scripts/databricks/demo.dml

#-------------------------------------------------------------
#
# 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.
#
#-------------------------------------------------------------

# SystemDS on Databricks smoke test.
# Reads a matrix from storage and computes column sums and a Gram-matrix trace,
# so the read path plus a few distributed-friendly operations are exercised.
#
# Args (all optional, with defaults):
#   -nvargs in=<input-matrix-path> fmt=<format> out=<output-path>
#
# `in` is any path readable from the cluster driver (a UC volume, /Workspace,
# or dbfs:) and `fmt` any SystemDS-supported matrix format (csv, binary,
# libsvm, mm, ...). Example:
#   in=/Volumes/<catalog>/<schema>/<volume>/demo_input.csv fmt=csv

in  = ifdef($in, "demo_input.csv")
fmt = ifdef($fmt, "csv")
out = ifdef($out, "demo_result.txt")

X = read(in, format=fmt)

# Column sums and a Gram-matrix trace: both push work through Spark
# instructions for large inputs.
colSums = colSums(X)
gramTrace = sum(X * X)

s = sum(colSums) + gramTrace

print("rows=" + nrow(X) + " cols=" + ncol(X))
print("result=" + s)

write(s, out, format="text")