#!/usr/bin/env bash # # Licensed to the Apache Software Foundation (ASF) under one or more # contributor license agreements. See the NOTICE file distributed with # this work for additional information regarding copyright ownership. # The ASF licenses this file to You under the Apache License, Version 2.0 # (the "License"); you may not use this file except in compliance with # the License. You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # This file is used for Binder integration to install PySpark available in # Jupyter notebook. # SPARK-45706: Should fail fast. Otherwise, the Binder image is successfully # built, and it cannot be rebuilt. set -o pipefail set -e VERSION=$(python -c "exec(open('python/pyspark/version.py').read()); print(__version__)") TAG=$(git describe --tags --exact-match 2> /dev/null || true) # If a commit is tagged, exactly specified version of pyspark should be installed to avoid # a kind of accident that an old version of pyspark is installed in the live notebook environment. # See SPARK-37170 if [ -n "$TAG" ]; then SPECIFIER="==" else SPECIFIER="<=" fi pip install plotly "pandas<2.0.0" "pyspark[sql,ml,mllib,pandas_on_spark,connect]$SPECIFIER$VERSION" # Add sbin to PATH to run `start-connect-server.sh`. SPARK_HOME=$(python -c "from pyspark.find_spark_home import _find_spark_home; print(_find_spark_home())") echo "export PATH=${PATH}:${SPARK_HOME}/sbin" >> ~/.profile echo "export SPARK_HOME=${SPARK_HOME}" >> ~/.profile # Add Spark version to env for running command dynamically based on Spark version. SPARK_VERSION=$(python -c "import pyspark; print(pyspark.__version__)") echo "export SPARK_VERSION=${SPARK_VERSION}" >> ~/.profile # Suppress warnings from Spark jobs, and UI progress bar. mkdir -p ~/.ipython/profile_default/startup echo "from pyspark.sql import SparkSession SparkSession.builder.config('spark.ui.showConsoleProgress', 'false').getOrCreate().sparkContext.setLogLevel('FATAL') " > ~/.ipython/profile_default/startup/00-init.py