{"cells":[{"metadata":{},"cell_type":"markdown","source":"This kernel will show you how to load complete parquet files into Pandas and how to read just a subset of the data."},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport pyarrow.parquet as pq\nimport os","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.listdir('../input')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Reading the entire parquet file is a one liner. Parquet will handle the parallelization and recover the original int8 datatype."},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train = pq.read_pandas('../input/train.parquet').to_pandas()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Note that each column contains a single 800,000 measurement signal."},{"metadata":{"trusted":true},"cell_type":"code","source":"train.info()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"If we wanted to instead load a subset of the data, we could load the metadata file to get the names of a few signals of interest. However, since the column names are just the column enumerations, we'll skip that step for now and just load the first five."},{"metadata":{"trusted":true},"cell_type":"code","source":"train.columns[:5]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"subset_train = pq.read_pandas('../input/train.parquet', columns=[str(i) for i in range(5)]).to_pandas()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"subset_train.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"subset_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}