diff --git a/exploration/ml_pipeline_classification.py b/exploration/ml_pipeline_classification.py
index 0b5dc15..53607ad 100644
--- a/exploration/ml_pipeline_classification.py
+++ b/exploration/ml_pipeline_classification.py
@@ -13,7 +13,7 @@
 #     name: straw2analysis
 # ---
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 # %matplotlib inline
 import os
 import sys
@@ -35,26 +35,29 @@ InteractiveShell.ast_node_interactivity = "all"
 nb_dir = os.path.split(os.getcwd())[0]
 if nb_dir not in sys.path:
     sys.path.append(nb_dir)
-
+    
 # %% [markdown]
 # # RAPIDS models
 
 # %% [markdown]
 # ## Set script's parameters
+#
+
+# %% jupyter={"source_hidden": false, "outputs_hidden": false} nteract={"transient": {"deleting": false}}
 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}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 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}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]
 model_input.set_index(index_columns, inplace=True)
 model_input['target'].value_counts()
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 # bins = [-10, 0, 10] # bins for z-scored targets
 bins = [-1, 0, 4] # bins for stressfulness (0-4) target
 model_input['target'], edges = pd.cut(model_input.target, bins=bins, labels=['low', 'high'], retbins=True, right=True) #['low', 'medium', 'high']
@@ -64,20 +67,20 @@ model_input['target'] = model_input['target'].astype(str).apply(lambda x: 0 if x
 
 model_input['target'].value_counts()
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 # UnderSampling
 if undersampling:
     model_input.groupby("pid").count()
     no_stress = model_input[model_input['target'] == 0]
     stress = model_input[model_input['target'] == 1]
-
+    
     no_stress = no_stress.sample(n=len(stress))
     model_input = pd.concat([stress,no_stress], axis=0)
-
+    
     model_input["target"].value_counts()
 
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 if cv_method_str == 'half_logo':
     model_input['pid_index'] = model_input.groupby('pid').cumcount()
     model_input['pid_count'] = model_input.groupby('pid')['pid'].transform('count')
@@ -90,7 +93,7 @@ else:
     data_x, data_y, data_groups = model_input.drop(["target", "pid"], axis=1), model_input["target"], model_input["pid"]
 
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 categorical_feature_colnames = ["gender", "startlanguage"]
 additional_categorical_features = [col for col in data_x.columns if "mostcommonactivity" in col or "homelabel" in col]
 categorical_feature_colnames += additional_categorical_features
@@ -110,7 +113,7 @@ numerical_features = data_x.drop(categorical_feature_colnames, axis=1)
 train_x = pd.concat([numerical_features, categorical_features], axis=1)
 train_x.dtypes
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 cv_method = StratifiedKFold(n_splits=5, shuffle=True) # Defaults to 5 k-folds in cross_validate method
 if cv_method_str == 'logo' or cv_method_str == 'half_logo':
     cv_method = LeaveOneGroupOut()
@@ -120,14 +123,16 @@ if cv_method_str == 'logo' or cv_method_str == 'half_logo':
         groups=data_groups,
     )
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 imputer = SimpleImputer(missing_values=np.nan, strategy='median')
 
