tutorials/notebooks/supervised-sequence-to-target.ipynb

{"cells":[{"cell_type":"markdown","id":"spMVAySTSEZ1","metadata":{"id":"spMVAySTSEZ1"},"source":["# Colab setup"]},{"cell_type":"code","execution_count":null,"id":"WyOYsMF2SEZ3","metadata":{"colab":{"background_save":true,"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":115761,"status":"ok","timestamp":1723817201233,"user":{"displayName":"Amurkhan Dzagkoev","userId":"04975642892911186905"},"user_tz":-180},"id":"WyOYsMF2SEZ3","outputId":"d4de792a-68f1-4f17-ddb0-120d89f7b39f"},"outputs":[{"name":"stdout","output_type":"stream","text":["Collecting pytorch-lifestream\n","  Downloading pytorch-lifestream-0.6.0.tar.gz (163 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m163.4/163.4 kB\u001b[0m \u001b[31m2.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25h  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n","  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n","  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n","Requirement already satisfied: duckdb in /usr/local/lib/python3.10/dist-packages (from pytorch-lifestream) (0.10.3)\n","Collecting hydra-core>=1.1.2 (from pytorch-lifestream)\n","  Downloading hydra_core-1.3.2-py3-none-any.whl.metadata (5.5 kB)\n","Requirement already satisfied: numpy>=1.21.5 in /usr/local/lib/python3.10/dist-packages (from pytorch-lifestream) (1.26.4)\n","Collecting omegaconf (from pytorch-lifestream)\n","  Downloading omegaconf-2.3.0-py3-none-any.whl.metadata (3.9 kB)\n","Requirement already satisfied: pandas>=1.3.5 in /usr/local/lib/python3.10/dist-packages (from pytorch-lifestream) (2.1.4)\n","Requirement already satisfied: pyarrow>=6.0.1 in /usr/local/lib/python3.10/dist-packages (from pytorch-lifestream) (14.0.2)\n","Collecting pytorch-lightning>=1.6.0 (from pytorch-lifestream)\n","  Downloading pytorch_lightning-2.4.0-py3-none-any.whl.metadata (21 kB)\n","Requirement already satisfied: scikit-learn>=1.0.2 in /usr/local/lib/python3.10/dist-packages (from pytorch-lifestream) (1.3.2)\n","Requirement already satisfied: torch>=1.12.0 in /usr/local/lib/python3.10/dist-packages (from pytorch-lifestream) (2.3.1+cu121)\n","Collecting torchmetrics>=0.9.0 (from pytorch-lifestream)\n","  Downloading torchmetrics-1.4.1-py3-none-any.whl.metadata (20 kB)\n","Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (from pytorch-lifestream) (4.42.4)\n","Collecting antlr4-python3-runtime==4.9.* (from hydra-core>=1.1.2->pytorch-lifestream)\n","  Downloading antlr4-python3-runtime-4.9.3.tar.gz (117 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m117.0/117.0 kB\u001b[0m \u001b[31m11.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n","Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from hydra-core>=1.1.2->pytorch-lifestream) (24.1)\n","Requirement already satisfied: PyYAML>=5.1.0 in /usr/local/lib/python3.10/dist-packages (from omegaconf->pytorch-lifestream) (6.0.2)\n","Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.3.5->pytorch-lifestream) (2.8.2)\n","Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.3.5->pytorch-lifestream) (2024.1)\n","Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.3.5->pytorch-lifestream) (2024.1)\n","Requirement already satisfied: tqdm>=4.57.0 in /usr/local/lib/python3.10/dist-packages (from pytorch-lightning>=1.6.0->pytorch-lifestream) (4.66.5)\n","Requirement already satisfied: fsspec>=2022.5.0 in /usr/local/lib/python3.10/dist-packages (from fsspec[http]>=2022.5.0->pytorch-lightning>=1.6.0->pytorch-lifestream) (2024.6.1)\n","Requirement already satisfied: typing-extensions>=4.4.0 in /usr/local/lib/python3.10/dist-packages (from pytorch-lightning>=1.6.0->pytorch-lifestream) (4.12.2)\n","Collecting lightning-utilities>=0.10.0 (from pytorch-lightning>=1.6.0->pytorch-lifestream)\n","  Downloading lightning_utilities-0.11.6-py3-none-any.whl.metadata (5.2 kB)\n","Requirement already satisfied: scipy>=1.5.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=1.0.2->pytorch-lifestream) (1.13.1)\n","Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=1.0.2->pytorch-lifestream) (1.4.2)\n","Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=1.0.2->pytorch-lifestream) (3.5.0)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.12.0->pytorch-lifestream) (3.15.4)\n","Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.12.0->pytorch-lifestream) (1.13.1)\n","Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.12.0->pytorch-lifestream) (3.3)\n","Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.12.0->pytorch-lifestream) (3.1.4)\n","Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch>=1.12.0->pytorch-lifestream)\n","  Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n","Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch>=1.12.0->pytorch-lifestream)\n","  Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n","Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch>=1.12.0->pytorch-lifestream)\n","  Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n","Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch>=1.12.0->pytorch-lifestream)\n","  Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n","Collecting nvidia-cublas-cu12==12.1.3.1 (from torch>=1.12.0->pytorch-lifestream)\n","  Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n","Collecting nvidia-cufft-cu12==11.0.2.54 (from torch>=1.12.0->pytorch-lifestream)\n","  Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n","Collecting nvidia-curand-cu12==10.3.2.106 (from torch>=1.12.0->pytorch-lifestream)\n","  Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n","Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch>=1.12.0->pytorch-lifestream)\n","  Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n","Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch>=1.12.0->pytorch-lifestream)\n","  Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n","Collecting nvidia-nccl-cu12==2.20.5 (from torch>=1.12.0->pytorch-lifestream)\n","  Using cached nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl.metadata (1.8 kB)\n","Collecting nvidia-nvtx-cu12==12.1.105 (from torch>=1.12.0->pytorch-lifestream)\n","  Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.7 kB)\n","Requirement already satisfied: triton==2.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.12.0->pytorch-lifestream) (2.3.1)\n","Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.12.0->pytorch-lifestream)\n","  Using cached nvidia_nvjitlink_cu12-12.6.20-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n","Requirement already satisfied: huggingface-hub<1.0,>=0.23.2 in /usr/local/lib/python3.10/dist-packages (from transformers->pytorch-lifestream) (0.23.5)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers->pytorch-lifestream) (2024.5.15)\n","Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers->pytorch-lifestream) (2.32.3)\n","Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers->pytorch-lifestream) (0.4.4)\n","Requirement already satisfied: tokenizers<0.20,>=0.19 in /usr/local/lib/python3.10/dist-packages (from transformers->pytorch-lifestream) (0.19.1)\n","Requirement already satisfied: aiohttp!=4.0.0a0,!