trie or convert a Trie to an automaton for efficient Aho-Corasick search. And pickle to disk for easy reuse of large automatons. Implemented in C and tested on Python 3.6+. Works on Linux, macOS and Windows. BSD-3-Cause license."
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+    {file = "pyahocorasick-1.4.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8d46bbb579205a73adee0a8ec73667e6fb5b4b92f9d837f8a9eedb69c2f5a252"},
+    {file = "pyahocorasick-1.4.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8dfa16ea7ad3297f925964d6fb5553cb6c365b224c6dd749cf0e6cdf91fc2212"},
+    {file = "pyahocorasick-1.4.4-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:737d331377936fb229529e830d9a654623d7714e8823bfa49433ae7158f0d01c"},
+    {file = "pyahocorasick-1.4.4-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:8fa7618f1fef1c25f4f375a4c2c7c24ba3aa300eff48c732c0035f2f9750b29b"},
+    {file = "pyahocorasick-1.4.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:e3cdeda23a1b2530b787440b0d22ba8f10a3e424b1c53d00ed963d68941fcbb7"},
+    {file = "pyahocorasick-1.4.4-cp310-cp310-win32.whl", hash = "sha256:0bc164eeebac0bfee721aef74843a566247fe85ea05bd30a51ede91a9786156c"},
+    {file = "pyahocorasick-1.4.4-cp310-cp310-win_amd64.whl", hash = "sha256:35d45492ebd1248f15f8e7500114a8156de63d45c9e6a675ab53b717bfb94bd2"},
+    {file = "pyahocorasick-1.4.4-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:7cf4d08e10ab7ad136654b237a0b8f1df982df2c5a6f77ef90316731797855db"},
+    {file = "pyahocorasick-1.4.4-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f842c8f37d360f34a06c31f19d1b42e6404b48b49a8dffbed2ec6089ce78cca7"},
+    {file = "pyahocorasick-1.4.4-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cf96ecf2ae36e9aad4693e48457a7b97dc3b4cd793275c85924850aafa5b5c38"},
+    {file = "pyahocorasick-1.4.4-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:50d88355ac8ef495a582615d639bb80712505d2d8cdadfb93b9123063a3ae23a"},
+    {file = "pyahocorasick-1.4.4-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:04d73bec7d1289378f5948f7f1d68b94c1b4d2a29d7e26ac9085ad403cc4e739"},
+    {file = "pyahocorasick-1.4.4-cp36-cp36m-win32.whl", hash = "sha256:e2fe9dc5114c0778234a96ba11807681ccf38fe92bdf2d70d69e701533c51cab"},
+    {file = "pyahocorasick-1.4.4-cp36-cp36m-win_amd64.whl", hash = "sha256:e6eee473787ca1dc49b4f94a62b5456251f6976141da60ea0e006507eb0f11b8"},
+    {file = "pyahocorasick-1.4.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:12aabdadc3354da6d846186629c80e52fe9b021bdc01e5d5718ca197441e121f"},
+    {file = "pyahocorasick-1.4.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f46bc7b8ec0e0cee499c5066684397ac93ed8c2ca4529d396ceda775ce05a445"},
+    {file = "pyahocorasick-1.4.4-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:67bac0152c08d8cf40b738e011c36d8fab99f0610f5e709eb4929dd8be2a781d"},
+    {file = "pyahocorasick-1.4.4-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:3b20cc27c03c84f7a5d305012f302d0e7b3faa43ab02da665bb11b60135a1dd3"},
+    {file = "pyahocorasick-1.4.4-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:e3d7f2c7a0442540f373d0bf13d19d5d213136e217d050010da705afd09c3a00"},
+    {file = "pyahocorasick-1.4.4-cp37-cp37m-win32.whl", hash = "sha256:1ab503f0bff5537ef3da37681cfd52a3f964553f69eef561bd157b70b4aedf84"},
+    {file = "pyahocorasick-1.4.4-cp37-cp37m-win_amd64.whl", hash = "sha256:ab84c9425eb245c1baa2f91218c977561e01b700773ee232389222458a32316e"},
+    {file = "pyahocorasick-1.4.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:df422bf5c50115c58cdb972e9086d99bdd34367c56ba8827a939c8cc973f17d8"},
+    {file = "pyahocorasick-1.4.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:23cf21893b6ba3b47637f007c1e355c45726b98cd9cf473ea6dc706c47332646"},
+    {file = "pyahocorasick-1.4.4-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bee494e54939b737e4e44a04cbdbcfdf9b62c8bd762c05d435f4a7883dae8a94"},
+    {file = "pyahocorasick-1.4.4-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:e61994166562e8460115aa5a57fb0aafa852a173f4207a1a1381ba4322adf174"},
+    {file = "pyahocorasick-1.4.4-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:8fea989f2802eae1aacf26b817e4d532fe9f42434b49ddbff38b412bdeb763ac"},
+    {file = "pyahocorasick-1.4.4-cp38-cp38-win32.whl", hash = "sha256:31108e1cdf055acb9d0ba5e302926bf4e904db61dfbaa08c4d40284802950414"},
+    {file = "pyahocorasick-1.4.4-cp38-cp38-win_amd64.whl", hash = "sha256:4f37a464dbf4f091560a02e135f917259fde6c0a43f6cdf5558480a102bc1843"},
+    {file = "pyahocorasick-1.4.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c13190af4dd382c915ca37f173a407736be4dc1912d834bbc6555a79a2e6c9e2"},
+    {file = "pyahocorasick-1.4.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9b1b7ba6d9c717bb6d7310ab8185f739ff416b8c9323d8adf7b5bbbf48e2e775"},
+    {file = "pyahocorasick-1.4.4-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:38172bfa186da136cadc7438946d0d6d4fc1d64f62cad4d1a3038c20b37d5182"},
+    {file = "pyahocorasick-1.4.4-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:94894f5794b9e62a4c7b47a4fd3dc85bae952fe2b220396a627fae74b3eb7ad0"},
+    {file = "pyahocorasick-1.4.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:89085980232cc9cd2da2466a8a6232b0e1ff196ef275b2ed4e866941b35bf775"},
