Add StrtifiedKFold with shuffling as a default CV method.

exploration/ml_pipeline_classification.py

@@ -26,7 +26,7 @@ import pandas as pd
 import seaborn as sns
 
 from sklearn import linear_model, svm, naive_bayes, neighbors, tree, ensemble 
-from sklearn.model_selection import LeaveOneGroupOut, cross_validate
+from sklearn.model_selection import LeaveOneGroupOut, cross_validate, StratifiedKFold
 from sklearn.dummy import DummyClassifier
 from sklearn.impute import SimpleImputer
 
@@ -47,20 +47,19 @@ import machine_learning.model
 
 # %% [markdown]
 # ## Set script's parameters
-cv_method_str = 'logo' # logo, halflogo, 5kfold # Cross-validation method (could be regarded as a hyperparameter)
+cv_method_str = 'logo' # logo, half_logo, 5kfold # Cross-validation method (could be regarded as a hyperparameter)
 n_sl = 1 # Number of largest/smallest accuracies (of particular CV) outputs
 
 # %% jupyter={"source_hidden": true}
-model_input = pd.read_csv("../data/stressfulness_event_nonstandardized/input_appraisal_stressfulness_event_mean.csv")
+model_input = pd.read_csv("../data/intradaily_30_min_all_targets/input_JCQ_job_demand_mean.csv")
 
 # %% jupyter={"source_hidden": true}
 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}
-# bins = [-10, -1, 1, 10] # bins for z-scored targets
+bins = [-10, 0, 10] # bins for z-scored targets
-bins = [0, 1, 4] # bins for stressfulness (1-4) target
+# bins = [1, 2.5, 4] # bins for stressfulness (1-4) target
 model_input['target'], edges = pd.cut(model_input.target, bins=bins, labels=['low', 'high'], retbins=True, right=True) #['low', 'medium', 'high']
 model_input['target'].value_counts(), edges
 # model_input = model_input[model_input['target'] != "medium"]
@@ -68,7 +67,7 @@ model_input['target'] = model_input['target'].astype(str).apply(lambda x: 0 if x
 
 model_input['target'].value_counts()
 
-if cv_method_str == 'halflogo':
+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')
 
@@ -101,7 +100,7 @@ train_x = pd.concat([numerical_features, categorical_features], axis=1)
 train_x.dtypes
 
 # %% jupyter={"source_hidden": true}
-cv_method = None # Defaults to 5 k-folds in cross_validate method
+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()
     cv_method.get_n_splits(

exploration/ml_pipeline_classification_with_clustering.py

@@ -26,7 +26,7 @@ import pandas as pd
 import seaborn as sns
 from scipy import stats
 
-from sklearn.model_selection import LeaveOneGroupOut, cross_validate
+from sklearn.model_selection import LeaveOneGroupOut, cross_validate, StratifiedKFold
 from sklearn.impute import SimpleImputer
 
 from sklearn.dummy import DummyClassifier
@@ -52,8 +52,8 @@ from machine_learning.classification_models import ClassificationModels
 
 # %% [markdown]
 # ## Set script's parameters
-n_clusters = 5 # Number of clusters (could be regarded as a hyperparameter)
+n_clusters = 3 # Number of clusters (could be regarded as a hyperparameter)
-cv_method_str = 'logo' # logo, halflogo, 5kfold # Cross-validation method (could be regarded as a hyperparameter)
+cv_method_str = 'half_logo' # logo, half_logo, 5kfold # Cross-validation method (could be regarded as a hyperparameter)
 n_sl = 1 # Number of largest/smallest accuracies (of particular CV) outputs
 
 # %% jupyter={"source_hidden": true}
@@ -109,7 +109,7 @@ for k in range(n_clusters):
 
     model_input_subset['target'].value_counts()
     
-    if cv_method_str == 'halflogo':
+    if cv_method_str == 'half_logo':
         model_input_subset['pid_index'] = model_input_subset.groupby('pid').cumcount()
         model_input_subset['pid_count'] = model_input_subset.groupby('pid')['pid'].transform('count')
 
@@ -140,7 +140,7 @@ for k in range(n_clusters):
     train_x = pd.concat([numerical_features, categorical_features], axis=1)
 
     # Establish cv method
-    cv_method = None # Defaults to 5 k-folds in cross_validate method
+    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()
         cv_method.get_n_splits(