=4.0.0a1 in /usr/local/lib/python3.10/dist-packages (from fsspec[http]>=2022.5.0->pytorch-lightning>=1.6.0->pytorch-lifestream) (3.10.2)\n","Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from lightning-utilities>=0.10.0->pytorch-lightning>=1.6.0->pytorch-lifestream) (71.0.4)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas>=1.3.5->pytorch-lifestream) (1.16.0)\n","Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.12.0->pytorch-lifestream) (2.1.5)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers->pytorch-lifestream) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers->pytorch-lifestream) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers->pytorch-lifestream) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers->pytorch-lifestream) (2024.7.4)\n","Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.12.0->pytorch-lifestream) (1.3.0)\n","Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch-lightning>=1.6.0->pytorch-lifestream) (2.3.5)\n","Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch-lightning>=1.6.0->pytorch-lifestream) (1.3.1)\n","Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch-lightning>=1.6.0->pytorch-lifestream) (24.2.0)\n","Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch-lightning>=1.6.0->pytorch-lifestream) (1.4.1)\n","Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch-lightning>=1.6.0->pytorch-lifestream) (6.0.5)\n","Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch-lightning>=1.6.0->pytorch-lifestream) (1.9.4)\n","Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch-lightning>=1.6.0->pytorch-lifestream) (4.0.3)\n","Downloading hydra_core-1.3.2-py3-none-any.whl (154 kB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m154.5/154.5 kB\u001b[0m \u001b[31m12.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading omegaconf-2.3.0-py3-none-any.whl (79 kB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.5/79.5 kB\u001b[0m \u001b[31m7.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading pytorch_lightning-2.4.0-py3-none-any.whl (815 kB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m815.2/815.2 kB\u001b[0m \u001b[31m30.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hUsing cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n","Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n","Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n","Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n","Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n","Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n","Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n","Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n","Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n","Using cached nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl (176.2 MB)\n","Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n","Downloading torchmetrics-1.4.1-py3-none-any.whl (866 kB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m866.2/866.2 kB\u001b[0m \u001b[31m1.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading lightning_utilities-0.11.6-py3-none-any.whl (26 kB)\n","Using cached nvidia_nvjitlink_cu12-12.6.20-py3-none-manylinux2014_x86_64.whl (19.7 MB)\n","Building wheels for collected packages: pytorch-lifestream, antlr4-python3-runtime\n","  Building wheel for pytorch-lifestream (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n","  Created wheel for pytorch-lifestream: filename=pytorch_lifestream-0.6.0-py3-none-any.whl size=274603 sha256=97e4e5f1c7cbb65581cd06f326c7f3a08b4fe6748a3d111d03fa7ee9523f444e\n","  Stored in directory: /root/.cache/pip/wheels/90/76/b4/0a944bc7c5a69201e4d757cc54886971117a2a581740e7f11d\n","  Building wheel for antlr4-python3-runtime (setup.py) ... \u001b[?25l\u001b[?25hdone\n","  Created wheel for antlr4-python3-runtime: filename=antlr4_python3_runtime-4.9.3-py3-none-any.whl size=144554 sha256=06f71913772e0a071b8eb49a7454f9aaf3caf5e7bbdd3cd894a8712e8d55fdfb\n","  Stored in directory: /root/.cache/pip/wheels/12/93/dd/1f6a127edc45659556564c5730f6d4e300888f4bca2d4c5a88\n","Successfully built pytorch-lifestream antlr4-python3-runtime\n","Installing collected packages: antlr4-python3-runtime, omegaconf, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, lightning-utilities, nvidia-cusparse-cu12, nvidia-cudnn-cu12, hydra-core, nvidia-cusolver-cu12, torchmetrics, pytorch-lightning, pytorch-lifestream\n","Successfully installed antlr4-python3-runtime-4.9.3 hydra-core-1.3.2 lightning-utilities-0.11.6 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.20.5 nvidia-nvjitlink-cu12-12.6.20 nvidia-nvtx-cu12-12.1.105 omegaconf-2.3.0 pytorch-lifestream-0.6.0 pytorch-lightning-2.4.0 torchmetrics-1.4.1\n","Collecting catboost\n","  Downloading catboost-1.2.5-cp310-cp310-manylinux2014_x86_64.whl.metadata (1.2 kB)\n","Requirement already satisfied: graphviz in /usr/local/lib/python3.10/dist-packages (from catboost) (0.20.3)\n","Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from catboost) (3.7.1)\n","Requirement already satisfied: numpy>=1.16.0 in /usr/local/lib/python3.10/dist-packages (from catboost) (1.26.4)\n","Requirement already satisfied: pandas>=0.24 in /usr/local/lib/python3.10/dist-packages (from catboost) (2.1.4)\n","Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from catboost) (1.13.1)\n","Requirement already satisfied: plotly in /usr/local/lib/python3.10/dist-packages (from catboost) (5.15.0)\n","Requirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from catboost) (1.16.0)\n","Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24->catboost) (2.8.2)\n","Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24->catboost) (2024.1)\n","Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24->catboost) (2024.1)\n","Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (1.2.1)\n","Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (0.12.1)\n","Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (4.53.1)\n","Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (1.4.5)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (24.1)\n","Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (9.4.0)\n","Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (3.1.2)\n","Requirement already satisfied: tenacity>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from plotly->catboost) (9.0.0)\n","Downloading catboost-1.2.5-cp310-cp310-manylinux2014_x86_64.whl (98.2 MB)\n","\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m98.2/98.2 MB\u001b[0m \u001b[31m8.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hInstalling collected packages: catboost\n","Successfully installed catboost-1.2.5\n","Requirement already satisfied: catboost in /usr/local/lib/python3.10/dist-packages (1.2.5)\n","Requirement already satisfied: graphviz in /usr/local/lib/python3.10/dist-packages (from catboost) (0.20.3)\n","Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from catboost) (3.7.1)\n","Requirement already satisfied: numpy>=1.16.0 in /usr/local/lib/python3.10/dist-packages (from catboost) (1.26.4)\n","Requirement already satisfied: pandas>=0.24 in /usr/local/lib/python3.10/dist-packages (from catboost) (2.1.4)\n","Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from catboost) (1.13.1)\n","Requirement already satisfied: plotly in /usr/local/lib/python3.10/dist-packages (from catboost) (5.15.0)\n","Requirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from catboost) (1.16.0)\n","Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24->catboost) (2.8.2)\n","Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24->catboost) (2024.1)\n","Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24->catboost) (2024.1)\n","Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (1.2.1)\n","Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (0.12.1)\n","Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (4.53.1)\n","Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (1.4.5)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (24.1)\n","Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (9.4.0)\n","Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->catboost) (3.1.2)\n","Requirement already satisfied: tenacity>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from plotly->catboost) (9.0.0)\n"]}],"source":["import sys\n","if \"google.colab\" in str(get_ipython()):\n","    ! {sys.executable} -m pip install pytorch-lifestream\n","    ! {sys.executable} -m pip install catboost\n","    ! {sys.executable} -m pip install torchmetrics"]},{"cell_type":"markdown","id":"T6ZAv6VUd1pq","metadata":{"id":"T6ZAv6VUd1pq"},"source":["# Supervised task"]},{"cell_type":"markdown","id":"ipR01Z_jd1pt","metadata":{"id":"ipR01Z_jd1pt"},"source":["## Prepare your data\n","\n","- Use `Pyspark` in local or cluster mode for big dataset and `Pandas` for small.