+    {file = "pyahocorasick-1.4.4-cp39-cp39-win32.whl", hash = "sha256:ef24ec2b11a09e0aba1f2a9c47f3c07444771a8b8def672713f79901509ed6b7"},
+    {file = "pyahocorasick-1.4.4-cp39-cp39-win_amd64.whl", hash = "sha256:062c5ac842e3fe51f231ada754acb1e5ad986cd28a2181c9a22b21268e22f8c7"},
+    {file = "pyahocorasick-1.4.4.tar.gz", hash = "sha256:32545cad135660ceef556f1d987aee3206e00096735405d7a8de84eb0a15bb27"},
+]
+
 [[package]]
 name = "pyarrow"
 version = "10.0.1"
@@ -1617,6 +1971,59 @@ files = [
 [package.dependencies]
 numpy = ">=1.16.6"
 
+[[package]]
+name = "pydantic"
+version = "1.10.2"
+description = "Data validation and settings management using python type hints"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "pydantic-1.10.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:bb6ad4489af1bac6955d38ebcb95079a836af31e4c4f74aba1ca05bb9f6027bd"},
+    {file = "pydantic-1.10.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a1f5a63a6dfe19d719b1b6e6106561869d2efaca6167f84f5ab9347887d78b98"},
+    {file = "pydantic-1.10.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:352aedb1d71b8b0736c6d56ad2bd34c6982720644b0624462059ab29bd6e5912"},
+    {file = "pydantic-1.10.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:19b3b9ccf97af2b7519c42032441a891a5e05c68368f40865a90eb88833c2559"},
+    {file = "pydantic-1.10.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:e9069e1b01525a96e6ff49e25876d90d5a563bc31c658289a8772ae186552236"},
+    {file = "pydantic-1.10.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:355639d9afc76bcb9b0c3000ddcd08472ae75318a6eb67a15866b87e2efa168c"},
+    {file = "pydantic-1.10.2-cp310-cp310-win_amd64.whl", hash = "sha256:ae544c47bec47a86bc7d350f965d8b15540e27e5aa4f55170ac6a75e5f73b644"},
+    {file = "pydantic-1.10.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a4c805731c33a8db4b6ace45ce440c4ef5336e712508b4d9e1aafa617dc9907f"},
+    {file = "pydantic-1.10.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d49f3db871575e0426b12e2f32fdb25e579dea16486a26e5a0474af87cb1ab0a"},
+    {file = "pydantic-1.10.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:37c90345ec7dd2f1bcef82ce49b6235b40f282b94d3eec47e801baf864d15525"},
+    {file = "pydantic-1.10.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7b5ba54d026c2bd2cb769d3468885f23f43710f651688e91f5fb1edcf0ee9283"},
+    {file = "pydantic-1.10.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:05e00dbebbe810b33c7a7362f231893183bcc4251f3f2ff991c31d5c08240c42"},
+    {file = "pydantic-1.10.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:2d0567e60eb01bccda3a4df01df677adf6b437958d35c12a3ac3e0f078b0ee52"},
+    {file = "pydantic-1.10.2-cp311-cp311-win_amd64.whl", hash = "sha256:c6f981882aea41e021f72779ce2a4e87267458cc4d39ea990729e21ef18f0f8c"},
+    {file = "pydantic-1.10.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:c4aac8e7103bf598373208f6299fa9a5cfd1fc571f2d40bf1dd1955a63d6eeb5"},
+    {file = "pydantic-1.10.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:81a7b66c3f499108b448f3f004801fcd7d7165fb4200acb03f1c2402da73ce4c"},
+    {file = "pydantic-1.10.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bedf309630209e78582ffacda64a21f96f3ed2e51fbf3962d4d488e503420254"},
+    {file = "pydantic-1.10.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:9300fcbebf85f6339a02c6994b2eb3ff1b9c8c14f502058b5bf349d42447dcf5"},
+    {file = "pydantic-1.10.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:216f3bcbf19c726b1cc22b099dd409aa371f55c08800bcea4c44c8f74b73478d"},
+    {file = "pydantic-1.10.2-cp37-cp37m-win_amd64.whl", hash = "sha256:dd3f9a40c16daf323cf913593083698caee97df2804aa36c4b3175d5ac1b92a2"},
+    {file = "pydantic-1.10.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:b97890e56a694486f772d36efd2ba31612739bc6f3caeee50e9e7e3ebd2fdd13"},
+    {file = "pydantic-1.10.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:9cabf4a7f05a776e7793e72793cd92cc865ea0e83a819f9ae4ecccb1b8aa6116"},
+    {file = "pydantic-1.10.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:06094d18dd5e6f2bbf93efa54991c3240964bb663b87729ac340eb5014310624"},
+    {file = "pydantic-1.10.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cc78cc83110d2f275ec1970e7a831f4e371ee92405332ebfe9860a715f8336e1"},
+    {file = "pydantic-1.10.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:1ee433e274268a4b0c8fde7ad9d58ecba12b069a033ecc4645bb6303c062d2e9"},
+    {file = "pydantic-1.10.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:7c2abc4393dea97a4ccbb4ec7d8658d4e22c4765b7b9b9445588f16c71ad9965"},
+    {file = "pydantic-1.10.2-cp38-cp38-win_amd64.whl", hash = "sha256:0b959f4d8211fc964772b595ebb25f7652da3f22322c007b6fed26846a40685e"},
+    {file = "pydantic-1.10.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c33602f93bfb67779f9c507e4d69451664524389546bacfe1bee13cae6dc7488"},
+    {file = "pydantic-1.10.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5760e164b807a48a8f25f8aa1a6d857e6ce62e7ec83ea5d5c5a802eac81bad41"},
+    {file = "pydantic-1.10.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6eb843dcc411b6a2237a694f5e1d649fc66c6064d02b204a7e9d194dff81eb4b"},
+    {file = "pydantic-1.10.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4b8795290deaae348c4eba0cebb196e1c6b98bdbe7f50b2d0d9a4a99716342fe"},
