1
0
AMUseBot/ai_talks/AMUseBotBackend/utils/NLU_Trainer.ipynb
2023-06-05 21:23:33 +02:00

2 lines
67 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{"cells":[{"cell_type":"code","execution_count":2,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":11794,"status":"ok","timestamp":1671521150117,"user":{"displayName":"Mikołaj Krzymiński","userId":"01535337980860424008"},"user_tz":-60},"id":"rac6R0-Kd6QN","outputId":"9b8817b6-7f2c-4465-d2c4-40cffa0a40e4"},"outputs":[{"name":"stdout","output_type":"stream","text":["Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"]}],"source":["# Load the Drive helper and mount\n","from google.colab import drive\n","drive.mount('/content/drive')"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":7,"status":"ok","timestamp":1671454953415,"user":{"displayName":"Mikołaj Krzymiński","userId":"01535337980860424008"},"user_tz":-60},"id":"EWTlBiRIKFK7","outputId":"fc6860da-bfe4-40ee-e65e-42f809e3bf09"},"outputs":[{"name":"stdout","output_type":"stream","text":["shell-init: error retrieving current directory: getcwd: cannot access parent directories: No such file or directory\n","fatal: could not create work tree dir 'CookDial': No such file or directory\n"]}],"source":["! git clone https://github.com/YiweiJiang2015/CookDial.git"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":405,"status":"ok","timestamp":1671455100412,"user":{"displayName":"Mikołaj Krzymiński","userId":"01535337980860424008"},"user_tz":-60},"id":"a03eUTKjeJbT","outputId":"7ef67f9a-b599-48b7-9752-fa25bad2fac4"},"outputs":[{"name":"stdout","output_type":"stream","text":["/content/drive/MyDrive/CookDial\n"]}],"source":["!pwd\n"]},{"cell_type":"code","execution_count":2,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":221,"status":"ok","timestamp":1671493724901,"user":{"displayName":"Mikołaj Krzymiński","userId":"01535337980860424008"},"user_tz":-60},"id":"21J3SKwHKMPm","outputId":"2bd50190-1a30-4739-8f5d-a75117b9e310"},"outputs":[{"name":"stdout","output_type":"stream","text":["/content/drive/MyDrive/CookDial\n"]}],"source":["%cd /content/drive/MyDrive/CookDial"]},{"cell_type":"code","execution_count":3,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":117638,"status":"ok","timestamp":1671493844497,"user":{"displayName":"Mikołaj Krzymiński","userId":"01535337980860424008"},"user_tz":-60},"id":"LGdaIt1DN42D","outputId":"e1e9f5b4-e6ed-4ce4-b711-3df575c5cbaf"},"outputs":[{"name":"stdout","output_type":"stream","text":["--2022-12-19 23:48:47-- https://repo.anaconda.com/miniconda/Miniconda3-py39_4.9.2-Linux-x86_64.sh\n","Resolving repo.anaconda.com (repo.anaconda.com)... 104.16.131.3, 104.16.130.3, 2606:4700::6810:8303, ...\n","Connecting to repo.anaconda.com (repo.anaconda.com)|104.16.131.3|:443... connected.\n","HTTP request sent, awaiting response... 200 OK\n","Length: 61451533 (59M) [application/x-sh]\n","Saving to: mini.sh\n","\n","mini.sh 100%[===================>] 58.60M 62.7MB/s in 0.9s \n","\n","2022-12-19 23:48:48 (62.7 MB/s) - mini.sh saved [61451533/61451533]\n","\n","PREFIX=/usr/local\n","Unpacking payload ...\n","Collecting package metadata (current_repodata.json): - \b\b\\ \b\bdone\n","Solving environment: / \b\b- \b\b\\ \b\bdone\n","\n","## Package Plan ##\n","\n"," environment location: /usr/local\n","\n"," added / updated specs:\n"," - _libgcc_mutex==0.1=main\n"," - brotlipy==0.7.0=py39h27cfd23_1003\n"," - ca-certificates==2020.12.8=h06a4308_0\n"," - certifi==2020.12.5=py39h06a4308_0\n"," - cffi==1.14.4=py39h261ae71_0\n"," - chardet==3.0.4=py39h06a4308_1003\n"," - conda-package-handling==1.7.2=py39h27cfd23_1\n"," - conda==4.9.2=py39h06a4308_0\n"," - cryptography==3.3.1=py39h3c74f83_0\n"," - idna==2.10=py_0\n"," - ld_impl_linux-64==2.33.1=h53a641e_7\n"," - libedit==3.1.20191231=h14c3975_1\n"," - libffi==3.3=he6710b0_2\n"," - libgcc-ng==9.1.0=hdf63c60_0\n"," - libstdcxx-ng==9.1.0=hdf63c60_0\n"," - ncurses==6.2=he6710b0_1\n"," - openssl==1.1.1i=h27cfd23_0\n"," - pip==20.3.1=py39h06a4308_0\n"," - pycosat==0.6.3=py39h27cfd23_0\n"," - pycparser==2.20=py_2\n"," - pyopenssl==20.0.0=pyhd3eb1b0_1\n"," - pysocks==1.7.1=py39h06a4308_0\n"," - python==3.9.1=hdb3f193_2\n"," - readline==8.0=h7b6447c_0\n"," - requests==2.25.0=pyhd3eb1b0_0\n"," - ruamel_yaml==0.15.80=py39h27cfd23_0\n"," - setuptools==51.0.0=py39h06a4308_2\n"," - six==1.15.0=py39h06a4308_0\n"," - sqlite==3.33.0=h62c20be_0\n"," - tk==8.6.10=hbc83047_0\n"," - tqdm==4.54.1=pyhd3eb1b0_0\n"," - tzdata==2020d=h14c3975_0\n"," - urllib3==1.25.11=py_0\n"," - wheel==0.36.1=pyhd3eb1b0_0\n"," - xz==5.2.5=h7b6447c_0\n"," - yaml==0.2.5=h7b6447c_0\n"," - zlib==1.2.11=h7b6447c_3\n","\n","\n","The following NEW packages will be INSTALLED:\n","\n"," _libgcc_mutex pkgs/main/linux-64::_libgcc_mutex-0.1-main\n"," brotlipy pkgs/main/linux-64::brotlipy-0.7.0-py39h27cfd23_1003\n"," ca-certificates pkgs/main/linux-64::ca-certificates-2020.12.8-h06a4308_0\n"," certifi pkgs/main/linux-64::certifi-2020.12.5-py39h06a4308_0\n"," cffi pkgs/main/linux-64::cffi-1.14.4-py39h261ae71_0\n"," chardet pkgs/main/linux-64::chardet-3.0.4-py39h06a4308_1003\n"," conda pkgs/main/linux-64::conda-4.9.2-py39h06a4308_0\n"," conda-package-han~ pkgs/main/linux-64::conda-package-handling-1.7.2-py39h27cfd23_1\n"," cryptography pkgs/main/linux-64::cryptography-3.3.1-py39h3c74f83_0\n"," idna pkgs/main/noarch::idna-2.10-py_0\n"," ld_impl_linux-64 pkgs/main/linux-64::ld_impl_linux-64-2.33.1-h53a641e_7\n"," libedit pkgs/main/linux-64::libedit-3.1.20191231-h14c3975_1\n"," libffi pkgs/main/linux-64::libffi-3.3-he6710b0_2\n"," libgcc-ng pkgs/main/linux-64::libgcc-ng-9.1.0-hdf63c60_0\n"," libstdcxx-ng pkgs/main/linux-64::libstdcxx-ng-9.1.0-hdf63c60_0\n"," ncurses pkgs/main/linux-64::ncurses-6.2-he6710b0_1\n"," openssl pkgs/main/linux-64::openssl-1.1.1i-h27cfd23_0\n"," pip pkgs/main/linux-64::pip-20.3.1-py39h06a4308_0\n"," pycosat pkgs/main/linux-64::pycosat-0.6.3-py39h27cfd23_0\n"," pycparser pkgs/main/noarch::pycparser-2.20-py_2\n"," pyopenssl pkgs/main/noarch::pyopenssl-20.0.0-pyhd3eb1b0_1\n"," pysocks pkgs/main/linux-64::pysocks-1.7.1-py39h06a4308_0\n"," python pkgs/main/linux-64::python-3.9.1-hdb3f193_2\n"," readline pkgs/main/linux-64::readline-8.0-h7b6447c_0\n"," requests pkgs/main/noarch::requests-2.25.0-pyhd3eb1b0_0\n"," ruamel_yaml pkgs/main/linux-64::ruamel_yaml-0.15.80-py39h27cfd23_0\n"," setuptools pkgs/main/linux-64::setuptools-51.0.0-py39h06a4308_2\n"," six pkgs/main/linux-64::six-1.15.0-py39h06a4308_0\n"," sqlite pkgs/main/linux-64::sqlite-3.33.0-h62c20be_0\n"," tk pkgs/main/linux-64::tk-8.6.10-hbc83047_0\n"," tqdm pkgs/main/noarch::tqdm-4.54.1-pyhd3eb1b0_0\n"," tzdata pkgs/main/noarch::tzdata-2020d-h14c3975_0\n"," urllib3 pkgs/main/noarch::urllib3-1.25.11-py_0\n"," wheel pkgs/main/noarch::wheel-0.36.1-pyhd3eb1b0_0\n"," xz pkgs/main/linux-64::xz-5.2.5-h7b6447c_0\n"," yaml pkgs/main/linux-64::yaml-0.2.5-h7b6447c_0\n"," zlib pkgs/main/linux-64::zlib-1.2.11-h7b6447c_3\n","\n","\n","Preparing transaction: / \b\b- \b\b\\ \b\b| \b\bdone\n","Executing transaction: - \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\bdone\n","installation finished.