diff --git a/.gitignore b/.gitignore
index a2c3170..f11c9ac 100644
--- a/.gitignore
+++ b/.gitignore
@@ -7,7 +7,8 @@
# Add your own ignores here!
-
+data/raw/
+data/db/
##################
# Python ignores #
diff --git a/.idea/inspectionProfiles/Project_Default.xml b/.idea/inspectionProfiles/Project_Default.xml
new file mode 100644
index 0000000..06bb031
--- /dev/null
+++ b/.idea/inspectionProfiles/Project_Default.xml
@@ -0,0 +1,12 @@
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/misc.xml b/.idea/misc.xml
index 2ca2389..c31251c 100644
--- a/.idea/misc.xml
+++ b/.idea/misc.xml
@@ -4,7 +4,7 @@
-
+
\ No newline at end of file
diff --git a/data/scripts/import-db.sh b/data/scripts/import-db.sh
new file mode 100755
index 0000000..ab0f5cb
--- /dev/null
+++ b/data/scripts/import-db.sh
@@ -0,0 +1,3 @@
+#!/usr/bin/env bash
+repo=$(git rev-parse --show-toplevel)
+mongoimport --db='reviews' --collection='reviews' --file="$repo/data/raw/reviewsexport.json" --verbose
diff --git a/data/scripts/run-db.sh b/data/scripts/run-db.sh
new file mode 100755
index 0000000..dced127
--- /dev/null
+++ b/data/scripts/run-db.sh
@@ -0,0 +1,3 @@
+#!/usr/bin/env bash
+repo=$(git rev-parse --show-toplevel)
+mongod --dbpath "$repo/data/db"
\ No newline at end of file
diff --git a/poetry.lock b/poetry.lock
new file mode 100644
index 0000000..6ce832e
--- /dev/null
+++ b/poetry.lock
@@ -0,0 +1,372 @@
+# This file is automatically @generated by Poetry and should not be changed by hand.
+
+[[package]]
+name = "cfig"
+version = "0.3.0"
+description = "A configuration manager for Python"
+category = "main"
+optional = false
+python-versions = ">=3.10,<4.0"
+files = [
+ {file = "cfig-0.3.0-py3-none-any.whl", hash = "sha256:47310ec4e57b4f92b79f7ae223619d318d9bd068ed021cb24eb47d4cf55372b3"},
+ {file = "cfig-0.3.0.tar.gz", hash = "sha256:1343e7b5eddbd609a4349826b55498beead0d0e1ae27d53784c30a3749dcbe6b"},
+]
+
+[package.dependencies]
+click = {version = ">=8.1.2,<9.0.0", optional = true, markers = "extra == \"cli\""}
+colorama = {version = ">=0.4.4,<0.5.0", optional = true, markers = "extra == \"cli\""}
+lazy-object-proxy = ">=1.7.1,<2.0.0"
+
+[package.extras]
+cli = ["click (>=8.1.2,<9.0.0)", "colorama (>=0.4.4,<0.5.0)"]
+
+[[package]]
+name = "click"
+version = "8.1.3"
+description = "Composable command line interface toolkit"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "click-8.1.3-py3-none-any.whl", hash = "sha256:bb4d8133cb15a609f44e8213d9b391b0809795062913b383c62be0ee95b1db48"},
+ {file = "click-8.1.3.tar.gz", hash = "sha256:7682dc8afb30297001674575ea00d1814d808d6a36af415a82bd481d37ba7b8e"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[[package]]
+name = "colorama"
+version = "0.4.6"
+description = "Cross-platform colored terminal text."
+category = "main"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
+files = [
+ {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
+ {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
+]
+
+[[package]]
+name = "dnspython"
+version = "2.3.0"
+description = "DNS toolkit"
+category = "main"
+optional = false
+python-versions = ">=3.7,<4.0"
+files = [
+ {file = "dnspython-2.3.0-py3-none-any.whl", hash = "sha256:89141536394f909066cabd112e3e1a37e4e654db00a25308b0f130bc3152eb46"},
+ {file = "dnspython-2.3.0.tar.gz", hash = "sha256:224e32b03eb46be70e12ef6d64e0be123a64e621ab4c0822ff6d450d52a540b9"},
+]
+
+[package.extras]
+curio = ["curio (>=1.2,<2.0)", "sniffio (>=1.1,<2.0)"]
+dnssec = ["cryptography (>=2.6,<40.0)"]
+doh = ["h2 (>=4.1.0)", "httpx (>=0.21.1)", "requests (>=2.23.0,<3.0.0)", "requests-toolbelt (>=0.9.1,<0.11.0)"]
+doq = ["aioquic (>=0.9.20)"]
+idna = ["idna (>=2.1,<4.0)"]
+trio = ["trio (>=0.14,<0.23)"]
+wmi = ["wmi (>=1.5.1,<2.0.0)"]
+
+[[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 = "lazy-object-proxy"
+version = "1.9.0"
+description = "A fast and thorough lazy object proxy."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "lazy-object-proxy-1.9.0.tar.gz", hash = "sha256:659fb5809fa4629b8a1ac5106f669cfc7bef26fbb389dda53b3e010d1ac4ebae"},
+ {file = "lazy_object_proxy-1.9.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:b40387277b0ed2d0602b8293b94d7257e17d1479e257b4de114ea11a8cb7f2d7"},
+ {file = "lazy_object_proxy-1.9.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e8c6cfb338b133fbdbc5cfaa10fe3c6aeea827db80c978dbd13bc9dd8526b7d4"},
+ {file = "lazy_object_proxy-1.9.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:721532711daa7db0d8b779b0bb0318fa87af1c10d7fe5e52ef30f8eff254d0cd"},
+ {file = "lazy_object_proxy-1.9.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:66a3de4a3ec06cd8af3f61b8e1ec67614fbb7c995d02fa224813cb7afefee701"},
+ {file = "lazy_object_proxy-1.9.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:1aa3de4088c89a1b69f8ec0dcc169aa725b0ff017899ac568fe44ddc1396df46"},
+ {file = "lazy_object_proxy-1.9.0-cp310-cp310-win32.whl", hash = "sha256:f0705c376533ed2a9e5e97aacdbfe04cecd71e0aa84c7c0595d02ef93b6e4455"},
+ {file = "lazy_object_proxy-1.9.0-cp310-cp310-win_amd64.whl", hash = "sha256:ea806fd4c37bf7e7ad82537b0757999264d5f70c45468447bb2b91afdbe73a6e"},