 # %% [markdown]
 # ### Baseline: Dummy Classifier (most frequent)
+
+# %% jupyter={"source_hidden": false, "outputs_hidden": false} nteract={"transient": {"deleting": false}}
 dummy_class = DummyClassifier(strategy="most_frequent")
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 dummy_classifier = cross_validate(
     dummy_class,
     X=imputer.fit_transform(train_x),
@@ -138,7 +143,7 @@ dummy_classifier = cross_validate(
     error_score='raise',
     scoring=('accuracy', 'precision', 'recall', 'f1')
 )
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 print("Acc (median)", np.nanmedian(dummy_classifier['test_accuracy']))
 print("Acc (mean)", np.mean(dummy_classifier['test_accuracy']))
 print("Precision", np.mean(dummy_classifier['test_precision']))
@@ -150,10 +155,10 @@ print(f"Smallest {n_sl} ACC:", np.sort(np.partition(dummy_classifier['test_accur
 # %% [markdown]
 # ### Logistic Regression
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 logistic_regression = linear_model.LogisticRegression()
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 log_reg_scores = cross_validate(
     logistic_regression,
     X=imputer.fit_transform(train_x),
@@ -163,7 +168,7 @@ log_reg_scores = cross_validate(
     n_jobs=-1,
     scoring=('accuracy', 'precision', 'recall', 'f1')
 )
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 print("Acc (median)", np.nanmedian(log_reg_scores['test_accuracy']))
 print("Acc (mean)", np.mean(log_reg_scores['test_accuracy']))
 print("Precision", np.mean(log_reg_scores['test_precision']))
@@ -175,10 +180,10 @@ print(f"Smallest {n_sl} ACC:", np.sort(np.partition(log_reg_scores['test_accurac
 # %% [markdown]
 # ### Support Vector Machine
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 svc = svm.SVC()
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 svc_scores = cross_validate(
     svc,
     X=imputer.fit_transform(train_x),
@@ -188,7 +193,7 @@ svc_scores = cross_validate(
     n_jobs=-1,
     scoring=('accuracy', 'precision', 'recall', 'f1')
 )
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 print("Acc (median)", np.nanmedian(svc_scores['test_accuracy']))
 print("Acc (mean)", np.mean(svc_scores['test_accuracy']))
 print("Precision", np.mean(svc_scores['test_precision']))
@@ -200,10 +205,10 @@ print(f"Smallest {n_sl} ACC:", np.sort(np.partition(svc_scores['test_accuracy'],
 # %% [markdown]
 # ### Gaussian Naive Bayes
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 gaussian_nb = naive_bayes.GaussianNB()
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 gaussian_nb_scores = cross_validate(
     gaussian_nb,
     X=imputer.fit_transform(train_x),
@@ -214,7 +219,7 @@ gaussian_nb_scores = cross_validate(
     error_score='raise',
     scoring=('accuracy', 'precision', 'recall', 'f1')
 )
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 print("Acc (median)", np.nanmedian(gaussian_nb_scores['test_accuracy']))
 print("Acc (mean)", np.mean(gaussian_nb_scores['test_accuracy']))
 print("Precision", np.mean(gaussian_nb_scores['test_precision']))
@@ -226,10 +231,10 @@ print(f"Smallest {n_sl} ACC:", np.sort(np.partition(gaussian_nb_scores['test_acc
 # %% [markdown]
 # ### Stochastic Gradient Descent Classifier
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 sgdc = linear_model.SGDClassifier()
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 sgdc_scores = cross_validate(
     sgdc,
     X=imputer.fit_transform(train_x),
@@ -240,7 +245,7 @@ sgdc_scores = cross_validate(
     error_score='raise',
     scoring=('accuracy', 'precision', 'recall', 'f1')
 )
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 print("Acc (median)", np.nanmedian(sgdc_scores['test_accuracy']))
 print("Acc (mean)", np.mean(sgdc_scores['test_accuracy']))
 print("Precision", np.mean(sgdc_scores['test_precision']))
@@ -252,10 +257,10 @@ print(f"Smallest {n_sl} ACC:", np.sort(np.partition(sgdc_scores['test_accuracy']
 # %% [markdown]
 # ### K-nearest neighbors
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 knn = neighbors.KNeighborsClassifier()
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 knn_scores = cross_validate(
     knn,
     X=imputer.fit_transform(train_x),
@@ -266,7 +271,7 @@ knn_scores = cross_validate(
     error_score='raise',
     scoring=('accuracy', 'precision', 'recall', 'f1')
 )
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 print("Acc (median)", np.nanmedian(knn_scores['test_accuracy']))
 print("Acc (mean)", np.mean(knn_scores['test_accuracy']))
 print("Precision", np.mean(knn_scores['test_precision']))