\n","WARNING:\n"," You currently have a PYTHONPATH environment variable set. This may cause\n"," unexpected behavior when running the Python interpreter in Miniconda3.\n"," For best results, please verify that your PYTHONPATH only points to\n"," directories of packages that are compatible with the Python interpreter\n"," in Miniconda3: /usr/local\n","Collecting package metadata (current_repodata.json): ...working... done\n","Solving environment: ...working... done\n","\n","## Package Plan ##\n","\n"," environment location: /usr/local\n","\n"," added / updated specs:\n"," - jupyter\n","\n","\n","The following packages will be downloaded:\n","\n"," package | build\n"," ---------------------------|-----------------\n"," _openmp_mutex-5.1 | 1_gnu 21 KB\n"," anyio-3.5.0 | py39h06a4308_0 167 KB\n"," argon2-cffi-21.3.0 | pyhd3eb1b0_0 15 KB\n"," argon2-cffi-bindings-21.2.0| py39h7f8727e_0 33 KB\n"," asttokens-2.0.5 | pyhd3eb1b0_0 20 KB\n"," attrs-22.1.0 | py39h06a4308_0 85 KB\n"," babel-2.9.1 | pyhd3eb1b0_0 5.5 MB\n"," backcall-0.2.0 | pyhd3eb1b0_0 13 KB\n"," beautifulsoup4-4.11.1 | py39h06a4308_0 185 KB\n"," bleach-4.1.0 | pyhd3eb1b0_0 123 KB\n"," ca-certificates-2022.10.11 | h06a4308_0 124 KB\n"," certifi-2022.9.24 | py39h06a4308_0 154 KB\n"," conda-22.11.1 | py39h06a4308_4 927 KB\n"," dbus-1.13.18 | hb2f20db_0 504 KB\n"," debugpy-1.5.1 | py39h295c915_0 1.7 MB\n"," decorator-5.1.1 | pyhd3eb1b0_0 12 KB\n"," defusedxml-0.7.1 | pyhd3eb1b0_0 23 KB\n"," entrypoints-0.4 | py39h06a4308_0 16 KB\n"," executing-0.8.3 | pyhd3eb1b0_0 18 KB\n"," expat-2.4.9 | h6a678d5_0 156 KB\n"," flit-core-3.6.0 | pyhd3eb1b0_0 42 KB\n"," fontconfig-2.14.1 | h52c9d5c_1 281 KB\n"," freetype-2.12.1 | h4a9f257_0 626 KB\n"," giflib-5.2.1 | h7b6447c_0 78 KB\n"," glib-2.69.1 | h4ff587b_1 1.7 MB\n"," gst-plugins-base-1.14.0 | h8213a91_2 4.9 MB\n"," gstreamer-1.14.0 | h28cd5cc_2 3.2 MB\n"," icu-58.2 | he6710b0_3 10.5 MB\n"," importlib-metadata-4.11.3 | py39h06a4308_0 40 KB\n"," ipykernel-6.15.2 | py39h06a4308_0 190 KB\n"," ipython-8.7.0 | py39h06a4308_0 1.0 MB\n"," ipython_genutils-0.2.0 | pyhd3eb1b0_1 27 KB\n"," ipywidgets-7.6.5 | pyhd3eb1b0_1 105 KB\n"," jedi-0.18.1 | py39h06a4308_1 982 KB\n"," jinja2-3.1.2 | py39h06a4308_0 211 KB\n"," jpeg-9e | h7f8727e_0 240 KB\n"," json5-0.9.6 | pyhd3eb1b0_0 21 KB\n"," jsonschema-4.16.0 | py39h06a4308_0 129 KB\n"," jupyter-1.0.0 | py39h06a4308_8 7 KB\n"," jupyter_client-7.4.7 | py39h06a4308_0 209 KB\n"," jupyter_console-6.4.3 | pyhd3eb1b0_0 23 KB\n"," jupyter_core-4.11.2 | py39h06a4308_0 80 KB\n"," jupyter_server-1.18.1 | py39h06a4308_0 356 KB\n"," jupyterlab-3.5.0 | py39h06a4308_0 4.2 MB\n"," jupyterlab_pygments-0.1.2 | py_0 8 KB\n"," jupyterlab_server-2.16.3 | py39h06a4308_0 80 KB\n"," jupyterlab_widgets-1.0.0 | pyhd3eb1b0_1 109 KB\n"," krb5-1.19.2 | hac12032_0 1.2 MB\n"," lerc-3.0 | h295c915_0 196 KB\n"," libclang-10.0.1 |default_hb85057a_2 10.8 MB\n"," libdeflate-1.8 | h7f8727e_5 51 KB\n"," libedit-3.1.20221030 | h5eee18b_0 181 KB\n"," libevent-2.1.12 | h8f2d780_0 425 KB\n"," libgcc-ng-11.2.0 | h1234567_1 5.3 MB\n"," libgomp-11.2.0 | h1234567_1 474 KB\n"," libllvm10-10.0.1 | hbcb73fb_5 22.1 MB\n"," libpng-1.6.37 | hbc83047_0 278 KB\n"," libpq-12.9 | h16c4e8d_3 2.1 MB\n"," libsodium-1.0.18 | h7b6447c_0 244 KB\n"," libstdcxx-ng-11.2.0 | h1234567_1 4.7 MB\n"," libtiff-4.4.0 | hecacb30_0 471 KB\n"," libuuid-1.41.5 | h5eee18b_0 27 KB\n"," libwebp-1.2.4 | h11a3e52_0 79 KB\n"," libwebp-base-1.2.4 | h5eee18b_0 347 KB\n"," libxcb-1.15 | h7f8727e_0 505 KB\n"," libxkbcommon-1.0.1 | hfa300c1_0 483 KB\n"," libxml2-2.9.14 | h74e7548_0 718 KB\n"," libxslt-1.1.35 | h4e12654_0 453 KB\n"," lxml-4.9.1 | py39h1edc446_0 1.3 MB\n"," lz4-c-1.9.4 | h6a678d5_0 154 KB\n"," markupsafe-2.1.1 | py39h7f8727e_0 21 KB\n"," matplotlib-inline-0.1.6 | py39h06a4308_0 16 KB\n"," mistune-0.8.4 |py39h27cfd23_1000 57 KB\n"," nbclassic-0.4.8 | py39h06a4308_0 5.8 MB\n"," nbclient-0.5.13 | py39h06a4308_0 91 KB\n"," nbconvert-6.5.4 | py39h06a4308_0 513 KB\n"," nbformat-5.7.0 | py39h06a4308_0 133 KB\n"," ncurses-6.3 | h5eee18b_3 781 KB\n"," nest-asyncio-1.5.5 | py39h06a4308_0 16 KB\n"," notebook-6.5.2 | py39h06a4308_0 511 KB\n"," notebook-shim-0.2.2 | py39h06a4308_0 22 KB\n"," nspr-4.33 | h295c915_0 222 KB\n"," nss-3.74 | h0370c37_0 1.9 MB\n"," openssl-1.1.1s | h7f8727e_0 3.6 MB\n"," packaging-21.3 | pyhd3eb1b0_0 36 KB\n"," pandocfilters-1.5.0 | pyhd3eb1b0_0 11 KB\n"," parso-0.8.3 | pyhd3eb1b0_0 70 KB\n"," pcre-8.45 | h295c915_0 207 KB\n"," pexpect-4.8.0 | pyhd3eb1b0_3 53 KB\n"," pickleshare-0.7.5 | pyhd3eb1b0_1003 13 KB\n"," pluggy-1.0.0 | py39h06a4308_1 28 KB\n"," ply-3.11 | py39h06a4308_0 81 KB\n"," prometheus_client-0.14.1 | py39h06a4308_0 90 KB\n"," prompt-toolkit-3.0.20 | pyhd3eb1b0_0 259 KB\n"," prompt_toolkit-3.0.20 | hd3eb1b0_0 12 KB\n"," psutil-5.9.0 | py39h5eee18b_0 330 KB\n"," ptyprocess-0.7.0 | pyhd3eb1b0_2 17 KB\n"," pure_eval-0.2.2 | pyhd3eb1b0_0 14 KB\n"," pygments-2.11.2 | pyhd3eb1b0_0 759 KB\n"," pyparsing-3.0.9 | py39h06a4308_0 151 KB\n"," pyqt-5.15.7 | py39h6a678d5_1 5.1 MB\n"," pyqt5-sip-12.11.0 | py39h6a678d5_1 87 KB\n"," pyrsistent-0.18.0 | py39heee7806_0 94 KB\n"," python-dateutil-2.8.2 | pyhd3eb1b0_0 233 KB\n"," python-fastjsonschema-2.16.2| py39h06a4308_0 231 KB\n"," pytz-2022.1 | py39h06a4308_0 194 KB\n"," pyzmq-23.2.0 | py39h6a678d5_0 445 KB\n"," qt-main-5.15.2 | h327a75a_7 45.1 MB\n"," qt-webengine-5.15.9 | hd2b0992_4 47.1 MB\n"," qtconsole-5.3.2 | py39h06a4308_0 176 KB\n"," qtpy-2.2.0 | py39h06a4308_0 84 KB\n"," qtwebkit-5.212 | h4eab89a_4 14.3 MB\n"," ruamel.yaml-0.17.21 | py39h5eee18b_0 178 KB\n"," ruamel.yaml.clib-0.2.6 | py39h5eee18b_1 140 KB\n"," send2trash-1.8.0 | pyhd3eb1b0_1 19 KB\n"," sip-6.6.2 | py39h6a678d5_0 423 KB\n"," sniffio-1.2.0 | py39h06a4308_1 15 KB\n"," soupsieve-2.3.2.post1 | py39h06a4308_0 65 KB\n"," sqlite-3.40.0 | h5082296_0 1.2 MB\n"," stack_data-0.2.0 | pyhd3eb1b0_0 22 KB\n"," terminado-0.13.1 | py39h06a4308_0 30 KB\n"," tinycss2-1.2.1 | py39h06a4308_0 39 KB\n"," toml-0.10.2 | pyhd3eb1b0_0 20 KB\n"," tomli-2.0.1 | py39h06a4308_0 24 KB\n"," toolz-0.12.0 | py39h06a4308_0 105 KB\n"," tornado-6.2 | py39h5eee18b_0 590 KB\n"," traitlets-5.7.1 | py39h06a4308_0 200 KB\n"," typing-extensions-4.4.0 | py39h06a4308_0 8 KB\n"," typing_extensions-4.4.0 | py39h06a4308_0 46 KB\n"," wcwidth-0.2.5 | pyhd3eb1b0_0 26 KB\n"," webencodings-0.5.1 | py39h06a4308_1 20 KB\n"," websocket-client-0.58.0 | py39h06a4308_4 66 KB\n"," widgetsnbextension-3.5.2 | py39h06a4308_0 645 KB\n"," zeromq-4.3.4 | h2531618_0 331 KB\n"," zipp-3.8.0 | py39h06a4308_0 15 KB\n"," zlib-1.2.13 | h5eee18b_0 103 KB\n"," zstd-1.5.2 | ha4553b6_0 488 KB\n"," ------------------------------------------------------------\n"," Total: 224.9 MB\n","\n","The following NEW packages will be INSTALLED:\n","\n"," _openmp_mutex