[ALGOS-263] feat(algos): Develop test scripts for evaluating the algorithms

algorithms/Centrality/article_rank/tg_article_rank.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_article_rank (STRING v_type, STRING e_type,
+CREATE DISTRIBUTED QUERY tg_article_rank (STRING v_type, STRING e_type,
     FLOAT max_change = 0.001, INT maximum_iteration = 25, FLOAT damping = 0.85, INT top_k = 100,
     BOOL print_results = TRUE, STRING result_attribute =    "", STRING file_path = "") SYNTAX V1 {
 

algorithms/Centrality/closeness/approximate/tg_closeness_cent_approx.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_closeness_cent_approx (
+CREATE DISTRIBUTED QUERY tg_closeness_cent_approx (
     SET<STRING> v_type_set, SET<STRING> e_type_set, STRING reverse_e_type, INT top_k=100, INT k = 100,  INT max_hops = 10,  DOUBLE epsilon = 0.1,  BOOL print_results = true, 
     STRING file_path = "",  INT debug = 0,  INT sample_index = 0,  INT max_size = 1000,   BOOL wf = True ) SYNTAX V1 {
 

algorithms/Centrality/degree/unweighted/tg_degree_cent.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_degree_cent(SET<STRING> v_type_set, SET<STRING> e_type_set, SET<STRING> reverse_e_type_set, BOOL in_degree = TRUE, BOOL out_degree = TRUE, INT top_k=100, BOOL print_results = TRUE, STRING result_attribute = "",STRING file_path = "", BOOL normalize = TRUE) SYNTAX V1 {
+CREATE DISTRIBUTED QUERY tg_degree_cent(SET<STRING> v_type_set, SET<STRING> e_type_set, SET<STRING> reverse_e_type_set, BOOL in_degree = TRUE, BOOL out_degree = TRUE, INT top_k=100, BOOL print_results = TRUE, STRING result_attribute = "",STRING file_path = "", BOOL normalize = TRUE) SYNTAX V1 {
     /*
         First Author: <First Author Name>
         First Commit Date:  <First Commit Date>

algorithms/Centrality/degree/weighted/tg_weighted_degree_cent.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_weighted_degree_cent(STRING v_type, STRING e_type, STRING reverse_e_type, STRING weight_attribute, BOOL in_degree = TRUE, BOOL out_degree = TRUE, INT top_k=100, BOOL print_results = TRUE, STRING result_attribute = "",STRING file_path = "") SYNTAX V1 {
+CREATE DISTRIBUTED QUERY tg_weighted_degree_cent(STRING v_type, STRING e_type, STRING reverse_e_type, STRING weight_attribute, BOOL in_degree = TRUE, BOOL out_degree = TRUE, INT top_k=100, BOOL print_results = TRUE, STRING result_attribute = "",STRING file_path = "") SYNTAX V1 {
    /*
    First Author: <First Author Name>
    First Commit Date:  <First Commit Date>

algorithms/Centrality/eigenvector/tg_eigenvector_cent.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_eigenvector_cent(SET<STRING> v_type_set, SET<STRING> e_type_set, INT maximum_iteration = 100, FLOAT conv_limit = 0.000001,
+CREATE DISTRIBUTED QUERY tg_eigenvector_cent(SET<STRING> v_type_set, SET<STRING> e_type_set, INT maximum_iteration = 100, FLOAT conv_limit = 0.000001,
     INT top_k = 100, BOOL print_results = True, STRING result_attribute = "",STRING file_path = ""
     ) SYNTAX V1 {
 

algorithms/Centrality/harmonic/tg_harmonic_cent.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_harmonic_cent(SET<STRING> v_type_set, SET<STRING> e_type_set, SET<STRING> reverse_e_type_set,INT max_hops = 10,
+CREATE DISTRIBUTED QUERY tg_harmonic_cent(SET<STRING> v_type_set, SET<STRING> e_type_set, SET<STRING> reverse_e_type_set,INT max_hops = 10,
   INT top_k = 100, BOOL wf = TRUE, BOOL print_results = True, STRING result_attribute = "",
   STRING file_path = "", BOOL display_edges = FALSE) SYNTAX V1 { 
 

algorithms/Centrality/influence_maximization/CELF/tg_influence_maximization_CELF.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_influence_maximization_CELF(STRING v_type,STRING e_type,STRING weight_attribute,INT top_k,
+CREATE DISTRIBUTED QUERY tg_influence_maximization_CELF(STRING v_type,STRING e_type,STRING weight_attribute,INT top_k,
   BOOL print_results = True, STRING file_path = "")  SYNTAX V1 {
 
