# Config file to set features

# Select the feature set you want by uncommenting the relevant set under features_to_extract

# graph_columns provides the name of the columns in the output graph CSV file 
# Update this list if you add a new graph attribute

# feature_columns_adgraph and feature_columns provide the name of the columns 
# in the output feature file for AdGraph and WebGraph respectively
# Note: If running AdGraph, change feature_columns_adgraph to feature_columns 
# (the old feature_columns can be changed to feature_columns_webgraph)

# label_columns provides the name of the columns in the output label file

features_to_extract:
      #- content
      - structure
      - dataflow
      #- additional
     
graph_columns:
      - visit_id
      - name
      - top_level_url
      - type 
      - attr 
      - domain
      - document_url
      - setter
      - setting_time_stamp
      - top_level_domain
      - setter_domain
      - graph_attr
      - party
      - src 
      - dst
      - action
      - time_stamp
      - reqattr
      - respattr
      - response_status 
      - content_hash 
      - post_body
      - post_body_raw

feature_columns_adgraph:
      - visit_id
      - name
      - content_policy_type
      - url_length
      - is_subdomain
      - is_valid_qs
      - is_third_party
      - base_domain_in_query 
      - semicolon_in_query 
      - screen_size_present 
      - ad_size_present
      - ad_size_in_qs_present
      - keyword_raw_present 
      - keyword_char_present
      - num_nodes
      - num_edges
      - nodes_div_by_edges
      - edges_div_by_nodes
      - in_degree
      - out_degree
      - in_out_degree
      - average_degree_connectivity
      - is_parent_script
      - is_ancestor_script
      - ascendant_has_ad_keyword
      - is_eval_or_function
      - descendant_of_eval_or_function
      - ascendant_script_has_eval_or_function
      - ascendant_script_has_fp_keyword
      - ascendant_script_length

feature_columns:
      - visit_id
      - name
      - num_nodes
      - num_edges
      - nodes_div_by_edges
      - edges_div_by_nodes
      - in_degree
      - out_degree
      - in_out_degree
      - ancestors
      - descendants
      - closeness_centrality
      - average_degree_connectivity
      - eccentricity 
      - is_parent_script
      - is_ancestor_script
      - ascendant_has_ad_keyword
      - is_eval_or_function
      - descendant_of_eval_or_function
      - ascendant_script_has_eval_or_function
      - ascendant_script_has_fp_keyword
      - ascendant_script_length
      - num_get_storage
      - num_set_storage
      - num_get_cookie
      - num_set_cookie
      - num_script_predecessors
      - num_script_successors
      - num_requests_sent
      - num_requests_received
      - num_redirects_sent
      - num_redirects_rec
      - max_depth_redirect
      - indirect_in_degree
      - indirect_out_degree
      - indirect_ancestors
      - indirect_descendants
      - indirect_closeness_centrality
      - indirect_average_degree_connectivity
      - indirect_eccentricity
      - indirect_mean_in_weights
      - indirect_min_in_weights
      - indirect_max_in_weights
      - indirect_mean_out_weights
      - indirect_min_out_weights
      - indirect_max_out_weights
      - num_set_get_src
      - num_set_mod_src
      - num_set_url_src
      - num_get_url_src
      - num_set_get_dst
      - num_set_mod_dst
      - num_set_url_dst
      - num_get_url_dst
      - indirect_all_in_degree
      - indirect_all_out_degree
      - indirect_all_ancestors
      - indirect_all_descendants
      - indirect_all_closeness_centrality
      - indirect_all_average_degree_connectivity
      - indirect_all_eccentricity

label_columns:
      - visit_id
      - top_level_url
      - name
      - label