+ {file = "lazy_object_proxy-1.9.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:946d27deaff6cf8452ed0dba83ba38839a87f4f7a9732e8f9fd4107b21e6ff07"},
+ {file = "lazy_object_proxy-1.9.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:79a31b086e7e68b24b99b23d57723ef7e2c6d81ed21007b6281ebcd1688acb0a"},
+ {file = "lazy_object_proxy-1.9.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f699ac1c768270c9e384e4cbd268d6e67aebcfae6cd623b4d7c3bfde5a35db59"},
+ {file = "lazy_object_proxy-1.9.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:bfb38f9ffb53b942f2b5954e0f610f1e721ccebe9cce9025a38c8ccf4a5183a4"},
+ {file = "lazy_object_proxy-1.9.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:189bbd5d41ae7a498397287c408617fe5c48633e7755287b21d741f7db2706a9"},
+ {file = "lazy_object_proxy-1.9.0-cp311-cp311-win32.whl", hash = "sha256:81fc4d08b062b535d95c9ea70dbe8a335c45c04029878e62d744bdced5141586"},
+ {file = "lazy_object_proxy-1.9.0-cp311-cp311-win_amd64.whl", hash = "sha256:f2457189d8257dd41ae9b434ba33298aec198e30adf2dcdaaa3a28b9994f6adb"},
+ {file = "lazy_object_proxy-1.9.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:d9e25ef10a39e8afe59a5c348a4dbf29b4868ab76269f81ce1674494e2565a6e"},
+ {file = "lazy_object_proxy-1.9.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cbf9b082426036e19c6924a9ce90c740a9861e2bdc27a4834fd0a910742ac1e8"},
+ {file = "lazy_object_proxy-1.9.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9f5fa4a61ce2438267163891961cfd5e32ec97a2c444e5b842d574251ade27d2"},
+ {file = "lazy_object_proxy-1.9.0-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:8fa02eaab317b1e9e03f69aab1f91e120e7899b392c4fc19807a8278a07a97e8"},
+ {file = "lazy_object_proxy-1.9.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:e7c21c95cae3c05c14aafffe2865bbd5e377cfc1348c4f7751d9dc9a48ca4bda"},
+ {file = "lazy_object_proxy-1.9.0-cp37-cp37m-win32.whl", hash = "sha256:f12ad7126ae0c98d601a7ee504c1122bcef553d1d5e0c3bfa77b16b3968d2734"},
+ {file = "lazy_object_proxy-1.9.0-cp37-cp37m-win_amd64.whl", hash = "sha256:edd20c5a55acb67c7ed471fa2b5fb66cb17f61430b7a6b9c3b4a1e40293b1671"},
+ {file = "lazy_object_proxy-1.9.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:2d0daa332786cf3bb49e10dc6a17a52f6a8f9601b4cf5c295a4f85854d61de63"},
+ {file = "lazy_object_proxy-1.9.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9cd077f3d04a58e83d04b20e334f678c2b0ff9879b9375ed107d5d07ff160171"},
+ {file = "lazy_object_proxy-1.9.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:660c94ea760b3ce47d1855a30984c78327500493d396eac4dfd8bd82041b22be"},
+ {file = "lazy_object_proxy-1.9.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:212774e4dfa851e74d393a2370871e174d7ff0ebc980907723bb67d25c8a7c30"},
+ {file = "lazy_object_proxy-1.9.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:f0117049dd1d5635bbff65444496c90e0baa48ea405125c088e93d9cf4525b11"},
+ {file = "lazy_object_proxy-1.9.0-cp38-cp38-win32.whl", hash = "sha256:0a891e4e41b54fd5b8313b96399f8b0e173bbbfc03c7631f01efbe29bb0bcf82"},
+ {file = "lazy_object_proxy-1.9.0-cp38-cp38-win_amd64.whl", hash = "sha256:9990d8e71b9f6488e91ad25f322898c136b008d87bf852ff65391b004da5e17b"},
+ {file = "lazy_object_proxy-1.9.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9e7551208b2aded9c1447453ee366f1c4070602b3d932ace044715d89666899b"},
+ {file = "lazy_object_proxy-1.9.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5f83ac4d83ef0ab017683d715ed356e30dd48a93746309c8f3517e1287523ef4"},
+ {file = "lazy_object_proxy-1.9.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7322c3d6f1766d4ef1e51a465f47955f1e8123caee67dd641e67d539a534d006"},
+ {file = "lazy_object_proxy-1.9.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:18b78ec83edbbeb69efdc0e9c1cb41a3b1b1ed11ddd8ded602464c3fc6020494"},
+ {file = "lazy_object_proxy-1.9.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:09763491ce220c0299688940f8dc2c5d05fd1f45af1e42e636b2e8b2303e4382"},
+ {file = "lazy_object_proxy-1.9.0-cp39-cp39-win32.whl", hash = "sha256:9090d8e53235aa280fc9239a86ae3ea8ac58eff66a705fa6aa2ec4968b95c821"},
+ {file = "lazy_object_proxy-1.9.0-cp39-cp39-win_amd64.whl", hash = "sha256:db1c1722726f47e10e0b5fdbf15ac3b8adb58c091d12b3ab713965795036985f"},
+]
+
+[[package]]
+name = "nltk"
+version = "3.8.1"
+description = "Natural Language Toolkit"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "nltk-3.8.1-py3-none-any.whl", hash = "sha256:fd5c9109f976fa86bcadba8f91e47f5e9293bd034474752e92a520f81c93dda5"},
+ {file = "nltk-3.8.1.zip", hash = "sha256:1834da3d0682cba4f2cede2f9aad6b0fafb6461ba451db0efb6f9c39798d64d3"},
+]
+
+[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 = "pymongo"
+version = "4.3.3"
+description = "Python driver for MongoDB "
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+ {file = "pymongo-4.3.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:74731c9e423c93cbe791f60c27030b6af6a948cef67deca079da6cd1bb583a8e"},
+ {file = "pymongo-4.3.3-cp310-cp310-manylinux1_i686.whl", hash = "sha256:66413c50d510e5bcb0afc79880d1693a2185bcea003600ed898ada31338c004e"},
