MachineLearningNotebooks/databricks/02.Ingest_data.ipynb

{"cells":[{"cell_type":"markdown","source":["Azure ML & Azure Databricks notebooks by Parashar Shah.\n\nCopyright (c) Microsoft Corporation. All rights reserved.\n\nLicensed under the MIT License."],"metadata":{}},{"cell_type":"markdown","source":["Please ensure you have run all previous notebooks in sequence before running this."],"metadata":{}},{"cell_type":"markdown","source":["#Data Ingestion"],"metadata":{}},{"cell_type":"code","source":["import os\nimport urllib"],"metadata":{},"outputs":[],"execution_count":4},{"cell_type":"code","source":["# Download AdultCensusIncome.csv from Azure CDN. This file has 32,561 rows.\nbasedataurl = \"https://amldockerdatasets.azureedge.net\"\ndatafile = \"AdultCensusIncome.csv\"\ndatafile_dbfs = os.path.join(\"/dbfs\", datafile)\n\nif os.path.isfile(datafile_dbfs):\n    print(\"found {} at {}\".format(datafile, datafile_dbfs))\nelse:\n    print(\"downloading {} to {}\".format(datafile, datafile_dbfs))\n    urllib.request.urlretrieve(os.path.join(basedataurl, datafile), datafile_dbfs)"],"metadata":{},"outputs":[],"execution_count":5},{"cell_type":"code","source":["# Create a Spark dataframe out of the csv file.\ndata_all = sqlContext.read.format('csv').options(header='true', inferSchema='true', ignoreLeadingWhiteSpace='true', ignoreTrailingWhiteSpace='true').load(datafile)\nprint(\"({}, {})\".format(data_all.count(), len(data_all.columns)))\ndata_all.printSchema()"],"metadata":{},"outputs":[],"execution_count":6},{"cell_type":"code","source":["#renaming columns\ncolumns_new = [col.replace(\"-\", \"_\") for col in data_all.columns]\ndata_all = data_all.toDF(*columns_new)\ndata_all.printSchema()"],"metadata":{},"outputs":[],"execution_count":7},{"cell_type":"code","source":["display(data_all.limit(5))"],"metadata":{},"outputs":[],"execution_count":8},{"cell_type":"markdown","source":["#Data Preparation"],"metadata":{}},{"cell_type":"code","source":["# Choose feature columns and the label column.\nlabel = \"income\"\nxvals_all = set(data_all.columns) - {label}\n\n#dbutils.widgets.remove(\"xvars_multiselect\")\ndbutils.widgets.removeAll()\n\ndbutils.widgets.multiselect('xvars_multiselect', 'hours_per_week', xvals_all)\nxvars_multiselect = dbutils.widgets.get(\"xvars_multiselect\")\nxvars = xvars_multiselect.split(\",\")\n\nprint(\"label = {}\".format(label))\nprint(\"features = {}\".format(xvars))\n\ndata = data_all.select([*xvars, label])\n\n# Split data into train and test.\ntrain, test = data.randomSplit([0.75, 0.25], seed=123)\n\nprint(\"train ({}, {})\".format(train.count(), len(train.columns)))\nprint(\"test ({}, {})\".format(test.count(), len(test.columns)))"],"metadata":{},"outputs":[],"execution_count":10},{"cell_type":"markdown","source":["#Data Persistence"],"metadata":{}},{"cell_type":"code","source":["# Write the train and test data sets to intermediate storage\ntrain_data_path = \"AdultCensusIncomeTrain\"\ntest_data_path = \"AdultCensusIncomeTest\"\n\ntrain_data_path_dbfs = os.path.join(\"/dbfs\", \"AdultCensusIncomeTrain\")\ntest_data_path_dbfs = os.path.join(\"/dbfs\", \"AdultCensusIncomeTest\")\n\ntrain.write.mode('overwrite').parquet(train_data_path)\ntest.write.mode('overwrite').parquet(test_data_path)\nprint(\"train and test datasets saved to {} and {}\".format(train_data_path_dbfs, test_data_path_dbfs))"],"metadata":{},"outputs":[],"execution_count":12},{"cell_type":"code","source":["dbutils.notebook.exit(\"success\")"],"metadata":{},"outputs":[],"execution_count":13},{"cell_type":"code","source":[""],"metadata":{},"outputs":[],"execution_count":14}],"metadata":{"name":"02.Ingest_data","notebookId":3874566296719393},"nbformat":4,"nbformat_minor":0}