     /*
@@ -128,4 +128,4 @@ CREATE QUERY tg_influence_maximization_CELF(STRING v_type,STRING e_type,STRING w
   IF print_results THEN
      PRINT @@res_list;
   END;
-}
+}

algorithms/Centrality/influence_maximization/greedy/tg_influence_maximization_greedy.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_influence_maximization_greedy(STRING v_type,STRING e_type,STRING weight_attribute,INT top_k,
+CREATE DISTRIBUTED QUERY tg_influence_maximization_greedy(STRING v_type,STRING e_type,STRING weight_attribute,INT top_k,
   BOOL print_results = True, STRING file_path = "") SYNTAX V1 {
 
     /*

algorithms/Centrality/pagerank/global/unweighted/tg_pagerank.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_pagerank (STRING v_type, STRING e_type,
+CREATE DISTRIBUTED QUERY tg_pagerank (STRING v_type, STRING e_type,
  FLOAT max_change=0.001, INT maximum_iteration=25, FLOAT damping=0.85, INT top_k = 100,
  BOOL print_results = TRUE, STRING result_attribute =  "", STRING file_path = "",
  BOOL display_edges = FALSE) SYNTAX V1 {

algorithms/Centrality/pagerank/global/weighted/tg_pagerank_wt.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_pagerank_wt (STRING v_type, STRING e_type, STRING weight_attribute,
+CREATE DISTRIBUTED QUERY tg_pagerank_wt (STRING v_type, STRING e_type, STRING weight_attribute,
  FLOAT max_change=0.001, INT maximum_iteration=25, FLOAT damping=0.85, INT top_k = 100,
  BOOL print_results = TRUE, STRING result_attribute =  "", STRING file_path = "",
  BOOL display_edges = FALSE) SYNTAX V1 {

algorithms/Centrality/pagerank/personalized/all_pairs/tg_pagerank_pers_ap_batch.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_pagerank_pers_ap_batch(STRING v_type, STRING e_type,
+CREATE DISTRIBUTED QUERY tg_pagerank_pers_ap_batch(STRING v_type, STRING e_type,
   FLOAT max_change=0.001, INT maximum_iteration=25, FLOAT damping = 0.85, INT top_k = 100,INT batch_num,BOOL print_results,STRING file_path) SYNTAX V1 {
 
     /*

algorithms/Centrality/pagerank/personalized/multi_source/tg_pagerank_pers.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_pagerank_pers(SET<VERTEX> source, STRING e_type,
+CREATE DISTRIBUTED QUERY tg_pagerank_pers(SET<VERTEX> source, STRING e_type,
   FLOAT max_change=0.001, INT maximum_iteration=25, FLOAT damping = 0.85, INT top_k = 100,
   BOOL print_results = TRUE, STRING result_attribute = "", STRING file_path = "") SYNTAX V1 {
 

algorithms/Classification/greedy_graph_coloring/tg_greedy_graph_coloring.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_greedy_graph_coloring(SET<STRING> v_type_set,SET<STRING> e_type_set,UINT max_colors = 999999,
+CREATE DISTRIBUTED QUERY tg_greedy_graph_coloring(SET<STRING> v_type_set,SET<STRING> e_type_set,UINT max_colors = 999999,
   BOOL print_color_count = TRUE, BOOL print_stats = TRUE, STRING file_path = "")  SYNTAX V1 {
 
     /*

algorithms/Classification/k_nearest_neighbors/single_source/tg_knn_cosine_ss.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_knn_cosine_ss (VERTEX source, SET<STRING> v_type_set, SET<STRING> e_type_set, SET<STRING> reverse_e_type_set, STRING weight_attribute, 
+CREATE DISTRIBUTED QUERY tg_knn_cosine_ss (VERTEX source, SET<STRING> v_type_set, SET<STRING> e_type_set, SET<STRING> reverse_e_type_set, STRING weight_attribute, 
   STRING label, INT top_k, BOOL print_results = TRUE, STRING file_path = "", STRING result_attribute = "") RETURNS (STRING)  SYNTAX V1 {
 