+ {file = "pymongo-4.3.3-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:9b87b23570565a6ddaa9244d87811c2ee9cffb02a753c8a2da9c077283d85845"},
+ {file = "pymongo-4.3.3-cp310-cp310-manylinux2014_i686.whl", hash = "sha256:695939036a320f4329ccf1627edefbbb67cc7892b8222d297b0dd2313742bfee"},
+ {file = "pymongo-4.3.3-cp310-cp310-manylinux2014_ppc64le.whl", hash = "sha256:ffcc8394123ea8d43fff8e5d000095fe7741ce3f8988366c5c919c4f5eb179d3"},
+ {file = "pymongo-4.3.3-cp310-cp310-manylinux2014_s390x.whl", hash = "sha256:943f208840777f34312c103a2d1caab02d780c4e9be26b3714acf6c4715ba7e1"},
+ {file = "pymongo-4.3.3-cp310-cp310-manylinux2014_x86_64.whl", hash = "sha256:01f7cbe88d22440b6594c955e37312d932fd632ffed1a86d0c361503ca82cc9d"},
+ {file = "pymongo-4.3.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cdb87309de97c63cb9a69132e1cb16be470e58cffdfbad68fdd1dc292b22a840"},
+ {file = "pymongo-4.3.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d86c35d94b5499689354ccbc48438a79f449481ee6300f3e905748edceed78e7"},
+ {file = "pymongo-4.3.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a966d5304b7d90c45c404914e06bbf02c5bf7e99685c6c12f0047ef2aa837142"},
+ {file = "pymongo-4.3.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:be1d2ce7e269215c3ee9a215e296b7a744aff4f39233486d2c4d77f5f0c561a6"},
+ {file = "pymongo-4.3.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:55b6163dac53ef1e5d834297810c178050bd0548a4136cd4e0f56402185916ca"},
+ {file = "pymongo-4.3.3-cp310-cp310-win32.whl", hash = "sha256:dc0cff74cd36d7e1edba91baa09622c35a8a57025f2f2b7a41e3f83b1db73186"},
+ {file = "pymongo-4.3.3-cp310-cp310-win_amd64.whl", hash = "sha256:cafa52873ae12baa512a8721afc20de67a36886baae6a5f394ddef0ce9391f91"},
+ {file = "pymongo-4.3.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:599d3f6fbef31933b96e2d906b0f169b3371ff79ea6aaf6ecd76c947a3508a3d"},
+ {file = "pymongo-4.3.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c0640b4e9d008e13956b004d1971a23377b3d45491f87082161c92efb1e6c0d6"},
+ {file = "pymongo-4.3.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:341221e2f2866a5960e6f8610f4cbac0bb13097f3b1a289aa55aba984fc0d969"},
+ {file = "pymongo-4.3.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e7fac06a539daef4fcf5d8288d0d21b412f9b750454cd5a3cf90484665db442a"},
+ {file = "pymongo-4.3.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d3a51901066696c4af38c6c63a1f0aeffd5e282367ff475de8c191ec9609b56d"},
+ {file = "pymongo-4.3.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f3055510fdfdb1775bc8baa359783022f70bb553f2d46e153c094dfcb08578ff"},
+ {file = "pymongo-4.3.3-cp311-cp311-win32.whl", hash = "sha256:524d78673518dcd352a91541ecd2839c65af92dc883321c2109ef6e5cd22ef23"},
+ {file = "pymongo-4.3.3-cp311-cp311-win_amd64.whl", hash = "sha256:b8a03af1ce79b902a43f5f694c4ca8d92c2a4195db0966f08f266549e2fc49bc"},
+ {file = "pymongo-4.3.3-cp37-cp37m-macosx_10_6_intel.whl", hash = "sha256:39b03045c71f761aee96a12ebfbc2f4be89e724ff6f5e31c2574c1a0e2add8bd"},
+ {file = "pymongo-4.3.3-cp37-cp37m-manylinux1_i686.whl", hash = "sha256:6fcfbf435eebf8a1765c6d1f46821740ebe9f54f815a05c8fc30d789ef43cb12"},
+ {file = "pymongo-4.3.3-cp37-cp37m-manylinux1_x86_64.whl", hash = "sha256:7d43ac9c7eeda5100fb0a7152fab7099c9cf9e5abd3bb36928eb98c7d7a339c6"},
+ {file = "pymongo-4.3.3-cp37-cp37m-manylinux2014_aarch64.whl", hash = "sha256:3b93043b14ba7eb08c57afca19751658ece1cfa2f0b7b1fb5c7a41452fbb8482"},
+ {file = "pymongo-4.3.3-cp37-cp37m-manylinux2014_i686.whl", hash = "sha256:c09956606c08c4a7c6178a04ba2dd9388fcc5db32002ade9c9bc865ab156ab6d"},
+ {file = "pymongo-4.3.3-cp37-cp37m-manylinux2014_ppc64le.whl", hash = "sha256:b0cfe925610f2fd59555bb7fc37bd739e4b197d33f2a8b2fae7b9c0c6640318c"},
+ {file = "pymongo-4.3.3-cp37-cp37m-manylinux2014_s390x.whl", hash = "sha256:4d00b91c77ceb064c9b0459f0d6ea5bfdbc53ea9e17cf75731e151ef25a830c7"},
+ {file = "pymongo-4.3.3-cp37-cp37m-manylinux2014_x86_64.whl", hash = "sha256:c6258a3663780ae47ba73d43eb63c79c40ffddfb764e09b56df33be2f9479837"},
+ {file = "pymongo-4.3.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c29e758f0e734e1e90357ae01ec9c6daf19ff60a051192fe110d8fb25c62600e"},
+ {file = "pymongo-4.3.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:12f3621a46cdc7a9ba8080422262398a91762a581d27e0647746588d3f995c88"},
+ {file = "pymongo-4.3.3-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:47f7aa217b25833cd6f0e72b0d224be55393c2692b4f5e0561cb3beeb10296e9"},
+ {file = "pymongo-4.3.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c2fdc855149efe7cdcc2a01ca02bfa24761c640203ea94df467f3baf19078be"},
+ {file = "pymongo-4.3.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5effd87c7d363890259eac16c56a4e8da307286012c076223997f8cc4a8c435b"},
+ {file = "pymongo-4.3.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:6dd1cf2995fdbd64fc0802313e8323f5fa18994d51af059b5b8862b73b5e53f0"},
+ {file = "pymongo-4.3.3-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:bb869707d8e30645ed6766e44098600ca6cdf7989c22a3ea2b7966bb1d98d4b2"},