pkgs/main/linux-64::_openmp_mutex-5.1-1_gnu\n"," anyio pkgs/main/linux-64::anyio-3.5.0-py39h06a4308_0\n"," argon2-cffi pkgs/main/noarch::argon2-cffi-21.3.0-pyhd3eb1b0_0\n"," argon2-cffi-bindi~ pkgs/main/linux-64::argon2-cffi-bindings-21.2.0-py39h7f8727e_0\n"," asttokens pkgs/main/noarch::asttokens-2.0.5-pyhd3eb1b0_0\n"," attrs pkgs/main/linux-64::attrs-22.1.0-py39h06a4308_0\n"," babel pkgs/main/noarch::babel-2.9.1-pyhd3eb1b0_0\n"," backcall pkgs/main/noarch::backcall-0.2.0-pyhd3eb1b0_0\n"," beautifulsoup4 pkgs/main/linux-64::beautifulsoup4-4.11.1-py39h06a4308_0\n"," bleach pkgs/main/noarch::bleach-4.1.0-pyhd3eb1b0_0\n"," dbus pkgs/main/linux-64::dbus-1.13.18-hb2f20db_0\n"," debugpy pkgs/main/linux-64::debugpy-1.5.1-py39h295c915_0\n"," decorator pkgs/main/noarch::decorator-5.1.1-pyhd3eb1b0_0\n"," defusedxml pkgs/main/noarch::defusedxml-0.7.1-pyhd3eb1b0_0\n"," entrypoints pkgs/main/linux-64::entrypoints-0.4-py39h06a4308_0\n"," executing pkgs/main/noarch::executing-0.8.3-pyhd3eb1b0_0\n"," expat pkgs/main/linux-64::expat-2.4.9-h6a678d5_0\n"," flit-core pkgs/main/noarch::flit-core-3.6.0-pyhd3eb1b0_0\n"," fontconfig pkgs/main/linux-64::fontconfig-2.14.1-h52c9d5c_1\n"," freetype pkgs/main/linux-64::freetype-2.12.1-h4a9f257_0\n"," giflib pkgs/main/linux-64::giflib-5.2.1-h7b6447c_0\n"," glib pkgs/main/linux-64::glib-2.69.1-h4ff587b_1\n"," gst-plugins-base pkgs/main/linux-64::gst-plugins-base-1.14.0-h8213a91_2\n"," gstreamer pkgs/main/linux-64::gstreamer-1.14.0-h28cd5cc_2\n"," icu pkgs/main/linux-64::icu-58.2-he6710b0_3\n"," importlib-metadata pkgs/main/linux-64::importlib-metadata-4.11.3-py39h06a4308_0\n"," ipykernel pkgs/main/linux-64::ipykernel-6.15.2-py39h06a4308_0\n"," ipython pkgs/main/linux-64::ipython-8.7.0-py39h06a4308_0\n"," ipython_genutils pkgs/main/noarch::ipython_genutils-0.2.0-pyhd3eb1b0_1\n"," ipywidgets pkgs/main/noarch::ipywidgets-7.6.5-pyhd3eb1b0_1\n"," jedi pkgs/main/linux-64::jedi-0.18.1-py39h06a4308_1\n"," jinja2 pkgs/main/linux-64::jinja2-3.1.2-py39h06a4308_0\n"," jpeg pkgs/main/linux-64::jpeg-9e-h7f8727e_0\n"," json5 pkgs/main/noarch::json5-0.9.6-pyhd3eb1b0_0\n"," jsonschema pkgs/main/linux-64::jsonschema-4.16.0-py39h06a4308_0\n"," jupyter pkgs/main/linux-64::jupyter-1.0.0-py39h06a4308_8\n"," jupyter_client pkgs/main/linux-64::jupyter_client-7.4.7-py39h06a4308_0\n"," jupyter_console pkgs/main/noarch::jupyter_console-6.4.3-pyhd3eb1b0_0\n"," jupyter_core pkgs/main/linux-64::jupyter_core-4.11.2-py39h06a4308_0\n"," jupyter_server pkgs/main/linux-64::jupyter_server-1.18.1-py39h06a4308_0\n"," jupyterlab pkgs/main/linux-64::jupyterlab-3.5.0-py39h06a4308_0\n"," jupyterlab_pygmen~ pkgs/main/noarch::jupyterlab_pygments-0.1.2-py_0\n"," jupyterlab_server pkgs/main/linux-64::jupyterlab_server-2.16.3-py39h06a4308_0\n"," jupyterlab_widgets pkgs/main/noarch::jupyterlab_widgets-1.0.0-pyhd3eb1b0_1\n"," krb5 pkgs/main/linux-64::krb5-1.19.2-hac12032_0\n"," lerc pkgs/main/linux-64::lerc-3.0-h295c915_0\n"," libclang pkgs/main/linux-64::libclang-10.0.1-default_hb85057a_2\n"," libdeflate pkgs/main/linux-64::libdeflate-1.8-h7f8727e_5\n"," libevent pkgs/main/linux-64::libevent-2.1.12-h8f2d780_0\n"," libgomp pkgs/main/linux-64::libgomp-11.2.0-h1234567_1\n"," libllvm10 pkgs/main/linux-64::libllvm10-10.0.1-hbcb73fb_5\n"," libpng pkgs/main/linux-64::libpng-1.6.37-hbc83047_0\n"," libpq pkgs/main/linux-64::libpq-12.9-h16c4e8d_3\n"," libsodium pkgs/main/linux-64::libsodium-1.0.18-h7b6447c_0\n"," libtiff pkgs/main/linux-64::libtiff-4.4.0-hecacb30_0\n"," libuuid pkgs/main/linux-64::libuuid-1.41.5-h5eee18b_0\n"," libwebp pkgs/main/linux-64::libwebp-1.2.4-h11a3e52_0\n"," libwebp-base pkgs/main/linux-64::libwebp-base-1.2.4-h5eee18b_0\n"," libxcb pkgs/main/linux-64::libxcb-1.15-h7f8727e_0\n"," libxkbcommon pkgs/main/linux-64::libxkbcommon-1.0.1-hfa300c1_0\n"," libxml2 pkgs/main/linux-64::libxml2-2.9.14-h74e7548_0\n"," libxslt pkgs/main/linux-64::libxslt-1.1.35-h4e12654_0\n"," lxml pkgs/main/linux-64::lxml-4.9.1-py39h1edc446_0\n"," lz4-c pkgs/main/linux-64::lz4-c-1.9.4-h6a678d5_0\n"," markupsafe pkgs/main/linux-64::markupsafe-2.1.1-py39h7f8727e_0\n"," matplotlib-inline pkgs/main/linux-64::matplotlib-inline-0.1.6-py39h06a4308_0\n"," mistune pkgs/main/linux-64::mistune-0.8.4-py39h27cfd23_1000\n"," nbclassic pkgs/main/linux-64::nbclassic-0.4.8-py39h06a4308_0\n"," nbclient pkgs/main/linux-64::nbclient-0.5.13-py39h06a4308_0\n"," nbconvert pkgs/main/linux-64::nbconvert-6.5.4-py39h06a4308_0\n"," nbformat pkgs/main/linux-64::nbformat-5.7.0-py39h06a4308_0\n"," nest-asyncio pkgs/main/linux-64::nest-asyncio-1.5.5-py39h06a4308_0\n"," notebook pkgs/main/linux-64::notebook-6.5.2-py39h06a4308_0\n"," notebook-shim pkgs/main/linux-64::notebook-shim-0.2.2-py39h06a4308_0\n"," nspr pkgs/main/linux-64::nspr-4.33-h295c915_0\n"," nss pkgs/main/linux-64::nss-3.74-h0370c37_0\n"," packaging pkgs/main/noarch::packaging-21.3-pyhd3eb1b0_0\n"," pandocfilters pkgs/main/noarch::pandocfilters-1.5.0-pyhd3eb1b0_0\n"," parso pkgs/main/noarch::parso-0.8.3-pyhd3eb1b0_0\n"," pcre pkgs/main/linux-64::pcre-8.45-h295c915_0\n"," pexpect pkgs/main/noarch::pexpect-4.8.0-pyhd3eb1b0_3\n"," pickleshare pkgs/main/noarch::pickleshare-0.7.5-pyhd3eb1b0_1003\n"," pluggy pkgs/main/linux-64::pluggy-1.0.0-py39h06a4308_1\n"," ply pkgs/main/linux-64::ply-3.11-py39h06a4308_0\n"," prometheus_client pkgs/main/linux-64::prometheus_client-0.14.1-py39h06a4308_0\n"," prompt-toolkit pkgs/main/noarch::prompt-toolkit-3.0.20-pyhd3eb1b0_0\n"," prompt_toolkit pkgs/main/noarch::prompt_toolkit-3.0.20-hd3eb1b0_0\n"," psutil pkgs/main/linux-64::psutil-5.9.0-py39h5eee18b_0\n"," ptyprocess pkgs/main/noarch::ptyprocess-0.7.0-pyhd3eb1b0_2\n"," pure_eval pkgs/main/noarch::pure_eval-0.2.2-pyhd3eb1b0_0\n"," pygments pkgs/main/noarch::pygments-2.11.2-pyhd3eb1b0_0\n"," pyparsing pkgs/main/linux-64::pyparsing-3.0.9-py39h06a4308_0\n"," pyqt pkgs/main/linux-64::pyqt-5.15.7-py39h6a678d5_1\n"," pyqt5-sip pkgs/main/linux-64::pyqt5-sip-12.11.0-py39h6a678d5_1\n"," pyrsistent pkgs/main/linux-64::pyrsistent-0.18.0-py39heee7806_0\n"," python-dateutil pkgs/main/noarch::python-dateutil-2.8.2-pyhd3eb1b0_0\n"," python-fastjsonsc~ pkgs/main/linux-64::python-fastjsonschema-2.16.2-py39h06a4308_0\n"," pytz pkgs/main/linux-64::pytz-2022.1-py39h06a4308_0\n"," pyzmq pkgs/main/linux-64::pyzmq-23.2.0-py39h6a678d5_0\n"," qt-main pkgs/main/linux-64::qt-main-5.15.2-h327a75a_7\n"," qt-webengine pkgs/main/linux-64::qt-webengine-5.15.9-hd2b0992_4\n"," qtconsole pkgs/main/linux-64::qtconsole-5.3.2-py39h06a4308_0\n"," qtpy pkgs/main/linux-64::qtpy-2.2.0-py39h06a4308_0\n"," qtwebkit pkgs/main/linux-64::qtwebkit-5.212-h4eab89a_4\n"," ruamel.yaml pkgs/main/linux-64::ruamel.yaml-0.17.21-py39h5eee18b_0\n"," ruamel.yaml.clib pkgs/main/linux-64::ruamel.yaml.clib-0.2.6-py39h5eee18b_1\n"," send2trash pkgs/main/noarch::send2trash-1.8.0-pyhd3eb1b0_1\n"," sip pkgs/main/linux-64::sip-6.6.2-py39h6a678d5_0\n"," sniffio pkgs/main/linux-64::sniffio-1.2.0-py39h06a4308_1\n"," soupsieve