     /*

algorithms/Classification/maximal_independent_set/deterministic/tg_maximal_indep_set.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_maximal_indep_set(STRING v_type, STRING e_type, INT maximum_iteration = 100, BOOL print_results = TRUE, STRING file_path = "")  SYNTAX V1 { 
+CREATE DISTRIBUTED QUERY tg_maximal_indep_set(STRING v_type, STRING e_type, INT maximum_iteration = 100, BOOL print_results = TRUE, STRING file_path = "")  SYNTAX V1 { 
 
     /*
     First Author: <First Author Name>

algorithms/Community/connected_components/strongly_connected_components/standard/tg_scc.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_scc (SET<STRING> v_type_set, SET<STRING> e_type_set, SET<STRING> reverse_e_type_set,
+CREATE DISTRIBUTED QUERY tg_scc (SET<STRING> v_type_set, SET<STRING> e_type_set, SET<STRING> reverse_e_type_set,
   INT top_k_dist, INT print_limit, INT maximum_iteration = 500, INT iter_wcc = 5, BOOL print_results = TRUE, STRING result_attribute= "", STRING file_path="")  SYNTAX V1 { 
     //INT iter_end_trim = 3
 

algorithms/Community/connected_components/weakly_connected_components/standard/tg_wcc.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_wcc (SET<STRING> v_type_set, SET<STRING> e_type_set, INT print_limit = 100,
+CREATE DISTRIBUTED QUERY tg_wcc (SET<STRING> v_type_set, SET<STRING> e_type_set, INT print_limit = 100,
  BOOL print_results = TRUE, STRING result_attribute = "", STRING file_path = "")  SYNTAX V1 {
 
     /*

algorithms/Community/k_core/tg_kcore.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_kcore(STRING v_type, STRING e_type, INT k_min = 0, INT k_max = -1, BOOL print_results = TRUE, 
+CREATE DISTRIBUTED QUERY tg_kcore(STRING v_type, STRING e_type, INT k_min = 0, INT k_max = -1, BOOL print_results = TRUE, 
   STRING result_attribute = "", STRING file_path = "", BOOL print_all_k = FALSE, BOOL show_shells=FALSE)  SYNTAX V1 { 
 
     /*

algorithms/Community/label_propagation/tg_label_prop.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_label_prop (SET<STRING> v_type_set, SET<STRING> e_type_set, INT maximum_iteration, INT print_limit, 
+CREATE DISTRIBUTED QUERY tg_label_prop (SET<STRING> v_type_set, SET<STRING> e_type_set, INT maximum_iteration, INT print_limit, 
   BOOL print_results = TRUE, STRING file_path = "", STRING result_attribute = "")  SYNTAX V1 {
 
 

algorithms/Community/local_clustering_coefficient/tg_lcc.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_lcc (STRING v_type, STRING e_type,INT top_k=100,BOOL print_results = True, STRING result_attribute = "",
+CREATE DISTRIBUTED QUERY tg_lcc (STRING v_type, STRING e_type,INT top_k=100,BOOL print_results = True, STRING result_attribute = "",
   STRING file_path = "", BOOL display_edges = FALSE)  SYNTAX V1 { 
 
     /*

algorithms/Community/louvain/tg_louvain.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_louvain(SET<STRING> v_type_set, SET<STRING> e_type_set, STRING weight_attribute = "weight", INT maximum_iteration = 10, 
+CREATE DISTRIBUTED QUERY tg_louvain(SET<STRING> v_type_set, SET<STRING> e_type_set, STRING weight_attribute = "weight", INT maximum_iteration = 10, 
   STRING result_attribute = "cid", STRING file_path = "", BOOL print_stats = FALSE)  SYNTAX V1 {
 
     /*

algorithms/Community/speaker-listener_label_propagation/tg_slpa.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_slpa (SET<STRING> v_type_set, SET<STRING> e_type_set, FLOAT threshold, INT maximum_iteration, INT print_limit,
+CREATE DISTRIBUTED QUERY tg_slpa (SET<STRING> v_type_set, SET<STRING> e_type_set, FLOAT threshold, INT maximum_iteration, INT print_limit,
 BOOL print_results = TRUE, STRING file_path = "") SYNTAX V1 {
 
