| Title: | The Best Wavelet Filter-Level for Prepared Wavelet-Based Models |
|---|---|
| Description: | Four filters have been chosen namely 'haar', 'c6', 'la8', and 'bl14' (Kindly refer to 'wavelets' in 'CRAN' repository for more supported filters). Levels of decomposition are 2, 3, 4, etc. up to maximum decomposition level which is ceiling value of logarithm of length of the series base 2. For each combination two models are run separately. Results are stored in 'input'. First five metrics are expected to be minimum and last three metrics are expected to be maximum for a model to be considered good. Firstly, every metric value (among first five) is searched in every columns and minimum values are denoted as 'MIN' and other values are denoted as 'NA'. Secondly, every metric (among last three) is searched in every columns and maximum values are denoted as 'MAX' and other values are denoted as 'NA'. 'output' contains the similar number of rows (which is 8) and columns (which is number filter-level combinations) as of 'input'. Values in 'output' are corresponding 'NA', 'MIN' or 'MAX'. Finally, the column containing minimum number of 'NA' values is denoted as the best ('FL'). In special case, if two columns having equal 'NA', it has been checked among these two columns which one is having least 'NA' in first five rows and has been inferred as the best. 'FL_metrics_values' are the corresponding metrics values. 'WARIGAANbest' is the data frame (dimension: 1*8) containing different metrics of the best filter-level combination. More details can be found in Garai and others (2023) <doi:10.13140/RG.2.2.11977.42087>. |
| Authors: | Mr. Sandip Garai [aut, cre], Dr. Ranjit Kumar Paul [aut] |
| Maintainer: | Mr. Sandip Garai <[email protected]> |
| License: | GPL-3 |
| Version: | 0.1.0 |
| Built: | 2024-11-04 04:19:20 UTC |
| Source: | https://github.com/cran/WaveletMLbestFL |
In statistical modeling, multiple models need to be compared based on certain critera. The method described here uses eight metrics from "AllMetrics" package. ‘input_df’ is the data frame (at least two columns for comparison) containing metrics values in different rows of a column (which denotes a particular model’s performance). First five metrics are expected to be minimum and last three metrics are expected to be maximum for a model to be considered good. Firstly, every metric value (among first five) is searched in every columns and minimum values are denoted as ‘MIN’ and other values are denoted as ‘NA’. Secondly, every metric (among last three) is searched in every columns and maximum values are denoted as ‘MAX’ and other values are denoted as ‘NA’. ‘output_df’ contains the similar number of rows (which is 8) and columns (which is number of models to be compared) as of ‘input_df’. Values in ‘output_df’ are corresponding ‘NA’, ‘MIN’ or ‘MAX’. Finally, the column containing minimum number of ‘NA’ values is denoted as the best column. ‘min_NA_col’ gives the name of the best column (model). ‘min_NA_values’ are the corresponding metrics values. ‘BestColumn_metrics’ is the data frame (dimension: 1*8) containing different metrics of the best column (model). ‘best_column_results’ is the final result (a list) containing all of these output elements. In special case, if two columns having equal 'NA', it will be checked among these two column which one is having least 'NA' in first five rows and will be inferred as the best. More details about 'AllMetrics' can be found in Garai (2023) <doi:10.13140/RG.2.2.18688.30723>.
best_column(input_df)best_column(input_df)
input_df |
Data Frame Containing Eight Metrics Values In Different Columns |
best_column_results: A list containing four data frames
Paul, R. K., & Garai, S. (2021). Performance comparison of wavelets-based machine learning technique for forecasting agricultural commodity prices. Soft Computing, 25(20), 12857-12873.
Paul, R. K., & Garai, S. (2022). Wavelets based artificial neural network technique for forecasting agricultural prices. Journal of the Indian Society for Probability and Statistics, 23(1), 47-61.
Garai, S., & Paul, R. K. (2023). Development of MCS based-ensemble models using CEEMDAN decomposition and machine intelligence. Intelligent Systems with Applications, 18, 200202.
Garai, S., Paul, R. K., Rakshit, D., Yeasin, M., Paul, A. K., Roy, H. S., Barman, S. & Manjunatha, B. (2023). An MRA Based MLR Model for Forecasting Indian Annual Rainfall Using Large Scale Climate Indices. International Journal of Environment and Climate Change, 13(5), 137-150.