+ {file = "pymongo-4.3.3-cp37-cp37m-win32.whl", hash = "sha256:49210feb0be8051a64d71691f0acbfbedc33e149f0a5d6e271fddf6a12493fed"},
+ {file = "pymongo-4.3.3-cp37-cp37m-win_amd64.whl", hash = "sha256:54c377893f2cbbffe39abcff5ff2e917b082c364521fa079305f6f064e1a24a9"},
+ {file = "pymongo-4.3.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:c184ec5be465c0319440734491e1aa4709b5f3ba75fdfc9dbbc2ae715a7f6829"},
+ {file = "pymongo-4.3.3-cp38-cp38-manylinux1_i686.whl", hash = "sha256:dca34367a4e77fcab0693e603a959878eaf2351585e7d752cac544bc6b2dee46"},
+ {file = "pymongo-4.3.3-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:cd6a4afb20fb3c26a7bfd4611a0bbb24d93cbd746f5eb881f114b5e38fd55501"},
+ {file = "pymongo-4.3.3-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:0c466710871d0026c190fc4141e810cf9d9affbf4935e1d273fbdc7d7cda6143"},
+ {file = "pymongo-4.3.3-cp38-cp38-manylinux2014_i686.whl", hash = "sha256:d07d06dba5b5f7d80f9cc45501456e440f759fe79f9895922ed486237ac378a8"},
+ {file = "pymongo-4.3.3-cp38-cp38-manylinux2014_ppc64le.whl", hash = "sha256:711bc52cb98e7892c03e9b669bebd89c0a890a90dbc6d5bb2c47f30239bac6e9"},
+ {file = "pymongo-4.3.3-cp38-cp38-manylinux2014_s390x.whl", hash = "sha256:34b040e095e1671df0c095ec0b04fc4ebb19c4c160f87c2b55c079b16b1a6b00"},
+ {file = "pymongo-4.3.3-cp38-cp38-manylinux2014_x86_64.whl", hash = "sha256:4ed00f96e147f40b565fe7530d1da0b0f3ab803d5dd5b683834500fa5d195ec4"},
+ {file = "pymongo-4.3.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ef888f48eb9203ee1e04b9fb27429017b290fb916f1e7826c2f7808c88798394"},
+ {file = "pymongo-4.3.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:316498b642c00401370b2156b5233b256f9b33799e0a8d9d0b8a7da217a20fca"},
+ {file = "pymongo-4.3.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:fa7e202feb683dad74f00dea066690448d0cfa310f8a277db06ec8eb466601b5"},
+ {file = "pymongo-4.3.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:52896e22115c97f1c829db32aa2760b0d61839cfe08b168c2b1d82f31dbc5f55"},
+ {file = "pymongo-4.3.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7c051fe37c96b9878f37fa58906cb53ecd13dcb7341d3a85f1e2e2f6b10782d9"},
+ {file = "pymongo-4.3.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:5134d33286c045393c7beb51be29754647cec5ebc051cf82799c5ce9820a2ca2"},
+ {file = "pymongo-4.3.3-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:a9c2885b4a8e6e39db5662d8b02ca6dcec796a45e48c2de12552841f061692ba"},
+ {file = "pymongo-4.3.3-cp38-cp38-win32.whl", hash = "sha256:a6cd6f1db75eb07332bd3710f58f5fce4967eadbf751bad653842750a61bda62"},
+ {file = "pymongo-4.3.3-cp38-cp38-win_amd64.whl", hash = "sha256:d5571b6978750601f783cea07fb6b666837010ca57e5cefa389c1d456f6222e2"},
+ {file = "pymongo-4.3.3-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:81d1a7303bd02ca1c5be4aacd4db73593f573ba8e0c543c04c6da6275fd7a47e"},
+ {file = "pymongo-4.3.3-cp39-cp39-manylinux1_i686.whl", hash = "sha256:016c412118e1c23fef3a1eada4f83ae6e8844fd91986b2e066fc1b0013cdd9ae"},
+ {file = "pymongo-4.3.3-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:8fd6e191b92a10310f5a6cfe10d6f839d79d192fb02480bda325286bd1c7b385"},
+ {file = "pymongo-4.3.3-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:e2961b05f9c04a53da8bfc72f1910b6aec7205fcf3ac9c036d24619979bbee4b"},
+ {file = "pymongo-4.3.3-cp39-cp39-manylinux2014_i686.whl", hash = "sha256:b38a96b3eed8edc515b38257f03216f382c4389d022a8834667e2bc63c0c0c31"},
+ {file = "pymongo-4.3.3-cp39-cp39-manylinux2014_ppc64le.whl", hash = "sha256:c1a70c51da9fa95bd75c167edb2eb3f3c4d27bc4ddd29e588f21649d014ec0b7"},
+ {file = "pymongo-4.3.3-cp39-cp39-manylinux2014_s390x.whl", hash = "sha256:8a06a0c02f5606330e8f2e2f3b7949877ca7e4024fa2bff5a4506bec66c49ec7"},
+ {file = "pymongo-4.3.3-cp39-cp39-manylinux2014_x86_64.whl", hash = "sha256:6c2216d8b6a6d019c6f4b1ad55f890e5e77eb089309ffc05b6911c09349e7474"},
+ {file = "pymongo-4.3.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:eac0a143ef4f28f49670bf89cb15847eb80b375d55eba401ca2f777cd425f338"},
+ {file = "pymongo-4.3.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:08fc250b5552ee97ceeae0f52d8b04f360291285fc7437f13daa516ce38fdbc6"},
+ {file = "pymongo-4.3.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704d939656e21b073bfcddd7228b29e0e8a93dd27b54240eaafc0b9a631629a6"},
+ {file = "pymongo-4.3.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1074f1a6f23e28b983c96142f2d45be03ec55d93035b471c26889a7ad2365db3"},
+ {file = "pymongo-4.3.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7b16250238de8dafca225647608dddc7bbb5dce3dd53b4d8e63c1cc287394c2f"},
+ {file = "pymongo-4.3.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:7761cacb8745093062695b11574effea69db636c2fd0a9269a1f0183712927b4"},
+ {file = "pymongo-4.3.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:fd7bb378d82b88387dc10227cfd964f6273eb083e05299e9b97cbe075da12d11"},
+ {file = "pymongo-4.3.3-cp39-cp39-win32.whl", hash = "sha256:dc24d245026a72d9b4953729d31813edd4bd4e5c13622d96e27c284942d33f24"},
