Merge branch 'main' of https://github.com/DanielCorralesAlonso/Decisi…

…on_Model_Screening_CRC
DanielCorralesAlonso · Nov 21, 2024 · e8e30e5 · e8e30e5
2 parents b20c3bd + b0b13d8
commit e8e30e5
Show file tree

Hide file tree

Showing 4 changed files with 7 additions and 163 deletions.
diff --git a/config.yaml b/config.yaml
@@ -148,9 +148,9 @@ colors:
 
 # -- Use case
 
-single_run: True
-num_runs: 200
-max_workers: 32
+single_run: False
+num_runs: 640
+max_workers: 64
 
 all_variables: True
 from_elicitation: False
@@ -161,7 +161,7 @@ operational_limit : {
         "gFOBT": 30000,
         "FIT": 42000,
         "Blood_based": 7000,
-        "Stool_DNA": 5000,
+        "Stool_DNA": 6000,
         "CTC": 2000,
         "Colon_capsule": 2000,
     }

diff --git a/full_example.py b/full_example.py
@@ -63,7 +63,7 @@ def full_example(only_counts = False):
             _ , counts, possible_outcomes = calculate_network_utilities(net, df_test, full_calculation = True)
 
             #code from plots.py function plot_screening_counts()
-            bars1 = axes[i,j].bar(possible_outcomes, counts, color = 'blue', label = 'Number of tests')
+            bars1 = axes[i,j].bar(possible_outcomes, counts, color = 'steelblue', alpha= 0.3, label = 'Number of tests')
             for bar in bars1:
                 axes[i,j].text(bar.get_x() + bar.get_width()/2, bar.get_height() + 3000, str(bar.get_height()), ha='center', color='black', fontsize=10)
 

diff --git a/network_functions.py b/network_functions.py
@@ -408,163 +408,7 @@ def compare_strategies(df_selected, net, possible_outcomes, operational_limit =
                 cost += col_costs
 
