Start exploring PANAS data.

Add a function to clean up ESM data.

exploration/expl_esm_labels.py

@@ -0,0 +1,53 @@
+# ---
+# jupyter:
+#   jupytext:
+#     formats: ipynb,py:percent
+#     text_representation:
+#       extension: .py
+#       format_name: percent
+#       format_version: '1.3'
+#       jupytext_version: 1.11.2
+#   kernelspec:
+#     display_name: straw2analysis
+#     language: python
+#     name: straw2analysis
+# ---
+
+# %%
+import os
+import sys
+
+import seaborn as sns
+
+nb_dir = os.path.split(os.getcwd())[0]
+if nb_dir not in sys.path:
+    sys.path.append(nb_dir)
+import participants.query_db
+from features.esm import *
+
+# %% [markdown]
+# # ESM data
+
+# %% [markdown]
+# Only take data from the main part of the study. The pilot data have different structure, there were especially many additions to ESM_JSON.
+
+# %%
+participants_inactive_usernames = participants.query_db.get_usernames(
+    collection_start=datetime.date.fromisoformat("2020-08-01")
+)
+df_esm_inactive = get_esm_data(participants_inactive_usernames)
+
+# %%
+df_esm_preprocessed = preprocess_esm(df_esm_inactive)
+df_esm_clean = clean_up_esm(df_esm_preprocessed)
+
+# %%
+df_esm_PANAS = df_esm_clean[
+    (df_esm_clean["questionnaire_id"] == 8) | (df_esm_clean["questionnaire_id"] == 9)
+]
+df_esm_PANAS_grouped = df_esm_PANAS.groupby(["participant_id", "questionnaire_id"])
+
+# %%
+df_esm_PANAS.head()
+
+# %%

features/esm.py

@@ -213,3 +213,25 @@ def classify_sessions_by_completion_time(
     df_session_counts_time.loc[morning_transition_to_daytime, "time"] = "daytime"
 
     return df_session_counts_time
+
+
+def clean_up_esm(df_esm_preprocessed: pd.DataFrame) -> pd.DataFrame:
+    """
+    This function eliminates invalid ESM responses.
+    It removes unanswered ESMs.
+
+    Parameters
+    ----------
+    df_esm_preprocessed: pd.DataFrame
+        A preprocessed dataframe of esm data.
+
+    Returns
+    -------
+    df_esm_clean: pd.DataFrame
+        A subset of the original dataframe.
+
+    """
+    df_esm_clean = df_esm_preprocessed[
+        df_esm_preprocessed["esm_status"] == ESM_STATUS_ANSWERED
+    ]
+    return df_esm_clean

statistical_analysis/adherence.py

@@ -221,7 +221,13 @@ df_session_workday = df_session_workday.assign(
 )
 
 # %%
-g1 = sns.displot(df_session_workday["time_diff_minutes"], binwidth=5, height=5, aspect=1.5, color="#28827C")
+g1 = sns.displot(
+    df_session_workday["time_diff_minutes"],
+    binwidth=5,
+    height=5,
+    aspect=1.5,
+    color="#28827C",
+)
 g1.set_axis_labels("Time difference [min]", "Session count")
 # g1.savefig("WorkdayEMAtimeDiff.pdf")
 
@@ -278,7 +284,13 @@ df_mean_daytime_interval = df_session_workday.groupby("participant_id").median()
 df_mean_daytime_interval.describe()
 
 # %%
-g2 = sns.displot(df_mean_daytime_interval.time_diff_minutes, binwidth=5, height=5, aspect=1.5, color="#28827C")
+g2 = sns.displot(
+    df_mean_daytime_interval.time_diff_minutes,
+    binwidth=5,
+    height=5,
+    aspect=1.5,
+    color="#28827C",
+)
 g2.set_axis_labels("Median time difference [min]", "Participant count")
 # g2.savefig("WorkdayEMAtimeDiffMedianParticip.pdf")
 
@@ -303,7 +315,13 @@ df_count_daytime_per_participant = df_session_workday.groupby(
 df_count_daytime_per_participant["time"].describe()
 
 # %%
-sns.displot(df_count_daytime_per_participant.time, binwidth=1, height=5, aspect=1.5, color="#28827C")
+sns.displot(
+    df_count_daytime_per_participant.time,
+    binwidth=1,
+    height=5,
+    aspect=1.5,
+    color="#28827C",
+)
 
 # %% [markdown]
 # ## Evening EMA
@@ -334,7 +352,13 @@ s_evening_completed_ratio = (
 s_evening_completed_ratio.describe()
 
 # %%
-g3 = sns.displot(s_evening_completed_ratio - 0.001, binwidth=0.05, height=5, aspect=1.5, color="#28827C")
+g3 = sns.displot(
+    s_evening_completed_ratio - 0.001,
+    binwidth=0.05,
+    height=5,
+    aspect=1.5,
+    color="#28827C",
+)
 g3.set_axis_labels("Ratio of days with the evening EMA filled out", "Participant count")
 g3.set(xlim=(1.01, 0.59))
 # g3.savefig("EveningEMAratioParticip.pdf")