pkgs/main/linux-64::soupsieve-2.3.2.post1-py39h06a4308_0\n"," stack_data pkgs/main/noarch::stack_data-0.2.0-pyhd3eb1b0_0\n"," terminado pkgs/main/linux-64::terminado-0.13.1-py39h06a4308_0\n"," tinycss2 pkgs/main/linux-64::tinycss2-1.2.1-py39h06a4308_0\n"," toml pkgs/main/noarch::toml-0.10.2-pyhd3eb1b0_0\n"," tomli pkgs/main/linux-64::tomli-2.0.1-py39h06a4308_0\n"," toolz pkgs/main/linux-64::toolz-0.12.0-py39h06a4308_0\n"," tornado pkgs/main/linux-64::tornado-6.2-py39h5eee18b_0\n"," traitlets pkgs/main/linux-64::traitlets-5.7.1-py39h06a4308_0\n"," typing-extensions pkgs/main/linux-64::typing-extensions-4.4.0-py39h06a4308_0\n"," typing_extensions pkgs/main/linux-64::typing_extensions-4.4.0-py39h06a4308_0\n"," wcwidth pkgs/main/noarch::wcwidth-0.2.5-pyhd3eb1b0_0\n"," webencodings pkgs/main/linux-64::webencodings-0.5.1-py39h06a4308_1\n"," websocket-client pkgs/main/linux-64::websocket-client-0.58.0-py39h06a4308_4\n"," widgetsnbextension pkgs/main/linux-64::widgetsnbextension-3.5.2-py39h06a4308_0\n"," zeromq pkgs/main/linux-64::zeromq-4.3.4-h2531618_0\n"," zipp pkgs/main/linux-64::zipp-3.8.0-py39h06a4308_0\n"," zstd pkgs/main/linux-64::zstd-1.5.2-ha4553b6_0\n","\n","The following packages will be UPDATED:\n","\n"," ca-certificates 2020.12.8-h06a4308_0 --> 2022.10.11-h06a4308_0\n"," certifi 2020.12.5-py39h06a4308_0 --> 2022.9.24-py39h06a4308_0\n"," conda 4.9.2-py39h06a4308_0 --> 22.11.1-py39h06a4308_4\n"," libedit 3.1.20191231-h14c3975_1 --> 3.1.20221030-h5eee18b_0\n"," libgcc-ng 9.1.0-hdf63c60_0 --> 11.2.0-h1234567_1\n"," libstdcxx-ng 9.1.0-hdf63c60_0 --> 11.2.0-h1234567_1\n"," ncurses 6.2-he6710b0_1 --> 6.3-h5eee18b_3\n"," openssl 1.1.1i-h27cfd23_0 --> 1.1.1s-h7f8727e_0\n"," sqlite 3.33.0-h62c20be_0 --> 3.40.0-h5082296_0\n"," zlib 1.2.11-h7b6447c_3 --> 1.2.13-h5eee18b_0\n","\n","\n","Preparing transaction: ...working... done\n","Verifying transaction: ...working... done\n","Executing transaction: ...working... done\n","Collecting package metadata (current_repodata.json): ...working... done\n","Solving environment: ...working... done\n","\n","## Package Plan ##\n","\n"," environment location: /usr/local\n","\n"," added / updated specs:\n"," - google-colab\n","\n","\n","The following packages will be downloaded:\n","\n"," package | build\n"," ---------------------------|-----------------\n"," aiohttp-3.8.1 | py39hb9d737c_1 565 KB conda-forge\n"," aiosignal-1.3.1 | pyhd8ed1ab_0 12 KB conda-forge\n"," async-timeout-4.0.2 | pyhd8ed1ab_0 9 KB conda-forge\n"," ca-certificates-2022.12.7 | ha878542_0 143 KB conda-forge\n"," cachetools-5.2.0 | pyhd8ed1ab_0 13 KB conda-forge\n"," certifi-2022.12.7 | pyhd8ed1ab_0 147 KB conda-forge\n"," charset-normalizer-2.1.1 | pyhd8ed1ab_0 36 KB conda-forge\n"," conda-22.11.1 | py39hf3d152e_1 904 KB conda-forge\n"," frozenlist-1.3.3 | py39h5eee18b_0 45 KB\n"," google-auth-2.15.0 | pyh1a96a4e_0 95 KB conda-forge\n"," google-colab-1.0.0 | pyh44b312d_0 77 KB conda-forge\n"," libblas-3.9.0 |15_linux64_openblas 12 KB conda-forge\n"," libcblas-3.9.0 |15_linux64_openblas 12 KB conda-forge\n"," libgfortran-ng-12.2.0 | h69a702a_19 22 KB conda-forge\n"," libgfortran5-12.2.0 | h337968e_19 1.8 MB conda-forge\n"," liblapack-3.9.0 |15_linux64_openblas 12 KB conda-forge\n"," libopenblas-0.3.20 |pthreads_h78a6416_0 10.1 MB conda-forge\n"," multidict-6.0.2 | py39hb9d737c_1 51 KB conda-forge\n"," numpy-1.22.3 | py39hc58783e_2 6.8 MB conda-forge\n"," pandas-1.2.3 | py39hde0f152_0 12.1 MB conda-forge\n"," portpicker-1.5.2 | pyhd8ed1ab_0 17 KB conda-forge\n"," pyasn1-0.4.8 | py_0 53 KB conda-forge\n"," pyasn1-modules-0.2.7 | py_0 60 KB conda-forge\n"," python_abi-3.9 | 2_cp39 4 KB conda-forge\n"," pyu2f-0.1.5 | pyhd8ed1ab_0 31 KB conda-forge\n"," rsa-4.9 | pyhd8ed1ab_0 29 KB conda-forge\n"," yarl-1.7.2 | py39hb9d737c_2 132 KB conda-forge\n"," ------------------------------------------------------------\n"," Total: 33.1 MB\n","\n","The following NEW packages will be INSTALLED:\n","\n"," aiohttp conda-forge/linux-64::aiohttp-3.8.1-py39hb9d737c_1 \n"," aiosignal conda-forge/noarch::aiosignal-1.3.1-pyhd8ed1ab_0 \n"," async-timeout conda-forge/noarch::async-timeout-4.0.2-pyhd8ed1ab_0 \n"," cachetools conda-forge/noarch::cachetools-5.2.0-pyhd8ed1ab_0 \n"," charset-normalizer conda-forge/noarch::charset-normalizer-2.1.1-pyhd8ed1ab_0 \n"," frozenlist pkgs/main/linux-64::frozenlist-1.3.3-py39h5eee18b_0 \n"," google-auth conda-forge/noarch::google-auth-2.15.0-pyh1a96a4e_0 \n"," google-colab conda-forge/noarch::google-colab-1.0.0-pyh44b312d_0 \n"," libblas conda-forge/linux-64::libblas-3.9.0-15_linux64_openblas \n"," libcblas conda-forge/linux-64::libcblas-3.9.0-15_linux64_openblas \n"," libgfortran-ng conda-forge/linux-64::libgfortran-ng-12.2.0-h69a702a_19 \n"," libgfortran5 conda-forge/linux-64::libgfortran5-12.2.0-h337968e_19 \n"," liblapack conda-forge/linux-64::liblapack-3.9.0-15_linux64_openblas \n"," libopenblas conda-forge/linux-64::libopenblas-0.3.20-pthreads_h78a6416_0 \n"," multidict conda-forge/linux-64::multidict-6.0.2-py39hb9d737c_1 \n"," numpy conda-forge/linux-64::numpy-1.22.3-py39hc58783e_2 \n"," pandas conda-forge/linux-64::pandas-1.2.3-py39hde0f152_0 \n"," portpicker conda-forge/noarch::portpicker-1.5.2-pyhd8ed1ab_0 \n"," pyasn1 conda-forge/noarch::pyasn1-0.4.8-py_0 \n"," pyasn1-modules conda-forge/noarch::pyasn1-modules-0.2.7-py_0 \n"," python_abi conda-forge/linux-64::python_abi-3.9-2_cp39 \n"," pyu2f conda-forge/noarch::pyu2f-0.1.5-pyhd8ed1ab_0 \n"," rsa conda-forge/noarch::rsa-4.9-pyhd8ed1ab_0 \n"," yarl conda-forge/linux-64::yarl-1.7.2-py39hb9d737c_2 \n","\n","The following packages will be UPDATED:\n","\n"," ca-certificates pkgs/main::ca-certificates-2022.10.11~ --> conda-forge::ca-certificates-2022.12.7-ha878542_0 \n"," certifi pkgs/main/linux-64::certifi-2022.9.24~ --> conda-forge/noarch::certifi-2022.12.7-pyhd8ed1ab_0 \n","\n","The following packages will be SUPERSEDED by a higher-priority channel:\n","\n"," conda pkgs/main::conda-22.11.1-py39h06a4308~ --> conda-forge::conda-22.11.1-py39hf3d152e_1 \n","\n","\n","Preparing transaction: ...working... done\n","Verifying transaction: ...working... done\n","Executing transaction: ...working... done\n","Installed kernelspec py39 in /root/.local/share/jupyter/kernels/py39\n"]}],"source":["!wget -O mini.sh https://repo.anaconda.com/miniconda/Miniconda3-py39_4.9.2-Linux-x86_64.sh\n","!chmod +x mini.sh\n","!bash ./mini.sh -b -f -p /usr/local\n","!conda install -q -y jupyter\n","!conda install -q -y google-colab -c conda-forge\n","!python -m ipykernel install --name \"py39\" --user"]},{"cell_type":"code","execution_count":4,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":194951,"status":"ok","timestamp":1671494053444,"user":{"displayName":"Mikołaj Krzymiński","userId":"01535337980860424008"},"user_tz":-60},"id":"wvVcJ-ftJ9Mr","outputId":"a7af336d-e882-4beb-81e6-89e7e42fbdef"},"outputs":[{"name":"stdout","output_type":"stream","text":["Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Collecting