+    {file = "pydantic-1.10.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:e0bedafe4bc165ad0a56ac0bd7695df25c50f76961da29c050712596cf092d6d"},
+    {file = "pydantic-1.10.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:2e05aed07fa02231dbf03d0adb1be1d79cabb09025dd45aa094aa8b4e7b9dcda"},
+    {file = "pydantic-1.10.2-cp39-cp39-win_amd64.whl", hash = "sha256:c1ba1afb396148bbc70e9eaa8c06c1716fdddabaf86e7027c5988bae2a829ab6"},
+    {file = "pydantic-1.10.2-py3-none-any.whl", hash = "sha256:1b6ee725bd6e83ec78b1aa32c5b1fa67a3a65badddde3976bca5fe4568f27709"},
+    {file = "pydantic-1.10.2.tar.gz", hash = "sha256:91b8e218852ef6007c2b98cd861601c6a09f1aa32bbbb74fab5b1c33d4a1e410"},
+]
+
+[package.dependencies]
+typing-extensions = ">=4.1.0"
+
+[package.extras]
+dotenv = ["python-dotenv (>=0.10.4)"]
+email = ["email-validator (>=1.0.3)"]
+
 [[package]]
 name = "pydocstyle"
 version = "6.1.1"
@@ -2137,6 +2544,88 @@ setuptools = ">=19.3"
 github = ["jinja2 (>=3.1.0)", "pygithub (>=1.43.3)"]
 gitlab = ["python-gitlab (>=1.3.0)"]
 
+[[package]]
+name = "scikit-learn"
+version = "1.2.0"
+description = "A set of python modules for machine learning and data mining"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "scikit-learn-1.2.0.tar.gz", hash = "sha256:680b65b3caee469541385d2ca5b03ff70408f6c618c583948312f0d2125df680"},
+    {file = "scikit_learn-1.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1beaa631434d1f17a20b1eef5d842e58c195875d2bc11901a1a70b5fe544745b"},
+    {file = "scikit_learn-1.2.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:d395730f26d8fc752321f1953ddf72647c892d8bed74fad4d7c816ec9b602dfa"},
+    {file = "scikit_learn-1.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fd3480c982b9e616b9f76ad8587804d3f4e91b4e2a6752e7dafb8a2e1f541098"},
+    {file = "scikit_learn-1.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:184a42842a4e698ffa4d849b6019de50a77a0aa24d26afa28fa49c9190bb144b"},
+    {file = "scikit_learn-1.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:867023a044fdfe59e5014a7fec7a3086a8928f10b5dce9382eedf4135f6709a2"},
+    {file = "scikit_learn-1.2.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5546a8894a0616e92489ef995b39a0715829f3df96e801bb55cbf196be0d9649"},
+    {file = "scikit_learn-1.2.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:bc7073e025b62c1067cbfb76e69d08650c6b9d7a0e7afdfa20cb92d4afe516f6"},
+    {file = "scikit_learn-1.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fc0a72237f0c56780cf550df87201a702d3bdcbbb23c6ef7d54c19326fa23f19"},
+    {file = "scikit_learn-1.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4e1ea0bc1706da45589bcf2490cde6276490a1b88f9af208dbb396fdc3a0babf"},
+    {file = "scikit_learn-1.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:f17420a8e3f40129aeb7e0f5ee35822d6178617007bb8f69521a2cefc20d5f00"},
+    {file = "scikit_learn-1.2.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:25ba705ee1600ffc5df1dccd8fae129d7c6836e44ffcbb52d78536c9eaf8fcf9"},
+    {file = "scikit_learn-1.2.0-cp38-cp38-macosx_12_0_arm64.whl", hash = "sha256:6b63ca2b0643d30fbf9d25d93017ed3fb8351f31175d82d104bfec60cba7bb87"},
+    {file = "scikit_learn-1.2.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:83c772fa8c64776ad769fd764752c8452844307adcf10dee3adcc43988260f21"},
+    {file = "scikit_learn-1.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0834e4cec2a2e0d8978f39cb8fe1cad3be6c27a47927e1774bf5737ea65ec228"},
+    {file = "scikit_learn-1.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:da29d2e379c396a63af5ed4b671ad2005cd690ac373a23bee5a0f66504e05272"},
+    {file = "scikit_learn-1.2.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:23a88883ca60c571a06278e4726b3b51b3709cfa4c93cacbf5568b22ba960899"},
+    {file = "scikit_learn-1.2.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:40f3ff68c505cb9d1f3693397c73991875d609da905087e00e7b4477645ec67b"},
+    {file = "scikit_learn-1.2.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e9535e867281ae6987bb80620ba14cf1649e936bfe45f48727b978b7a2dbe835"},
+    {file = "scikit_learn-1.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:de897720173b26842e21bed54362f5294e282422116b61cd931d4f5d870b9855"},
+    {file = "scikit_learn-1.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:ceb0008f345188aa236e49c973dc160b9ed504a3abd7b321a0ecabcb669be0bd"},
+]
+
+[package.dependencies]
+joblib = ">=1.1.1"
+numpy = ">=1.17.3"
+scipy = ">=1.3.2"
+threadpoolctl = ">=2.0.0"
+
+[package.extras]
+benchmark = ["matplotlib (>=3.1.3)", "memory-profiler (>=0.57.0)", "pandas (>=1.0.5)"]
+docs = ["Pillow (>=7.1.2)", "matplotlib (>=3.1.3)", "memory-profiler (>=0.57.0)", "numpydoc (>=1.2.0)", "pandas (>=1.0.5)", "plotly (>=5.10.0)", "pooch (>=1.6.0)", "scikit-image (>=0.16.2)", "seaborn (>=0.9.0)", "sphinx (>=4.0.1)", "sphinx-gallery (>=0.7.0)", "sphinx-prompt (>=1.3.0)", "sphinxext-opengraph (>=0.4.2)"]
+examples = ["matplotlib (>=3.1.3)", "pandas (>=1.0.5)", "plotly (>=5.10.0)", "pooch (>=1.6.0)", "scikit-image (>=0.16.2)", "seaborn (>=0.9.0)"]
+tests = ["black (>=22.3.0)", "flake8 (>=3.8.2)", "matplotlib (>=3.1.3)", "mypy (>=0.961)", "numpydoc (>=1.2.0)", "pandas (>=1.0.5)", "pooch (>=1.6.0)", "pyamg (>=4.0.0)", "pytest (>=5.3.1)", "pytest-cov (>=2.9.0)", "scikit-image (>=0.16.2)"]
