diff --git a/exploration/expl_stress_event.py b/exploration/expl_stress_event.py
index b2aaabc..8fc5bf1 100644
--- a/exploration/expl_stress_event.py
+++ b/exploration/expl_stress_event.py
@@ -75,7 +75,7 @@ extracted_ers.reset_index(drop=True, inplace=True)
 # Add default duration in case if participant answered that no stressful event occured
 
 # Prepare data to fit the data structure in the CSV file ...
-# Add the event time as the end of the questionnaire if no stress event occured
+# Add the event time as the start of the questionnaire if no stress event occured
 extracted_ers['se_time'] = extracted_ers['se_time'].fillna(extracted_ers['session_start_timestamp'])
 # Type could be an int (timestamp [ms]) which stays the same, and datetime str which is converted to timestamp in miliseconds 
 extracted_ers['event_timestamp'] = extracted_ers['se_time'].apply(lambda x: x if isinstance(x, int) else pd.to_datetime(x).timestamp() * 1000).astype('int64')
@@ -102,7 +102,7 @@ extracted_ers['se_duration'] = \
 
 """>>>>> end section <<<<<"""
 
-# %%
+# %% [markdown]
 # Count negative values of duration
 print("Count all:", extracted_ers[['se_duration', 'temp_duration', 'session_end_timestamp', 'event_timestamp']].shape[0])
 print("Count stressed:", extracted_ers[(~extracted_ers['se_duration'].isna())][['se_duration', 'temp_duration', 'session_end_timestamp', 'event_timestamp']].shape[0])
@@ -111,14 +111,12 @@ print("Count 0 durations:", extracted_ers[extracted_ers['se_duration'] == 0][['s
 extracted_ers[extracted_ers['se_duration'] <= 0][['se_duration', 'temp_duration', 'session_end_timestamp', 'event_timestamp']].shape[0]
 extracted_ers[(~extracted_ers['se_duration'].isna()) & (extracted_ers['se_duration'] <= 0)][['se_duration', 'temp_duration', 'session_end_timestamp', 'event_timestamp']]
 
-ax = extracted_ers[(extracted_ers['se_duration'] < 5000) & (extracted_ers['se_duration'] > -300)].hist(column='se_duration', bins='auto', grid=False, figsize=(12,8), color='#86bf91', zorder=2, rwidth=0.9)
-extracted_ers[(extracted_ers['se_duration'] < 1000) & (extracted_ers['se_duration'] > -1000)]['se_duration'].value_counts()
+ax = extracted_ers.hist(column='se_duration', bins='auto', grid=False, figsize=(12,8), color='#86bf91', zorder=2, rwidth=0.9)
 hist, bin_edges = np.histogram(extracted_ers['se_duration'].dropna())
 hist
 bin_edges
 
-extracted_ers['se_duration'].describe()
-extracted_ers['se_duration'].median()
+extracted_ers = extracted_ers[extracted_ers['se_duration'] >= 0]
 
 # %%
 # bins = [-100000000, 0, 0.0000001, 1200, 7200, 100000000] #'neg', 'zero', '<20min', '2h', 'high_pos'  ..... right=False
@@ -131,15 +129,23 @@ sns.displot(
     binwidth=0.1,
 )
 