     /*

algorithms/Path/bfs/tg_bfs.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_bfs(SET<STRING> v_type_set, SET<STRING> e_type_set,INT max_hops=10, VERTEX v_start,
+CREATE DISTRIBUTED QUERY tg_bfs(SET<STRING> v_type_set, SET<STRING> e_type_set,INT max_hops=10, VERTEX v_start,
 BOOL print_results = True, STRING result_attribute = "",STRING file_path = "", BOOL display_edges = TRUE) SYNTAX V1 { 
 
     /*

algorithms/Path/cycle_component/tg_cycle_component.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_cycle_component(STRING v_type,STRING e_type,BOOL print_results = TRUE, STRING result_attribute =  "", STRING file_path = "") SYNTAX v1{ 
+CREATE DISTRIBUTED QUERY tg_cycle_component(STRING v_type,STRING e_type,BOOL print_results = TRUE, STRING result_attribute =  "", STRING file_path = "") SYNTAX v1{ 
 
 
     /*

algorithms/Path/minimum_spanning_forest/tg_msf.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_msf (SET<STRING> v_type_set, SET<STRING> e_type_set, STRING weight_attribute, STRING weight_type,
+CREATE DISTRIBUTED QUERY tg_msf (SET<STRING> v_type_set, SET<STRING> e_type_set, STRING weight_attribute, STRING weight_type,
 	BOOL print_results = TRUE, STRING result_attribute = "", STRING file_path = "")  SYNTAX V1 {
 
     /*

algorithms/Path/minimum_spanning_tree/tg_mst.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_mst(VERTEX opt_source, SET<STRING> v_type_set, SET<STRING> e_type_set, STRING weight_attribute, STRING weight_type,
+CREATE DISTRIBUTED QUERY tg_mst(VERTEX opt_source, SET<STRING> v_type_set, SET<STRING> e_type_set, STRING weight_attribute, STRING weight_type,
   INT maximum_iteration = -1, BOOL print_results = TRUE, STRING result_attribute = "", STRING file_path = "")  SYNTAX V1 {
 
     /*

algorithms/Path/path_between_two_vertices/one_direction/tg_all_path.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_all_path(VERTEX v_source, VERTEX target_v, INT depth = 10,
+CREATE DISTRIBUTED QUERY tg_all_path(VERTEX v_source, VERTEX target_v, INT depth = 10,
   BOOL print_results = TRUE, STRING file_path = "")SYNTAX v1 {
 
     /*

algorithms/Path/shortest_path/unweighted/tg_shortest_ss_no_wt.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_shortest_ss_no_wt (VERTEX source, SET<STRING> v_type_set, SET<STRING> e_type_set, 
+CREATE DISTRIBUTED QUERY tg_shortest_ss_no_wt (VERTEX source, SET<STRING> v_type_set, SET<STRING> e_type_set, 
   INT print_limit = -1, BOOL print_results =TRUE, STRING result_attribute ="", STRING file_path ="",
   BOOL display_edges =FALSE)  SYNTAX V1 {
 

algorithms/Path/shortest_path/weighted/any_sign/tg_shortest_ss_any_wt.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_shortest_ss_any_wt (VERTEX source, SET<STRING> v_type_set, SET<STRING> e_type_set,
+CREATE DISTRIBUTED QUERY tg_shortest_ss_any_wt (VERTEX source, SET<STRING> v_type_set, SET<STRING> e_type_set,
  STRING weight_attribute, STRING weight_type, INT print_limit = -1, BOOL print_results = TRUE,
  STRING result_attribute = "", STRING file_path = "", BOOL display_edges = FALSE)  SYNTAX V1 {
 

algorithms/Path/shortest_path/weighted/positive/summary/tg_shortest_ss_pos_wt.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_shortest_ss_pos_wt (VERTEX source, SET<STRING> v_type_set, SET<STRING> e_type_set,
+CREATE DISTRIBUTED QUERY tg_shortest_ss_pos_wt (VERTEX source, SET<STRING> v_type_set, SET<STRING> e_type_set,
  STRING weight_attribute, STRING weight_type, FLOAT epsilon = 0.001,BOOL print_results = TRUE, INT print_limit = -1, 
  BOOL display_edges = FALSE, STRING result_attribute = "", 
  STRING file_path = "")  SYNTAX V1 {

algorithms/Path/shortest_path/weighted/positive/traceback/tg_shortest_ss_pos_wt_tb.gsql