+
+[[package]]
+name = "scipy"
+version = "1.9.3"
+description = "Fundamental algorithms for scientific computing in Python"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "scipy-1.9.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1884b66a54887e21addf9c16fb588720a8309a57b2e258ae1c7986d4444d3bc0"},
+    {file = "scipy-1.9.3-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:83b89e9586c62e787f5012e8475fbb12185bafb996a03257e9675cd73d3736dd"},
+    {file = "scipy-1.9.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1a72d885fa44247f92743fc20732ae55564ff2a519e8302fb7e18717c5355a8b"},
+    {file = "scipy-1.9.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d01e1dd7b15bd2449c8bfc6b7cc67d630700ed655654f0dfcf121600bad205c9"},
+    {file = "scipy-1.9.3-cp310-cp310-win_amd64.whl", hash = "sha256:68239b6aa6f9c593da8be1509a05cb7f9efe98b80f43a5861cd24c7557e98523"},
+    {file = "scipy-1.9.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b41bc822679ad1c9a5f023bc93f6d0543129ca0f37c1ce294dd9d386f0a21096"},
+    {file = "scipy-1.9.3-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:90453d2b93ea82a9f434e4e1cba043e779ff67b92f7a0e85d05d286a3625df3c"},
+    {file = "scipy-1.9.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:83c06e62a390a9167da60bedd4575a14c1f58ca9dfde59830fc42e5197283dab"},
+    {file = "scipy-1.9.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:abaf921531b5aeaafced90157db505e10345e45038c39e5d9b6c7922d68085cb"},
+    {file = "scipy-1.9.3-cp311-cp311-win_amd64.whl", hash = "sha256:06d2e1b4c491dc7d8eacea139a1b0b295f74e1a1a0f704c375028f8320d16e31"},
+    {file = "scipy-1.9.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:5a04cd7d0d3eff6ea4719371cbc44df31411862b9646db617c99718ff68d4840"},
+    {file = "scipy-1.9.3-cp38-cp38-macosx_12_0_arm64.whl", hash = "sha256:545c83ffb518094d8c9d83cce216c0c32f8c04aaf28b92cc8283eda0685162d5"},
+    {file = "scipy-1.9.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0d54222d7a3ba6022fdf5773931b5d7c56efe41ede7f7128c7b1637700409108"},
+    {file = "scipy-1.9.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cff3a5295234037e39500d35316a4c5794739433528310e117b8a9a0c76d20fc"},
+    {file = "scipy-1.9.3-cp38-cp38-win_amd64.whl", hash = "sha256:2318bef588acc7a574f5bfdff9c172d0b1bf2c8143d9582e05f878e580a3781e"},
+    {file = "scipy-1.9.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d644a64e174c16cb4b2e41dfea6af722053e83d066da7343f333a54dae9bc31c"},
+    {file = "scipy-1.9.3-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:da8245491d73ed0a994ed9c2e380fd058ce2fa8a18da204681f2fe1f57f98f95"},
+    {file = "scipy-1.9.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4db5b30849606a95dcf519763dd3ab6fe9bd91df49eba517359e450a7d80ce2e"},
+    {file = "scipy-1.9.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c68db6b290cbd4049012990d7fe71a2abd9ffbe82c0056ebe0f01df8be5436b0"},
+    {file = "scipy-1.9.3-cp39-cp39-win_amd64.whl", hash = "sha256:5b88e6d91ad9d59478fafe92a7c757d00c59e3bdc3331be8ada76a4f8d683f58"},
+    {file = "scipy-1.9.3.tar.gz", hash = "sha256:fbc5c05c85c1a02be77b1ff591087c83bc44579c6d2bd9fb798bb64ea5e1a027"},
+]
+
+[package.dependencies]
+numpy = ">=1.18.5,<1.26.0"
+
+[package.extras]
+dev = ["flake8", "mypy", "pycodestyle", "typing_extensions"]
+doc = ["matplotlib (>2)", "numpydoc", "pydata-sphinx-theme (==0.9.0)", "sphinx (!=4.1.0)", "sphinx-panels (>=0.5.2)", "sphinx-tabs"]
+test = ["asv", "gmpy2", "mpmath", "pytest", "pytest-cov", "pytest-xdist", "scikit-umfpack", "threadpoolctl"]
+
 [[package]]
 name = "setuptools"
 version = "65.6.3"
@@ -2178,6 +2667,28 @@ files = [
     {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
 ]
 
+[[package]]
+name = "smart-open"
+version = "6.3.0"
+description = "Utils for streaming large files (S3, HDFS, GCS, Azure Blob Storage, gzip, bz2...)"
+category = "main"
+optional = false
+python-versions = ">=3.6,<4.0"
+files = [
+    {file = "smart_open-6.3.0-py3-none-any.whl", hash = "sha256:b4c9ae193ad6d3e7add50944b86afa0d150bd821ab8ec21edb26d9a06b66f6a8"},
+    {file = "smart_open-6.3.0.tar.gz", hash = "sha256:d5238825fe9a9340645fac3d75b287c08fbb99fb2b422477de781c9f5f09e019"},
+]
+
+[package.extras]
+all = ["azure-common", "azure-core", "azure-storage-blob", "boto3", "google-cloud-storage (>=2.6.0)", "paramiko", "requests"]
+azure = ["azure-common", "azure-core", "azure-storage-blob"]
+gcs = ["google-cloud-storage (>=2.6.0)"]
+http = ["requests"]
+s3 = ["boto3"]
+ssh = ["paramiko"]
+test = ["azure-common", "azure-core", "azure-storage-blob", "boto3", "google-cloud-storage (>=2.6.0)", "moto[server]", "paramiko", "pytest", "pytest-rerunfailures", "requests", "responses"]
+webhdfs = ["requests"]
+
 [[package]]
 name = "smmap"
 version = "5.0.0"
@@ -2202,6 +2713,170 @@ files = [
     {file = "snowballstemmer-2.2.0.tar.gz", hash = "sha256:09b16deb8547d3412ad7b590689584cd0fe25ec8db3be37788be3810cbf19cb1"},
 ]
 
+[[package]]
+name = "soupsieve"
+version = "2.3.2.post1"
+description = "A modern CSS selector implementation for Beautiful Soup."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "soupsieve-2.3.2.post1-py3-none-any.whl", hash = "sha256:3b2503d3c7084a42b1ebd08116e5f81aadfaea95863628c80a3b774a11b7c759"},