\n","- Split data into required parts (train, valid, test, ...).\n","- Use `ptls.preprocessing` for simple data preparation.\n","- Transform features to compatible format using `Pyspark` or `Pandas` functions.\n","You can also use `ptls.data_load.preprocessing` for common data transformation patterns.\n","- Split sequences to `ptls-data` format with `ptls.data_load.split_tools`. Save prepared data into `Parquet` format or\n","keep it in memory (`Pickle` also works).\n","- Use one of the available `ptls.data_load.datasets` to define input for the models."]},{"cell_type":"code","execution_count":null,"id":"Om-SP9LKd1pv","metadata":{"colab":{"background_save":true},"id":"Om-SP9LKd1pv"},"outputs":[],"source":["import torch\n","\n","import numpy as np\n","import pandas as pd\n","import torchmetrics\n","import pytorch_lightning as pl\n","\n","from sklearn.metrics import confusion_matrix, accuracy_score\n","from sklearn.model_selection import train_test_split\n","from functools import partial\n","from ptls.frames import PtlsDataModule\n","from ptls.nn import TrxEncoder, RnnSeqEncoder, Head\n","from ptls.data_load.datasets import MemoryMapDataset\n","from ptls.preprocessing import PandasDataPreprocessor\n","from ptls.frames.supervised import SeqToTargetDataset, SequenceToTarget\n","from ptls.data_load.utils import collate_feature_dict\n","from ptls.frames.inference_module import InferenceModule"]},{"cell_type":"code","execution_count":null,"id":"H5e7oTeqd1py","metadata":{"colab":{"background_save":true,"base_uri":"https://localhost:8080/","height":206},"executionInfo":{"elapsed":552,"status":"ok","timestamp":1723817219254,"user":{"displayName":"Amurkhan Dzagkoev","userId":"04975642892911186905"},"user_tz":-180},"id":"H5e7oTeqd1py","outputId":"3ad59ce8-fe24-4f3b-dc98-a35947910692"},"outputs":[{"data":{"application/vnd.google.colaboratory.intrinsic+json":{"summary":"{\n  \"name\": \"df_target\",\n  \"rows\": 30000,\n  \"fields\": [\n    {\n      \"column\": \"client_id\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 14448,\n        \"min\": 4,\n        \"max\": 49998,\n        \"num_unique_values\": 30000,\n        \"samples\": [\n          36627,\n          16901,\n          23218\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"bins\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1,\n        \"min\": 0,\n        \"max\": 3,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          0,\n          3,\n          2\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}","type":"dataframe","variable_name":"df_target"},"text/html":["\n","  <div id=\"df-d7b41418-6a28-4da2-96a6-b09583586415\" class=\"colab-df-container\">\n","    <div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>client_id</th>\n","      <th>bins</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>24662</td>\n","      <td>2</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>1046</td>\n","      <td>0</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>34089</td>\n","      <td>2</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>34848</td>\n","      <td>1</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>47076</td>\n","      <td>3</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>\n","    <div class=\"colab-df-buttons\">\n","\n","  <div class=\"colab-df-container\">\n","    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d7b41418-6a28-4da2-96a6-b09583586415')\"\n","            title=\"Convert this dataframe to an interactive table.\"\n","            style=\"display:none;\">\n","\n","  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n","    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n","  </svg>\n","    </button>\n","\n","  <style>\n","    .colab-df-container {\n","      display:flex;\n","      gap: 12px;\n","    }\n","\n","    .colab-df-convert {\n","      background-color: #E8F0FE;\n","      border: none;\n","      border-radius: 50%;\n","      cursor: pointer;\n","      display: none;\n","      fill: #1967D2;\n","      height: 32px;\n","      padding: 0 0 0 0;\n","      width: 32px;\n","    }\n","\n","    .colab-df-convert:hover {\n","      background-color: #E2EBFA;\n","      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n","      fill: #174EA6;\n","    }\n","\n","    .colab-df-buttons div {\n","      margin-bottom: 4px;\n","    }\n","\n","    [theme=dark] .colab-df-convert {\n","      background-color: #3B4455;\n","      fill: #D2E3FC;\n","    }\n","\n","    [theme=dark] .colab-df-convert:hover {\n","      background-color: #434B5C;\n","      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n","      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n","      fill: #FFFFFF;\n","    }\n","  </style>\n","\n","    <script>\n","      const buttonEl =\n","        document.querySelector('#df-d7b41418-6a28-4da2-96a6-b09583586415 button.colab-df-convert');\n","      buttonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","\n","      async function convertToInteractive(key) {\n","        const element = document.querySelector('#df-d7b41418-6a28-4da2-96a6-b09583586415');\n","        const dataTable =\n","          await google.colab.kernel.invokeFunction('convertToInteractive',\n","                                                    [key], {});\n","        if (!dataTable) return;\n","\n","        const docLinkHtml = 'Like what you see? Visit the ' +\n","          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n","          + ' to learn more about interactive tables.';\n","        element.innerHTML = '';\n","        dataTable['output_type'] = 'display_data';\n","        await google.colab.output.renderOutput(dataTable, element);\n","        const docLink = document.createElement('div');\n","        docLink.innerHTML = docLinkHtml;\n","        element.appendChild(docLink);\n","      }\n","    </script>\n","  </div>\n","\n","\n","<div id=\"df-578c65ce-f7b9-4fa6-8963-8e5c7787fbb6\">\n","  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-578c65ce-f7b9-4fa6-8963-8e5c7787fbb6')\"\n","            title=\"Suggest charts\"\n","            style=\"display:none;\">\n","\n","<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n","     width=\"24px\">\n","    <g>\n","        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n","    </g>\n","</svg>\n","  </button>\n","\n","<style>\n","  .colab-df-quickchart {\n","      --bg-color: #E8F0FE;\n","      --fill-color: #1967D2;\n","      --hover-bg-color: #E2EBFA;\n","      --hover-fill-color: #174EA6;\n","      --disabled-fill-color: #AAA;\n","      --disabled-bg-color: #DDD;\n","  }\n","\n","  [theme=dark] .colab-df-quickchart {\n","      --bg-color: #3B4455;\n","      --fill-color: #D2E3FC;\n","      --hover-bg-color: #434B5C;\n","      --hover-fill-color: #FFFFFF;\n","      --disabled-bg-color: #3B4455;\n","      --disabled-fill-color: #666;\n","  }\n","\n","  .colab-df-quickchart {\n","    background-color: var(--bg-color);\n","    border: none;\n","    border-radius: 50%;\n","    cursor: pointer;\n","    display: none;\n","    fill: var(--fill-color);\n","    height: 32px;\n","    padding: 0;\n","    width: 32px;\n","  }\n","\n","  .colab-df-quickchart:hover {\n","    background-color: var(--hover-bg-color);\n","    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n","    fill: var(--button-hover-fill-color);\n","  }\n","\n","  .colab-df-quickchart-complete:disabled,\n","  .colab-df-quickchart-complete:disabled:hover {\n","    background-color: var(--disabled-bg-color);\n","    fill: var(--disabled-fill-color);\n","    box-shadow: none;\n","  }\n","\n","  .colab-df-spinner {\n","    border: 2px solid var(--fill-color);\n","    border-color: transparent;\n","    border-bottom-color: var(--fill-color);\n","    animation:\n","      spin 1s steps(1) infinite;\n","  }\n","\n","  @keyframes spin {\n","    0% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","      border-left-color: var(--fill-color);\n","    }\n","    20% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    30% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","      border-right-color: var(--fill-color);\n","    }\n","    40% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    60% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","    }\n","    80% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-bottom-color: var(--fill-color);\n","    }\n","    90% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","    }\n","  }\n","</style>\n","\n","  <script>\n","    async function quickchart(key) {\n","      const quickchartButtonEl =\n","        document.querySelector('#' + key + ' button');\n","      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n","      quickchartButtonEl.classList.add('colab-df-spinner');\n","      try {\n","        const charts = await google.colab.kernel.invokeFunction(\n","            'suggestCharts', [key], {});\n","      } catch (error) {\n","        console.error('Error during call to suggestCharts:', error);\n","      }\n","      quickchartButtonEl.classList.remove('colab-df-spinner');\n","      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n","    }\n","    (() => {\n","      let quickchartButtonEl =\n","        document.querySelector('#df-578c65ce-f7b9-4fa6-8963-8e5c7787fbb6 button');\n","      quickchartButtonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","    })();\n","  </script>\n","</div>\n","    </div>\n","  </div>\n"],"text/plain":["   client_id  bins\n","0      24662     2\n","1       1046     0\n","2      34089     2\n","3      34848     1\n","4      47076     3"]},"execution_count":3,"metadata":{},"output_type":"execute_result"}],"source":["df_target = pd.read_csv(\n","    \"https://huggingface.co/datasets/dllllb/age-group-prediction/resolve/main/train_target.csv?download=true\"\n",")\n","df_target.head()"]},{"cell_type":"code","execution_count":null,"id":"pvunZAm9d1pz","metadata":{"colab":{"background_save":true,"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":20,"status":"ok","timestamp":1723817219254,"user":{"displayName":"Amurkhan Dzagkoev","userId":"04975642892911186905"},"user_tz":-180},"id":"pvunZAm9d1pz","outputId":"d8c825c8-9a2a-434a-8a1e-284d84373479"},"outputs":[{"name":"stdout","output_type":"stream","text":["Split 30000 records to train: 20000, valid: 3000, test: 7000\n"]}],"source":["df_target_train, df_target_test = train_test_split(\n","    df_target, test_size=7000, stratify=df_target[\"bins\"], random_state=142)\n","df_target_train, df_target_valid = train_test_split(\n","    df_target_train, test_size=3000, stratify=df_target_train[\"bins\"], random_state=142)\n","print(\"Split {} records to train: {}, valid: {}, test: {}\".format(\n","    *[\n","      len(df)\n","      for df in [df_target, df_target_train, df_target_valid, df_target_test]\n","    ]\n","))"]},{"cell_type":"code","execution_count":null,"id":"Of3-MPEBd1pz","metadata":{"colab":{"background_save":true,"base_uri":"https://localhost:8080/","height":423},"executionInfo":{"elapsed":20085,"status":"ok","timestamp":1723817296326,"user":{"displayName":"Amurkhan Dzagkoev","userId":"04975642892911186905"},"user_tz":-180},"id":"Of3-MPEBd1pz","outputId":"24771ae2-1236-40a0-da8c-5bdb9401ff56"},"outputs":[{"data":{"application/vnd.google.colaboratory.intrinsic+json":{"type":"dataframe","variable_name":"df_trx"},"text/html":["\n","  <div id=\"df-432f67ec-cc29-4503-855c-64f61cbd63a3\" class=\"colab-df-container\">\n","    <div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>client_id</th>\n","      <th>trans_date</th>\n","      <th>small_group</th>\n","      <th>amount_rur</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>33172</td>\n","      <td>6</td>\n","      <td>4</td>\n","      <td>71.463</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>33172</td>\n","      <td>6</td>\n","      <td>35</td>\n","      <td>45.017</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>33172</td>\n","      <td>8</td>\n","      <td>11</td>\n","      <td>13.887</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>33172</td>\n","      <td>9</td>\n","      <td>11</td>\n","      <td>15.983</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>33172</td>\n","      <td>10</td>\n","      <td>11</td>\n","      <td>21.341</td>\n","    </tr>\n","    <tr>\n","      <th>...</th>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","    </tr>\n","    <tr>\n","      <th>26450572</th>\n","      <td>43300</td>\n","      <td>727</td>\n","      <td>25</td>\n","      <td>7.602</td>\n","    </tr>\n","    <tr>\n","      <th>26450573</th>\n","      <td>43300</td>\n","      <td>727</td>\n","      <td>15</td>\n","      <td>3.709</td>\n","    </tr>\n","    <tr>\n","      <th>26450574</th>\n","      <td>43300</td>\n","      <td>727</td>\n","      <td>1</td>\n","      <td>6.448</td>\n","    </tr>\n","    <tr>\n","      <th>26450575</th>\n","      <td>43300</td>\n","      <td>727</td>\n","      <td>11</td>\n","      <td>24.669</td>\n","    </tr>\n","    <tr>\n","      <th>26450576</th>\n","      <td>43300</td>\n","      <td>729</td>\n","      <td>3</td>\n","      <td>19.408</td>\n","    </tr>\n","  </tbody>\n","</table>\n","<p>26450577 rows × 4 columns</p>\n","</div>\n","    <div class=\"colab-df-buttons\">\n","\n","  <div class=\"colab-df-container\">\n","    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-432f67ec-cc29-4503-855c-64f61cbd63a3')\"\n","            title=\"Convert this dataframe to an interactive table.\"\n","            style=\"display:none;\">\n","\n","  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n","    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n","  </svg>\n","    </button>\n","\n","  <style>\n","    .colab-df-container {\n","      display:flex;\n","      gap: 12px;\n","    }\n","\n","    .colab-df-convert {\n","      background-color: #E8F0FE;\n","      border: none;\n","      border-radius: 50%;\n","      cursor: pointer;\n","      display: none;\n","      fill: #1967D2;\n","      height: 32px;\n","      padding: 0 0 0 0;\n","      width: 32px;\n","    }\n","\n","    .colab-df-convert:hover {\n","      background-color: #E2EBFA;\n","      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n","      fill: #174EA6;\n","    }\n","\n","    .colab-df-buttons div {\n","      margin-bottom: 4px;\n","    }\n","\n","    [theme=dark] .colab-df-convert {\n","      background-color: #3B4455;\n","      fill: #D2E3FC;\n","    }\n","\n","    [theme=dark] .colab-df-convert:hover {\n","      background-color: #434B5C;\n","      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n","      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n","      fill: #FFFFFF;\n","    }\n","  </style>\n","\n","    <script>\n","      const buttonEl =\n","        document.querySelector('#df-432f67ec-cc29-4503-855c-64f61cbd63a3 button.colab-df-convert');\n","      buttonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","\n","      async function convertToInteractive(key) {\n","        const element = document.querySelector('#df-432f67ec-cc29-4503-855c-64f61cbd63a3');\n","        const dataTable =\n","          await google.colab.kernel.invokeFunction('convertToInteractive',\n","                                                    [key], {});\n","        if (!dataTable) return;\n","\n","        const docLinkHtml = 'Like what you see? Visit the ' +\n","          