Garai, S. (2023). Package 'AllMetrics' Type Package Title Calculating Multiple Performance Metrics of a Prediction Model Version 0.1.0, Repository: https://cran.r-project.org/web/packages/AllMetrics/index.html.
set.seed(123) # for reproducibility Y <- rnorm(50, 25, 5) model_1 <-CEEMDANML::carigaan(Y, ratio = 0.8, n_lag = 4) model_2 <- CEEMDANML::carigas(Y, ratio = 0.8, n_lag = 4) model_1_metrics_values <- model_1$Accuracy[,2] model_2_metrics_values <- model_2$Accuracy[,2] combined_results <- data.frame(cbind(model_1_metrics_values, model_2_metrics_values)) colnames(combined_results) <- c("model_1", "model_2") best_model <- best_column(input_df = combined_results)set.seed(123) # for reproducibility Y <- rnorm(50, 25, 5) model_1 <-CEEMDANML::carigaan(Y, ratio = 0.8, n_lag = 4) model_2 <- CEEMDANML::carigas(Y, ratio = 0.8, n_lag = 4) model_1_metrics_values <- model_1$Accuracy[,2] model_2_metrics_values <- model_2$Accuracy[,2] combined_results <- data.frame(cbind(model_1_metrics_values, model_2_metrics_values)) colnames(combined_results) <- c("model_1", "model_2") best_model <- best_column(input_df = combined_results)
Four filters have been chosen namely ‘haar’, ‘c6’, ‘la8’, and ‘bl14’. (Kindly refer to 'wavelets' in 'CRAN' repository for more supported filters). Levels of decomposition are 2, 3, 4, etc. up to maximum decomposition level which is ceiling value of logarithm of length of the series base 2. For each combination ‘warigaan’ are run (from ‘WaveletML’ package). Results are stored in ‘WARIGAANbest_input_df’. First five metrics are expected to be minimum and last three metrics are expected to be maximum for a model to be considered good. Firstly, every metric value (among first five) is searched in every columns and minimum values are denoted as ‘MIN’ and other values are denoted as ‘NA’. Secondly, every metric (among last three) is searched in every columns and maximum values are denoted as ‘MAX’ and other values are denoted as ‘NA’. ‘WARIGAANbest_output_df’ contains the similar number of rows (which is 8) and columns (which is number filter-level combinations) as of ‘WARIGAANbest_input_df’. Values in ‘WARIGAANbest_output_df’ are corresponding ‘NA’, ‘MIN’ or ‘MAX’. Finally, the column containing minimum number of ‘NA’ values is denoted as the best (‘WARIGAANbest_FL). In special case, if two columns having equal 'NA', it has been checked among these two columns which one is having least 'NA' in first five rows and has been inferred as the best. ‘WARIGAANbest_FL_metrics_values’ are the corresponding metrics values. ‘WARIGAANbest’ is the data frame (dimension: 1*8) containing different metrics of the best filter-level combination. More details about 'AllMetrics' can be found in Garai et al. (2023) <doi:10.13140/RG.2.2.11977.42087>.
warigaan_best(df, col = 2, f_l = list(f_vals = c('haar', 'c6', 'la8', 'bl14'), l_vals = 2:floor(log2(length(Y)))))warigaan_best(df, col = 2, f_l = list(f_vals = c('haar', 'c6', 'la8', 'bl14'), l_vals = 2:floor(log2(length(Y)))))
df |
Data Frame Containing various time series data except in the the 1st column |
col |
Mention the column number to be analysed except the 1st column |
f_l |
filter and level of decomposition should be chosen in this format |
WARIGAANbest_input_df: Data frame containing metrics values for WARIGAAN model different filter-level combinations
WARIGAANbest_output_df: Data frame containing ‘NA’, ‘MIN’ or ‘MAX’ values as described earlier
WARIGAANbest_FL: Best filter-level combination
WARIGAANbest_FL_metrics_values: Corresponding metrics values of WARIGAANbest_FL
WARIGAANbest: WARIGAANbest_FL with all metrics values
Aldrich, E. (2020). wavelets: Functions for Computing Wavelet Filters, Wavelet Transforms and Multiresolution Analyses. Repository:https://cran.r-project.org/web/packages/wavelets/index.html.
Paul, R. K., & Garai, S. (2021). Performance comparison of wavelets-based machine learning technique for forecasting agricultural commodity prices. Soft Computing, 25(20), 12857-12873.
Paul, R. K., & Garai, S. (2022). Wavelets based artificial neural network technique for forecasting agricultural prices. Journal of the Indian Society for Probability and Statistics, 23(1), 47-61.
Garai, S., & Paul, R. K. (2023). Development of MCS based-ensemble models using CEEMDAN decomposition and machine intelligence. Intelligent Systems with Applications, 18, 200202.
Garai, S., Paul, R. K., Rakshit, D., Yeasin, M., Paul, A. K., Roy, H. S., Barman, S. & Manjunatha, B. (2023). An MRA Based MLR Model for Forecasting Indian Annual Rainfall Using Large Scale Climate Indices. International Journal of Environment and Climate Change, 13(5), 137-150.
Garai, S. Paul, R. K., Yeasin, M.(2023). Package 'WaveletML' Type Package Title Wavelet Decomposition Based Hybrid Machine Learning Models, Repository: https://cran.r-project.org/web/packages/WaveletML/index.html.
# example_data # Set the seed for reproducibility set.seed(123) # Define the values of N and CV N <- 25 CV <- "(5-10)" mu <- 20 # define named list with f_vals and l_vals params <- list(f_vals = 'c18', l_vals = 2:3) # Define the number of data points to generate for each combination of N and CV n_data <- 3 cv_range <- as.numeric(strsplit(gsub("[()]", "", CV), "-")[[1]]) cv_values <- seq(cv_range[1], cv_range[2]) cv_sample <- sample(cv_values, n_data, replace = TRUE) sd <- mu * (cv_sample/100) data <- replicate(n_data, { d <- round(abs(rnorm(N, mean = mu, sd = sd))) d[d == 0] <- 1 d }) colnames(data) <- paste0("N_", N, "_CV_", CV, "_", 1:n_data) # Add a column for sequential numbers data_new <- data.frame(cbind("sl no" = 1:N, data)) # example warigaan_best_model <- warigaan_best(df = data_new, col = 2, f_l = params) warigaan_best_model# example_data # Set the seed for reproducibility set.seed(123) # Define the values of N and CV N <- 25 CV <- "(5-10)" mu <- 20 # define named list with f_vals and l_vals params <- list(f_vals = 'c18', l_vals = 2:3) # Define the number of data points to generate for each combination of N and CV n_data <- 3 cv_range <- as.numeric(strsplit(gsub("[()]", "", CV), "-")[[1]]) cv_values <- seq(cv_range[1], cv_range[2]) cv_sample <- sample(cv_values, n_data, replace = TRUE) sd <- mu * (cv_sample/100) data <- replicate(n_data, { d <- round(abs(rnorm(N, mean = mu, sd = sd))) d[d == 0] <- 1 d }) colnames(data) <- paste0("N_", N, "_CV_", CV, "_", 1:n_data) # Add a column for sequential numbers data_new <- data.frame(cbind("sl no" = 1:N, data)) # example warigaan_best_model <- warigaan_best(df = data_new, col = 2, f_l = params) warigaan_best_model
Four filters have been chosen namely ‘haar’, ‘c6’, ‘la8’, and ‘bl14’. (Kindly refer to 'wavelets' in 'CRAN' repository for more supported filters). Levels of decomposition are 2, 3, 4, etc. up to maximum decomposition level which is ceiling value of logarithm of length of the series base 2. For each combination ‘warigas’ are run (from ‘WaveletML’ package). Results are stored in ‘WARIGASbest_input_df’. First five metrics are expected to be minimum and last three metrics are expected to be maximum for a model to be considered good. Firstly, every metric value (among first five) is searched in every columns and minimum values are denoted as ‘MIN’ and other values are denoted as ‘NA’. Secondly, every metric (among last three) is searched in every columns and maximum values are denoted as ‘MAX’ and other values are denoted as ‘NA’. ‘WARIGASbest_output_df’ contains the similar number of rows (which is 8) and columns (which is number filter-level combinations) as of ‘WARIGASbest_input_df’. Values in ‘WARIGASbest_output_df’ are corresponding ‘NA’, ‘MIN’ or ‘MAX’. Finally, the column containing minimum number of ‘NA’ values is denoted as the best (‘WARIGASbest_FL). In special case, if two columns having equal 'NA', it has been checked among these two columns which one is having least 'NA' in first five rows and has been inferred as the best. ‘WARIGASbest_FL_metrics_values’ are the corresponding metrics values. ‘WARIGASbest’ is the data frame (dimension: 1*8) containing different metrics of the best filter-level combination. More details about 'AllMetrics' can be found in Garai et al. (2023) <doi:10.13140/RG.2.2.11977.42087>.