+    {file = "soupsieve-2.3.2.post1.tar.gz", hash = "sha256:fc53893b3da2c33de295667a0e19f078c14bf86544af307354de5fcf12a3f30d"},
+]
+
+[[package]]
+name = "spacy"
+version = "3.4.4"
+description = "Industrial-strength Natural Language Processing (NLP) in Python"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "spacy-3.4.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:07a10999a3e37f896758a92c2eed263638bcbf2747dc3a4aeea929aaa20ea28c"},
+    {file = "spacy-3.4.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e6d98511dc8a88d3a96bcae13971a284459362076738c85053d1a3791f6cde92"},
+    {file = "spacy-3.4.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f2cad9c5543f03b3375c252e4dd45670ee8ed99c925dca15eadab5084fd1b033"},
+    {file = "spacy-3.4.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4ade19c1e676cac2546f268db22bc5eba08d12beafabe80f1b9f06028b3a0b52"},
+    {file = "spacy-3.4.4-cp310-cp310-win_amd64.whl", hash = "sha256:e782c8a7c4805cc1b34ed2b11f72a5cf2b9851e20f7afe3e97caf206f19f761b"},
+    {file = "spacy-3.4.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:aa027e69ef9fe42c8b02b940872e5bde0ce1bf66b6bf488c6493e3ce660c4b3a"},
+    {file = "spacy-3.4.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ddeb5d725b6fa9c9009b1ff645db8f5caab9ed8956ee3a84b8379951caad1d36"},
+    {file = "spacy-3.4.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:29d6bb428a6bb19e026d8bbb9d4385c25b21e1ce51fcaabadfb5599b2390a79c"},
+    {file = "spacy-3.4.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a21187ad4c44e166dc3deed23992ea1a74d731c9a6bdd9fca306d455181577fa"},
+    {file = "spacy-3.4.4-cp311-cp311-win_amd64.whl", hash = "sha256:10643c6d335a02805f6676738a3e992323cfd9438115cc253435e5053dc93824"},
+    {file = "spacy-3.4.4-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:486228cfa7ced18ec99008388028bd2329262ab8108e7c19252c1a67b2801909"},
+    {file = "spacy-3.4.4-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bcb7a213178c298b95532075d6dddfb374bbe56ef8d2687212763b4583048da2"},
+    {file = "spacy-3.4.4-cp36-cp36m-win_amd64.whl", hash = "sha256:15e5c41d408d1d30d8f3dd8e4eed9ed28e6174e011b8d61c1345981562e2e8f5"},
+    {file = "spacy-3.4.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:8979dbd3594c5c268cedad53f456a3ec3a0a2b78a1199788aacedcd68eef3a00"},
+    {file = "spacy-3.4.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1f4736fea2630e696422dfe38bfb3d0a7864bc6a9072d6e49a906af46870e36e"},
+    {file = "spacy-3.4.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:498bf01e8c7ab601c3f8d6c51497817b40a3322a3967c032536b18ce9ea26d0a"},
+    {file = "spacy-3.4.4-cp37-cp37m-win_amd64.whl", hash = "sha256:95f880c6fea57d51c448ad84f96d79d8758e5e18bdbaaee060c15af11641079b"},
+    {file = "spacy-3.4.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9ccbede9be470c5d795168bf3be41fc86e18892a9247a742b394ba866c005391"},
+    {file = "spacy-3.4.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:2f1edbecfde9c11b17e87768bb5f2c33948fb1e3bf54b2197031ff9053607277"},
+    {file = "spacy-3.4.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:66eaf4764e95699934cbd8f38717b283db185c896cfd3d1fb1ad5c6552e8b3c9"},
+    {file = "spacy-3.4.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0bb7d53f1a780bb8cc1b27a81e02e8b9bc71abb959f4dc13c21af4041fdd2c7a"},
+    {file = "spacy-3.4.4-cp38-cp38-win_amd64.whl", hash = "sha256:c1a5ce5c9b19cdfb4469079e710e72bb09c3cab855f21ef6a614b84c765e0311"},
+    {file = "spacy-3.4.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:f7044dca3542579ea1e3ac6cdd821640c2f65dd0c56230688f36e15aca1b8217"},
+    {file = "spacy-3.4.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:8a495b0fc00910fb5c1fbe64fdbfe1d3c11b09f421d1ae4e30cdb4c2388a91e4"},
+    {file = "spacy-3.4.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:31e9a637960b60c1bb7a36a187271425717e97c14e9d1df613dc4efeffefcbec"},
+    {file = "spacy-3.4.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:71f9449ffadef85b048c9735ee235da5dca9d0a87038dba6d4ed20c5188e0f13"},
+    {file = "spacy-3.4.4-cp39-cp39-win_amd64.whl", hash = "sha256:1b7791a6c0592615b0566001596cc48c72325d1b97e46e574c91bff34f4e3f4c"},
+    {file = "spacy-3.4.4.tar.gz", hash = "sha256:e500cf2cb5f1849461a7928fa269703756069bdfb71559065240af6d0208b08c"},
+]
+
+[package.dependencies]
+catalogue = ">=2.0.6,<2.1.0"
+cymem = ">=2.0.2,<2.1.0"
+jinja2 = "*"
+langcodes = ">=3.2.0,<4.0.0"
+murmurhash = ">=0.28.0,<1.1.0"
+numpy = ">=1.15.0"
+packaging = ">=20.0"
+pathy = ">=0.3.5"
+preshed = ">=3.0.2,<3.1.0"
+pydantic = ">=1.7.4,<1.8 || >1.8,<1.8.1 || >1.8.1,<1.11.0"
+requests = ">=2.13.0,<3.0.0"
+setuptools = "*"
+smart-open = ">=5.2.1,<7.0.0"
+spacy-legacy = ">=3.0.10,<3.1.0"
+spacy-loggers = ">=1.0.0,<2.0.0"
+srsly = ">=2.4.3,<3.0.0"
+thinc = ">=8.1.0,<8.2.0"
+tqdm = ">=4.38.0,<5.0.0"
+typer = ">=0.3.0,<0.8.0"
+wasabi = ">=0.9.1,<1.1.0"
+
+[package.extras]
+apple = ["thinc-apple-ops (>=0.1.0.dev0,<1.0.0)"]
+cuda = ["cupy (>=5.0.0b4,<12.0.0)"]
+cuda-autodetect = ["cupy-wheel (>=11.0.0,<12.0.0)"]
+cuda100 = ["cupy-cuda100 (>=5.0.0b4,<12.0.0)"]
+cuda101 = ["cupy-cuda101 (>=5.0.0b4,<12.0.0)"]
+cuda102 = ["cupy-cuda102 (>=5.0.0b4,<12.0.0)"]