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n","          + ' to learn more about interactive tables.';\n","        element.innerHTML = '';\n","        dataTable['output_type'] = 'display_data';\n","        await google.colab.output.renderOutput(dataTable, element);\n","        const docLink = document.createElement('div');\n","        docLink.innerHTML = docLinkHtml;\n","        element.appendChild(docLink);\n","      }\n","    </script>\n","  </div>\n","\n","\n","<div id=\"df-965cee74-a180-4a42-a321-bcfd6929d50f\">\n","  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-965cee74-a180-4a42-a321-bcfd6929d50f')\"\n","            title=\"Suggest charts\"\n","            style=\"display:none;\">\n","\n","<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n","     width=\"24px\">\n","    <g>\n","        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n","    </g>\n","</svg>\n","  </button>\n","\n","<style>\n","  .colab-df-quickchart {\n","      --bg-color: #E8F0FE;\n","      --fill-color: #1967D2;\n","      --hover-bg-color: #E2EBFA;\n","      --hover-fill-color: #174EA6;\n","      --disabled-fill-color: #AAA;\n","      --disabled-bg-color: #DDD;\n","  }\n","\n","  [theme=dark] .colab-df-quickchart {\n","      --bg-color: #3B4455;\n","      --fill-color: #D2E3FC;\n","      --hover-bg-color: #434B5C;\n","      --hover-fill-color: #FFFFFF;\n","      --disabled-bg-color: #3B4455;\n","      --disabled-fill-color: #666;\n","  }\n","\n","  .colab-df-quickchart {\n","    background-color: var(--bg-color);\n","    border: none;\n","    border-radius: 50%;\n","    cursor: pointer;\n","    display: none;\n","    fill: var(--fill-color);\n","    height: 32px;\n","    padding: 0;\n","    width: 32px;\n","  }\n","\n","  .colab-df-quickchart:hover {\n","    background-color: var(--hover-bg-color);\n","    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n","    fill: var(--button-hover-fill-color);\n","  }\n","\n","  .colab-df-quickchart-complete:disabled,\n","  .colab-df-quickchart-complete:disabled:hover {\n","    background-color: var(--disabled-bg-color);\n","    fill: var(--disabled-fill-color);\n","    box-shadow: none;\n","  }\n","\n","  .colab-df-spinner {\n","    border: 2px solid var(--fill-color);\n","    border-color: transparent;\n","    border-bottom-color: var(--fill-color);\n","    animation:\n","      spin 1s steps(1) infinite;\n","  }\n","\n","  @keyframes spin {\n","    0% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","      border-left-color: var(--fill-color);\n","    }\n","    20% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    30% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","      border-right-color: var(--fill-color);\n","    }\n","    40% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    60% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","    }\n","    80% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-bottom-color: var(--fill-color);\n","    }\n","    90% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","    }\n","  }\n","</style>\n","\n","  <script>\n","    async function quickchart(key) {\n","      const quickchartButtonEl =\n","        document.querySelector('#' + key + ' button');\n","      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n","      quickchartButtonEl.classList.add('colab-df-spinner');\n","      try {\n","        const charts = await google.colab.kernel.invokeFunction(\n","            'suggestCharts', [key], {});\n","      } catch (error) {\n","        console.error('Error during call to suggestCharts:', error);\n","      }\n","      quickchartButtonEl.classList.remove('colab-df-spinner');\n","      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n","    }\n","    (() => {\n","      let quickchartButtonEl =\n","        document.querySelector('#df-965cee74-a180-4a42-a321-bcfd6929d50f button');\n","      quickchartButtonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","    })();\n","  </script>\n","</div>\n","    </div>\n","  </div>\n"],"text/plain":["          client_id  trans_date  small_group  amount_rur\n","0             33172           6            4      71.463\n","1             33172           6           35      45.017\n","2             33172           8           11      13.887\n","3             33172           9           11      15.983\n","4             33172          10           11      21.341\n","...             ...         ...          ...         ...\n","26450572      43300         727           25       7.602\n","26450573      43300         727           15       3.709\n","26450574      43300         727            1       6.448\n","26450575      43300         727           11      24.669\n","26450576      43300         729            3      19.408\n","\n","[26450577 rows x 4 columns]"]},"execution_count":5,"metadata":{},"output_type":"execute_result"}],"source":["df_trx = pd.read_csv(\n","    \"https://huggingface.co/datasets/dllllb/age-group-prediction/resolve/main/transactions_train.csv.gz?download=true\",\n","    compression=\"gzip\"\n",")\n","df_trx"]},{"cell_type":"code","execution_count":null,"id":"aVgNE8ivd1p0","metadata":{"colab":{"background_save":true,"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":4654,"status":"ok","timestamp":1723817300975,"user":{"displayName":"Amurkhan Dzagkoev","userId":"04975642892911186905"},"user_tz":-180},"id":"aVgNE8ivd1p0","outputId":"3af94211-fe35-4fd3-cb2b-5df6331157fa"},"outputs":[{"name":"stdout","output_type":"stream","text":["Split 26450577 transactions to train: 17622321, valid: 2634248, test: 6194008\n"]}],"source":["df_trx_train = pd.merge(df_trx, df_target_train[\"client_id\"], on=\"client_id\", how=\"inner\")\n","df_trx_valid = pd.merge(df_trx, df_target_valid[\"client_id\"], on=\"client_id\", how=\"inner\")\n","df_trx_test = pd.merge(df_trx, df_target_test[\"client_id\"], on=\"client_id\", how=\"inner\")\n","print(\"Split {} transactions to train: {}, valid: {}, test: {}\".format(\n","    *[len(df) for df in [df_trx, df_trx_train, df_trx_valid, df_trx_test]]))"]},{"cell_type":"code","execution_count":null,"id":"ZUW0HSmFd1p1","metadata":{"colab":{"background_save":true},"id":"ZUW0HSmFd1p1"},"outputs":[],"source":["preprocessor = PandasDataPreprocessor(\n","    col_id=\"client_id\",\n","    col_event_time=\"trans_date\",\n","    event_time_transformation=\"none\",\n","    cols_category=[\"small_group\"],\n","    cols_numerical=[\"amount_rur\"],\n","    return_records=False,\n",")"]},{"cell_type":"code","execution_count":null,"id":"C7M29FMid1p2","metadata":{"colab":{"background_save":true},"id":"C7M29FMid1p2"},"outputs":[],"source":["df_data_train = preprocessor.fit_transform(df_trx_train)\n","df_data_valid = preprocessor.transform(df_trx_valid)\n","df_data_test = preprocessor.transform(df_trx_test)"]},{"cell_type":"code","execution_count":null,"id":"uszS5xVWd1p2","metadata":{"colab":{"background_save":true,"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":337,"status":"ok","timestamp":1723817466728,"user":{"displayName":"Amurkhan Dzagkoev","userId":"04975642892911186905"},"user_tz":-180},"id":"uszS5xVWd1p2","outputId":"f276a741-94d5-47de-d835-49a5e8ef3154"},"outputs":[{"name":"stdout","output_type":"stream","text":["Record in dataset, train 20000, valid 3000, test 7000\n","Each record is a client with list of transactions\n"]}],"source":["print(\n","    \"Record in dataset, train {}, valid {}, test {}\".format(\n","        *[len(df) for df in [df_data_train, df_data_valid, df_data_test]]\n","    )\n",")\n","print(\"Each record is a client with list of transactions\")"]},{"cell_type":"code","execution_count":null,"id":"gFplN0kPd1p4","metadata":{"colab":{"background_save":true},"id":"gFplN0kPd1p4"},"outputs":[],"source":["df_target = df_target.rename(columns={\"bins\": \"target_bin\"})"]},{"cell_type":"code","execution_count":null,"id":"wV_Bpudwd1p5","metadata":{"colab":{"background_save":true},"id":"wV_Bpudwd1p5"},"outputs":[],"source":["df_data_train = pd.merge(df_data_train, df_target, on=\"client_id\")\n","df_data_valid = pd.merge(df_data_valid, df_target, on=\"client_id\")\n","df_data_test = pd.merge(df_data_test, df_target, on=\"client_id\")"]},{"cell_type":"code","execution_count":null,"id":"we8cIc8Td1p5","metadata":{"colab":{"background_save":true},"id":"we8cIc8Td1p5"},"outputs":[],"source":["df_data_train = df_data_train.to_dict(orient=\"records\")\n","df_data_valid = df_data_valid.to_dict(orient=\"records\")\n","df_data_test = df_data_test.to_dict(orient=\"records\")"]},{"cell_type":"code","execution_count":null,"id":"OTB2DU5Bd1p6","metadata":{"colab":{"background_save":true,"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":421,"status":"ok","timestamp":1723817492425,"user":{"displayName":"Amurkhan Dzagkoev","userId":"04975642892911186905"},"user_tz":-180},"id":"OTB2DU5Bd1p6","outputId":"61bb44f5-1db6-4b9a-85b7-acb3d9ff824a"},"outputs":[{"data":{"text/plain":["{'client_id': 6,\n"," 'trans_date': tensor([ 0,  5, 10, 11, 15, 15, 16, 16, 17, 18]),\n"," 'event_time': tensor([ 0,  5, 10, 11, 15, 15, 16, 16, 17, 18]),\n"," 'small_group': tensor([ 4,  3,  1,  3,  4,  1,  4,  3, 18,  2]),\n"," 'amount_rur': tensor([ 4.0540, 13.7380, 20.7010, 21.5640, 13.4990, 23.7220,  4.3040,  8.6250,\n","         12.9380, 28.1620], dtype=torch.float64),\n"," 'target_bin': 1}"]},"execution_count":13,"metadata":{},"output_type":"execute_result"}],"source":["# show first 10 transactions from one record\n","rec = df_data_train[0]\n","{k: v[:10] if type(v) is torch.Tensor else v for k, v in rec.items()}"]},{"cell_type":"code","execution_count":null,"id":"Tn1GavvHd1p7","metadata":{"colab":{"background_save":true},"id":"Tn1GavvHd1p7"},"outputs":[],"source":["dataset_train = MemoryMapDataset(df_data_train)\n","dataset_valid = MemoryMapDataset(df_data_valid)\n","dataset_test = MemoryMapDataset(df_data_test)"]},{"cell_type":"markdown","id":"RYzkuiKod1p8","metadata":{"id":"RYzkuiKod1p8"},"source":["## Build encoder\n","\n","- All parts are available in `ptls.nn`.\n","- You can also use pretrained layers."]},{"cell_type":"code","execution_count":null,"id":"YnLQHWf9d1p8","metadata":{"colab":{"background_save":true,"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":394,"status":"ok","timestamp":1723817498480,"user":{"displayName":"Amurkhan Dzagkoev","userId":"04975642892911186905"},"user_tz":-180},"id":"YnLQHWf9d1p8","outputId":"47b8e33b-f582-4006-f733-c2d3a0bcbf47"},"outputs":[{"data":{"text/plain":["{'small_group': 203}"]},"execution_count":15,"metadata":{},"output_type":"execute_result"}],"source":["preprocessor.get_category_dictionary_sizes()"]},{"cell_type":"code","execution_count":null,"id":"E1mBh_afd1p9","metadata":{"colab":{"background_save":true},"id":"E1mBh_afd1p9"},"outputs":[],"source":["seq_encoder = RnnSeqEncoder(\n","    trx_encoder=TrxEncoder(\n","        embeddings={\n","            \"small_group\": {\"in\": 150, \"out\": 32},\n","        },\n","        numeric_values={\n","            \"amount_rur\": \"log\",\n","        },\n","        embeddings_noise=0.001,\n","    ),\n","    hidden_size=48,\n",")"]},{"cell_type":"markdown","id":"-QFPpgmhd1p9","metadata":{"id":"-QFPpgmhd1p9"},"source":["## Choose framework for encoder train\n","\n","- There are both supervised of unsupervised frameworks in `ptls.frames`.\n","- Keep in mind that each framework requires his own batch format.\n","Tools for batch collate can be found in the selected framework package."]},{"cell_type":"code","execution_count":null,"id":"WgTwHpPjd1p-","metadata":{"colab":{"background_save":true},"id":"WgTwHpPjd1p-"},"outputs":[],"source":["sup_module = SequenceToTarget(\n","    seq_encoder=seq_encoder,\n","    head=Head(input_size=seq_encoder.embedding_size, objective=\"classification\", num_classes=4),\n","    loss=torch.nn.NLLLoss(),\n","    metric_list=torchmetrics.Accuracy(task=\"multiclass\", num_classes=4),\n","    optimizer_partial=partial(torch.optim.Adam),\n","    lr_scheduler_partial=partial(torch.optim.lr_scheduler.StepLR, step_size=4, gamma=0.5),\n",")"]},{"cell_type":"code","execution_count":null,"id":"UAEWU5Y6d1p_","metadata":{"colab":{"background_save":true},"id":"UAEWU5Y6d1p_"},"outputs":[],"source":["sup_data = PtlsDataModule(\n","    train_data=SeqToTargetDataset(dataset_train, target_col_name=\"target_bin\", target_dtype=torch.long),\n","    valid_data=SeqToTargetDataset(dataset_valid, target_col_name=\"target_bin\", target_dtype=torch.long),\n","    test_data=SeqToTargetDataset(dataset_test, target_col_name=\"target_bin\", target_dtype=torch.long),\n","    train_batch_size=128,\n","    valid_batch_size=1024,\n","    train_num_workers=8,\n",")"]},{"cell_type":"markdown","id":"AU1Iljy2d1p_","metadata":{"id":"AU1Iljy2d1p_"},"source":["## Train your encoder with selected framework and `pytorch_lightning`"]},{"cell_type":"code","execution_count":null,"id":"5u-D0he_d1qF","metadata":{"colab":{"background_save":true,"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":30,"status":"ok","timestamp":1723818276270,"user":{"displayName":"Amurkhan Dzagkoev","userId":"04975642892911186905"},"user_tz":-180},"id":"5u-D0he_d1qF","outputId":"53ed6804-b910-4462-c226-2ec9a0332484"},"outputs":[{"name":"stderr","output_type":"stream","text":["INFO:pytorch_lightning.utilities.rank_zero:GPU available: True (cuda), used: True\n","INFO:pytorch_lightning.utilities.rank_zero:TPU available: False, using: 0 TPU cores\n","INFO:pytorch_lightning.utilities.rank_zero:HPU available: False, using: 0 HPUs\n"]}],"source":["trainer = pl.Trainer(\n","    max_epochs=1,\n","    accelerator=\"gpu\" if torch.cuda.is_available() else \"cpu\",\n","    enable_progress_bar=False,\n",")"]},{"cell_type":"code","execution_count":null,"id":"0swdBb1cd1qF","metadata":{"colab":{"background_save":true,"base_uri":"https://localhost:8080/"},"id":"0swdBb1cd1qF","scrolled":false,"outputId":"0678ce01-4ae1-4e27-e22e-49d60635de01"},"outputs":[{"name":"stderr","output_type":"stream","text":["INFO:pytorch_lightning.accelerators.cuda:LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n","INFO:pytorch_lightning.callbacks.model_summary:\n","  | Name          | Type          | Params | Mode \n","--------------------------------------------------------\n","0 | seq_encoder   | RnnSeqEncoder | 16.8 K | train\n","1 | head          | Head          | 196    | train\n","2 | loss          | NLLLoss       | 0      | train\n","3 | train_metrics | ModuleDict    | 0      | train\n","4 | valid_metrics | ModuleDict    | 0      | train\n","5 | test_metrics  | ModuleDict    | 0      | train\n","--------------------------------------------------------\n","17.0 K    Trainable params\n","0         Non-trainable params\n","17.0 K    Total params\n","0.068     Total estimated model params size (MB)\n","24        Modules in train mode\n","0         Modules in eval mode\n","/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py:558: UserWarning: This DataLoader will create 8 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n","  warnings.warn(_create_warning_msg(\n","/usr/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.\n","  self.pid = os.fork()\n","/usr/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.\n","  self.pid = os.fork()\n","INFO:pytorch_lightning.utilities.rank_zero:`Trainer.fit` stopped: `max_epochs=1` reached.