def collate_individual_user_results():
# A list to hold the resulting stats in
project_by_project_results = []
# loop over the projects in the project_configuration above
for project in project_configuration:
# A list to hold the resulting stats in
individual_project_results = []
# Get the basic details we need from the project
project_short_name = project["project_short_name"]
# Get a list of all potential include ids for this projects
include_ids = project["include_user_ids"]
# Create a list of user_ids for this project that have not completed the required number of tasks
exclude_id_based_on_task_count = create_list_of_users_not_completing_req_no_of_tasks(project_short_name, min_no_tasks = 324)
# Filter the include_ids removing any that should be excluded based on task count
include_ids = [id for id in include_ids if id not in exclude_id_based_on_task_count]
# Create a list of user_ids to exclude based on marginal distribution
exclude_id_based_on_marginal_distribution = calculate_marginal_distribution_for_each_user(project_short_name)
# Filter the include_ids removing any that should be excluded based on marginal distributions
include_ids = [id for id in include_ids if id not in exclude_id_based_on_marginal_distribution]
# Select the correct gold standard data set and associated expert_ids for each project
gold_standard_data = define_gold_standard_data(project_short_name=project_short_name)
expert_ids = define_gold_standard_ids(project_short_name=project_short_name)
# Build the combined dict using the filtered ids and relevant gold standard data
combined_dict = build_combined_dict_keyed_on_composite_key(project_short_name=project_short_name, user_ids_to_include=include_ids, expert_project_short_name=gold_standard_data, expert_user_ids_to_include=expert_ids)
# Run the analysis on the combined dict
create_user_agreement_pre_processing_dict(combined_dict)
individual_user_results = create_user_agreement_dict(combined_dict)
# Compile the project results object
for user_id, results_dict in individual_user_results.items():
project_results = {
"project_name": project_short_name.split("-")[-1],
"user_id": user_id,
"accuracy": results_dict["accuracy_based_on_excluding_tied"],
"sensitivity": results_dict["sensitivity_excluding_tied"],
"specificity": results_dict["specificity_excluding_tied"],
"precision": results_dict["precision_excluding_tied"],
"f-measure": results_dict["f_measure_excluding_tied"],
"kappa": results_dict["inter_rater_agreement_excluding_tied"]
}
individual_project_results.append(project_results)
project_by_project_results.append(individual_project_results)
return project_by_project_results
exclude_id_based_on_task_count = create_list_of_users_not_completing_req_no_of_tasks(
project_short_name, min_no_tasks=360
)
# Filter the include_ids removing any that should be excluded based on task count
include_ids = [id for id in include_ids if id not in exclude_id_based_on_task_count]
# Create a list of user_ids to exclude based on marginal distribution
exclude_id_based_on_marginal_distribution = calculate_marginal_distribution_for_each_user(project_short_name)
# Filter the include_ids removing any that should be excluded based on marginal distributions
include_ids = [id for id in include_ids if id not in exclude_id_based_on_marginal_distribution]
# Select the appropriate gold standard data and corresponding expert_ids for the project
gold_standard_data = define_gold_standard_data(project_short_name=project_short_name)
expert_ids = define_gold_standard_ids(project_short_name=project_short_name)
# Build the complete dictionary using all of the above
combined_dict = build_combined_dict_keyed_on_composite_key(
project_short_name=project_short_name,
user_ids_to_include=include_ids,
expert_project_short_name=gold_standard_data,
expert_user_ids_to_include=expert_ids,
)
# Create list of users
list_of_users = create_list_of_users(filtered_dict=combined_dict)
# Create list of number of citizen scientists
no_citizen_scientists = [10, 15]