+cuda110 = ["cupy-cuda110 (>=5.0.0b4,<12.0.0)"]
+cuda111 = ["cupy-cuda111 (>=5.0.0b4,<12.0.0)"]
+cuda112 = ["cupy-cuda112 (>=5.0.0b4,<12.0.0)"]
+cuda113 = ["cupy-cuda113 (>=5.0.0b4,<12.0.0)"]
+cuda114 = ["cupy-cuda114 (>=5.0.0b4,<12.0.0)"]
+cuda115 = ["cupy-cuda115 (>=5.0.0b4,<12.0.0)"]
+cuda116 = ["cupy-cuda116 (>=5.0.0b4,<12.0.0)"]
+cuda117 = ["cupy-cuda117 (>=5.0.0b4,<12.0.0)"]
+cuda11x = ["cupy-cuda11x (>=11.0.0,<12.0.0)"]
+cuda80 = ["cupy-cuda80 (>=5.0.0b4,<12.0.0)"]
+cuda90 = ["cupy-cuda90 (>=5.0.0b4,<12.0.0)"]
+cuda91 = ["cupy-cuda91 (>=5.0.0b4,<12.0.0)"]
+cuda92 = ["cupy-cuda92 (>=5.0.0b4,<12.0.0)"]
+ja = ["sudachidict-core (>=20211220)", "sudachipy (>=0.5.2,!=0.6.1)"]
+ko = ["natto-py (>=0.9.0)"]
+lookups = ["spacy-lookups-data (>=1.0.3,<1.1.0)"]
+ray = ["spacy-ray (>=0.1.0,<1.0.0)"]
+th = ["pythainlp (>=2.0)"]
+transformers = ["spacy-transformers (>=1.1.2,<1.2.0)"]
+
+[[package]]
+name = "spacy-legacy"
+version = "3.0.10"
+description = "Legacy registered functions for spaCy backwards compatibility"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "spacy-legacy-3.0.10.tar.gz", hash = "sha256:16104595d8ab1b7267f817a449ad1f986eb1f2a2edf1050748f08739a479679a"},
+    {file = "spacy_legacy-3.0.10-py2.py3-none-any.whl", hash = "sha256:8526a54d178dee9b7f218d43e5c21362c59056c5da23380b319b56043e9211f3"},
+]
+
+[[package]]
+name = "spacy-loggers"
+version = "1.0.4"
+description = "Logging utilities for SpaCy"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "spacy-loggers-1.0.4.tar.gz", hash = "sha256:e6f983bf71230091d5bb7b11bf64bd54415eca839108d5f83d9155d0ba93bf28"},
+    {file = "spacy_loggers-1.0.4-py3-none-any.whl", hash = "sha256:e050bf2e63208b2f096b777e494971c962ad7c1dc997641c8f95c622550044ae"},
+]
+
+[[package]]
+name = "srsly"
+version = "2.4.5"
+description = "Modern high-performance serialization utilities for Python"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "srsly-2.4.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8fed31ef8acbb5fead2152824ef39e12d749fcd254968689ba5991dd257b63b4"},
+    {file = "srsly-2.4.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:04d0b4cd91e098cdac12d2c28e256b1181ba98bcd00e460b8e42dee3e8542804"},
+    {file = "srsly-2.4.5-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6d83bea1f774b54d9313a374a95f11a776d37bcedcda93c526bf7f1cb5f26428"},
+    {file = "srsly-2.4.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cae5d48a0bda55a3728f49976ea0b652f508dbc5ac3e849f41b64a5753ec7f0a"},
+    {file = "srsly-2.4.5-cp310-cp310-win_amd64.whl", hash = "sha256:f74c64934423bcc2d3508cf3a079c7034e5cde988255dc57c7a09794c78f0610"},
+    {file = "srsly-2.4.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:0f9abb7857f9363f1ac52123db94dfe1c4af8959a39d698eff791d17e45e00b6"},
+    {file = "srsly-2.4.5-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f48d40c3b3d20e38410e7a95fa5b4050c035f467b0793aaf67188b1edad37fe3"},
+    {file = "srsly-2.4.5-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1434759effec2ee266a24acd9b53793a81cac01fc1e6321c623195eda1b9c7df"},
+    {file = "srsly-2.4.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5e7b0cd9853b0d9e00ad23d26199c1e44d8fd74096cbbbabc92447a915bcfd78"},
+    {file = "srsly-2.4.5-cp311-cp311-win_amd64.whl", hash = "sha256:874010587a807264963de9a1c91668c43cee9ed2f683f5406bdf5a34dfe12cca"},
+    {file = "srsly-2.4.5-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:afa4e1fe143275339d1c4a74e46d4c75168eed8b200f44f2ea023d45ff089a2f"},
+    {file = "srsly-2.4.5-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1c4291ee125796fb05e778e9ca8f9a829e8c314b757826f2e1d533e424a93531"},
+    {file = "srsly-2.4.5-cp36-cp36m-win_amd64.whl", hash = "sha256:8f258ee69aefb053258ac2e4f4b9d597e622b79f78874534430e864cef0be199"},
+    {file = "srsly-2.4.5-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:ace951c3088204bd66f30326f93ab6e615ce1562a461a8a464759d99fa9c2a02"},
+    {file = "srsly-2.4.5-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:facab907801fbcb0e54b3532e04bc6a0709184d68004ef3a129e8c7e3ca63d82"},
+    {file = "srsly-2.4.5-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a49c089541a9a0a27ccb841a596350b7ee1d6adfc7ebd28eddedfd34dc9f12c5"},
+    {file = "srsly-2.4.5-cp37-cp37m-win_amd64.whl", hash = "sha256:db6bc02bd1e3372a3636e47b22098107c9df2cf12d220321b51c586ba17904b3"},
+    {file = "srsly-2.4.5-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9a95c682de8c6e6145199f10a7c597647ff7d398fb28874f845ba7d34a86a033"},
+    {file = "srsly-2.4.5-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:8c26c5c0e07ea7bb7b8b8735e1b2261fea308c2c883b99211d11747162c6d897"},
+    {file = "srsly-2.4.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e0043eff95be45acb5ce09cebb80ebdb9f2b6856aa3a15979e6fe3cc9a486753"},
+    {file = "srsly-2.4.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a2075124d4872e754af966e76f3258cd526eeac84f0995ee8cd561fd4cf1b68e"},
+    {file = "srsly-2.4.5-cp38-cp38-win_amd64.whl", hash = "sha256:1a41e5b10902c885cabe326ba86d549d7011e38534c45bed158ecb8abd4b44ce"},
+    {file = "srsly-2.4.5-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:b5a96f0ae15b651fa3fd87421bd93e61c6dc46c0831cbe275c9b790d253126b5"},