\n"]}],"source":["trainer.fit(sup_module, sup_data)"]},{"cell_type":"code","execution_count":null,"id":"19Y1mzVAd1qG","metadata":{"colab":{"background_save":true},"id":"19Y1mzVAd1qG","outputId":"cff0d919-3135-465d-cbba-42ddfc6219a8"},"outputs":[{"name":"stdout","output_type":"stream","text":["{'loss': tensor(1.0582), 'seq_len': tensor(849.3438), 'y': tensor(1.7188), 'val_loss': tensor(1.1752), 'valid/MulticlassAccuracy': tensor(0.4507)}\n"]}],"source":["# train and validation metrics\n","print(trainer.logged_metrics)"]},{"cell_type":"code","execution_count":null,"id":"8V3OF1-td1qG","metadata":{"colab":{"background_save":true},"id":"8V3OF1-td1qG","outputId":"8f38a795-964e-435f-9ed6-9976a2764aac"},"outputs":[{"name":"stderr","output_type":"stream","text":["INFO:pytorch_lightning.utilities.rank_zero:Restoring states from the checkpoint path at /content/lightning_logs/version_0/checkpoints/epoch=0-step=157.ckpt\n","INFO:pytorch_lightning.accelerators.cuda:LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n","INFO:pytorch_lightning.utilities.rank_zero:Loaded model weights from the checkpoint at /content/lightning_logs/version_0/checkpoints/epoch=0-step=157.ckpt\n"]},{"data":{"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\">        Test metric        </span>┃<span style=\"font-weight: bold\">       DataLoader 0        </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n","│<span style=\"color: #008080; text-decoration-color: #008080\">  test/MulticlassAccuracy  </span>│<span style=\"color: #800080; text-decoration-color: #800080\">    0.44699999690055847    </span>│\n","└───────────────────────────┴───────────────────────────┘\n","</pre>\n"],"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1m       Test metric       \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      DataLoader 0       \u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n","│\u001b[36m \u001b[0m\u001b[36m test/MulticlassAccuracy \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m   0.44699999690055847   \u001b[0m\u001b[35m \u001b[0m│\n","└───────────────────────────┴───────────────────────────┘\n"]},"metadata":{},"output_type":"display_data"},{"data":{"text/plain":["[{'test/MulticlassAccuracy': 0.44699999690055847}]"]},"execution_count":22,"metadata":{},"output_type":"execute_result"}],"source":["# test metrics\n","trainer.test(ckpt_path=\"best\", dataloaders=sup_data.test_dataloader())"]},{"cell_type":"markdown","id":"hSYiJ5Dcd1qG","metadata":{"id":"hSYiJ5Dcd1qG"},"source":["# Make predict\n","\n","Let\"s make predict to check metrics"]},{"cell_type":"code","execution_count":null,"id":"6t7bovStd1qH","metadata":{"colab":{"background_save":true},"id":"6t7bovStd1qH","outputId":"8c7355e0-70ce-4bb5-ce30-5859c6e3e8dc"},"outputs":[{"name":"stderr","output_type":"stream","text":["/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py:558: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n","  warnings.warn(_create_warning_msg(\n"]}],"source":["inference_dl = torch.utils.data.DataLoader(\n","    dataset=dataset_test,\n","    collate_fn=collate_feature_dict,\n","    shuffle=False,\n","    batch_size=1000,\n","    num_workers=4,\n",")"]},{"cell_type":"code","execution_count":null,"id":"tljZnLcbd1qH","metadata":{"colab":{"background_save":true},"id":"tljZnLcbd1qH"},"outputs":[],"source":["inf_module = InferenceModule(\n","    torch.nn.Sequential(\n","        sup_module,\n","        torch.nn.Softmax(dim=1),\n","    ),\n","    model_out_name=\"prob\",\n",")"]},{"cell_type":"code","execution_count":null,"id":"sqcGaiwxd1qH","metadata":{"colab":{"background_save":true},"id":"sqcGaiwxd1qH","outputId":"6f6714e7-ce8d-49cc-80d5-48c1a8cc75ca"},"outputs":[{"name":"stderr","output_type":"stream","text":["INFO:pytorch_lightning.accelerators.cuda:LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]\n"]}],"source":["df_predict = trainer.predict(inf_module, inference_dl)"]},{"cell_type":"code","execution_count":null,"id":"zak-Ax0Rd1qI","metadata":{"colab":{"background_save":true},"id":"zak-Ax0Rd1qI"},"outputs":[],"source":["df_predict = pd.concat(df_predict, axis=0)"]},{"cell_type":"code","execution_count":null,"id":"v3p-OVvHd1qI","metadata":{"colab":{"background_save":true},"id":"v3p-OVvHd1qI","outputId":"509b3378-5c38-4318-c78c-7b2042ba35f2"},"outputs":[{"data":{"application/vnd.google.colaboratory.intrinsic+json":{"summary":"{\n  \"name\": \"df_predict\",\n  \"rows\": 7000,\n  \"fields\": [\n    {\n      \"column\": \"client_id\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 14429,\n        \"min\": 10,\n        \"max\": 49993,\n        \"num_unique_values\": 7000,\n        \"samples\": [\n          46288,\n          20956,\n          14353\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"target_bin\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1,\n        \"min\": 0,\n        \"max\": 3,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          1,\n          2,\n          3\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"prob_0000\",\n      \"properties\": {\n        \"dtype\": \"float32\",\n        \"num_unique_values\": 6999,\n        \"samples\": [\n          0.17546747624874115,\n          0.18937087059020996,\n          0.14228983223438263\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"prob_0001\",\n      \"properties\": {\n        \"dtype\": \"float32\",\n        \"num_unique_values\": 7000,\n        \"samples\": [\n          0.5890853404998779,\n          0.06300126016139984,\n          0.5031793713569641\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"prob_0002\",\n      \"properties\": {\n        \"dtype\": \"float32\",\n        \"num_unique_values\": 6999,\n        \"samples\": [\n          0.032598040997982025,\n          0.7208210229873657,\n          0.02351311780512333\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"prob_0003\",\n      \"properties\": {\n        \"dtype\": \"float32\",\n        \"num_unique_values\": 6996,\n        \"samples\": [\n          0.06157274544239044,\n          0.2945510745048523,\n          0.3347427248954773\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}","type":"dataframe","variable_name":"df_predict"},"text/html":["\n","  <div id=\"df-de64abf8-d594-48b5-8247-730c31138874\" class=\"colab-df-container\">\n","    <div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>client_id</th>\n","      <th>target_bin</th>\n","      <th>prob_0000</th>\n","      <th>prob_0001</th>\n","      <th>prob_0002</th>\n","      <th>prob_0003</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>10</td>\n","      <td>3</td>\n","      <td>0.149224</td>\n","      <td>0.519380</td>\n","      <td>0.025183</td>\n","      <td>0.306213</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>11</td>\n","      <td>3</td>\n","      <td>0.210812</td>\n","      <td>0.052006</td>\n","      <td>0.653654</td>\n","      <td>0.083527</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>18</td>\n","      <td>1</td>\n","      <td>0.198591</td>\n","      <td>0.430765</td>\n","      <td>0.046228</td>\n","      <td>0.324416</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>33</td>\n","      <td>0</td>\n","      <td>0.273370</td>\n","      <td>0.043580</td>\n","      <td>0.577292</td>\n","      <td>0.105758</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>34</td>\n","      <td>2</td>\n","      <td>0.336681</td>\n","      <td>0.175975</td>\n","      <td>0.179719</td>\n","      <td>0.307625</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>\n","    <div class=\"colab-df-buttons\">\n","\n","  <div class=\"colab-df-container\">\n","    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-de64abf8-d594-48b5-8247-730c31138874')\"\n","            title=\"Convert this dataframe to an interactive table.