en_core_web_sm\n"," Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.3.1/en_core_web_sm-2.3.1.tar.gz (12.0 MB)\n","\u001b[K |████████████████████████████████| 12.0 MB 4.9 MB/s \n","\u001b[?25hCollecting overrides==3.1.0\n"," Downloading overrides-3.1.0.tar.gz (11 kB)\n","Collecting pandas==1.2.4\n"," Downloading pandas-1.2.4-cp39-cp39-manylinux1_x86_64.whl (9.7 MB)\n","\u001b[K |████████████████████████████████| 9.7 MB 4.5 MB/s \n","\u001b[?25hRequirement already satisfied: numpy>=1.16.5 in /usr/local/lib/python3.9/site-packages (from pandas==1.2.4->-r ./src/requirements.txt (line 1)) (1.22.3)\n","Requirement already satisfied: pytz>=2017.3 in /usr/local/lib/python3.9/site-packages (from pandas==1.2.4->-r ./src/requirements.txt (line 1)) (2022.1)\n","Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.9/site-packages (from pandas==1.2.4->-r ./src/requirements.txt (line 1)) (2.8.2)\n","Collecting pytorch-crf==0.7.2\n"," Downloading pytorch_crf-0.7.2-py3-none-any.whl (9.5 kB)\n","Collecting spacy==2.3.5\n"," Downloading spacy-2.3.5-cp39-cp39-manylinux2014_x86_64.whl (10.3 MB)\n","\u001b[K |████████████████████████████████| 10.3 MB 64.1 MB/s \n","\u001b[?25hRequirement already satisfied: setuptools in /usr/local/lib/python3.9/site-packages (from spacy==2.3.5->-r ./src/requirements.txt (line 2)) (51.0.0.post20201207)\n","Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.9/site-packages (from spacy==2.3.5->-r ./src/requirements.txt (line 2)) (2.25.0)\n","Requirement already satisfied: numpy>=1.16.5 in /usr/local/lib/python3.9/site-packages (from pandas==1.2.4->-r ./src/requirements.txt (line 1)) (1.22.3)\n","Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.9/site-packages (from spacy==2.3.5->-r ./src/requirements.txt (line 2)) (4.54.1)\n","Collecting tensorboard>=2.4\n"," Downloading tensorboard-2.11.0-py3-none-any.whl (6.0 MB)\n","\u001b[K |████████████████████████████████| 6.0 MB 64.9 MB/s \n","\u001b[?25hRequirement already satisfied: wheel>=0.26 in /usr/local/lib/python3.9/site-packages (from tensorboard>=2.4->-r ./src/requirements.txt (line 8)) (0.36.1)\n","Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.9/site-packages (from spacy==2.3.5->-r ./src/requirements.txt (line 2)) (2.25.0)\n","Requirement already satisfied: setuptools in /usr/local/lib/python3.9/site-packages (from spacy==2.3.5->-r ./src/requirements.txt (line 2)) (51.0.0.post20201207)\n","Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.9/site-packages (from tensorboard>=2.4->-r ./src/requirements.txt (line 8)) (2.15.0)\n","Requirement already satisfied: numpy>=1.16.5 in /usr/local/lib/python3.9/site-packages (from pandas==1.2.4->-r ./src/requirements.txt (line 1)) (1.22.3)\n","Collecting tensorboardX==2.1\n"," Downloading tensorboardX-2.1-py2.py3-none-any.whl (308 kB)\n","\u001b[K |████████████████████████████████| 308 kB 67.2 MB/s \n","\u001b[?25hRequirement already satisfied: six in /usr/local/lib/python3.9/site-packages (from tensorboardX==2.1->-r ./src/requirements.txt (line 6)) (1.15.0)\n","Requirement already satisfied: numpy>=1.16.5 in /usr/local/lib/python3.9/site-packages (from pandas==1.2.4->-r ./src/requirements.txt (line 1)) (1.22.3)\n","Collecting torch>=1.7.1\n"," Downloading torch-1.13.1-cp39-cp39-manylinux1_x86_64.whl (887.4 MB)\n","\u001b[K |██████████████████████████████ | 834.1 MB 1.5 MB/s eta 0:00:37tcmalloc: large alloc 1147494400 bytes == 0x55a05534a000 @ 0x7f01f16fc615 0x559ff0b66226 0x559ff0bcd322 0x559ff0bcd46b 0x559ff0bcd4c9 0x559ff0bba883 0x559ff0b1ef88 0x559ff0bc904d 0x559ff0b1efc1 0x559ff0bc904d 0x559ff0b1f4fe 0x559ff0c612f5 0x559ff0bf1f07 0x559ff0c612f5 0x559ff0bf1f07 0x559ff0c612f5 0x559ff0bf1f07 0x559ff0bcf8f9 0x559ff0bcfcaa 0x559ff0bcfdc6 0x559ff0b6b69f 0x559ff0bf18b6 0x559ff0bc782a 0x559ff0bc8357 0x559ff0b1f4fe 0x559ff0bc782a 0x559ff0bc8357 0x559ff0b1f0f8 0x559ff0bc8603 0x559ff0b1ef88 0x559ff0bc904d\n","\u001b[K |████████████████████████████████| 887.4 MB 13 kB/s \n","\u001b[?25hRequirement already satisfied: typing-extensions in /usr/local/lib/python3.9/site-packages (from torch>=1.7.1->-r ./src/requirements.txt (line 7)) (4.4.0)\n","Collecting transformers>=4.6.1\n"," Downloading transformers-4.25.1-py3-none-any.whl (5.8 MB)\n","\u001b[K |████████████████████████████████| 5.8 MB 58.0 MB/s \n","\u001b[?25hRequirement already satisfied: numpy>=1.16.5 in /usr/local/lib/python3.9/site-packages (from pandas==1.2.4->-r ./src/requirements.txt (line 1)) (1.22.3)\n","Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.9/site-packages (from spacy==2.3.5->-r ./src/requirements.txt (line 2)) (2.25.0)\n","Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.9/site-packages (from spacy==2.3.5->-r ./src/requirements.txt (line 2)) (4.54.1)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.9/site-packages (from transformers>=4.6.1->-r ./src/requirements.txt (line 9)) (21.3)\n","Collecting absl-py>=0.4\n"," Downloading absl_py-1.3.0-py3-none-any.whl (124 kB)\n","\u001b[K |████████████████████████████████| 124 kB 42.1 MB/s \n","\u001b[?25hCollecting blis<0.8.0,>=0.4.0\n"," Downloading blis-0.7.9-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (10.2 MB)\n","\u001b[K |████████████████████████████████| 10.2 MB 63.2 MB/s \n","\u001b[?25hRequirement already satisfied: numpy>=1.16.5 in /usr/local/lib/python3.9/site-packages (from pandas==1.2.4->-r ./src/requirements.txt (line 1)) (1.22.3)\n","Collecting catalogue<1.1.0,>=0.0.7\n"," Downloading catalogue-1.0.2-py2.py3-none-any.whl (16 kB)\n","Collecting cymem<2.1.0,>=2.0.2\n"," Downloading cymem-2.0.7-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (35 kB)\n","Collecting filelock\n"," Downloading filelock-3.8.2-py3-none-any.whl (10 kB)\n","Requirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.9/site-packages (from google-auth<3,>=1.6.3->tensorboard>=2.4->-r ./src/requirements.txt (line 8)) (5.2.0)\n","Requirement already satisfied: six in /usr/local/lib/python3.9/site-packages (from tensorboardX==2.1->-r ./src/requirements.txt (line 6)) (1.15.0)\n","Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.9/site-packages (from google-auth<3,>=1.6.3->tensorboard>=2.4->-r ./src/requirements.txt (line 8)) (4.9)\n","Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.9/site-packages (from google-auth<3,>=1.6.3->tensorboard>=2.4->-r ./src/requirements.txt (line 8)) (0.2.7)\n","Collecting google-auth-oauthlib<0.5,>=0.4.1\n"," Downloading google_auth_oauthlib-0.4.6-py2.py3-none-any.whl (18 kB)\n","Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.9/site-packages (from tensorboard>=2.4->-r ./src/requirements.txt (line 8)) (2.15.0)\n","Collecting grpcio>=1.24.3\n"," Downloading grpcio-1.51.