Raku DSL::Bulgarian

use DSL::English::DataQueryWorkflows;

my $command = '
зареди данните iris;
вземи елементите от 1 до 120;
филтрирай чрез Sepal.Width е по-голямо от 2.4 и Petal.Length е по-малко от 5.5; 
групирай с колоната Species;
покажи размерите
';
for <English Python::pandas Raku::Reshapers Spanish Russian> -> $t {
   say '=' x 60, "\n", $t, "\n", '-' x 60;
   say ToDataQueryWorkflowCode($command, $t, language => 'Bulgarian', format => 'code');
}

# ============================================================
# English
# ------------------------------------------------------------
# load the data table: "iris"
# take elements from 1 to 120
# filter with the predicate: ((Sepal.Width greater than 2.4) и (Petal.Length less than 5.5))
# group by the columns: Species
# show the count(s)
# ============================================================
# Python::pandas
# ------------------------------------------------------------
# obj = example_dataset('iris')
# obj = obj.iloc[1-1:120]
# obj = obj[((obj["Sepal.Width"]> 2.4) & (obj["Petal.Length"]< 5.5))]
# obj = obj.groupby(["Species"])
# print(obj.size())
# ============================================================
# Raku::Reshapers
# ------------------------------------------------------------
# my $obj = example-dataset('iris') ;
# $obj = $obj[ (1 - 1) ... (120 - 1 ) ] ;
# $obj = $obj.grep({ $_{"Sepal.Width"} > 2.4 and $_{"Petal.Length"} < 5.5 }).Array ;
# $obj = group-by($obj, "Species") ;
# say "counts: ", $obj>>.elems
# ============================================================
# Spanish
# ------------------------------------------------------------
# cargar la tabla: "iris"
# tomar los elementos de 1 a 120
# filtrar con la condicion: ((Sepal.Width más grande 2.4) y (Petal.Length menos 5.5))
# agrupar con columnas: "Species"
# mostrar recuentos
# ============================================================
# Russian
# ------------------------------------------------------------
# загрузить таблицу: "iris"
# взять элементы с 1 по 120
# фильтровать с предикатом: ((Sepal.Width больше 2.4) и (Petal.Length меньше 5.5))
# групировать с колонками: Species
# показать число

use DSL::English::ClassificationWorkflows;

my $command = '
използвай dfTitanic;
раздели данните с цепещо съотношение 0.82;
направи gradient boosted trees класификатор;
покажи TruePositiveRate и FalsePositiveRate;
';

for <English Russian WL::ClCon> -> $t {
    say '=' x 60, "\n", $t, "\n", '-' x 60;
    say ToClassificationWorkflowCode($command, $t, language => 'Bulgarian', format => 'code');
}

# ============================================================
# English
# ------------------------------------------------------------
# use the data: dfTitanic 
# split into training and testing data with the proportion 0.82 
# train classifier with method: gradient boosted trees
# ============================================================
# Russian
# ------------------------------------------------------------
# использовать данные: dfTitanic 
# разделить данные на пропорцию 0.82 
# обучить классификатор методом: gradient boosted trees
# ============================================================
# WL::ClCon
# ------------------------------------------------------------
# ClConUnit[ dfTitanic ] \[DoubleLongRightArrow]
# ClConSplitData[ 0.82 ] \[DoubleLongRightArrow]
# ClConMakeClassifier[ "GradientBoostedTrees" ] \[DoubleLongRightArrow]
# ClConClassifierMeasurements[ {"Recall", "FalsePositiveRate"} ] \[DoubleLongRightArrow] ClConEchoValue[]

use DSL::English::LatentSemanticAnalysisWorkflows;

my $command = '
създай със textHamlet;
направи документ-термин матрица със автоматични стоп думи;
приложи LSI функциите IDF, TermFrequency, и Cosine;
извади 12 теми чрез NNMF и максимален брой стъпки 12;
покажи таблица  на темите с 12 термина;
покажи текущата лентова стойност
';

for <English Python::LSAMon R::LSAMon Russian> -> $t {
    say '=' x 60, "\n", $t, "\n", '-' x 60;
    say ToLatentSemanticAnalysisWorkflowCode($command, $t, language => 'Bulgarian', format => 'code');
}

#ERROR: Possible misspelling of 'термини' as 'термина'.
#ERROR: Possible misspelling of 'термини' as 'термина'.
#ERROR: Possible misspelling of 'термини' as 'термина'.
#ERROR: Possible misspelling of 'термини' as 'термина'.
# ============================================================
# English
# ------------------------------------------------------------
# create LSA object with the data: textHamlet
# make the document-term matrix with the parameters: use the stop words: NULL
# apply the latent semantic analysis (LSI) functions: global weight function : "IDF", local weight function : "None", normalizer function : "Cosine"
# extract 12 topics using the parameters: method : Non-Negative Matrix Factorization (NNMF), max number of steps : 12
# show topics table using the parameters: numberOfTerms = 12
# show the pipeline value
# ============================================================
# Python::LSAMon
# ------------------------------------------------------------
# LatentSemanticAnalyzer(textHamlet).make_document_term_matrix( stop_words = None).apply_term_weight_functions(global_weight_func = "IDF", local_weight_func = "None", normalizer_func = "Cosine").extract_topics(number_of_topics = 12, method = "NNMF", max_steps = 12).echo_topics_table(numberOfTerms = 12).echo_value()
# ============================================================
# R::LSAMon
# ------------------------------------------------------------
# LSAMonUnit(textHamlet) %>%
# LSAMonMakeDocumentTermMatrix( stopWords = NULL) %>%
# LSAMonApplyTermWeightFunctions(globalWeightFunction = "IDF", localWeightFunction = "None", normalizerFunction = "Cosine") %>%
# LSAMonExtractTopics( numberOfTopics = 12, method = "NNMF",  maxSteps = 12) %>%
# LSAMonEchoTopicsTable(numberOfTerms = 12) %>%
# LSAMonEchoValue()
# ============================================================
# Russian
# ------------------------------------------------------------
# создать латентный семантический анализатор с данных: textHamlet
# сделать матрицу документов-терминов с параметрами: стоп-слова: null
# применять функции латентного семантического индексирования (LSI): глобальная весовая функция: "IDF", локальная весовая функция: "None", нормализующая функция: "Cosine"
# извлечь 12 тем с параметрами: метод: Разложение Неотрицательных Матричных Факторов (NNMF), максимальное число шагов: 12
# показать таблицу темы по параметрам: numberOfTerms = 12
# показать текущее значение конвейера