+ {file = "pymongo-4.3.3-cp39-cp39-win_amd64.whl", hash = "sha256:fc28e8d85d392a06434e9a934908d97e2cf453d69488d2bcd0bfb881497fd975"},
+ {file = "pymongo-4.3.3.tar.gz", hash = "sha256:34e95ffb0a68bffbc3b437f2d1f25fc916fef3df5cdeed0992da5f42fae9b807"},
+]
+
+[package.dependencies]
+dnspython = ">=1.16.0,<3.0.0"
+
+[package.extras]
+aws = ["pymongo-auth-aws (<2.0.0)"]
+encryption = ["pymongo-auth-aws (<2.0.0)", "pymongocrypt (>=1.3.0,<2.0.0)"]
+gssapi = ["pykerberos"]
+ocsp = ["certifi", "pyopenssl (>=17.2.0)", "requests (<3.0.0)", "service-identity (>=18.1.0)"]
+snappy = ["python-snappy"]
+zstd = ["zstandard"]
+
+[[package]]
+name = "regex"
+version = "2022.10.31"
+description = "Alternative regular expression module, to replace re."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+ {file = "regex-2022.10.31-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:a8ff454ef0bb061e37df03557afda9d785c905dab15584860f982e88be73015f"},
+ {file = "regex-2022.10.31-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:1eba476b1b242620c266edf6325b443a2e22b633217a9835a52d8da2b5c051f9"},
+ {file = "regex-2022.10.31-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d0e5af9a9effb88535a472e19169e09ce750c3d442fb222254a276d77808620b"},
+ {file = "regex-2022.10.31-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d03fe67b2325cb3f09be029fd5da8df9e6974f0cde2c2ac6a79d2634e791dd57"},
+ {file = "regex-2022.10.31-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a9d0b68ac1743964755ae2d89772c7e6fb0118acd4d0b7464eaf3921c6b49dd4"},
+ {file = "regex-2022.10.31-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8a45b6514861916c429e6059a55cf7db74670eaed2052a648e3e4d04f070e001"},
+ {file = "regex-2022.10.31-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8b0886885f7323beea6f552c28bff62cbe0983b9fbb94126531693ea6c5ebb90"},
+ {file = "regex-2022.10.31-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:5aefb84a301327ad115e9d346c8e2760009131d9d4b4c6b213648d02e2abe144"},
+ {file = "regex-2022.10.31-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:702d8fc6f25bbf412ee706bd73019da5e44a8400861dfff7ff31eb5b4a1276dc"},
+ {file = "regex-2022.10.31-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:a3c1ebd4ed8e76e886507c9eddb1a891673686c813adf889b864a17fafcf6d66"},
+ {file = "regex-2022.10.31-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:50921c140561d3db2ab9f5b11c5184846cde686bb5a9dc64cae442926e86f3af"},
+ {file = "regex-2022.10.31-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:7db345956ecce0c99b97b042b4ca7326feeec6b75facd8390af73b18e2650ffc"},
+ {file = "regex-2022.10.31-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:763b64853b0a8f4f9cfb41a76a4a85a9bcda7fdda5cb057016e7706fde928e66"},
+ {file = "regex-2022.10.31-cp310-cp310-win32.whl", hash = "sha256:44136355e2f5e06bf6b23d337a75386371ba742ffa771440b85bed367c1318d1"},
+ {file = "regex-2022.10.31-cp310-cp310-win_amd64.whl", hash = "sha256:bfff48c7bd23c6e2aec6454aaf6edc44444b229e94743b34bdcdda2e35126cf5"},
+ {file = "regex-2022.10.31-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4b4b1fe58cd102d75ef0552cf17242705ce0759f9695334a56644ad2d83903fe"},
+ {file = "regex-2022.10.31-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:542e3e306d1669b25936b64917285cdffcd4f5c6f0247636fec037187bd93542"},
+ {file = "regex-2022.10.31-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c27cc1e4b197092e50ddbf0118c788d9977f3f8f35bfbbd3e76c1846a3443df7"},
+ {file = "regex-2022.10.31-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b8e38472739028e5f2c3a4aded0ab7eadc447f0d84f310c7a8bb697ec417229e"},
+ {file = "regex-2022.10.31-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:76c598ca73ec73a2f568e2a72ba46c3b6c8690ad9a07092b18e48ceb936e9f0c"},
+ {file = "regex-2022.10.31-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c28d3309ebd6d6b2cf82969b5179bed5fefe6142c70f354ece94324fa11bf6a1"},
+ {file = "regex-2022.10.31-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9af69f6746120998cd9c355e9c3c6aec7dff70d47247188feb4f829502be8ab4"},
+ {file = "regex-2022.10.31-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:a5f9505efd574d1e5b4a76ac9dd92a12acb2b309551e9aa874c13c11caefbe4f"},
+ {file = "regex-2022.10.31-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:5ff525698de226c0ca743bfa71fc6b378cda2ddcf0d22d7c37b1cc925c9650a5"},
+ {file = "regex-2022.10.31-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:4fe7fda2fe7c8890d454f2cbc91d6c01baf206fbc96d89a80241a02985118c0c"},
+ {file = "regex-2022.10.31-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:2cdc55ca07b4e70dda898d2ab7150ecf17c990076d3acd7a5f3b25cb23a69f1c"},
+ {file = "regex-2022.10.31-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:44a6c2f6374e0033873e9ed577a54a3602b4f609867794c1a3ebba65e4c93ee7"},
+ {file = "regex-2022.10.31-cp311-cp311-win32.whl", hash = "sha256:d8716f82502997b3d0895d1c64c3b834181b1eaca28f3f6336a71777e437c2af"},
+ {file = "regex-2022.10.31-cp311-cp311-win_amd64.whl", hash = "sha256:61edbca89aa3f5ef7ecac8c23d975fe7261c12665f1d90a6b1af527bba86ce61"},