+    {file = "srsly-2.4.5-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:764906e9f4c2ac5f748c49d95c8bf79648404ebc548864f9cb1fa0707942d830"},
+    {file = "srsly-2.4.5-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:95afe9625badaf5ce326e37b21362423d7e8578a5ec9c85b15c3fca93205a883"},
+    {file = "srsly-2.4.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:90359cc3c5601afd45ec12c52bde1cf1ccbe0dc7d4244fd1f8d0c9e100c71707"},
+    {file = "srsly-2.4.5-cp39-cp39-win_amd64.whl", hash = "sha256:2d3b0d32be2267fb489da172d71399ac59f763189b47dbe68eedb0817afaa6dc"},
+    {file = "srsly-2.4.5.tar.gz", hash = "sha256:c842258967baa527cea9367986e42b8143a1a890e7d4a18d25a36edc3c7a33c7"},
+]
+
+[package.dependencies]
+catalogue = ">=2.0.3,<2.1.0"
+
 [[package]]
 name = "stevedore"
 version = "4.1.1"
@@ -2217,6 +2892,110 @@ files = [
 [package.dependencies]
 pbr = ">=2.0.0,<2.1.0 || >2.1.0"
 
+[[package]]
+name = "textsearch"
+version = "0.0.24"
+description = "Find strings/words in text; convenience and C speed"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+    {file = "textsearch-0.0.24-py2.py3-none-any.whl", hash = "sha256:1bbc4cc36300fbf0bbaa865500f84e907c85f6a48faf37da6e098407b405ed09"},
+    {file = "textsearch-0.0.24.tar.gz", hash = "sha256:2d23b5c3116715b65bccc18bc870ecc236ec8480d48cd5f257cc60bf66bb241a"},
+]
+
+[package.dependencies]
+anyascii = "*"
+pyahocorasick = "*"
+
+[[package]]
+name = "thinc"
+version = "8.1.6"
+description = "A refreshing functional take on deep learning, compatible with your favorite libraries"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "thinc-8.1.6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:a699c6d6550df4f5f6afafe3bfb0616e66f1780ab59c1aef3035e73b4da13c32"},
+    {file = "thinc-8.1.6-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ffeac5cf7d45ff1951dc34a9b6ee81a5c0bc6f96c3a477ab895dc68b35fdca13"},
+    {file = "thinc-8.1.6-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a7e06adaae2f48992b942ca72b4e4278e75ee9d582b691e151271bdee6ca013c"},
+    {file = "thinc-8.1.6-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b0cee9aea2c22c297411e02ad4b058c40e3e4d6f4ad076c1667000f8f4a6a81e"},
+    {file = "thinc-8.1.6-cp310-cp310-win_amd64.whl", hash = "sha256:8b53deac89ad1021a3fcac36b674c7809df769a5b3dcd1e14eab2fe0f3c68ab2"},
+    {file = "thinc-8.1.6-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:150a6e6b7fd7bebc9e2caab481d1d3accab8b649702820d577813e3db8681c0b"},
+    {file = "thinc-8.1.6-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2f3348c052e031ec701c8b36b9cc285eab061d8f2c335a0056a30e58c891583d"},
+    {file = "thinc-8.1.6-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3ee47c618f54b729f6a60fe7bd1961a9a78dd34dd81f6a99ebe8835cb498e557"},
+    {file = "thinc-8.1.6-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:35cf8ce97ab10f2cd99bacc5e2d925ac1072d551d5ce0c24f67503cd09811a25"},
+    {file = "thinc-8.1.6-cp311-cp311-win_amd64.whl", hash = "sha256:8061678c1747dd307d585b60b7be8cfd2c1d56cd20312e160226ae75639136c0"},
+    {file = "thinc-8.1.6-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ef70037c4ac5322dbf21eebe44b02eefdff6b651cc85d6a0b9ee0ca9a742e6fb"},
+    {file = "thinc-8.1.6-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:740480d39321f9ab923576496ef4e7690a48bebc17cdb466041012d6a86d84b7"},
+    {file = "thinc-8.1.6-cp36-cp36m-win_amd64.whl", hash = "sha256:4a92c6dca06e91960bd684d61c8eeed0d48c676ba1f8bad52f7b9ba26faa9ff3"},
+    {file = "thinc-8.1.6-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:0baca8b752992595a664f299d9e3146ecedeb101e468260e4eb156f3d60611dd"},
+    {file = "thinc-8.1.6-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f1c685e3edf0d174dc22e947db4ea9bc0034e2fc5a73fb317731c90b2b2f28d1"},
+    {file = "thinc-8.1.6-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75e6139fb3f00bbc340fbf1e7ac7dcbfac8552249df34cb7807d864eebd0fa08"},
+    {file = "thinc-8.1.6-cp37-cp37m-win_amd64.whl", hash = "sha256:ebb41c1a47e72d31c9635c955a69d827cde7aadfa7369c56bba512a7d11c0c45"},
+    {file = "thinc-8.1.6-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:b6e8d59e720c1e75b1ce29be5460372f26211327e827328e8afbbe15a30f3e0f"},
+    {file = "thinc-8.1.6-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:4f0c2842dc85c6d4e0784ea9471bfdd55c800e8269662bbf3e6ea27a5af376a6"},
+    {file = "thinc-8.1.6-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ebab1f7618d2bf6a616ea56f2d745193307f0f3f5373c3a589ee761731bf4907"},
+    {file = "thinc-8.1.6-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b952a6430a4e4c6f4ddc757a49612f00d207174cad16f0e3e9ab82980a4960b5"},
+    {file = "thinc-8.1.6-cp38-cp38-win_amd64.whl", hash = "sha256:dfa86f2d7f97eefa8b457a8bc857b9c3eb33c2c628710ae9ec4fe139b350db45"},
+    {file = "thinc-8.1.6-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:540b63b74a56e565c863bf8f4e551798873fa21668d50693eb10e11de51d8530"},
+    {file = "thinc-8.1.6-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:b22381917e533c422285c989a9e798ca953f963476238ad988cb63732c413930"},
+    {file = "thinc-8.1.6-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8eb07322ae636bcba6f90df203c00ba428437de88d700b195236fad830551cd5"},
+    {file = "thinc-8.1.6-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:13db03222d595f6b00091a3c8b303f11a9a82cfa529af614127bbd940c0d9de5"},
