Start support for phone_keyboard

Snakefile

@@ -100,6 +100,15 @@ for provider in config["PHONE_LIGHT"]["PROVIDERS"].keys():
         files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
         files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
 
+for provider in config["PHONE_KEYBOARD"]["PROVIDERS"].keys():
+    if config["PHONE_KEYBOARD"]["PROVIDERS"][provider]["COMPUTE"]:
+        files_to_compute.extend(expand("data/raw/{pid}/phone_keyboard_raw.csv", pid=config["PIDS"]))
+        files_to_compute.extend(expand("data/raw/{pid}/phone_keyboard_with_datetime.csv", pid=config["PIDS"]))
+        files_to_compute.extend(expand("data/interim/{pid}/phone_keyboard_features/phone_keyboard_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_KEYBOARD"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
+        files_to_compute.extend(expand("data/processed/features/{pid}/phone_keyboard.csv", pid=config["PIDS"],))
+        files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
+        files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
+
 for provider in config["PHONE_ACCELEROMETER"]["PROVIDERS"].keys():
     if config["PHONE_ACCELEROMETER"]["PROVIDERS"][provider]["COMPUTE"]:
         files_to_compute.extend(expand("data/raw/{pid}/phone_accelerometer_raw.csv", pid=config["PIDS"]))

config.yaml

@@ -189,6 +189,15 @@ PHONE_DATA_YIELD:
       SRC_LANGUAGE: "r"
       SRC_FOLDER: "rapids" # inside src/features/phone_data_yield
 
+PHONE_KEYBOARD:
+  TABLE: keyboard
+  PROVIDERS:
+    RAPIDS:
+      COMPUTE: True
+      FEATURES: []
+      SRC_FOLDER: "rapids" # inside src/features/phone_keyboard
+      SRC_LANGUAGE: "python"
+
 # See https://www.rapids.science/latest/features/phone-light/
 PHONE_LIGHT:
   TABLE: light

rules/features.smk

@@ -262,6 +262,32 @@ rule phone_light_r_features:
     script:
         "../src/features/entry.R"
 
+rule phone_keyboard_python_features:
+    input:
+        sensor_data = "data/raw/{pid}/phone_keyboard_with_datetime.csv",
+        time_segments_labels = "data/interim/time_segments/{pid}_time_segments_labels.csv"
+    params:
+        provider = lambda wildcards: config["PHONE_KEYBOARD"]["PROVIDERS"][wildcards.provider_key.upper()],
+        provider_key = "{provider_key}",
+        sensor_key = "phone_keyboard"
+    output:
+        "data/interim/{pid}/phone_keyboard_features/phone_keyboard_python_{provider_key}.csv"
+    script:
+        "../src/features/entry.py"
+
+rule phone_keyboard_r_features:
+    input:
+        sensor_data = "data/raw/{pid}/phone_keyboard_with_datetime.csv",
+        time_segments_labels = "data/interim/time_segments/{pid}_time_segments_labels.csv"
+    params:
+        provider = lambda wildcards: config["PHONE_KEYBOARD"]["PROVIDERS"][wildcards.provider_key.upper()],
+        provider_key = "{provider_key}",
+        sensor_key = "phone_keyboard"
+    output:
+        "data/interim/{pid}/phone_keyboard_features/phone_keyboard_r_{provider_key}.csv"
+    script:
+        "../src/features/entry.R"
+
 rule phone_locations_python_features:
     input:
         sensor_data = "data/interim/{pid}/phone_locations_processed_with_datetime.csv",

src/features/phone_keyboard/rapids/main.py

@@ -0,0 +1,40 @@
+import pandas as pd
+import numpy as np
+
+def rapids_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
+
+    # I copied this from light, modify it to make it work for keyboard
+
+    light_data = pd.read_csv(sensor_data_files["sensor_data"])
+    print(light_data)
+    raise ValueError("Test")
+    requested_features = provider["FEATURES"]
+    # name of the features this function can compute
+    base_features_names = ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
+    # the subset of requested features this function can compute
+    features_to_compute = list(set(requested_features) & set(base_features_names))
+
+    light_features = pd.DataFrame(columns=["local_segment"] + features_to_compute)
+    if not light_data.empty:
+        light_data = filter_data_by_segment(light_data, time_segment)
+        
+        if not light_data.empty:
+            light_features = pd.DataFrame()
+            if "count" in features_to_compute:
+                light_features["count"] = light_data.groupby(["local_segment"]).count()["timestamp"]
+            
+            # get light ambient luminance related features
+            if "maxlux" in features_to_compute:
+                light_features["maxlux"] = light_data.groupby(["local_segment"])["double_light_lux"].max()
+            if "minlux" in features_to_compute:
+                light_features["minlux"] = light_data.groupby(["local_segment"])["double_light_lux"].min()
+            if "avglux" in features_to_compute:
+                light_features["avglux"] = light_data.groupby(["local_segment"])["double_light_lux"].mean()
+            if "medianlux" in features_to_compute:
+                light_features["medianlux"] = light_data.groupby(["local_segment"])["double_light_lux"].median()
+            if "stdlux" in features_to_compute:
+                light_features["stdlux"] = light_data.groupby(["local_segment"])["double_light_lux"].std()
+            
+            light_features = light_features.reset_index()
+
+    return light_features