-# %%
+# %% [markdown]
+extracted_ers[extracted_ers['session_end_timestamp'] - extracted_ers['event_timestamp'] >= 0]
+extracted_ers['se_time'].value_counts()
+pd.set_option('display.max_rows', 100)
 # Tukaj nas zanima, koliko so oddaljeni časi stresnega dogodka od konca vprašalnika. 
-extracted_ers = extracted_ers[~extracted_ers['se_duration'].isna()]
-extracted_ers[['session_end_timestamp', 'event_timestamp']]
+extracted_ers = extracted_ers[~extracted_ers['se_duration'].isna()] # Remove no stress events
 extracted_ers['diff_se_time_session_end'] = (extracted_ers['session_end_timestamp'] - extracted_ers['event_timestamp'])
-extracted_ers['diff_se_time_session_end'].dropna().value_counts()
-extracted_ers = extracted_ers[(extracted_ers['diff_se_time_session_end'] > 0)]
-bins2 = [-0.0000001, 0, 300, 600, 1200, 3600, 7200, 14400, 1000000000] # 'zero', '5min', '10min', '20min', '1h', '2h', '4h', 'more'
-extracted_ers['bins2'], edges = pd.cut(extracted_ers.diff_se_time_session_end, bins=bins2, labels=['zero', '5min', '10min', '20min', '1h', '2h', '4h', 'more'], retbins=True, right=True) #['low', 'medium', 'high']
+
+print("Count all:", extracted_ers[['se_duration', 'temp_duration', 'session_start_timestamp', 'event_timestamp']].shape[0])
+print("Count negative durations:", extracted_ers[extracted_ers['diff_se_time_session_end'] < 0][['se_duration', 'temp_duration', 'session_start_timestamp', 'event_timestamp']])
+print("Count 0 durations:", extracted_ers[extracted_ers['diff_se_time_session_end'] == 0][['se_duration', 'temp_duration', 'session_start_timestamp', 'event_timestamp']].shape[0])
+
+extracted_ers[extracted_ers['diff_se_time_session_end'] < 0]['diff_se_time_session_end']
+# extracted_ers = extracted_ers[(extracted_ers['diff_se_time_session_end'] > 0)]
+bins2 = [-100000, 0, 300, 600, 1200, 3600, 7200, 14400, 1000000000] # 'zero', '5min', '10min', '20min', '1h', '2h', '4h', 'more'
+extracted_ers['bins2'], edges = pd.cut(extracted_ers.diff_se_time_session_end, bins=bins2, labels=['neg_zero', '5min', '10min', '20min', '1h', '2h', '4h', 'more'], retbins=True, right=True) #['low', 'medium', 'high']
+extracted_ers['bins2']
 sns.displot(
     data=extracted_ers.dropna(),
     x="bins2",
@@ -149,6 +155,8 @@ sns.displot(
 extracted_ers.shape
 extracted_ers.dropna().shape
 
+print()
+
 
 # %%
 extracted_ers['appraisal_stressfulness_event_num'] = extracted_ers['appraisal_stressfulness_event'].str[0].astype(int)
diff --git a/exploration/ml_pipeline_classification.py b/exploration/ml_pipeline_classification.py
index 736e3db..0b5dc15 100644
--- a/exploration/ml_pipeline_classification.py
+++ b/exploration/ml_pipeline_classification.py
@@ -41,12 +41,12 @@ if nb_dir not in sys.path:
 
 # %% [markdown]
 # ## Set script's parameters
-cv_method_str = 'logo' # logo, half_logo, 5kfold # Cross-validation method (could be regarded as a hyperparameter)
+cv_method_str = '5kfold' # logo, half_logo, 5kfold # Cross-validation method (could be regarded as a hyperparameter)
 n_sl = 3 # Number of largest/smallest accuracies (of particular CV) outputs
 undersampling = True # (bool) If True this will train and test data on balanced dataset (using undersampling method)
 
 # %% jupyter={"source_hidden": true}
-model_input = pd.read_csv("../data/stressfulness_event_with_target_0/input_appraisal_stressfulness_event_mean.csv")
+model_input = pd.read_csv("../data/stressfulness_event_with_target_0_ver2/input_appraisal_stressfulness_event_mean.csv")
 # model_input = model_input[model_input.columns.drop(list(model_input.filter(regex='empatica_temperature')))]
 
 # %% jupyter={"source_hidden": true}
@@ -334,15 +334,15 @@ print(f"Smallest {n_sl} ACC:", np.sort(np.partition(rfc_scores['test_accuracy'],
 # %% jupyter={"source_hidden": true}
 rfc_es_fimp = pd.DataFrame(columns=list(train_x.columns))
 for idx, estimator in enumerate(rfc_scores['estimator']):
-    print("\nFeatures sorted by their score for estimator {}:".format(idx))
     feature_importances = pd.DataFrame(estimator.feature_importances_,
                                        index = list(train_x.columns),
                                         columns=['importance'])
-    print(feature_importances.sort_values('importance', ascending=False).head(10))                                    
+    # print("\nFeatures sorted by their score for estimator {}:".format(idx))
+    # print(feature_importances.sort_values('importance', ascending=False).head(10))                                    
     rfc_es_fimp = pd.concat([rfc_es_fimp, feature_importances]).groupby(level=0).mean()
 
 pd.set_option('display.max_rows', 100)
-print(rfc_es_fimp.sort_values('importance', ascending=False).head(100))
+print(rfc_es_fimp.sort_values('importance', ascending=False).head(30))
 
 rfc_es_fimp.sort_values('importance', ascending=False).head(30).plot.bar()
 
diff --git a/rapids b/rapids
index 8a6b52a..7f5a4e6 160000
--- a/rapids
+++ b/rapids
@@ -1 +1 @@
-Subproject commit 8a6b52a97c95dcd8b70b980b4f46421b1a847905
+Subproject commit 7f5a4e6744e502d40dc38502e1e74bd2bf9fe786