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.8 MB)\n","\u001b[K |████████████████████████████████| 4.8 MB 69.1 MB/s \n","\u001b[?25hCollecting huggingface-hub<1.0,>=0.10.0\n"," Downloading huggingface_hub-0.11.1-py3-none-any.whl (182 kB)\n","\u001b[K |████████████████████████████████| 182 kB 70.7 MB/s \n","\u001b[?25hRequirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.9/site-packages (from transformers>=4.6.1->-r ./src/requirements.txt (line 9)) (21.3)\n","Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.9/site-packages (from spacy==2.3.5->-r ./src/requirements.txt (line 2)) (2.25.0)\n","Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.9/site-packages (from spacy==2.3.5->-r ./src/requirements.txt (line 2)) (4.54.1)\n","Requirement already satisfied: typing-extensions in /usr/local/lib/python3.9/site-packages (from torch>=1.7.1->-r ./src/requirements.txt (line 7)) (4.4.0)\n","Collecting markdown>=2.6.8\n"," Downloading Markdown-3.4.1-py3-none-any.whl (93 kB)\n","\u001b[K |████████████████████████████████| 93 kB 1.9 MB/s \n","\u001b[?25hRequirement already satisfied: importlib-metadata>=4.4 in /usr/local/lib/python3.9/site-packages (from markdown>=2.6.8->tensorboard>=2.4->-r ./src/requirements.txt (line 8)) (4.11.3)\n","Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.9/site-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard>=2.4->-r ./src/requirements.txt (line 8)) (3.8.0)\n","Collecting murmurhash<1.1.0,>=0.28.0\n"," Downloading murmurhash-1.0.9-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (21 kB)\n","Collecting nvidia-cublas-cu11==11.10.3.66\n"," Downloading nvidia_cublas_cu11-11.10.3.66-py3-none-manylinux1_x86_64.whl (317.1 MB)\n","\u001b[K |████████████████████████████████| 317.1 MB 32 kB/s \n","\u001b[?25hRequirement already satisfied: wheel>=0.26 in /usr/local/lib/python3.9/site-packages (from tensorboard>=2.4->-r ./src/requirements.txt (line 8)) (0.36.1)\n","Requirement already satisfied: setuptools in /usr/local/lib/python3.9/site-packages (from spacy==2.3.5->-r ./src/requirements.txt (line 2)) (51.0.0.post20201207)\n","Collecting nvidia-cuda-nvrtc-cu11==11.7.99\n"," Downloading nvidia_cuda_nvrtc_cu11-11.7.99-2-py3-none-manylinux1_x86_64.whl (21.0 MB)\n","\u001b[K |████████████████████████████████| 21.0 MB 1.2 MB/s \n","\u001b[?25hCollecting nvidia-cuda-runtime-cu11==11.7.99\n"," Downloading nvidia_cuda_runtime_cu11-11.7.99-py3-none-manylinux1_x86_64.whl (849 kB)\n","\u001b[K |████████████████████████████████| 849 kB 77.2 MB/s \n","\u001b[?25hRequirement already satisfied: wheel>=0.26 in /usr/local/lib/python3.9/site-packages (from tensorboard>=2.4->-r ./src/requirements.txt (line 8)) (0.36.1)\n","Requirement already satisfied: setuptools in /usr/local/lib/python3.9/site-packages (from spacy==2.3.5->-r ./src/requirements.txt (line 2)) (51.0.0.post20201207)\n","Collecting nvidia-cudnn-cu11==8.5.0.96\n"," Downloading nvidia_cudnn_cu11-8.5.0.96-2-py3-none-manylinux1_x86_64.whl (557.1 MB)\n","\u001b[K |████████████████████████████████| 557.1 MB 11 kB/s \n","\u001b[?25hRequirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /usr/local/lib/python3.9/site-packages (from packaging>=20.0->transformers>=4.6.1->-r ./src/requirements.txt (line 9)) (3.0.9)\n","Collecting plac<1.2.0,>=0.9.6\n"," Downloading plac-1.1.3-py2.py3-none-any.whl (20 kB)\n","Collecting preshed<3.1.0,>=3.0.2\n"," Downloading preshed-3.0.8-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (128 kB)\n","\u001b[K |████████████████████████████████| 128 kB 76.2 MB/s \n","\u001b[?25hCollecting protobuf<4,>=3.9.2\n"," Downloading protobuf-3.20.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.whl (1.0 MB)\n","\u001b[K |████████████████████████████████| 1.0 MB 62.5 MB/s \n","\u001b[?25hRequirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /usr/local/lib/python3.9/site-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard>=2.4->-r ./src/requirements.txt (line 8)) (0.4.8)\n","Requirement already satisfied: six in /usr/local/lib/python3.9/site-packages (from tensorboardX==2.1->-r ./src/requirements.txt (line 6)) (1.15.0)\n","Collecting pyyaml>=5.1\n"," Downloading PyYAML-6.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl (661 kB)\n","\u001b[K |████████████████████████████████| 661 kB 64.9 MB/s \n","\u001b[?25hCollecting regex!=2019.12.17\n"," Downloading regex-2022.10.31-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (769 kB)\n","\u001b[K |████████████████████████████████| 769 kB 61.3 MB/s \n","\u001b[?25hRequirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy==2.3.5->-r ./src/requirements.txt (line 2)) (3.0.4)\n","Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy==2.3.5->-r ./src/requirements.txt (line 2)) (2.10)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy==2.3.5->-r ./src/requirements.txt (line 2)) (2022.12.7)\n","Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy==2.3.5->-r ./src/requirements.txt (line 2)) (1.25.11)\n","Collecting requests-oauthlib>=0.7.0\n"," Downloading requests_oauthlib-1.3.1-py2.py3-none-any.whl (23 kB)\n","Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.9/site-packages (from spacy==2.3.5->-r ./src/requirements.txt (line 2)) (2.25.0)\n","Collecting oauthlib>=3.0.0\n"," Downloading oauthlib-3.2.2-py3-none-any.whl (151 kB)\n","\u001b[K |████████████████████████████████| 151 kB 72.9 MB/s \n","\u001b[?25hRequirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /usr/local/lib/python3.9/site-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard>=2.4->-r ./src/requirements.txt (line 8)) (0.4.8)\n","Collecting srsly<1.1.0,>=1.0.2\n"," Downloading srsly-1.0.6-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (209 kB)\n","\u001b[K |████████████████████████████████| 209 kB 75.4 MB/s \n","\u001b[?25hCollecting tensorboard-data-server<0.7.0,>=0.6.0\n"," Downloading tensorboard_data_server-0.6.1-py3-none-manylinux2010_x86_64.whl (4.9 MB)\n","\u001b[K |████████████████████████████████| 4.9 MB 50.9 MB/s \n","\u001b[?25hCollecting tensorboard-plugin-wit>=1.6.0\n"," Downloading tensorboard_plugin_wit-1.8.1-py3-none-any.whl (781 kB)\n","\u001b[K |████████████████████████████████| 781 kB 63.7 MB/s \n","\u001b[?25hCollecting thinc<7.5.0,>=7.4.1\n"," Downloading thinc-7.4.6-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.1 MB)\n","\u001b[K |████████████████████████████████| 1.1 MB 61.9 MB/s \n","\u001b[?25hRequirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.9/site-packages (from spacy==2.3.5->-r ./src/requirements.txt (line 2)) (4.54.1)\n","Requirement already satisfied: numpy>=1.16.5 in /usr/local/lib/python3.9/site-packages (from pandas==1.2.4->-r ./src/requirements.txt (line 1)) (1.22.3)\n","Collecting tokenizers!=0.11.3,<0.14,>=0.11.1\n"," Downloading tokenizers-0.13.