-
Notifications
You must be signed in to change notification settings - Fork 1
/
common.cc
130 lines (109 loc) · 3.58 KB
/
common.cc
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
// Copyright 2008 Google Inc.
//
// Licensed 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.
#include <stdio.h>
#include "common.h"
#include <sstream>
char kSegmentFaultCauser[] = "Used to cause artificial segmentation fault";
namespace learning_lda {
bool IsValidProbDistribution(const TopicProbDistribution& dist) {
const double kUnificationError = 0.00001;
double sum_distribution = 0;
for (int k = 0; k < dist.size(); ++k) {
sum_distribution += dist[k];
}
return (sum_distribution - 1) * (sum_distribution - 1)
<= kUnificationError;
}
int GetAccumulativeSample(const vector<double>& distribution) {
double distribution_sum = 0.0;
for (int i = 0; i < distribution.size(); ++i) {
distribution_sum += distribution[i];
}
double choice = RandDouble() * distribution_sum;
double sum_so_far = 0.0;
for (int i = 0; i < distribution.size(); ++i) {
sum_so_far += distribution[i];
if (sum_so_far >= choice) {
return i;
}
}
LOG(FATAL) << "Failed to choose element from distribution of size "
<< distribution.size() << " and sum " << distribution_sum;
return -1;
}
int LoadWordIndex(istream& in, map<string, int>& word_index_map) {
string line;
int maxindex = 0;
while (getline(in, line)) { // Each line is a training document.
if (line.size() > 0 && // Skip empty lines.
line[0] != '\r' && // Skip empty lines.
line[0] != '\n' && // Skip empty lines.
line[0] != '$' && // Skip empty lines.
line[0] != '#') { // Skip comment lines.
istringstream ss(line);
int index;
string word;
ss >> index >> word;
word_index_map[word] = index;
if (maxindex < index)
maxindex = index;
}
}
return maxindex;
}
int LoadWordSet(istream& in ,map<string, int>& word_index_map ,set<int>& word_set) {
string line;
int sum = 0;
while (getline(in, line)) { // Each line is a training document.
if (line.size() > 0 && // Skip empty lines.
line[0] != '\r' && // Skip empty lines.
line[0] != '\n' && // Skip empty lines.
line[0] != '#') { // Skip comment lines.
istringstream ss(line);
string word;
ss >> word;
if (word_index_map.end() != word_index_map.find(word))
{
word_set.insert(word_index_map[word]);
sum++;
}
}
}
return sum;
}
int LoadWordLex(map<string, int>& word_index_map,vector<string>& index_word_map){
for (map<string, int>::const_iterator iter = word_index_map.begin();
iter != word_index_map.end(); ++iter) {
index_word_map[iter->second] = iter->first;
}
return index_word_map.size();
}
string generate_model_name(string path , int myid , int iter) {
char buff[BUFF_SIZE_SHORT];
if (0 <= iter) {
sprintf(buff, "%d-%06d",myid, iter);
}else{
sprintf(buff, "%d-final",myid);
}
path += buff;
path +=".txt";
return path;
}
std::ostream& operator << (std::ostream& out, vector<double>& v) {
for (size_t i = 0; i < v.size(); ++i) {
out << v[i] << " ";
}
return out;
}
} // namespace learning_lda