blob: 2559af769a693cc9501dcfc40c08c8332f0e8b10 [file] [log] [blame]
#-------------------------------------------------------------
#
# 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.
#
#-------------------------------------------------------------
# Read the pre-trained word embeddings
E = read($1, rows=100, cols=300, format="text");
# Read the token sequence (1K) w/ 100 distinct tokens
Data = read($2, data_type="frame", format="csv");
# Read the recode map for the distinct tokens
Meta = read($3, data_type="frame", format="csv");
jspec = "{ids: true, word_embedding: [1]}";
Data_enc = transformapply(target=Data, spec=jspec, meta=Meta, embedding=E);
seq_len = 10
N = nrow(Data_enc) / seq_len
Data_enc = matrix(Data_enc, rows=N, cols=ncol(Data_enc)*seq_len)
write(Data_enc, $4, format="text");