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.6 MB)\n","\u001b[K |████████████████████████████████| 7.6 MB 55.7 MB/s \n","\u001b[?25hCollecting wasabi<1.1.0,>=0.4.0\n"," Downloading wasabi-0.10.1-py3-none-any.whl (26 kB)\n","Collecting werkzeug>=1.0.1\n"," Downloading Werkzeug-2.2.2-py3-none-any.whl (232 kB)\n","\u001b[K |████████████████████████████████| 232 kB 73.6 MB/s \n","\u001b[?25hRequirement already satisfied: MarkupSafe>=2.1.1 in /usr/local/lib/python3.9/site-packages (from werkzeug>=1.0.1->tensorboard>=2.4->-r ./src/requirements.txt (line 8)) (2.1.1)\n","Building wheels for collected packages: en-core-web-sm, overrides\n"," Building wheel for en-core-web-sm (setup.py) ... \u001b[?25l\u001b[?25hdone\n"," Created wheel for en-core-web-sm: filename=en_core_web_sm-2.3.1-py3-none-any.whl size=12047107 sha256=19466519d049944b18f99c457b2a0f157c00b3e1ea869289bc6a4431665de650\n"," Stored in directory: /root/.cache/pip/wheels/19/d6/1c/5484b95647df5d7afaf74abde458c66c1cd427e69e801fe826\n"," Building wheel for overrides (setup.py) ... \u001b[?25l\u001b[?25hdone\n"," Created wheel for overrides: filename=overrides-3.1.0-py3-none-any.whl size=10174 sha256=7e73fa98f72561a9ab69fbde0dd03ce1a28aded313b227e2eb71d099669a9259\n"," Stored in directory: /root/.cache/pip/wheels/7d/11/0e/73fdcb3d71d97e33c230900efe85923ee9d49515d050503174\n","Successfully built en-core-web-sm overrides\n","Installing collected packages: murmurhash, cymem, wasabi, srsly, preshed, plac, oauthlib, catalogue, blis, thinc, requests-oauthlib, pyyaml, nvidia-cublas-cu11, filelock, werkzeug, tokenizers, tensorboard-plugin-wit, tensorboard-data-server, spacy, regex, protobuf, nvidia-cudnn-cu11, nvidia-cuda-runtime-cu11, nvidia-cuda-nvrtc-cu11, markdown, huggingface-hub, grpcio, google-auth-oauthlib, absl-py, transformers, torch, tensorboardX, tensorboard, pytorch-crf, pandas, overrides, en-core-web-sm\n"," Attempting uninstall: pandas\n"," Found existing installation: pandas 1.2.3\n"," Uninstalling pandas-1.2.3:\n"," Successfully uninstalled pandas-1.2.3\n","Successfully installed absl-py-1.3.0 blis-0.7.9 catalogue-1.0.2 cymem-2.0.7 en-core-web-sm-2.3.1 filelock-3.8.2 google-auth-oauthlib-0.4.6 grpcio-1.51.1 huggingface-hub-0.11.1 markdown-3.4.1 murmurhash-1.0.9 nvidia-cublas-cu11-11.10.3.66 nvidia-cuda-nvrtc-cu11-11.7.99 nvidia-cuda-runtime-cu11-11.7.99 nvidia-cudnn-cu11-8.5.0.96 oauthlib-3.2.2 overrides-3.1.0 pandas-1.2.4 plac-1.1.3 preshed-3.0.8 protobuf-3.20.3 pytorch-crf-0.7.2 pyyaml-6.0 regex-2022.10.31 requests-oauthlib-1.3.1 spacy-2.3.5 srsly-1.0.6 tensorboard-2.11.0 tensorboard-data-server-0.6.1 tensorboard-plugin-wit-1.8.1 tensorboardX-2.1 thinc-7.4.6 tokenizers-0.13.2 torch-1.13.1 transformers-4.25.1 wasabi-0.10.1 werkzeug-2.2.2\n","Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Collecting en_core_web_sm==2.3.1\n"," Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.3.1/en_core_web_sm-2.3.1.tar.gz (12.0 MB)\n","\u001b[K |████████████████████████████████| 12.0 MB 4.8 MB/s \n","\u001b[?25hRequirement already satisfied: spacy<2.4.0,>=2.3.0 in /usr/local/lib/python3.9/site-packages (from en_core_web_sm==2.3.1) (2.3.5)\n","Requirement already satisfied: blis<0.8.0,>=0.4.0 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (0.7.9)\n","Requirement already satisfied: thinc<7.5.0,>=7.4.1 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (7.4.6)\n","Requirement already satisfied: wasabi<1.1.0,>=0.4.0 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (0.10.1)\n","Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (2.0.7)\n","Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (4.54.1)\n","Requirement already satisfied: plac<1.2.0,>=0.9.6 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (1.1.3)\n","Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (3.0.8)\n","Requirement already satisfied: srsly<1.1.0,>=1.0.2 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (1.0.6)\n","Requirement already satisfied: setuptools in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (51.0.0.post20201207)\n","Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (1.0.9)\n","Requirement already satisfied: catalogue<1.1.0,>=0.0.7 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (1.0.2)\n","Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (2.25.0)\n","Requirement already satisfied: numpy>=1.15.0 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (1.22.3)\n","Requirement already satisfied: numpy>=1.15.0 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (1.22.3)\n","Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (2.0.7)\n","Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (1.0.9)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (2022.12.7)\n","Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (1.25.11)\n","Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (2.10)\n","Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (3.0.4)\n","Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (3.0.8)\n","Requirement already satisfied: blis<0.8.0,>=0.4.0 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (0.7.9)\n","Requirement already satisfied: wasabi<1.1.0,>=0.4.0 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (0.10.1)\n","Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (4.54.1)\n","Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (2.0.7)\n","Requirement already satisfied: srsly<1.1.0,>=1.0.2 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (1.0.6)\n","Requirement already satisfied: plac<1.2.0,>=0.9.6 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (1.1.3)\n","Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (1.0.9)\n","Requirement already satisfied: catalogue<1.1.0,>=0.0.7 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (1.0.2)\n","Requirement already satisfied: numpy>=1.15.0 in /usr/local/lib/python3.9/site-packages (from spacy<2.4.0,>=2.3.0->en_core_web_sm==2.3.1) (1.22.3)\n","\u001b[38;5;2m✔ Download and installation successful\u001b[0m\n","You can now load the model via spacy.load('en_core_web_sm')\n"]}],"source":["# Install all the dependencies:\n","! pip install -r ./src/requirements.txt\n","# Install the spacy dictionary \n","! python -m spacy download en_core_web_sm"]},{"cell_type":"code","execution_count":5,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":200,"status":"ok","timestamp":1671494159073,"user":{"displayName":"Mikołaj Krzymiński","userId":"01535337980860424008"},"user_tz":-60},"id":"AJPYKjFsVczW","outputId":"d66d3fb7-63f8-422d-9861-327c98bfa7c9"},"outputs":[{"name":"stdout","output_type":"stream","text":["Python 3.9.1\n"]}],"source":["!python --version"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":244,"status":"ok","timestamp":1671451572774,"user":{"displayName":"Mikołaj Krzymiński","userId":"01535337980860424008"},"user_tz":-60},"id":"FOTjD9F6-dvl","outputId":"269c9b26-efdf-4b85-ef42-c9468acf1404"},"outputs":[{"name":"stdout","output_type":"stream","text":["[Errno 2] No such file or directory: 'CookDial'\n","/content/CookDial\n"]}],"source":["# %cd CookDial"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"KhP3bN3MRxp7"},"outputs":[],"source":["# !mkdir data/processed\n","# !touch data/processed/preprocess.log"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":653826,"status":"ok","timestamp":1671452326188,"user":{"displayName":"Mikołaj