From 9580533c1418b9a7e8b545308d541188c922c6f0 Mon Sep 17 00:00:00 2001
From: junos <junos.lukan@ijs.si>
Date: Fri, 23 Jul 2021 18:50:17 +0200
Subject: [PATCH] Explore between-participants differences in light.

---
 exploration/expl_light.py | 64 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)

diff --git a/exploration/expl_light.py b/exploration/expl_light.py
index b24ae26..65a06b0 100644
--- a/exploration/expl_light.py
+++ b/exploration/expl_light.py
@@ -102,3 +102,67 @@ df_light_nokia.loc[df_light_nokia["double_light_lux"] == 0, ["datetime_lj"]]
 # %% [markdown]
 # Zeroes are present during the day. It does happens when the sensor is physically blocked.
 
+# %% [markdown]
+# # Differences between participants
+
+# %%
+df_light_participants = (
+    df_light_inactive[["participant_id", "device_id", "double_light_lux"]]
+    .groupby(["participant_id", "device_id"])
+    .agg(["mean", "median", "std", "min", "max"])
+    .reset_index(col_level=1)
+)
+df_light_participants.columns = df_light_participants.columns.get_level_values(1)
+
+# %%
+df_light_participants[df_light_participants["min"] > 0]
+
+# %%
+df_light_inactive[
+    df_light_inactive["device_id"] == "3188b03e-8b6f-45da-894e-769eed81bbda"
+].shape
+
+# %% [markdown]
+# This was a Lenovo Vibe K6, but the small range of values is due to a reinstallation shortly after the first (unsuccessful) installation.
+
+# %%
+sns.displot(data=df_light_participants, x="mean", binwidth=0.1, log_scale=(True, False))
+
+# %%
+sns.displot(data=df_light_participants, x="max", binwidth=0.1, log_scale=(True, False))
+
+# %% [markdown]
+# Variability in means is probably due to variability in maxima.
+
+# %%
+histogram_median = sns.displot(
+    data=df_light_participants, x="median", binwidth=50, log_scale=(False, False)
+)
+
+# %%
+df_light_participants[df_light_participants["median"] > 1e4]
+
+# %% [markdown]
+# This was a Cubot KingKong Mini 2 phone.
+
+# %%
+histogram_median = sns.displot(
+    data=df_light_participants, x="median", binwidth=50, log_scale=(False, False)
+)
+histogram_median.set(xlim=(0, 600))
+
+# %% [markdown]
+# Other medians are much more similar.
+
+# %%
+df_light_participants["std_rel"] = (
+    df_light_participants["std"] / df_light_participants["max"]
+)
+
+# %%
+sns.displot(data=df_light_participants, x="std_rel", binwidth=0.005)
+
+# %% [markdown]
+# Relative variability is homogeneous.
+#
+# This means that light data needs to be standardized. Min/max standardization would probably fit best.