+ {file = "regex-2022.10.31-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:0a069c8483466806ab94ea9068c34b200b8bfc66b6762f45a831c4baaa9e8cdd"},
+ {file = "regex-2022.10.31-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d26166acf62f731f50bdd885b04b38828436d74e8e362bfcb8df221d868b5d9b"},
+ {file = "regex-2022.10.31-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ac741bf78b9bb432e2d314439275235f41656e189856b11fb4e774d9f7246d81"},
+ {file = "regex-2022.10.31-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:75f591b2055523fc02a4bbe598aa867df9e953255f0b7f7715d2a36a9c30065c"},
+ {file = "regex-2022.10.31-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b30bddd61d2a3261f025ad0f9ee2586988c6a00c780a2fb0a92cea2aa702c54"},
+ {file = "regex-2022.10.31-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ef4163770525257876f10e8ece1cf25b71468316f61451ded1a6f44273eedeb5"},
+ {file = "regex-2022.10.31-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:7b280948d00bd3973c1998f92e22aa3ecb76682e3a4255f33e1020bd32adf443"},
+ {file = "regex-2022.10.31-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:d0213671691e341f6849bf33cd9fad21f7b1cb88b89e024f33370733fec58742"},
+ {file = "regex-2022.10.31-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:22e7ebc231d28393dfdc19b185d97e14a0f178bedd78e85aad660e93b646604e"},
+ {file = "regex-2022.10.31-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:8ad241da7fac963d7573cc67a064c57c58766b62a9a20c452ca1f21050868dfa"},
+ {file = "regex-2022.10.31-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:586b36ebda81e6c1a9c5a5d0bfdc236399ba6595e1397842fd4a45648c30f35e"},
+ {file = "regex-2022.10.31-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:0653d012b3bf45f194e5e6a41df9258811ac8fc395579fa82958a8b76286bea4"},
+ {file = "regex-2022.10.31-cp36-cp36m-win32.whl", hash = "sha256:144486e029793a733e43b2e37df16a16df4ceb62102636ff3db6033994711066"},
+ {file = "regex-2022.10.31-cp36-cp36m-win_amd64.whl", hash = "sha256:c14b63c9d7bab795d17392c7c1f9aaabbffd4cf4387725a0ac69109fb3b550c6"},
+ {file = "regex-2022.10.31-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:4cac3405d8dda8bc6ed499557625585544dd5cbf32072dcc72b5a176cb1271c8"},
+ {file = "regex-2022.10.31-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:23cbb932cc53a86ebde0fb72e7e645f9a5eec1a5af7aa9ce333e46286caef783"},
+ {file = "regex-2022.10.31-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:74bcab50a13960f2a610cdcd066e25f1fd59e23b69637c92ad470784a51b1347"},
+ {file = "regex-2022.10.31-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:78d680ef3e4d405f36f0d6d1ea54e740366f061645930072d39bca16a10d8c93"},
+ {file = "regex-2022.10.31-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ce6910b56b700bea7be82c54ddf2e0ed792a577dfaa4a76b9af07d550af435c6"},
+ {file = "regex-2022.10.31-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:659175b2144d199560d99a8d13b2228b85e6019b6e09e556209dfb8c37b78a11"},
+ {file = "regex-2022.10.31-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:1ddf14031a3882f684b8642cb74eea3af93a2be68893901b2b387c5fd92a03ec"},
+ {file = "regex-2022.10.31-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:b683e5fd7f74fb66e89a1ed16076dbab3f8e9f34c18b1979ded614fe10cdc4d9"},
+ {file = "regex-2022.10.31-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:2bde29cc44fa81c0a0c8686992c3080b37c488df167a371500b2a43ce9f026d1"},
+ {file = "regex-2022.10.31-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:4919899577ba37f505aaebdf6e7dc812d55e8f097331312db7f1aab18767cce8"},
+ {file = "regex-2022.10.31-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:9c94f7cc91ab16b36ba5ce476f1904c91d6c92441f01cd61a8e2729442d6fcf5"},
+ {file = "regex-2022.10.31-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:ae1e96785696b543394a4e3f15f3f225d44f3c55dafe3f206493031419fedf95"},
+ {file = "regex-2022.10.31-cp37-cp37m-win32.whl", hash = "sha256:c670f4773f2f6f1957ff8a3962c7dd12e4be54d05839b216cb7fd70b5a1df394"},
+ {file = "regex-2022.10.31-cp37-cp37m-win_amd64.whl", hash = "sha256:8e0caeff18b96ea90fc0eb6e3bdb2b10ab5b01a95128dfeccb64a7238decf5f0"},
+ {file = "regex-2022.10.31-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:131d4be09bea7ce2577f9623e415cab287a3c8e0624f778c1d955ec7c281bd4d"},
+ {file = "regex-2022.10.31-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:e613a98ead2005c4ce037c7b061f2409a1a4e45099edb0ef3200ee26ed2a69a8"},
+ {file = "regex-2022.10.31-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:052b670fafbe30966bbe5d025e90b2a491f85dfe5b2583a163b5e60a85a321ad"},
+ {file = "regex-2022.10.31-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:aa62a07ac93b7cb6b7d0389d8ef57ffc321d78f60c037b19dfa78d6b17c928ee"},
+ {file = "regex-2022.10.31-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5352bea8a8f84b89d45ccc503f390a6be77917932b1c98c4cdc3565137acc714"},
+ {file = "regex-2022.10.31-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:20f61c9944f0be2dc2b75689ba409938c14876c19d02f7585af4460b6a21403e"},