warigas_best(df, col = 2, f_l = list(f_vals = c('haar', 'c6', 'la8', 'bl14'), l_vals = 2:floor(log2(length(Y)))))warigas_best(df, col = 2, f_l = list(f_vals = c('haar', 'c6', 'la8', 'bl14'), l_vals = 2:floor(log2(length(Y)))))
df |
Data Frame Containing various time series data except in the the 1st column |
col |
Mention the column number to be analysed except the 1st column |
f_l |
filter and level of decomposition should be chosen in this format |
WARIGASbest_input_df: Data frame containing metrics values for WARIGAS model different filter-level combinations
WARIGASbest_output_df: Data frame containing ‘NA’, ‘MIN’ or ‘MAX’ values as described earlier
WARIGASbest_FL: Best filter-level combination
WARIGASbest_FL_metrics_values: Corresponding metrics values of WARIGASbest_FL
WARIGASbest: WARIGASbest_FL with all metrics values
Aldrich, E. (2020). wavelets: Functions for Computing Wavelet Filters, Wavelet Transforms and Multiresolution Analyses. Repository:https://cran.r-project.org/web/packages/wavelets/index.html.
Paul, R. K., & Garai, S. (2021). Performance comparison of wavelets-based machine learning technique for forecasting agricultural commodity prices. Soft Computing, 25(20), 12857-12873.
Paul, R. K., & Garai, S. (2022). Wavelets based artificial neural network technique for forecasting agricultural prices. Journal of the Indian Society for Probability and Statistics, 23(1), 47-61.
Garai, S., & Paul, R. K. (2023). Development of MCS based-ensemble models using CEEMDAN decomposition and machine intelligence. Intelligent Systems with Applications, 18, 200202.
Garai, S., Paul, R. K., Rakshit, D., Yeasin, M., Paul, A. K., Roy, H. S., Barman, S. & Manjunatha, B. (2023). An MRA Based MLR Model for Forecasting Indian Annual Rainfall Using Large Scale Climate Indices. International Journal of Environment and Climate Change, 13(5), 137-150.
Garai, S. Paul, R. K., Yeasin, M.(2023). Package 'WaveletML' Type Package Title Wavelet Decomposition Based Hybrid Machine Learning Models, Repository: https://cran.r-project.org/web/packages/WaveletML/index.html.
# example_data # Set the seed for reproducibility set.seed(123) # Define the values of N and CV N <- 25 CV <- "(5-10)" mu <- 20 # define named list with f_vals and l_vals params <- list(f_vals = 'c18', l_vals = 2:3) # Define the number of data points to generate for each combination of N and CV n_data <- 3 cv_range <- as.numeric(strsplit(gsub("[()]", "", CV), "-")[[1]]) cv_values <- seq(cv_range[1], cv_range[2]) cv_sample <- sample(cv_values, n_data, replace = TRUE) sd <- mu * (cv_sample/100) data <- replicate(n_data, { d <- round(abs(rnorm(N, mean = mu, sd = sd))) d[d == 0] <- 1 d }) colnames(data) <- paste0("N_", N, "_CV_", CV, "_", 1:n_data) # Add a column for sequential numbers data_new <- data.frame(cbind("sl no" = 1:N, data)) # example warigas_best_model <- warigas_best(df = data_new, col = 2, f_l = params) warigas_best_model# example_data # Set the seed for reproducibility set.seed(123) # Define the values of N and CV N <- 25 CV <- "(5-10)" mu <- 20 # define named list with f_vals and l_vals params <- list(f_vals = 'c18', l_vals = 2:3) # Define the number of data points to generate for each combination of N and CV n_data <- 3 cv_range <- as.numeric(strsplit(gsub("[()]", "", CV), "-")[[1]]) cv_values <- seq(cv_range[1], cv_range[2]) cv_sample <- sample(cv_values, n_data, replace = TRUE) sd <- mu * (cv_sample/100) data <- replicate(n_data, { d <- round(abs(rnorm(N, mean = mu, sd = sd))) d[d == 0] <- 1 d }) colnames(data) <- paste0("N_", N, "_CV_", CV, "_", 1:n_data) # Add a column for sequential numbers data_new <- data.frame(cbind("sl no" = 1:N, data)) # example warigas_best_model <- warigas_best(df = data_new, col = 2, f_l = params) warigas_best_model