@@ -278,10 +283,10 @@ print(f"Smallest {n_sl} ACC:", np.sort(np.partition(knn_scores['test_accuracy'],
 # %% [markdown]
 # ### Decision Tree
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 dtree = tree.DecisionTreeClassifier()
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 dtree_scores = cross_validate(
     dtree,
     X=imputer.fit_transform(train_x),
@@ -292,7 +297,7 @@ dtree_scores = cross_validate(
     error_score='raise',
     scoring=('accuracy', 'precision', 'recall', 'f1')
 )
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 print("Acc (median)", np.nanmedian(dtree_scores['test_accuracy']))
 print("Acc (mean)", np.mean(dtree_scores['test_accuracy']))
 print("Precision", np.mean(dtree_scores['test_precision']))
@@ -304,10 +309,10 @@ print(f"Smallest {n_sl} ACC:", np.sort(np.partition(dtree_scores['test_accuracy'
 # %% [markdown]
 # ### Random Forest Classifier
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 rfc = ensemble.RandomForestClassifier()
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 rfc_scores = cross_validate(
     rfc,
     X=imputer.fit_transform(train_x),
@@ -319,7 +324,7 @@ rfc_scores = cross_validate(
     scoring=('accuracy', 'precision', 'recall', 'f1'), 
     return_estimator=True
 )
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 print("Acc (median)", np.nanmedian(rfc_scores['test_accuracy']))
 print("Acc (mean)", np.mean(rfc_scores['test_accuracy']))
 print("Precision", np.mean(rfc_scores['test_precision']))
@@ -331,7 +336,7 @@ print(f"Smallest {n_sl} ACC:", np.sort(np.partition(rfc_scores['test_accuracy'],
 # %% [markdown]
 # ### Feature importance (RFC)
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 rfc_es_fimp = pd.DataFrame(columns=list(train_x.columns))
 for idx, estimator in enumerate(rfc_scores['estimator']):
     feature_importances = pd.DataFrame(estimator.feature_importances_,
@@ -353,10 +358,10 @@ train_x['empatica_temperature_cr_stdDev_X_SO_mean'].value_counts()
 # %% [markdown]
 # ### Gradient Boosting Classifier
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 gbc = ensemble.GradientBoostingClassifier()
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 gbc_scores = cross_validate(
     gbc,
     X=imputer.fit_transform(train_x),
@@ -367,7 +372,7 @@ gbc_scores = cross_validate(
     error_score='raise',
     scoring=('accuracy', 'precision', 'recall', 'f1')
 )
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 print("Acc (median)", np.nanmedian(gbc_scores['test_accuracy']))
 print("Acc (mean)", np.mean(gbc_scores['test_accuracy']))
 print("Precision", np.mean(gbc_scores['test_precision']))
@@ -379,10 +384,10 @@ print(f"Smallest {n_sl} ACC:", np.sort(np.partition(gbc_scores['test_accuracy'],
 # %% [markdown]
 # ### LGBM Classifier
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 lgbm = LGBMClassifier()
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 lgbm_scores = cross_validate(
     lgbm,
     X=imputer.fit_transform(train_x),
@@ -393,7 +398,7 @@ lgbm_scores = cross_validate(
     error_score='raise',
     scoring=('accuracy', 'precision', 'recall', 'f1')
 )
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 print("Acc (median)", np.nanmedian(lgbm_scores['test_accuracy']))
 print("Acc (mean)", np.mean(lgbm_scores['test_accuracy']))
 print("Precision", np.mean(lgbm_scores['test_precision']))
@@ -405,10 +410,10 @@ print(f"Smallest {n_sl} ACC:", np.sort(np.partition(lgbm_scores['test_accuracy']
 # %% [markdown]
 # ### XGBoost Classifier
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 xgb_classifier = xg.sklearn.XGBClassifier()
 
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 xgb_classifier_scores = cross_validate(
     xgb_classifier,
     X=imputer.fit_transform(train_x),
@@ -419,7 +424,7 @@ xgb_classifier_scores = cross_validate(
     error_score='raise',
     scoring=('accuracy', 'precision', 'recall', 'f1')
 )
-# %% jupyter={"source_hidden": true}
+# %% jupyter={"source_hidden": false, "outputs_hidden": false}
 print("Acc (median)", np.nanmedian(xgb_classifier_scores['test_accuracy']))
 print("Acc (mean)", np.mean(xgb_classifier_scores['test_accuracy']))
 print("Precision", np.mean(xgb_classifier_scores['test_precision']))
@@ -428,4 +433,4 @@ print("F1", np.mean(xgb_classifier_scores['test_f1']))
 print(f"Largest {n_sl} ACC:", np.sort(-np.partition(-xgb_classifier_scores['test_accuracy'], n_sl)[:n_sl])[::-1])
 print(f"Smallest {n_sl} ACC:", np.sort(np.partition(xgb_classifier_scores['test_accuracy'], n_sl)[:n_sl]))
 
-# %%
+# %% jupyter={"outputs_hidden": false, "source_hidden": false}