use DSL::English::QuantileRegressionWorkflows;

my $command = '
създай с dfTemperatureData;
премахни липсващите стойности;
покажи данново обобщение;
премащабирай двете оси;
изчисли квантилна регресия с 20 възела и вероятности от 0.1 до 0.9 със стъпка 0.1;
покажи диаграма с дати;
покажи чертеж на абсолютните грешки;
покажи текущата лентова стойност
';

for <English R::QRMon Russian WL::QRMon> -> $t {
    say '=' x 60, "\n", $t, "\n", '-' x 60;
    say ToQuantileRegressionWorkflowCode($command, $t, language => 'Bulgarian', format => 'code');
}

#ERROR: Possible misspelling of 'възли' as 'възела'.
#ERROR: Possible misspelling of 'възли' as 'възела'.
#ERROR: Possible misspelling of 'възли' as 'възела'.
#ERROR: Possible misspelling of 'възли' as 'възела'.
# ============================================================
# English
# ------------------------------------------------------------
# create quantile regression object with the data: dfTemperatureData
# delete missing values
# show data summary
# rescale: over both regressor and value axes
# compute quantile regression with parameters: degrees of freedom (knots): 20, automatic probabilities
# show plot with parameters: use date axis
# show plot of relative errors
# show the pipeline value
# ============================================================
# R::QRMon
# ------------------------------------------------------------
# QRMonUnit( data = dfTemperatureData) %>%
# QRMonDeleteMissing() %>%
# QRMonEchoDataSummary() %>%
# QRMonRescale(regressorAxisQ = TRUE, valueAxisQ = TRUE) %>%
# QRMonQuantileRegression(df = 20, probabilities = seq(0.1, 0.9, 0.1)) %>%
# QRMonPlot( datePlotQ = TRUE) %>%
# QRMonErrorsPlot( relativeErrorsQ = TRUE) %>%
# QRMonEchoValue()
# ============================================================
# Russian
# ------------------------------------------------------------
# создать объект квантильной регрессии с данными: dfTemperatureData
# удалить пропущенные значения
# показать сводку данных
# перемасштабировать: по осям регрессии и значений
# рассчитать квантильную регрессию с параметрами: степени свободы (узлы): 20, автоматическими вероятностями
# показать диаграмму с параметрами: использованием оси дат
# показать диаграму на относительных ошибок
# показать текущее значение конвейера
# ============================================================
# WL::QRMon
# ------------------------------------------------------------
# QRMonUnit[dfTemperatureData] \[DoubleLongRightArrow]
# QRMonDeleteMissing[] \[DoubleLongRightArrow]
# QRMonEchoDataSummary[] \[DoubleLongRightArrow]
# QRMonRescale["Axes"->{True, True}] \[DoubleLongRightArrow]
# QRMonQuantileRegression["Knots" -> 20, "Probabilities" -> Range[0.1, 0.9, 0.1]] \[DoubleLongRightArrow]
# QRMonDateListPlot[] \[DoubleLongRightArrow]
# QRMonErrorPlots[ "RelativeErrors" -> True] \[DoubleLongRightArrow]
# QRMonEchoValue[]

use DSL::English::RecommenderWorkflows;

my $command = '
създай чрез dfTitanic;
препоръчай със профила "male" и "died";
покажи текущата лентова стойност
';

for <English Python::SMRMon R::SMRMon Russian> -> $t {
    say '=' x 60, "\n", $t, "\n", '-' x 60;
    say ToRecommenderWorkflowCode($command, $t, language => 'Bulgarian', format => 'code');
}

# ============================================================
# English
# ------------------------------------------------------------
# create with data table: dfTitanic
# recommend with the profile: ["male", "died"]
# show the pipeline value
# ============================================================
# Python::SMRMon
# ------------------------------------------------------------
# obj = SparseMatrixRecommender().create_from_wide_form(data = dfTitanic).recommend_by_profile( profile = ["male", "died"]).echo_value()
# ============================================================
# R::SMRMon
# ------------------------------------------------------------
# SMRMonCreate(data = dfTitanic) %>%
# SMRMonRecommendByProfile( profile = c("male", "died")) %>%
# SMRMonEchoValue()
# ============================================================
# Russian
# ------------------------------------------------------------
# создать с таблицу: dfTitanic
# рекомендуй с профилю: ["male", "died"]
# показать текущее значение конвейера