+    {file = "thinc-8.1.6-cp39-cp39-win_amd64.whl", hash = "sha256:3693c5eeaeace5ed178070f62ca7eb8e453f269d5c83abf8b44d16e85d1433a4"},
+    {file = "thinc-8.1.6.tar.gz", hash = "sha256:9241c37761f004fe684e637d2b4d8b79addebabc64e343aa1cba144fad2c9b47"},
+]
+
+[package.dependencies]
+blis = ">=0.7.8,<0.8.0"
+catalogue = ">=2.0.4,<2.1.0"
+confection = ">=0.0.1,<1.0.0"
+cymem = ">=2.0.2,<2.1.0"
+murmurhash = ">=1.0.2,<1.1.0"
+numpy = ">=1.15.0"
+packaging = ">=20.0"
+preshed = ">=3.0.2,<3.1.0"
+pydantic = ">=1.7.4,<1.8 || >1.8,<1.8.1 || >1.8.1,<1.11.0"
+setuptools = "*"
+srsly = ">=2.4.0,<3.0.0"
+wasabi = ">=0.8.1,<1.2.0"
+
+[package.extras]
+cuda = ["cupy (>=5.0.0b4)"]
+cuda-autodetect = ["cupy-wheel (>=11.0.0)"]
+cuda100 = ["cupy-cuda100 (>=5.0.0b4)"]
+cuda101 = ["cupy-cuda101 (>=5.0.0b4)"]
+cuda102 = ["cupy-cuda102 (>=5.0.0b4)"]
+cuda110 = ["cupy-cuda110 (>=5.0.0b4)"]
+cuda111 = ["cupy-cuda111 (>=5.0.0b4)"]
+cuda112 = ["cupy-cuda112 (>=5.0.0b4)"]
+cuda113 = ["cupy-cuda113 (>=5.0.0b4)"]
+cuda114 = ["cupy-cuda114 (>=5.0.0b4)"]
+cuda115 = ["cupy-cuda115 (>=5.0.0b4)"]
+cuda116 = ["cupy-cuda116 (>=5.0.0b4)"]
+cuda117 = ["cupy-cuda117 (>=5.0.0b4)"]
+cuda11x = ["cupy-cuda11x (>=11.0.0)"]
+cuda80 = ["cupy-cuda80 (>=5.0.0b4)"]
+cuda90 = ["cupy-cuda90 (>=5.0.0b4)"]
+cuda91 = ["cupy-cuda91 (>=5.0.0b4)"]
+cuda92 = ["cupy-cuda92 (>=5.0.0b4)"]
+datasets = ["ml-datasets (>=0.2.0,<0.3.0)"]
+mxnet = ["mxnet (>=1.5.1,<1.6.0)"]
+tensorflow = ["tensorflow (>=2.0.0,<2.6.0)"]
+torch = ["torch (>=1.6.0)"]
+
+[[package]]
+name = "threadpoolctl"
+version = "3.1.0"
+description = "threadpoolctl"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "threadpoolctl-3.1.0-py3-none-any.whl", hash = "sha256:8b99adda265feb6773280df41eece7b2e6561b772d21ffd52e372f999024907b"},
+    {file = "threadpoolctl-3.1.0.tar.gz", hash = "sha256:a335baacfaa4400ae1f0d8e3a58d6674d2f8828e3716bb2802c44955ad391380"},
+]
+
 [[package]]
 name = "timm"
 version = "0.6.12"
@@ -2529,6 +3308,36 @@ files = [
     {file = "typing_extensions-4.4.0.tar.gz", hash = "sha256:1511434bb92bf8dd198c12b1cc812e800d4181cfcb867674e0f8279cc93087aa"},
 ]
 
+[[package]]
+name = "uritools"
+version = "4.0.0"
+description = "URI parsing, classification and composition"
+category = "main"
+optional = false
+python-versions = "~=3.7"
+files = [
+    {file = "uritools-4.0.0-py3-none-any.whl", hash = "sha256:9a5a1495c55072093216f79931ca45fd81b59208aa64caae50ab68333514f97e"},
+    {file = "uritools-4.0.0.tar.gz", hash = "sha256:420d94c1ff4bf90c678fca9c17b8314243bbcaa992c400a95e327f7f622e1edf"},
+]
+
+[[package]]
+name = "urlextract"
+version = "1.8.0"
+description = "Collects and extracts URLs from given text."
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+    {file = "urlextract-1.8.0-py3-none-any.whl", hash = "sha256:98b38aca4a555116e8b46e5a134b9e4e54e351b8e37169d2857730d1d0ce42c7"},
+    {file = "urlextract-1.8.0.tar.gz", hash = "sha256:3573f6b812814efe06ca46e91e82d984edaa3cd07daaaaa296a467ad9881a037"},
+]
+
+[package.dependencies]
+filelock = "*"
+idna = "*"
+platformdirs = "*"
+uritools = "*"
+
 [[package]]
 name = "urllib3"
 version = "1.26.13"
@@ -2567,6 +3376,18 @@ platformdirs = ">=2.4,<3"
 docs = ["proselint (>=0.13)", "sphinx (>=5.3)", "sphinx-argparse (>=0.3.2)", "sphinx-rtd-theme (>=1)", "towncrier (>=22.8)"]
 testing = ["coverage (>=6.2)", "coverage-enable-subprocess (>=1)", "flaky (>=3.7)", "packaging (>=21.3)", "pytest (>=7.0.1)", "pytest-env (>=0.6.2)", "pytest-freezegun (>=0.4.2)", "pytest-mock (>=3.6.1)", "pytest-randomly (>=3.10.3)", "pytest-timeout (>=2.1)"]
 
+[[package]]
+name = "wasabi"
+version = "0.10.1"
+description = "A lightweight console printing and formatting toolkit"
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+    {file = "wasabi-0.10.1-py3-none-any.whl", hash = "sha256:fe862cc24034fbc9f04717cd312ab884f71f51a8ecabebc3449b751c2a649d83"},
+    {file = "wasabi-0.10.1.tar.gz", hash = "sha256:c8e372781be19272942382b14d99314d175518d7822057cb7a97010c4259d249"},
+]
+
 [[package]]
 name = "watchdog"
 version = "2.2.0"
@@ -2893,4 +3714,4 @@ testing = ["flake8 (<5)", "func-timeout", "jaraco.functools", "jaraco.itertools"
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "e8eeff06f176dabc6da74969404d8ec8983b9db6d11c6c7ff34ee151bae422e9"
+content-hash = "1176d6ed37e6dbd675b086a6eae2e8ad214ac12291285c1e46700f6600d5f0bf"

pyproject.toml

@@ -4,8 +4,8 @@ requires = ["poetry_core>=1.0.0"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
-name = "internet-ml"
+name = "internet_ml"
-version = "0.1.0"
+version = "0.1.1"
 description = "Internet-ML: Allowing ML to connect to the internet"
 readme = "./.github/README.md"
 authors = ["Thamognya Kodi <contact@thamognya.com>"]
@@ -32,7 +32,6 @@ classifiers = [
 
 [tool.poetry.dependencies]
 python = "^3.10"
-
 typer = {extras = ["all"], version = "^0.4.0"}
 rich = "^10.14.0"
 tokenizers = "^0.13.2"
@@ -48,6 +47,12 @@ torchaudio = "^0.13.1"
 python-dotenv = "^0.21.0"
 requests = "^2.28.1"
 types-requests = "^2.28.11.7"
+contractions = "^0.1.73"
+urlextract = "^1.8.0"
+scikit-learn = "^1.2.0"
+spacy = "^3.4.4"
+nltk = "^3.8"
+beautifulsoup4 = "^4.11.1"
 
 [tool.poetry.group.dev.dependencies]
 bandit = "^1.7.4"