-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathloadData.m
173 lines (158 loc) · 4.18 KB
/
loadData.m
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
% %% Load raw data
%
% %clear; clc; close all;
% addpath(genpath('raw_train'))
% addpath(genpath('raw_test'))
%
% numOfToken = length(load('raw_train/2.out'));
% numOfClass = 8;
%
% % Train
% trainLabel = [2:9]';
% trainMatrix = zeros(numOfClass, numOfToken);
% for i = 2:9
% trainMatrix(i - 1, :) = load(sprintf('raw_train/%d.out', i));
% end
%
% % Test model
% dir_name = 'raw_test/*.out';
% files = dir(dir_name);
% numFiles = size(files,1);
%
% testLabel = [5 7 3 5 9 9 6 5 8 2 8 7 6 3 2 4 8 6 6 3 7 4 8 7 6]';
% testMatrix = zeros(numFiles, numOfToken);
% % Test matrix
% for n = 1:size(files,1)
% fileName = files(n).name;
% % fprintf('Loading %s vector\n', fileName);
% testMatrix(n,:) = load(fileName);
% end
% %% Load w2v data
%
% % clear; clc; close all;
% addpath(genpath('w2v_train'))
% addpath(genpath('w2v_test'))
%
% numOfTweets = 10000;
% numOfToken = length(load('w2v_train/2.out'));
% numOfClass = 8;
%
% % Train model
% trainLabel = [2:9]';
% trainMatrix = zeros(numOfClass, numOfToken);
% for i = 2:9
% trainMatrix(i - 1, :) = load(sprintf('w2v_train/%d.out', i));
% end
%
% % Test model
% dir_name = 'w2v_test/*.out';
% files = dir(dir_name);
% numFiles = size(files,1);
%
% testLabel = [5 7 3 5 9 9 6 5 2 8 7 6 3 2 6 7 4 8 7 6]';
% testMatrix = zeros(numFiles, numOfToken);
% % Test matrix
% for n = 1:size(files,1)
% fileName = files(n).name;
% % fprintf('Loading %s vector\n', fileName);
% testMatrix(n,:) = load(fileName);
% end
% %% Load trainData300 testData300
%
% % clear; clc; close all;
% addpath(genpath('data300'))
%
% load('trainData300.mat')
% load('testData300.mat')
% trainLabel = double(trainLabel);
% testLabel = [2 8 7 6 3 2 5 7 3 6 5 9 7 9 4 6 8 4 7 6]';
% %% Load trainData500 testData500
%
% % clear; clc; close all;
% addpath(genpath('data500'))
%
% load('trainData500.mat')
% load('testData500.mat')
% trainLabel = double(trainLabel);
% testLabel = double(testLabel);
% %% Load rawTrain2 rawTest2
%
% % clear; clc; close all;
% addpath(genpath('rawData2'))
%
% load('RawTest.mat')
% load('RawTrain.mat')
% trainLabel = double(trainLabel);
% testLabel = double(testLabel);
% trainMatrix = double(trainMatrix);
% testMatrix = double(testMatrix);
% %% Load rawTrain3 rawTest3
%
% % clear; clc; close all;
% addpath(genpath('rawData3'))
%
% load('trainData500tweets.mat')
% load('testData500tweets.mat')
% trainLabel = double(trainLabel);
% testLabel = double(testLabel);
% trainMatrix = double(trainMatrix);
% testMatrix = double(testMatrix);
% %% Load W2Vtest1000.mat W2Vtrain1000.mat
%
% % clear; clc; close all;
% addpath(genpath('data1000'))
%
% load('W2Vtrain1000.mat')
% load('W2Vtest1000.mat')
% trainLabel = double(trainLabel);
% testLabel = double(testLabel);
% trainMatrix = double(trainMatrix);
% testMatrix = double(testMatrix);
% %% Load W2Vtest1000.mat W2Vtrain1000.mat
%
% % clear; clc; close all;
% addpath(genpath('data1000_1'))
%
% load('W2Vtrain1000new.mat')
% load('W2Vtest1000new.mat')
% trainLabel = double(trainLabel);
% testLabel = double(testLabel);
% trainMatrix = double(trainMatrix);
% testMatrix = double(testMatrix);
%% Load W2Vtrain2000-225.mat W2Vtest2000-225.mat
% clear; clc; close all;
addpath(genpath('data'))
load('W2Vtrain1000-225.mat')
load('W2Vtest1000-225.mat')
% load('W2Vtrain1000-225x.mat')
% load('W2Vtest1000-225x.mat')
% load('W2Vtrain1000-300.mat')
% load('W2Vtest1000-300.mat')
% load('W2Vtrain1000-300x.mat')
% load('W2Vtest1000-300x.mat')
% load('W2Vtrain1000-400.mat')
% load('W2Vtest1000-400.mat')
% load('W2Vtrain1000-400x.mat')
% load('W2Vtest1000-400x.mat')
% load('W2Vtrain2000-225.mat')
% load('W2Vtest2000-225.mat')
% load('W2Vtrain2000-300.mat')
% load('W2Vtest2000-300.mat')
% load('W2Vtrain2000-400.mat')
% load('W2Vtest2000-400.mat')
trainLabel = double(trainLabel);
testLabel = double(testLabel);
trainMatrix = double(trainMatrix);
testMatrix = double(testMatrix);
%% ALWAYS load these global variables
numOfClass = 8;
numTrain = size(trainMatrix, 1);
numTest = size(testMatrix, 1);
results = ones(numTest, 1);
%% Normalize raw vector
for i = 1:numTrain
trainMatrix(i,:) = trainMatrix(i,:) / norm(trainMatrix(i,:));
end
for i = 1:numTest
testMatrix(i,:) = testMatrix(i,:) / norm(testMatrix(i,:));
end