@@ -1,4 +1,4 @@
-CREATE QUERY tg_shortest_ss_pos_wt_tb (VERTEX source, SET<STRING> v_type_set, SET<STRING> e_type_set,
+CREATE DISTRIBUTED QUERY tg_shortest_ss_pos_wt_tb (VERTEX source, SET<STRING> v_type_set, SET<STRING> e_type_set,
  STRING weight_attribute, STRING weight_type, FLOAT epsilon = 0.001,BOOL print_results = TRUE, INT print_limit = -1, 
  BOOL display_edges = FALSE, STRING result_attribute = "",
  STRING file_path = "", UINT write_size = 10000)  SYNTAX V1 {

algorithms_test/1_dataset.sh

@@ -0,0 +1,89 @@
+#!/bin/bash
+
+# Main function
+main() {
+  # Check if required commands are available
+  if ! command -v jq &> /dev/null; then
+    echo "Error: jq is not installed."
+    exit 1
+  fi
+
+  # Read the JSON configuration file
+  dir=$(cd "$(dirname "$0")"; pwd)
+  config_file="${dir}/config/1_dataset.json"
+
+  # Check if the configuration file exists
+  if [ ! -f "$config_file" ]; then
+    echo "Configuration file not found: $config_file"
+    exit 1
+  fi
+
+  # Extract general settings
+  default_directory=$(jq -r '.general_settings.default_directory' "$config_file")
+  default_directory=${default_directory/#\~/$HOME}
+
+  # Iterate over each dataset
+  datasets=$(jq -r '.datasets | to_entries[] | @base64' "$config_file")
+
+  # Decode each dataset entry and process it
+  echo "$datasets" | while IFS= read -r dataset_b64; do
+    dataset=$(echo "${dataset_b64}" | base64 --decode)
+    dataset_name=$(echo "$dataset" | jq -r '.key')
+    download_link=$(echo "$dataset" | jq -r '.value.download_link')
+    directory=$(echo "$dataset" | jq -r '.value.directory // empty')
+    directory=${directory/#\~/$HOME}
+    directory=${directory:-$default_directory}
+    top_level_dir=$(echo "$dataset" | jq -r '.value.top_level_dir')
+
+    echo "======================================== ${dataset_name} ========================================"
+
+    # Create the directory if it doesn't exist
+    mkdir -p "$directory"
+
+    # Extract the file name from the download link
+    file_name=$(basename "$download_link")
+
+    # Check if the folder exists before downloading the dataset
+    dataset_folder="$directory/$top_level_dir"
+    if [ ! -d "$dataset_folder" ]; then
+      echo "Created directory: $dataset_folder"
+      mkdir -p "$dataset_folder"
+
+      # Download the dataset if it doesn't exist
+      if [ ! -f "$directory/$file_name" ]; then
+        echo "Downloading $file_name..."
+        if ! wget -O "$directory/$file_name" "$download_link"; then
+          echo "Failed to download $file_name"
+          continue
+        fi
+      fi
+
+      # Determine the file extension and unzip accordingly
+      echo "Unzipping $file_name into $directory..."
+      case "$file_name" in
+        *.tar.bz2)
+          if tar -xvjf "$directory/$file_name" -C "$directory" --strip-components=1 --one-top-level="$top_level_dir"; then
+            echo "Finished unzipping $file_name."
+          else
+            echo "Failed to unzip $file_name"
+          fi
+          ;;
+        *.gz)
+          if gunzip -c "$directory/$file_name" > "$directory/$top_level_dir/${file_name%.gz}"; then
+            echo "Finished unzipping $file_name."
+          else
+            echo "Failed to unzip $file_name"
+          fi
+          ;;
+        *)
+          echo "Unsupported file format: $file_name"
+          ;;
+      esac
+    else
+      echo "Directory $dataset_folder already exists, skipping unzipping."
+    fi
+  done
+}
+
+# Run the main function
+main