Add a couple of proximity features.

features/proximity.py

@@ -53,3 +53,33 @@ def recode_proximity(df_proximity: pd.DataFrame) -> pd.DataFrame:
     """
     df_proximity = df_proximity.assign(bool_prox_near=lambda x: x.double_proximity == 0)
     return df_proximity
+
+
+def count_proximity(df_proximity: pd.DataFrame) -> 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).
+
+    Parameters
+    ----------
+    df_proximity: pd.DataFrame
+        A dataframe of proximity data.
+
+    Returns
+    -------
+    df_proximity_features: pd.DataFrame
+        A dataframe with the count of "near" proximity values and their relative count.
+    """
+    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()[
+        ["bool_prox_near", "bool_prox_far"]
+    ]
+    df_proximity_features = df_proximity_features.assign(
+        prop_prox_near=lambda x: x.bool_prox_near / (x.bool_prox_near + x.bool_prox_far)
+    )
+    df_proximity_features = df_proximity_features.rename(
+        columns={"bool_prox_near": "freq_prox_near"}
+    ).drop(columns="bool_prox_far", inplace=False)
+    return df_proximity_features