{"cells":[{"metadata":{},"cell_type":"markdown","source":"### What I am trying to achieve with this notebook\n\nThe notebook is inspired by the following Medium blogpost by Nvidia: \n\n\"[Reading Larger than Memory CSVs with RAPIDS and Dask](https://medium.com/rapids-ai/reading-larger-than-memory-csvs-with-rapids-and-dask-e6e27dfa6c0f)\"\n\nWe will see how we can load the dask-cuda library (its a conda install) and then read a large dataset\n\n"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!nvcc --version","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!conda install -y -c rapidsai dask-cuda","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"from dask.distributed import Client, wait\n\nfrom dask.utils import parse_bytes\nimport cudf\nimport dask_cudf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from dask_cuda import LocalCUDACluster","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!nvidia-smi","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cluster = LocalCUDACluster(\n    CUDA_VISIBLE_DEVICES=\"0\",\n    rmm_pool_size=parse_bytes(\"14GB\"), # This GPU has 16GB of memory\n    device_memory_limit=parse_bytes(\"8GB\"),\n)\nclient = Client(cluster)\nclient","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\ntrain_ddf = dask_cudf.read_csv(\"/kaggle/input/riiid-test-answer-prediction/train.csv\", chunksize=\"500 MB\")\nprint(train_ddf.npartitions)\nlen(train_ddf)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_ddf.columns","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}