Add a parameter for grouping.

exploration/ex_ml_pipeline.py

@@ -61,6 +61,9 @@ df_proximity = proximity.get_proximity_data(ptcp_2)
 df_proximity = helper.get_date_from_timestamp(df_proximity)
 df_proximity = proximity.recode_proximity(df_proximity)
 
+# %% [markdown]
+# ## 1.3 Standardization/personalization
+
 # %% [markdown]
 # # 2. Grouping/segmentation
 
@@ -71,3 +74,19 @@ df_esm_PANAS_daily_means = (
     .reset_index()
     .rename(columns={"esm_user_answer_numeric": "esm_numeric_mean"})
 )
+
+# %%
+df_proximity_daily_counts = proximity.count_proximity(
+    df_proximity, ["participant_id", "date_lj"]
+)
+
+# %%
+df_proximity_daily_counts
+
+# %% [markdown]
+# # 3. Join features (and export to csv?)
+
+# %% [markdown]
+# # 4. Machine learning model and parameters
+
+# %%

features/proximity.py

@@ -55,7 +55,9 @@ def recode_proximity(df_proximity: pd.DataFrame) -> pd.DataFrame:
     return df_proximity
 
 
-def count_proximity(df_proximity: pd.DataFrame) -> pd.DataFrame:
+def count_proximity(
+    df_proximity: pd.DataFrame, group_by: Collection = ["participant_id"]
+) -> pd.DataFrame:
     """
     The function counts how many times a "near" value occurs in proximity
         and calculates the proportion of this counts to all proximity values (i.e. relative count).
@@ -64,6 +66,9 @@ def count_proximity(df_proximity: pd.DataFrame) -> pd.DataFrame:
     ----------
     df_proximity: pd.DataFrame
         A dataframe of proximity data.
+    group_by: Collection
+        A list of strings, specifying by which parameters to group.
+        By default, the features are calculated per participant, but could be "date_lj" etc.
 
     Returns
     -------
@@ -73,7 +78,7 @@ def count_proximity(df_proximity: pd.DataFrame) -> pd.DataFrame:
     if "bool_prox_near" not in df_proximity:
         df_proximity = recode_proximity(df_proximity)
     df_proximity["bool_prox_far"] = ~df_proximity["bool_prox_near"]
-    df_proximity_features = df_proximity.groupby("participant_id").sum()[
+    df_proximity_features = df_proximity.groupby(group_by).sum()[
         ["bool_prox_near", "bool_prox_far"]
     ]
     df_proximity_features = df_proximity_features.assign(