init research

tech.ml.dataset/java_test/deps.edn

@@ -0,0 +1,35 @@
+{:paths ["classes"
+         ;;Parquet logging is just over the top.  We eliminate a lot of noise here.
+         "logback"]
+ :deps {techascent/tech.ml.dataset {:mvn/version "6.069"
+
+                                    ;;smile has bindings to slf4j that error out with an
+                                    ;;exception if there is no logging backend so I
+                                    ;;included logback-classic with tmd.  That has
+                                    ;;caused issues with log4j based backends so if you
+                                    ;;use log4j or log4j2 then you need to exclude
+                                    ;;logback-classic from the tmd dependency
+
+                                    ;; :exclusions [ch.qos.logback/logback-classic]
+
+                                    }
+        uncomplicate/neanderthal {:mvn/version "0.43.3"}
+        ;;Re rebuilt the arrow bindings below the schema level to support
+        ;;mmap, compression, and JDK-17.  Due to this the version of arrow
+        ;;included isn't that important.
+        org.apache.arrow/arrow-vector {:mvn/version "6.0.0"}
+        ;;Compression packages for compressed arrow.
+        org.lz4/lz4-java {:mvn/version "1.8.0"}
+        com.github.luben/zstd-jni {:mvn/version "1.5.1-1"}
+
+
+        ;; Parquet Support
+        org.apache.parquet/parquet-hadoop {:mvn/version "1.12.0"
+                                           :exclusions [org.slf4j/slf4j-log4j12]}
+        org.apache.hadoop/hadoop-common {:mvn/version "3.3.0"
+                                         :exclusions [org.slf4j/slf4j-log4j12]}
+        ;; We literally need this for 1 POJO formatting object.
+        org.apache.hadoop/hadoop-mapreduce-client-core {:mvn/version "3.3.0"
+                                                        :exclusions [org.slf4j/slf4j-log4j12]}}
+ :jdk-17
+ {:jvm-opts ["--add-modules" "jdk.incubator.foreign" "--enable-native-access=ALL-UNNAMED"]}}