+ {file = "regex-2022.10.31-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:29c04741b9ae13d1e94cf93fca257730b97ce6ea64cfe1eba11cf9ac4e85afb6"},
+ {file = "regex-2022.10.31-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:543883e3496c8b6d58bd036c99486c3c8387c2fc01f7a342b760c1ea3158a318"},
+ {file = "regex-2022.10.31-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:b7a8b43ee64ca8f4befa2bea4083f7c52c92864d8518244bfa6e88c751fa8fff"},
+ {file = "regex-2022.10.31-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:6a9a19bea8495bb419dc5d38c4519567781cd8d571c72efc6aa959473d10221a"},
+ {file = "regex-2022.10.31-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:6ffd55b5aedc6f25fd8d9f905c9376ca44fcf768673ffb9d160dd6f409bfda73"},
+ {file = "regex-2022.10.31-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:4bdd56ee719a8f751cf5a593476a441c4e56c9b64dc1f0f30902858c4ef8771d"},
+ {file = "regex-2022.10.31-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:8ca88da1bd78990b536c4a7765f719803eb4f8f9971cc22d6ca965c10a7f2c4c"},
+ {file = "regex-2022.10.31-cp38-cp38-win32.whl", hash = "sha256:5a260758454580f11dd8743fa98319bb046037dfab4f7828008909d0aa5292bc"},
+ {file = "regex-2022.10.31-cp38-cp38-win_amd64.whl", hash = "sha256:5e6a5567078b3eaed93558842346c9d678e116ab0135e22eb72db8325e90b453"},
+ {file = "regex-2022.10.31-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:5217c25229b6a85049416a5c1e6451e9060a1edcf988641e309dbe3ab26d3e49"},
+ {file = "regex-2022.10.31-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4bf41b8b0a80708f7e0384519795e80dcb44d7199a35d52c15cc674d10b3081b"},
+ {file = "regex-2022.10.31-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0cf0da36a212978be2c2e2e2d04bdff46f850108fccc1851332bcae51c8907cc"},
+ {file = "regex-2022.10.31-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d403d781b0e06d2922435ce3b8d2376579f0c217ae491e273bab8d092727d244"},
+ {file = "regex-2022.10.31-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a37d51fa9a00d265cf73f3de3930fa9c41548177ba4f0faf76e61d512c774690"},
+ {file = "regex-2022.10.31-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e4f781ffedd17b0b834c8731b75cce2639d5a8afe961c1e58ee7f1f20b3af185"},
+ {file = "regex-2022.10.31-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d243b36fbf3d73c25e48014961e83c19c9cc92530516ce3c43050ea6276a2ab7"},
+ {file = "regex-2022.10.31-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:370f6e97d02bf2dd20d7468ce4f38e173a124e769762d00beadec3bc2f4b3bc4"},
+ {file = "regex-2022.10.31-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:597f899f4ed42a38df7b0e46714880fb4e19a25c2f66e5c908805466721760f5"},
+ {file = "regex-2022.10.31-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:7dbdce0c534bbf52274b94768b3498abdf675a691fec5f751b6057b3030f34c1"},
+ {file = "regex-2022.10.31-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:22960019a842777a9fa5134c2364efaed5fbf9610ddc5c904bd3a400973b0eb8"},
+ {file = "regex-2022.10.31-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:7f5a3ffc731494f1a57bd91c47dc483a1e10048131ffb52d901bfe2beb6102e8"},
+ {file = "regex-2022.10.31-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:7ef6b5942e6bfc5706301a18a62300c60db9af7f6368042227ccb7eeb22d0892"},
+ {file = "regex-2022.10.31-cp39-cp39-win32.whl", hash = "sha256:395161bbdbd04a8333b9ff9763a05e9ceb4fe210e3c7690f5e68cedd3d65d8e1"},
+ {file = "regex-2022.10.31-cp39-cp39-win_amd64.whl", hash = "sha256:957403a978e10fb3ca42572a23e6f7badff39aa1ce2f4ade68ee452dc6807692"},
+ {file = "regex-2022.10.31.tar.gz", hash = "sha256:a3a98921da9a1bf8457aeee6a551948a83601689e5ecdd736894ea9bbec77e83"},
+]
+
+[[package]]
+name = "tqdm"
+version = "4.64.1"
+description = "Fast, Extensible Progress Meter"
+category = "main"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,>=2.7"
+files = [
+ {file = "tqdm-4.64.1-py2.py3-none-any.whl", hash = "sha256:6fee160d6ffcd1b1c68c65f14c829c22832bc401726335ce92c52d395944a6a1"},
+ {file = "tqdm-4.64.1.tar.gz", hash = "sha256:5f4f682a004951c1b450bc753c710e9280c5746ce6ffedee253ddbcbf54cf1e4"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[package.extras]
+dev = ["py-make (>=0.1.0)", "twine", "wheel"]
+notebook = ["ipywidgets (>=6)"]
+slack = ["slack-sdk"]
+telegram = ["requests"]
+
+[metadata]
+lock-version = "2.0"
+python-versions = "^3.10"
+content-hash = "baf82d3820a17be0b6fcd6b31d1627a6ab198c9c094a2ee0fc2b0caca2659a72"
diff --git a/pyproject.toml b/pyproject.toml
index c29cc6b..06b5a44 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -132,6 +132,9 @@ classifiers = [
# 3.10.1 → == 3.10.1
python = "^3.10"
+pymongo = "^4.3.3"
+nltk = "^3.8.1"
+cfig = {extras = ["cli"], version = "^0.3.0"}
diff --git a/unimore-bda-6.iml b/unimore-bda-6.iml
index 9a5cfce..7616de1 100644
--- a/unimore-bda-6.iml
+++ b/unimore-bda-6.iml
@@ -2,7 +2,12 @@
-
+
+
+
+
+
+
\ No newline at end of file
diff --git a/unimore_bda_6/__main__.py b/unimore_bda_6/__main__.py
index a015126..d577504 100644
--- a/unimore_bda_6/__main__.py
+++ b/unimore_bda_6/__main__.py
@@ -1,4 +1,5 @@
-# If you are building an **application**, use this file to run code!