\"\n","            style=\"display:none;\">\n","\n","  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n","    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n","  </svg>\n","    </button>\n","\n","  <style>\n","    .colab-df-container {\n","      display:flex;\n","      gap: 12px;\n","    }\n","\n","    .colab-df-convert {\n","      background-color: #E8F0FE;\n","      border: none;\n","      border-radius: 50%;\n","      cursor: pointer;\n","      display: none;\n","      fill: #1967D2;\n","      height: 32px;\n","      padding: 0 0 0 0;\n","      width: 32px;\n","    }\n","\n","    .colab-df-convert:hover {\n","      background-color: #E2EBFA;\n","      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n","      fill: #174EA6;\n","    }\n","\n","    .colab-df-buttons div {\n","      margin-bottom: 4px;\n","    }\n","\n","    [theme=dark] .colab-df-convert {\n","      background-color: #3B4455;\n","      fill: #D2E3FC;\n","    }\n","\n","    [theme=dark] .colab-df-convert:hover {\n","      background-color: #434B5C;\n","      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n","      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n","      fill: #FFFFFF;\n","    }\n","  </style>\n","\n","    <script>\n","      const buttonEl =\n","        document.querySelector('#df-de64abf8-d594-48b5-8247-730c31138874 button.colab-df-convert');\n","      buttonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","\n","      async function convertToInteractive(key) {\n","        const element = document.querySelector('#df-de64abf8-d594-48b5-8247-730c31138874');\n","        const dataTable =\n","          await google.colab.kernel.invokeFunction('convertToInteractive',\n","                                                    [key], {});\n","        if (!dataTable) return;\n","\n","        const docLinkHtml = 'Like what you see? Visit the ' +\n","          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n","          + ' to learn more about interactive tables.';\n","        element.innerHTML = '';\n","        dataTable['output_type'] = 'display_data';\n","        await google.colab.output.renderOutput(dataTable, element);\n","        const docLink = document.createElement('div');\n","        docLink.innerHTML = docLinkHtml;\n","        element.appendChild(docLink);\n","      }\n","    </script>\n","  </div>\n","\n","\n","<div id=\"df-dbcd7251-1a67-4539-8e08-648553381728\">\n","  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-dbcd7251-1a67-4539-8e08-648553381728')\"\n","            title=\"Suggest charts\"\n","            style=\"display:none;\">\n","\n","<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n","     width=\"24px\">\n","    <g>\n","        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n","    </g>\n","</svg>\n","  </button>\n","\n","<style>\n","  .colab-df-quickchart {\n","      --bg-color: #E8F0FE;\n","      --fill-color: #1967D2;\n","      --hover-bg-color: #E2EBFA;\n","      --hover-fill-color: #174EA6;\n","      --disabled-fill-color: #AAA;\n","      --disabled-bg-color: #DDD;\n","  }\n","\n","  [theme=dark] .colab-df-quickchart {\n","      --bg-color: #3B4455;\n","      --fill-color: #D2E3FC;\n","      --hover-bg-color: #434B5C;\n","      --hover-fill-color: #FFFFFF;\n","      --disabled-bg-color: #3B4455;\n","      --disabled-fill-color: #666;\n","  }\n","\n","  .colab-df-quickchart {\n","    background-color: var(--bg-color);\n","    border: none;\n","    border-radius: 50%;\n","    cursor: pointer;\n","    display: none;\n","    fill: var(--fill-color);\n","    height: 32px;\n","    padding: 0;\n","    width: 32px;\n","  }\n","\n","  .colab-df-quickchart:hover {\n","    background-color: var(--hover-bg-color);\n","    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n","    fill: var(--button-hover-fill-color);\n","  }\n","\n","  .colab-df-quickchart-complete:disabled,\n","  .colab-df-quickchart-complete:disabled:hover {\n","    background-color: var(--disabled-bg-color);\n","    fill: var(--disabled-fill-color);\n","    box-shadow: none;\n","  }\n","\n","  .colab-df-spinner {\n","    border: 2px solid var(--fill-color);\n","    border-color: transparent;\n","    border-bottom-color: var(--fill-color);\n","    animation:\n","      spin 1s steps(1) infinite;\n","  }\n","\n","  @keyframes spin {\n","    0% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","      border-left-color: var(--fill-color);\n","    }\n","    20% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    30% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","      border-right-color: var(--fill-color);\n","    }\n","    40% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    60% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","    }\n","    80% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-bottom-color: var(--fill-color);\n","    }\n","    90% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","    }\n","  }\n","</style>\n","\n","  <script>\n","    async function quickchart(key) {\n","      const quickchartButtonEl =\n","        document.querySelector('#' + key + ' button');\n","      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n","      quickchartButtonEl.classList.add('colab-df-spinner');\n","      try {\n","        const charts = await google.colab.kernel.invokeFunction(\n","            'suggestCharts', [key], {});\n","      } catch (error) {\n","        console.error('Error during call to suggestCharts:', error);\n","      }\n","      quickchartButtonEl.classList.remove('colab-df-spinner');\n","      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n","    }\n","    (() => {\n","      let quickchartButtonEl =\n","        document.querySelector('#df-dbcd7251-1a67-4539-8e08-648553381728 button');\n","      quickchartButtonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","    })();\n","  </script>\n","</div>\n","    </div>\n","  </div>\n"],"text/plain":["   client_id  target_bin  prob_0000  prob_0001  prob_0002  prob_0003\n","0         10           3   0.149224   0.519380   0.025183   0.306213\n","1         11           3   0.210812   0.052006   0.653654   0.083527\n","2         18           1   0.198591   0.430765   0.046228   0.324416\n","3         33           0   0.273370   0.043580   0.577292   0.105758\n","4         34           2   0.336681   0.175975   0.179719   0.307625"]},"execution_count":27,"metadata":{},"output_type":"execute_result"}],"source":["df_predict.head()"]},{"cell_type":"code","execution_count":null,"id":"_2wu_SxTd1qI","metadata":{"colab":{"background_save":true},"id":"_2wu_SxTd1qI","outputId":"826e990b-e678-4f2c-f706-dc5214b017f1"},"outputs":[{"data":{"text/plain":["array([1, 2, 1, ..., 1, 2, 2])"]},"execution_count":28,"metadata":{},"output_type":"execute_result"}],"source":["y_pred = df_predict[[f\"prob_{i:04d}\" for i in range(4)]].values.argmax(axis=1)\n","y_pred"]},{"cell_type":"code","execution_count":null,"id":"d2yeBHeTd1qI","metadata":{"colab":{"background_save":true},"id":"d2yeBHeTd1qI","outputId":"f10f6725-760a-44fc-cd42-caca7308d031"},"outputs":[{"data":{"text/plain":["array([3, 3, 1, ..., 1, 2, 2])"]},"execution_count":29,"metadata":{},"output_type":"execute_result"}],"source":["y_true = df_predict[\"target_bin\"].values\n","y_true"]},{"cell_type":"code","execution_count":null,"id":"WSdnJW7vd1qJ","metadata":{"colab":{"background_save":true},"id":"WSdnJW7vd1qJ","outputId":"986fc37a-2cdb-4166-ce7c-2a824f20fb48"},"outputs":[{"data":{"text/plain":["0.447"]},"execution_count":30,"metadata":{},"output_type":"execute_result"}],"source":["accuracy_score(y_true, y_pred)"]},{"cell_type":"code","execution_count":null,"id":"QDs028Zod1qJ","metadata":{"colab":{"background_save":true},"id":"QDs028Zod1qJ","outputId":"5adcc904-c0f7-41c8-c41b-1c7a9ee67b64"},"outputs":[{"data":{"text/plain":["array([[ 319,  260,  928,  228],\n","       [ 164,  983,  368,  234],\n","       [ 125,   40, 1549,   50],\n","       [ 294,  656,  524,  278]])"]},"execution_count":31,"metadata":{},"output_type":"execute_result"}],"source":["confusion_matrix(y_true, y_pred)"]}],"metadata":{"colab":{"provenance":[]},"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.7.13"}},"nbformat":4,"nbformat_minor":5}