thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-12-01 20:12:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add charset_freq

Browse Source
This commit is contained in:
s-kat 2021-03-19 00:57:42 +03:00
parent 274601232b
commit 473c47abcc
4 changed files with 35783 additions and 57 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35722
src/Functions/ClassificationDictionaries/charset_freq.txt Normal file
View File

File diff suppressed because it is too large Load Diff

1
src/Functions/ClassificationDictionaries/emotional_dictionary_rus.txt Normal file
View File

File diff suppressed because one or more lines are too long

58
src/Functions/FrequencyHolder.h
View File

@ -1,9 +1,10 @@
#pragma once
#include <Functions/FunctionsTextClassification.h>
#include <Common/TLDListsHolder.h>
#include <Common/StringUtils/StringUtils.h>
#include <IO/ReadBufferFromFile.h>
#include <string_view>
#include <string>
#include <Functions/FunctionFactory.h>
#include <fstream>
#include <algorithm>
#include <cstring>
@ -31,29 +32,44 @@ public:
void parseDictionaries(const std::string& pt)
{
is_true = pt;
loadEmotionalDict("/home/sergey/datadump/myemo2.txt");
loadEncodingsFrequency("/home/sergey/data/dumps/encodings/russian/freq_enc/");
loadEmotionalDict("/home/sergey/ClickHouse/src/Functions/ClassificationDictionaries/emotional_dictionary_rus.txt");
loadEncodingsFrequency("/home/sergey/ClickHouse/src/Functions/ClassificationDictionaries/charset_freq.txt");
}
void loadEncodingsFrequency(const std::string path_to_encodings_freq)
void loadEncodingsFrequency(const std::string path_to_charset_freq)
{
std::vector<std::string> languages = {"freq_CP866", "freq_ISO", "freq_WINDOWS-1251", "freq_UTF-8"};
for (std::string & lang : languages) {
std::ifstream file(path_to_encodings_freq + lang + ".txt");
Map new_lang;
UInt16 bigram;
double count;
double total = 0;
while (file >> bigram >> count) {
new_lang[bigram] = count;
total += count;
char charset_name_buf [40];
std::string charset_name;
ReadBufferFromFile in(path_to_charset_freq);
while (!in.eof())
{
char * newline = find_first_symbols<'\n'>(in.position(), in.buffer().end());
if (newline >= in.buffer().end())
break;
std::string_view line(in.position(), newline - in.position());
in.position() = newline + 1;
if (line.empty())
continue;
// Start load new charset
if (line.size() > 2 && line[0] == '/' && line[1] == '/')
{
const char * st = line.data();
sscanf(st + 2, "%39s", charset_name_buf);
std::string s(charset_name_buf);
charset_name = s;
} else
{
const char * st = line.data();
UInt16 bigram;
double frequency;
sscanf(st, "%hd %lg", &bigram, &frequency);
encodings_freq[charset_name][bigram] = frequency;
}
for (auto & el : new_lang) {
el.second /= total;
}
encodings_freq[lang] = new_lang;
file.close();
}
}

