Read RAPIDS features and create columns.

exploration/ex_ml_pipeline.py

@@ -6,7 +6,7 @@
 #       extension: .py
 #       format_name: percent
 #       format_version: '1.3'
-#       jupytext_version: 1.12.0
+#       jupytext_version: 1.13.0
 #   kernelspec:
 #     display_name: straw2analysis
 #     language: python
@@ -24,6 +24,7 @@ import numpy as np
 import pandas as pd
 import seaborn as sns
 import yaml
+from pyprojroot import here
 from sklearn import linear_model
 from sklearn.model_selection import LeaveOneGroupOut, cross_val_score
 
@@ -257,4 +258,41 @@ model_validation.cross_validate()
 # %%
 model_validation.groups
 
+# %% [markdown]
+# # Use RAPIDS
+
 # %%
+with open(here("rapids/config.yaml"), "r") as file:
+    rapids_config = yaml.safe_load(file)
+
+# %%
+for key in rapids_config.keys():
+    if isinstance(rapids_config[key], dict):  # Remove top-level configs
+        if "PROVIDERS" in rapids_config[key]:  # Retain features (that have providers)
+            if rapids_config[key]["PROVIDERS"]:  # Remove non-implemented features
+                for provider in rapids_config[key]["PROVIDERS"]:
+                    if rapids_config[key]["PROVIDERS"][provider][
+                        "COMPUTE"
+                    ]:  # Check that the features were actually calculated
+                        if "FEATURES" in rapids_config[key]["PROVIDERS"][provider]:
+                            print(key)
+                            print(provider)
+                            print(rapids_config[key]["PROVIDERS"][provider]["FEATURES"])
+
+# %%
+features_rapids = pd.read_csv(
+    here("rapids/data/processed/features/all_participants/all_sensor_features.csv"),
+    parse_dates=["local_segment_start_datetime", "local_segment_end_datetime"],
+)
+
+# %%
+features_rapids.columns
+
+# %%
+features_rapids = features_rapids.assign(
+    date_lj=lambda x: x.local_segment_start_datetime.dt.date
+)
+
+# %%
+features_rapids["participant_id"] = features_rapids["pid"].str.extract("(\d+)")
+features_rapids["participant_id"] = pd.to_numeric(features_rapids["participant_id"])