blob: 20e7262660c03fc5628eb9872a133cefdc067fee [file] [log] [blame]
#!/usr/bin/env python
#/************************************************************
#*
#* 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.
#*
#*************************************************************/
# pls get linux_input.txt from http://cs.stanford.edu/people/karpathy/char-rnn/
data = open('linux_input.txt', 'r').read() # should be simple plain text file
chars = list(set(data))
data_size, vocab_size = len(data), len(chars)
print 'data has %d characters, %d unique.' % (data_size, vocab_size)
with open('vocab.txt', 'w') as fd:
fd.write("".join(chars))
fd.flush()