     return df_temp, cost
-
-
-
-
-
-
-
-# def simulate_test_results(sensitivity_scr, specificity_scr,
-#                            sensitivity_col, specificity_col, y_crc):
-#     """
-#     Simulate test results based on sensitivity, specificity, and actual number of patients
-#     with and without the disease.
-
-#     Parameters:
-#     - sensitivity (float): Sensitivity of the test (true positive rate)
-#     - specificity (float): Specificity of the test (true negative rate)
-#     - num_with_disease (int): Number of patients who have the disease
-#     - num_without_disease (int): Number of patients who do not have the disease
-
-#     Returns:
-#     - pandas DataFrame: A DataFrame with the simulated test results, true conditions, and test outcomes.
-#     """
-
-
-#     num_with_disease = y_crc.sum()
-#     num_without_disease = len(y_crc) - num_with_disease
-
-#     # Step 1: Create a list of patients with and without the disease
-
-#     # Step 2: Simulate test results
-#     scr_results = []
-#     col_results = []
-
-#     for y in y_crc:
-#         if y == 1:
-#             # Patient has the disease, test is positive with probability = sensitivity
-#             scr_result = np.random.choice([1, 0], p=[sensitivity_scr, 1 - sensitivity_scr])
-#         else:
-#             # Patient does not have the disease, test is negative with probability = specificity
-#             scr_result = np.random.choice([0, 1], p=[specificity_scr, 1 - specificity_scr])
-
-#         scr_results.append(scr_result)
-
-#     # Step 3: Create a DataFrame to store the results
-#     df_scr = pd.DataFrame({
-#         'Condition': y_crc,    # True condition of the patient
-#         'TestResult': scr_results  # Simulated test result
-#     })
-
-
-#     # For FIT positives, perform colonoscopy:
-#     FIT_positives = df_scr[df_scr["TestResult"] == 1]
-
-#     conditions = FIT_positives["Condition"].to_list()
-
-#     col_results = []
-
-#     for condition in conditions:
-#         if condition == 1:
-#             # Patient has the disease, test is positive with probability = sensitivity
-#             col_result = np.random.choice([1, 0], p=[sensitivity_col, 1 - sensitivity_col])
-#         else:
-#             # Patient does not have the disease, test is negative with probability = specificity
-#             col_result = np.random.choice([0, 1], p=[specificity_col, 1 - specificity_col])
-
-#         col_results.append(col_result)
-
-#     # Step 5: Create a DataFrame to store the results
-#     df_col = pd.DataFrame({
-#         'Condition': conditions,    # True condition of the patient
-#         'TestResult': col_results  # Simulated test result
-#     })
-
-
-
-#     return df_scr, df_col
-
-
-
-# def output_test_results(df_test, y,df_scr, cost_scr, df_col, cost_col, verbose = False):
-
-#     # Add columns to indicate true positives, false positives, etc.
-#     df_scr['TruePositive'] = (df_scr['Condition'] == 1) & (df_scr['TestResult'] == 1)
-#     df_scr['FalsePositive'] = (df_scr['Condition'] == 0) & (df_scr['TestResult'] == 1)
-#     df_scr['TrueNegative'] = (df_scr['Condition'] == 0) & (df_scr['TestResult'] == 0)
-#     df_scr['FalseNegative'] = (df_scr['Condition'] == 1) & (df_scr['TestResult'] == 0)
-
-#     # Step 4: Calculate confusion matrix components
-#     TP_scr = df_scr['TruePositive'].sum()
-#     FP_scr = df_scr['FalsePositive'].sum()
-#     TN_scr = df_scr['TrueNegative'].sum()
-#     FN_scr = df_scr['FalseNegative'].sum()
-
-#     # Create confusion matrix
-#     confusion_matrix_scr = pd.DataFrame({
-#         'Predicted Negative': [TN_scr, FN_scr],
-#         'Predicted Positive': [FP_scr, TP_scr]
-#     }, index=['Actual Negative', 'Actual Positive'])
-
-
-#     FIT_positives = df_scr[df_scr["TestResult"] == 1]
-#     patient_data = df_scr["Condition"]
-
-#     if verbose:
-#         logger.info("Number of patients considered: ", patient_data.shape[0])
-#         logger.info(f"Cost of screening: {cost_scr*(patient_data.shape[0])} €")
-#         logger.info("Number of FIT positives: ", FIT_positives.shape[0])
-#         logger.info("Number of colonoscopies to be done: ", FIT_positives.shape[0])
-#         logger.info(f"Cost of colonoscopy program: {cost_col*FIT_positives.shape[0]} €")
-
-
-#     # Add columns to indicate true positives, false positives, etc.
-#     df_col['TruePositive'] = (df_col['Condition'] == 1) & (df_col['TestResult'] == 1)
-#     df_col['FalsePositive'] = (df_col['Condition'] == 0) & (df_col['TestResult'] == 1)
-#     df_col['TrueNegative'] = (df_col['Condition'] == 0) & (df_col['TestResult'] == 0)
-#     df_col['FalseNegative'] = (df_col['Condition'] == 1) & (df_col['TestResult'] == 0)
-
-#     # Step 6: Calculate confusion matrix components
-#     TP_col = df_col['TruePositive'].sum()
-#     FP_col = df_col['FalsePositive'].sum()
-#     TN_col = df_col['TrueNegative'].sum()
-#     FN_col = df_col['FalseNegative'].sum()
-
-#     # Create confusion matrix
-#     confusion_matrix_col = pd.DataFrame({
-#         'Predicted Negative': [TN_col, FN_col],
-#         'Predicted Positive': [FP_col, TP_col]
-#     }, index=['Actual Negative', 'Actual Positive'])
-
-#     total_cost = cost_scr*df_scr["Condition"].shape[0] + cost_col*FIT_positives.shape[0]
-
-#     if verbose:
-#         logger.info("Number of CRC true positive cases detected by colonoscopy: ", TP_scr)
-#         logger.info("Number of false positives by colonoscopy: ", FP_scr)
-#         logger.info(f"Total cost of screening and colonoscopy: {total_cost} €")
-#         logger.info("Proportion of total CRC cases in the whole population detected by the method: ", TP_scr / df_test["CRC"].sum())
-#         logger.info("Proportion of cases in the high-risk target population detected by the method: ", TP_scr / y.sum())
-
-#     combined_confusion_matrix = pd.DataFrame({
-#         'Predicted Negative': [TN_scr + TN_col, FN_scr + FN_col],
-#         'Predicted Positive': [FP_col, TP_col]
-#     }, index=['Actual Negative', 'Actual Positive'])
-
-#     # Calculate sensitivity and specificity using the combined confusion matrix
-#     sensitivity = TP_col / (TP_col + FN_col + FN_scr)
-#     specificity = (TN_scr + TN_col) / (TN_scr +TN_col + FP_col)
-#     PPV = TP_col / (TP_col + FP_col)
-#     NPV = (TN_scr + TN_col) / (TN_scr + TN_col + FN_scr + FN_col)
-
-#     metrics = {
-#         "sensitivity": sensitivity,
-#         "specificity": specificity,
-#         "PPV": PPV,
-#         "NPV": NPV
-#     }
 
-#     return confusion_matrix_scr, confusion_matrix_col, combined_confusion_matrix, total_cost, metrics
 
 
 

diff --git a/use_case_new_strategy.py b/use_case_new_strategy.py
@@ -41,7 +41,7 @@ def use_case_new_strategy(net = None,
         log_dir = None,
         run_label = 'run',
         best_f1_score = {},
-        output_dir = None
+        output_dir = 'logs'
     ):
 
     # check if an element in operational limit is inf
@@ -51,7 +51,7 @@ def use_case_new_strategy(net = None,
         operational_limit_comp = {k: np.inf if v == "inf" else v for k, v in operational_limit_comp.items()}
 
     if logger == None:
-        logger, log_dir = create_folders_logger(single_run = single_run, label="use_case_", date = False, time = False, output_dir=output_dir)
+        logger, log_dir = create_folders_logger(single_run = single_run, label="use_case_", date = True, time = True, output_dir= output_dir)
     else:
         log_dir = os.path.join(log_dir, run_label)
         if not os.path.exists(log_dir):