diff --git a/Snakefile b/Snakefile
index ff348736..1fbb03db 100644
--- a/Snakefile
+++ b/Snakefile
@@ -206,7 +206,9 @@ if config["PARAMS_FOR_ANALYSIS"]["COMPUTE"]:
     files_to_compute.extend(expand("data/processed/data_for_population_model/targets_{summarised}.csv",
                                 summarised = config["PARAMS_FOR_ANALYSIS"]["SUMMARISED"]))
     files_to_compute.extend(expand(
-                                expand("data/processed/data_for_population_model/{{rows_nan_threshold}}|{{cols_nan_threshold}}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_nancellsratio.csv",
+                                expand("data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{{rows_nan_threshold}}|{{cols_nan_threshold}}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_nancellsratio.csv",
+                                    min_valid_hours_per_day=config["OVERALL_COMPLIANCE_HEATMAP"]["MIN_VALID_HOURS_PER_DAY"],
+                                    min_valid_bins_per_hour=config["PHONE_VALID_SENSED_DAYS"]["MIN_VALID_BINS_PER_HOUR"],
                                     days_before_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_BEFORE_THRESHOLD"],
                                     days_after_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_AFTER_THRESHOLD"],
                                     cols_var_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_VAR_THRESHOLD"],
@@ -216,7 +218,9 @@ if config["PARAMS_FOR_ANALYSIS"]["COMPUTE"]:
                                 rows_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["ROWS_NAN_THRESHOLD"],
                                 cols_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_NAN_THRESHOLD"]))
     files_to_compute.extend(expand(
-                                expand("data/processed/data_for_population_model/{{rows_nan_threshold}}|{{cols_nan_threshold}}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}.csv",
+                                expand("data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{{rows_nan_threshold}}|{{cols_nan_threshold}}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}.csv",
+                                    min_valid_hours_per_day=config["OVERALL_COMPLIANCE_HEATMAP"]["MIN_VALID_HOURS_PER_DAY"],
+                                    min_valid_bins_per_hour=config["PHONE_VALID_SENSED_DAYS"]["MIN_VALID_BINS_PER_HOUR"],
                                     days_before_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_BEFORE_THRESHOLD"],
                                     days_after_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_AFTER_THRESHOLD"],
                                     cols_var_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_VAR_THRESHOLD"],
@@ -227,7 +231,9 @@ if config["PARAMS_FOR_ANALYSIS"]["COMPUTE"]:
                                 rows_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["ROWS_NAN_THRESHOLD"],
                                 cols_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_NAN_THRESHOLD"]))
     files_to_compute.extend(expand(
-                                expand("data/processed/output_population_model/{{rows_nan_threshold}}|{{cols_nan_threshold}}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}_{cv_method}_baseline.csv",
+                                expand("data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{{rows_nan_threshold}}|{{cols_nan_threshold}}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}_{cv_method}_baseline.csv",
+                                    min_valid_hours_per_day=config["OVERALL_COMPLIANCE_HEATMAP"]["MIN_VALID_HOURS_PER_DAY"],
+                                    min_valid_bins_per_hour=config["PHONE_VALID_SENSED_DAYS"]["MIN_VALID_BINS_PER_HOUR"],
                                     days_before_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_BEFORE_THRESHOLD"],
                                     days_after_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_AFTER_THRESHOLD"],
                                     cols_var_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_VAR_THRESHOLD"],
@@ -239,7 +245,9 @@ if config["PARAMS_FOR_ANALYSIS"]["COMPUTE"]:
                                 rows_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["ROWS_NAN_THRESHOLD"],
                                 cols_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_NAN_THRESHOLD"]))
     files_to_compute.extend(expand(
-                                expand("data/processed/output_population_model/{{rows_nan_threshold}}|{{cols_nan_threshold}}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{{model}}/{cv_method}/{source}_{day_segment}_{summarised}_{{scaler}}/{result}.csv",
+                                expand("data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{{rows_nan_threshold}}|{{cols_nan_threshold}}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{{model}}/{cv_method}/{source}_{day_segment}_{summarised}_{{scaler}}/{result}.csv",
+                                    min_valid_hours_per_day=config["OVERALL_COMPLIANCE_HEATMAP"]["MIN_VALID_HOURS_PER_DAY"],
+                                    min_valid_bins_per_hour=config["PHONE_VALID_SENSED_DAYS"]["MIN_VALID_BINS_PER_HOUR"],
                                     days_before_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_BEFORE_THRESHOLD"],
                                     days_after_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_AFTER_THRESHOLD"],
                                     cols_var_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_VAR_THRESHOLD"],
diff --git a/rules/models.snakefile b/rules/models.snakefile
index 69b89aa0..36eb584b 100644
--- a/rules/models.snakefile
+++ b/rules/models.snakefile
@@ -99,7 +99,7 @@ rule nan_cells_ratio_of_cleaned_features:
  
