Extend ml pipeline scripts with two additional CV methods.

exploration/ml_pipeline_daily.py

@@ -72,11 +72,20 @@ sns.heatmap(model_input.sort_values('pid').set_index('pid').isna(), cbar=False)
 
 # %% jupyter={"source_hidden": true}
 index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]
-#if "pid" in model_input.columns:
+
-#    index_columns.append("pid")
 model_input.set_index(index_columns, inplace=True)
 
-data_x, data_y, data_groups = model_input.drop(["target", "pid"], axis=1), model_input["target"], model_input["pid"]
+cv_method = '5kfold'
+if cv_method == 'half_logo':
+    data_x, data_y, data_groups = model_input.drop(["target", "pid"], axis=1), model_input["target"], model_input["pid"]
+else:
+    model_input['pid_index'] = model_input.groupby('pid').cumcount()
+    model_input['pid_count'] = model_input.groupby('pid')['pid'].transform('count')
+
+    model_input["pid_index"] = (model_input['pid_index'] / model_input['pid_count'] + 1).round()
+    model_input["pid_half"] = model_input["pid"] + "_" +  model_input["pid_index"].astype(int).astype(str)
+
+    data_x, data_y, data_groups = model_input.drop(["target", "pid", "pid_index", "pid_half"], axis=1), model_input["target"], model_input["pid_half"]
 
 # %% jupyter={"source_hidden": true}
 categorical_feature_colnames = ["gender", "startlanguage"]
@@ -114,6 +123,10 @@ logo.get_n_splits(
     groups=data_groups,
 )
 
+# Defaults to 5 k folds in cross_validate method
+if cv_method != 'logo' and cv_method != 'half_logo':
+    logo = None
+
 # %% jupyter={"source_hidden": true}
 sum(data_y.isna())
 

exploration/ml_pipeline_daily_cleaned_intradaily.py

@@ -50,7 +50,7 @@ import machine_learning.model
 # ## PANAS negative affect
 
 # %% jupyter={"source_hidden": true}
-model_input = pd.read_csv("../data/intradaily_30_min_all_targets/input_PANAS_negative_affect_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"]
@@ -58,7 +58,17 @@ index_columns = ["local_segment", "local_segment_label", "local_segment_start_da
 #    index_columns.append("pid")
 model_input.set_index(index_columns, inplace=True)
 
-data_x, data_y, data_groups = model_input.drop(["target", "pid"], axis=1), model_input["target"], model_input["pid"]
+cv_method = '5kfold'
+if cv_method == 'half_logo':
+    data_x, data_y, data_groups = model_input.drop(["target", "pid"], axis=1), model_input["target"], model_input["pid"]
+else:
+    model_input['pid_index'] = model_input.groupby('pid').cumcount()
+    model_input['pid_count'] = model_input.groupby('pid')['pid'].transform('count')
+
+    model_input["pid_index"] = (model_input['pid_index'] / model_input['pid_count'] + 1).round()
+    model_input["pid_half"] = model_input["pid"] + "_" +  model_input["pid_index"].astype(int).astype(str)
+
+    data_x, data_y, data_groups = model_input.drop(["target", "pid", "pid_index", "pid_half"], axis=1), model_input["target"], model_input["pid_half"]
 
 # %% jupyter={"source_hidden": true}
 categorical_feature_colnames = ["gender", "startlanguage"]
@@ -98,6 +108,10 @@ logo.get_n_splits(
     groups=data_groups,
 )
 
+# Defaults to 5 k folds in cross_validate method
+if cv_method != 'logo' and cv_method != 'half_logo':
+    logo = None
+
 # %% jupyter={"source_hidden": true}
 sum(data_y.isna())
 

exploration/ml_pipeline_stress_event_cleaned.py

@@ -53,12 +53,25 @@ import machine_learning.model
 model_input = pd.read_csv("../data/stressfulness_event/input_appraisal_stressfulness_event_mean.csv")
 
 # %% jupyter={"source_hidden": true}
+
 index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]
-#if "pid" in model_input.columns:
+
-#    index_columns.append("pid")
 model_input.set_index(index_columns, inplace=True)
 
-data_x, data_y, data_groups = model_input.drop(["target", "pid"], axis=1), model_input["target"], model_input["pid"]
+cv_method = 'half_logo'
+if cv_method == 'logo':
+    data_x, data_y, data_groups = model_input.drop(["target", "pid"], axis=1), model_input["target"], model_input["pid"]
+else:
+
+    model_input[(model_input['pid'] == "p037") | (model_input['pid'] == "p064") | (model_input['pid'] == "p092")]
+
+    model_input['pid_index'] = model_input.groupby('pid').cumcount()
+    model_input['pid_count'] = model_input.groupby('pid')['pid'].transform('count')
+
+    model_input["pid_index"] = (model_input['pid_index'] / model_input['pid_count'] + 1).round()
+    model_input["pid_half"] = model_input["pid"] + "_" +  model_input["pid_index"].astype(int).astype(str)
+
+    data_x, data_y, data_groups = model_input.drop(["target", "pid", "pid_index", "pid_half"], axis=1), model_input["target"], model_input["pid_half"]
 
 # %% jupyter={"source_hidden": true}
 categorical_feature_colnames = ["gender", "startlanguage"]
@@ -97,12 +110,10 @@ logo.get_n_splits(
     data_y,
     groups=data_groups,
 )
-logo.split(
-    train_x,
-    data_y,
-    groups=data_groups,
-)
 
+# Defaults to 5 k folds in cross_validate method
+if cv_method != 'logo' and cv_method != 'half_logo':
+    logo = None
 
 # %% jupyter={"source_hidden": true}
 sum(data_y.isna())