+from .database import create_mongo_client_from_config
+
def main():
pass
diff --git a/unimore_bda_6/analysis.py b/unimore_bda_6/analysis.py
new file mode 100644
index 0000000..7a64c78
--- /dev/null
+++ b/unimore_bda_6/analysis.py
@@ -0,0 +1,14 @@
+import nltk
+import nltk.sentiment
+
+
+def create_sentiment_analysis_model() -> ntlk.sentiment.SentimentAnalyzer:
+ analyzer = nltk.sentiment.SentimentAnalyzer()
+
+
+def train():
+ ...
+
+
+def test():
+ ...
diff --git a/unimore_bda_6/config.py b/unimore_bda_6/config.py
new file mode 100644
index 0000000..5e5540d
--- /dev/null
+++ b/unimore_bda_6/config.py
@@ -0,0 +1,37 @@
+import cfig
+
+config = cfig.Configuration()
+
+
+@config.required()
+def MONGO_HOST(val: str) -> str:
+ """
+ The hostname of the MongoDB database to connect to.
+ """
+ return val
+
+
+@config.required()
+def MONGO_PORT(val: str) -> str:
+ """
+ The port of the MongoDB database to connect to.
+ """
+ return val
+
+
+@config.required()
+def TRAINING_SET_SIZE(val: str) -> int:
+ """
+ The number of reviews from each category to fetch for the training set.
+ """
+ try:
+ return int(val)
+ except ValueError:
+ raise cfig.InvalidValueError("Not an int.")
+
+
+__all__ = (
+ "config",
+ "MONGO_HOST",
+ "MONGO_PORT",
+)
diff --git a/unimore_bda_6/database.py b/unimore_bda_6/database.py
new file mode 100644
index 0000000..d4bcd6c
--- /dev/null
+++ b/unimore_bda_6/database.py
@@ -0,0 +1,101 @@
+import typing as t
+import pymongo
+import pymongo.collection
+import contextlib
+import bson
+
+from .config import MONGO_HOST, MONGO_PORT
+
+
+class Review(t.TypedDict):
+ _id: bson.ObjectId
+ reviewerID: str
+ asin: str
+ reviewerName: str
+ helpful: tuple[int, int]
+ reviewText: str
+ overall: float
+ summary: str
+ unixReviewTime: int
+ reviewTime: str
+
+
+@contextlib.contextmanager
+def mongo_client_from_config() -> t.ContextManager[pymongo.MongoClient]:
+ """
+ Create a new MongoDB client and yield it.
+ """
+ client = pymongo.MongoClient(
+ host=MONGO_HOST.__resolved__,
+ port=MONGO_PORT.__resolved__,
+ )
+ yield client
+ client.close()
+
+
+@contextlib.contextmanager
+def mongo_reviews_collection_from_config() -> pymongo.collection.Collection[Review]:
+ """
+ Create a new MongoDB client, access the ``reviews`` collection in the ``reviews`` database, and yield it.
+ """
+ with mongo_client_from_config() as db:
+ yield db.reviews.reviews
+
+
+def sample_reviews(reviews: pymongo.collection.Collection, amount: int) -> t.Iterable[Review]:
+ """
+ Get ``amount`` random reviews from the ``reviews`` collection.
+ """
+
+ return reviews.aggregate([
+ {"$sample": {"size": amount}}
+ ])
+
+
+def sample_reviews_by_rating(reviews: pymongo.collection.Collection, rating: float, amount: int) -> t.Iterable[Review]:
+ """
+ Get ``amount`` random reviews with ``rating`` stars from the ``reviews`` collection.
+ """
+
+ return reviews.aggregate([
+ {"$filter": {"overall": rating}},
+ {"$sample": {"size": amount}},
+ ])
+
+
+def sample_reviews_by_rating_polar(reviews: pymongo.collection.Collection, amount: int) -> t.Iterable[Review]:
+ """
+ Get ``amount`` random reviews with either a 5-star or 1-star rating from the ``reviews`` collection.
+ """
+
+ return reviews.aggregate([
+ {"$filter": {"overall": {"$or": [1.0, 5.0]}}},
+ {"$sample": {"size": amount}},
+ ])
+
+
+def get_reviews_training_set(reviews: pymongo.collection.Collection, amount: int) -> t.Iterable[Review]:
+ """
+ Get the subset of reviews that should act as training set.
+ """
+
+ # Handle odd numbers
+ positive_amount: int = amount // 2
+ negative_amount: int = amount - positive_amount
+
+ # Sample the required reviews
+ positive = sample_reviews_by_rating(reviews, 5.0, positive_amount)
+ negative = sample_reviews_by_rating(reviews, 1.0, negative_amount)
+
+ # Randomness here does not matter, so just merge the lists
+ both = [*positive, *negative]
+
+ return both
+
+
+def get_reviews_test_set(reviews: pymongo.collection.Collection, amount: int) -> t.Iterable[Review]:
+ """
+ Get the subset of reviews that should act as test set.
+ """
+
+ return sample_reviews_by_rating_polar(reviews, amount)