59
src/Functions/FunctionsTextClassification.cpp
View File

@ -71,15 +71,26 @@ struct TextClassificationImpl
static double Naive_bayes(std::unordered_map<UInt16, double> standart, std::unordered_map<UInt16, double> model)
{
double res = 1;
double res = 0;
for (auto & el : model) {
if (standart[el.first] != 0) {
res += el.second * log(standart[el.first]);
} else {
res += el.second * log(0.00001);
}
}
return res;
}
static double Simple(std::unordered_map<UInt16, double> standart, std::unordered_map<UInt16, double> model)
{
double res = 0;
for (auto & el : model) {
res += el.second * standart[el.first];
}
return res;
}
static ALWAYS_INLINE size_t readCodePoints(CodePoint * code_points, const char *& pos, const char * end)
{
@ -151,11 +162,6 @@ struct TextClassificationImpl
static std::unordered_map<std::string, std::vector<double>> emotional_dict = FrequencyHolder::getInstance().getEmotionalDict();
static std::unordered_map<std::string, std::unordered_map<UInt16, double>> encodings_freq = FrequencyHolder::getInstance().getEncodingsFrequency();
/*
static TextClassificationDictionaries classification_dictionaries;
static std::unordered_map<std::string, std::vector<double>> emotional_dict = classification_dictionaries.emotional_dict;
static std::unordered_map<std::string, std::unordered_map<UInt16, double>> encodings_freq = classification_dictionaries.encodings_frequency;
*/
if (!Emo)
{
@ -163,23 +169,20 @@ struct TextClassificationImpl
std::unique_ptr<NgramCount[]> ngram_storage{new NgramCount[map_size]{}}; // list of N-grams
size_t len = calculateStats(data.data(), data.size(), common_stats.get(), readCodePoints, ngram_storage.get()); // count of N-grams
std::string ans;
double count_bigram = data.size() - 1;
// double count_bigram = data.size() - 1;
std::unordered_map<UInt16, double> model;
for (size_t i = 0; i < len; ++i) {
ans += std::to_string(ngram_storage.get()[i]) + " " + std::to_string(static_cast<double>(common_stats.get()[ngram_storage.get()[i]]) / count_bigram) + "\n";
model[ngram_storage.get()[i]] = static_cast<double>(common_stats.get()[ngram_storage.get()[i]]) / count_bigram;
ans += std::to_string(ngram_storage.get()[i]) + " " + std::to_string(static_cast<double>(common_stats.get()[ngram_storage.get()[i]])) + "\n";
model[ngram_storage.get()[i]] = static_cast<double>(common_stats.get()[ngram_storage.get()[i]]);
}
double res1 = L2_distance(encodings_freq["freq_CP866"], model);
double res2 = L2_distance(encodings_freq["freq_ISO"], model);
double res3 = L2_distance(encodings_freq["freq_WINDOWS-1251"], model);
double res4 = L2_distance(encodings_freq["freq_UTF-8"], model);
ans += std::to_string(res1) + " " + std::to_string(res2) + " " + std::to_string(res3) + " " + std::to_string(res4) + "\n";
for (const auto& item : encodings_freq) {
ans += item.first + " " + std::to_string(Simple(item.second, model)) + "\n";
}
res = ans;
}
else
{
double freq = 0;
double count_words = 0;
@ -245,33 +248,17 @@ struct TextClassificationImpl
size_t len = calculateStats(str.data(), str.size(), common_stats.get(), readCodePoints, ngram_storage.get()); // count of N-grams
std::string prom;
double count_bigram = data.size() - 1;
std::unordered_map<UInt16, double> model1;
std::unordered_map<UInt16, double> model2;
// double count_bigram = data.size() - 1;
std::unordered_map<UInt16, double> model;
for (size_t j = 0; j < len; ++j)
{
model2[ngram_storage.get()[j]] = static_cast<double>(common_stats.get()[ngram_storage.get()[j]]);
model[ngram_storage.get()[j]] = static_cast<double>(common_stats.get()[ngram_storage.get()[j]]);
}
for (size_t j = 0; j < len; ++j)
{
model1[ngram_storage.get()[j]] = static_cast<double>(common_stats.get()[ngram_storage.get()[j]]) / count_bigram;
for (const auto& item : encodings_freq) {
prom += item.first + " " + std::to_string(Simple(item.second, model)) + "\n";
}
double res1 = L2_distance(encodings_freq["freq_CP866"], model1);
double res2 = L2_distance(encodings_freq["freq_ISO"], model1);
double res3 = L2_distance(encodings_freq["freq_WINDOWS-1251"], model1);
double res4 = L2_distance(encodings_freq["freq_UTF-8"], model1);
prom += std::to_string(res1) + " " + std::to_string(res2) + " " + std::to_string(res3) + " " + std::to_string(res4) + "\n";
double res12 = Naive_bayes(encodings_freq["freq_CP866"], model2);
double res22 = Naive_bayes(encodings_freq["freq_ISO"], model2);
double res32 = Naive_bayes(encodings_freq["freq_WINDOWS-1251"], model2);
double res42 = Naive_bayes(encodings_freq["freq_UTF-8"], model2);
prom += std::to_string(res12) + " " + std::to_string(res22) + " " + std::to_string(res32) + " " + std::to_string(res42) + "\n";
const auto ans = prom.c_str();