 rule merge_features_and_targets:
     input:
-        cleaned_features = "data/processed/data_for_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_clean.csv",
+        cleaned_features = "data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_clean.csv",
         demographic_features = "data/processed/data_for_population_model/demographic_features.csv",
         targets = "data/processed/data_for_population_model/targets_{summarised}.csv",
     params:
@@ -108,28 +108,28 @@ rule merge_features_and_targets:
         numerical_operators = config["PARAMS_FOR_ANALYSIS"]["NUMERICAL_OPERATORS"],
         categorical_operators = config["PARAMS_FOR_ANALYSIS"]["CATEGORICAL_OPERATORS"]
     output:
-        "data/processed/data_for_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}.csv"
+        "data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}.csv"
     script:
         "../src/models/merge_features_and_targets.py"
  
 rule baseline:
     input:
-        "data/processed/data_for_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}.csv"
+        "data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}.csv"
     params:
         cv_method = "{cv_method}",
         rowsnan_colsnan_days_colsvar_threshold = "{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}",
         demographic_features = config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC_FEATURES"]
     output:
-        "data/processed/output_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}_{cv_method}_baseline.csv"
+        "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}_{cv_method}_baseline.csv"
     log:
-        "data/processed/output_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}_{cv_method}_notes.log"
+        "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}_{cv_method}_notes.log"
     script:
         "../src/models/baseline.py"
  
  
 rule modeling:
     input:
-        data = "data/processed/data_for_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}.csv"
+        data = "data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}.csv"
     params:
         model = "{model}",
         cv_method = "{cv_method}",
@@ -142,21 +142,21 @@ rule modeling:
         model_hyperparams = config["PARAMS_FOR_ANALYSIS"]["MODEL_HYPERPARAMS"],
         rowsnan_colsnan_days_colsvar_threshold = "{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}"
     output:
-        fold_predictions = "data/processed/output_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/fold_predictions.csv",
-        fold_metrics = "data/processed/output_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/fold_metrics.csv",
-        overall_results = "data/processed/output_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/overall_results.csv",
-        fold_feature_importances = "data/processed/output_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/fold_feature_importances.csv"
+        fold_predictions = "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/fold_predictions.csv",
+        fold_metrics = "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/fold_metrics.csv",
+        overall_results = "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/overall_results.csv",
+        fold_feature_importances = "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/fold_feature_importances.csv"
     log:
-        "data/processed/output_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/notes.log"
+        "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/notes.log"
     script:
         "../src/models/modeling.py"
 
 rule merge_population_model_results:
     input:
-        overall_results = "data/processed/output_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/overall_results.csv",
-        nan_cells_ratio = "data/processed/data_for_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_nancellsratio.csv",
-        baseline =  "data/processed/output_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}_{cv_method}_baseline.csv"
+        overall_results = "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/overall_results.csv",
+        nan_cells_ratio = "data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_nancellsratio.csv",
+        baseline =  "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}_{cv_method}_baseline.csv"
     output:
-        "data/processed/output_population_model/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/merged_population_model_results.csv"
+        "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/merged_population_model_results.csv"
     script:
         "../src/models/merge_population_model_results.py"