{"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_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import dask.dataframe as dd\ntrain_df = dd.read_csv('../input/amex-default-prediction/train_data.csv')\ntrain_labels = dd.read_csv(\"../input/amex-default-prediction/train_labels.csv\")","metadata":{"execution":{"iopub.status.busy":"2023-04-02T10:33:14.223095Z","iopub.execute_input":"2023-04-02T10:33:14.223526Z","iopub.status.idle":"2023-04-02T10:33:17.582495Z","shell.execute_reply.started":"2023-04-02T10:33:14.223446Z","shell.execute_reply":"2023-04-02T10:33:17.581742Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from pyspark.sql import SparkSession\nspark = SparkSession.builder.appName('Read CSV File into DataFrame').getOrCreate()\nauthors = spark.read.csv('../input/amex-default-prediction/train_data.csv', sep=',',inferSchema=True, header=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.columns","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.dtypes","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.describe()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.customer_ID.nunique().compute()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}