Krzymiński","userId":"01535337980860424008"},"user_tz":-60},"id":"pQW06np5K0Yz","outputId":"b90655ae-c374-4e9f-b0f0-70a0125ad039"},"outputs":[{"name":"stdout","output_type":"stream","text":["File white list: ['000', '001', '002', '003', '004', '005', '006', '007', '008', '009', '010', '011', '012', '013', '014', '015', '016', '017', '018', '019', '020', '021', '022', '023', '024', '025', '026', '027', '028', '029', '030', '031', '032', '033', '034', '035', '036', '037', '038', '039', '040', '041', '042', '043', '044', '045', '046', '047', '048', '049', '050', '051', '052', '053', '054', '055', '056', '057', '058', '059', '060', '061', '062', '063', '064', '065', '066', '067', '068', '069', '070', '071', '072', '073', '074', '075', '076', '077', '078', '079', '080', '081', '082', '083', '084', '085', '086', '087', '088', '089', '090', '091', '092', '093', '094', '095', '096', '097', '098', '099', '100', '101', '102', '103', '104', '105', '106', '107', '108', '109', '110', '111', '112', '113', '114', '115', '116', '117', '118', '119', '120', '121', '122', '123', '124', '125', '126', '127', '128', '129', '130', '131', '132', '133', '134', '135', '136', '137', '138', '139', '140', '141', '142', '143', '144', '145', '146', '147', '148', '149', '150', '151', '152', '153', '154', '155', '156', '157', '158', '159', '160', '161', '162', '163', '164', '165', '166', '167', '168', '169', '170', '171', '172', '173', '174', '175', '176', '177', '178', '179', '180', '181', '182', '183', '184', '185', '186', '187', '188', '189', '190', '191', '192', '193', '194', '195', '196', '197', '198', '199', '200', '201', '202', '203', '204', '205', '206', '207', '208', '209', '210', '211', '212', '213', '214', '215', '216', '217', '218', '219', '220', '221', '222', '223', '224', '225', '226', '227', '228', '229', '230', '231', '232', '233', '234', '235', '236', '237', '238', '239', '240', '241', '242', '243', '244', '245', '246', '247', '248', '249', '250', '251', '252', '253', '254', '255', '256', '257', '258', '259']\n","File black list: {}\n","**********Preprocess starts***********\n","\n","Collate dialogue and recipe files\n","Start to shift agent action frames to user utterances...\n","\tFinish shifting agent action frames\n","Start to shift agent acts...\n","\tFinish shifting agent acts to user utterances.\n","Start to parse intents of user utterances...\n","\tFinish parsing intents\n","Start to add history (window=10) to each utterance...\n","\tFinish adding history.\n","Start to tokenize utterance (and history)...\n","\tFinish tokenization.\n","Build vocabularies from dialogues...\n","\tFinish building vocabs from dialogues: ['words', 'agent_acts', 'intent', 'section']\n","Recipe 009 has more than 512 tokens.\n","Recipe 160 has more than 512 tokens.\n","Build vocabularies from recipes...\n","\tFinish building vocabs from recipes.\n","\tVocab size: 2987\n"," There are multiple matches for span \"pan\"\n"," There are multiple matches for span \"bag\"\n"," There are multiple matches for span \"the pan\"\n"," There are multiple matches for span \"the pan\"\n"," There are multiple matches for span \"the foil\"\n"," There are multiple matches for span \"the foil\"\n"," There are multiple matches for span \"foil\"\n"," There are multiple matches for span \"foil\"\n","Start to integrate recipes into dialogues...\n","\tIntegrating recipes is done.\n","Start converting func-args to full_set pointer sequence...\n","/content/CookDial/src/scripts/preprocess.py:1162: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.\n","Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations\n"," gold_full_set_pointer_seq = np.zeros((SLOT_MATRIX_ROWS), dtype=np.int)\n","\tFinish full_set pointer sequence conversion.\n","Start to shift agent action frame args to user utterances...\n","\tFinish shifting agent action frame args\n","All data is merged into one file /content/CookDial/data/processed/dialog/cookdial_dialog_merged.json\n","**********Preprocess is finished. Elapsed time: 10.81 min**********\n"]}],"source":["! python src/scripts/preprocess.py -c \"./vocab_config.json\" --lowercase \"True\""]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":200,"status":"ok","timestamp":1671401517435,"user":{"displayName":"Mikołaj Krzymiński","userId":"01535337980860424008"},"user_tz":-60},"id":"Y0JhVnR9SdNm","outputId":"df022e34-f889-45d9-f3c6-57d4590a6874"},"outputs":[{"name":"stdout","output_type":"stream","text":["/content/CookDial/src\n"]}],"source":["%cd content/CookDial/src"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":216,"status":"ok","timestamp":1671401543987,"user":{"displayName":"Mikołaj Krzymiński","userId":"01535337980860424008"},"user_tz":-60},"id":"hdgeo7laQ3DM","outputId":"789d1145-412c-46e5-9249-bdf48e5fff5f"},"outputs":[{"name":"stdout","output_type":"stream","text":["config_agent_task.json\tlogger\t\t requirements.txt utils\n","config_gene_task.json\tmetrics\t\t scripts\t vocab_config.json\n","config_user_task.json\tmodels\t\t trainers\n","dataloaders\t\tmodules\t\t train.py\n","__init__.py\t\tparse_config.py train.sh\n"]}],"source":["!ls"]},{"cell_type":"code","execution_count":6,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":2580,"status":"ok","timestamp":1671494169457,"user":{"displayName":"Mikołaj Krzymiński","userId":"01535337980860424008"},"user_tz":-60},"id":"kIJAY-fWU5oE","outputId":"e38c9746-207c-4f53-f9ac-45319f1e1f81"},"outputs":[{"name":"stdout","output_type":"stream","text":["Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Collecting sentencepiece\n"," Downloading sentencepiece-0.1.97-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n","\u001b[K |████████████████████████████████| 1.3 MB 4.4 MB/s \n","\u001b[?25hInstalling collected packages: sentencepiece\n","Successfully installed sentencepiece-0.1.97\n"]}],"source":["!pip install sentencepiece\n"]},{"cell_type":"code","execution_count":1,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":20,"status":"ok","timestamp":1671521123810,"user":{"displayName":"Mikołaj Krzymiński","userId":"01535337980860424008"},"user_tz":-60},"id":"wUibtU5RThxF","outputId":"dcddbf15-8caa-4710-bc0c-ea8de14372a0"},"outputs":[{"name":"stdout","output_type":"stream","text":["[Errno 2] No such file or directory: './src'\n","/content\n","chmod: cannot access 'train.sh': No such file or directory\n","/bin/bash: ./train.sh: No such file or directory\n"]}],"source":["%cd ./src\n","# Make sure train.sh is executable\n","!chmod 751 train.sh\n","!./train.sh --config ./config_user_task.json --mode \"train\""]}],"metadata":{"accelerator":"GPU","colab":{"authorship_tag":"ABX9TyNSNwyMdI1idTLH0c8HB9DF","mount_file_id":"1wY4y3knqDcirqSohbT8xf-ExehmzdZiq","provenance":[]},"gpuClass":"standard","kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.10.4 (tags/v3.10.4:9d38120, Mar 23 2022, 23:13:41) [MSC v.1929 64 bit (AMD64)]"},"vscode":{"interpreter":{"hash":"369f2c481f4da34e4445cda3fffd2e751bd1c4d706f27375911949ba6bb62e1c"}}},"nbformat":4,"nbformat_minor":0}