Add SAM event and period analysis.

exploration/expl_esm_labels.py

@@ -102,22 +102,114 @@ df_esm_SAM = df_esm_preprocessed[
     (df_esm_preprocessed["questionnaire_id"] >= 87)
     & (df_esm_preprocessed["questionnaire_id"] <= 93)
 ]
+df_esm_SAM_clean = clean_up_esm(df_esm_SAM)
+
+# %% [markdown]
+# ## Stressful events
 
 # %%
-clean_up_esm(df_esm_SAM)[["esm_user_answer", "esm_user_answer_numeric"]].head(9)
+df_esm_SAM_event = df_esm_SAM_clean[df_esm_SAM_clean["questionnaire_id"] == 87].assign(
+    stressful_event=lambda x: (x.esm_user_answer_numeric > 0)
+)
 
 # %%
-df_esm_PANAS_clean[["esm_user_answer", "esm_user_answer_numeric"]].head(n=10)
+df_esm_SAM_daily_events = (
+    df_esm_SAM_event.groupby(["participant_id", "date_lj"])
+    .stressful_event.agg("mean")
+    .reset_index()
+    .rename(columns={"stressful_event": "SAM_event_ratio"})
+)
+
+# %% [markdown]
+# Calculate the daily mean of YES (1) or NO (0) answers to the question about a stressful events. This is then the daily ratio of EMA sessions that included a stressful event.
 
 # %%
-df_esm_SAM[
+df_esm_SAM_event_summary_participant = (
-    [
+    df_esm_SAM_daily_events.groupby(["participant_id"])
-        "esm_instructions",
+    .agg(["mean", "median", "std"])
-        "question_id",
+    .reset_index(col_level=1)
-        "questionnaire_id",
+)
-        "esm_user_answer",
+df_esm_SAM_event_summary_participant.columns = df_esm_SAM_event_summary_participant.columns.get_level_values(
-        "esm_type",
+    1
-    ]
+)
-].head(n=10)
 
 # %%
+sns.displot(data=df_esm_SAM_event_summary_participant, x="mean", binwidth=0.1)
+
+# %%
+sns.displot(data=df_esm_SAM_event_summary_participant, x="std", binwidth=0.05)
+
+# %% [markdown]
+# ### Threat and challenge
+
+# %% [markdown]
+# * Example of threat: "Did this event make you feel anxious?"
+# * Example of challenge: "How eager are you to tackle this event?"
+# * Possible answers: 0 - Not at all, 1 - Slightly, 2 - Moderately, 3 - Considerably, 4 - Extremely
+
+# %%
+df_esm_SAM_daily = (
+    df_esm_SAM_clean.groupby(["participant_id", "date_lj", "questionnaire_id"])
+    .esm_user_answer_numeric.agg("mean")
+    .reset_index()
+    .rename(columns={"esm_user_answer_numeric": "esm_numeric_mean"})
+)
+
+# %%
+df_esm_SAM_daily_threat_challenge = df_esm_SAM_daily[
+    (df_esm_SAM_daily["questionnaire_id"] == 88)
+    | (df_esm_SAM_daily["questionnaire_id"] == 89)
+]
+
+# %%
+df_esm_SAM_summary_participant = (
+    df_esm_SAM_daily.groupby(["participant_id", "questionnaire_id"])
+    .agg(["mean", "median", "std"])
+    .reset_index(col_level=1)
+)
+df_esm_SAM_summary_participant.columns = df_esm_SAM_summary_participant.columns.get_level_values(
+    1
+)
+
+# %%
+df_esm_SAM_threat_challenge_summary_participant = df_esm_SAM_summary_participant[
+    (df_esm_SAM_summary_participant["questionnaire_id"] == 88)
+    | (df_esm_SAM_summary_participant["questionnaire_id"] == 89)
+]
+df_esm_SAM_threat_challenge_summary_participant[
+    "event_subscale"
+] = df_esm_SAM_threat_challenge_summary_participant.questionnaire_id.astype(
+    "category"
+).cat.rename_categories(
+    {88: "threat", 89: "challenge"}
+)
+
+# %%
+sns.displot(
+    data=df_esm_SAM_threat_challenge_summary_participant,
+    x="mean",
+    hue="event_subscale",
+    binwidth=0.2,
+)
+
+# %%
+sns.displot(
+    data=df_esm_SAM_threat_challenge_summary_participant,
+    x="std",
+    hue="event_subscale",
+    binwidth=0.1,
+)
+
+# %% [markdown]
+# ## Stressfulness of period
+
+# %%
+df_esm_SAM_period_summary_participant = df_esm_SAM_summary_participant[
+    df_esm_SAM_summary_participant["questionnaire_id"] == 93
+]
+
+# %%
+sns.displot(data=df_esm_SAM_period_summary_participant, x="mean", binwidth=0.2)
+
+# %%
+sns.displot(data=df_esm_SAM_period_summary_participant, x="std", binwidth=0.1)