Created
June 24, 2019 12:34
-
-
Save ayushoriginal/2fe6f3abab6ccac7e3dd97e96552b10b to your computer and use it in GitHub Desktop.
word_index
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
int len_tweet = 0; | |
int size_vocab = 0; | |
// Tweet Length and Size of Vocab | |
foreach (var line in File.ReadLines("metadata_length_tweet_size_vocab.txt")) | |
{ | |
string[] temp = line.Split(" "); | |
len_tweet = Convert.ToInt32(temp[0]); | |
size_vocab = Convert.ToInt32(temp[1]); | |
} | |
// Vocab Mapping | |
var word_code = new Dictionary<string, int>(); | |
string temp_word = null; | |
int temp_code = 0; | |
foreach (var line in File.ReadLines("vocab_mapping.txt")) | |
{ | |
string[] temp2 = line.Split(" "); | |
temp_word = temp2[0]; | |
temp_code = Convert.ToInt32(temp2[1]); | |
if (word_code.ContainsKey(temp_word)) | |
{ | |
continue; | |
} | |
else | |
{ | |
word_code.Add(temp_word, temp_code); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment