Explore PANAS statistics.

communication
junos 2021-07-03 18:46:06 +02:00
parent b8301ca458
commit 5362f64941
1 changed files with 37 additions and 1 deletions

View File

@ -46,7 +46,43 @@ df_esm_PANAS_clean = clean_up_esm(df_esm_PANAS)
# %%
df_esm_PANAS_grouped = df_esm_PANAS_clean.groupby(
["participant_id", "questionnaire_id"]
["participant_id", "date_lj", "questionnaire_id"]
)
# %%
df_esm_PANAS_daily_sums = (
df_esm_PANAS_grouped.esm_user_answer_numeric.agg("sum")
.reset_index()
.rename(columns={"esm_user_answer_numeric": "esm_numeric_sum"})
)
# %% [markdown]
# Group by participants, date, and subscale and calculate daily sums.
# %%
df_esm_PANAS_summary_participant = (
df_esm_PANAS_daily_sums.groupby(["participant_id", "questionnaire_id"])
.agg(["mean", "median", "std"])
.reset_index(col_level=1)
)
df_esm_PANAS_summary_participant.columns = df_esm_PANAS_summary_participant.columns.get_level_values(
1
)
df_esm_PANAS_summary_participant[
"PANAS_subscale"
] = df_esm_PANAS_daily_sums.questionnaire_id.astype("category").cat.rename_categories(
{8.0: "PA", 9.0: "NA"}
)
# %% [markdown]
# Next, calculate mean and standard deviation across all days for each participant.
# %%
sns.displot(
data=df_esm_PANAS_summary_participant, x="mean", hue="PANAS_subscale", binwidth=2
)
# %%
sns.displot(
data=df_esm_PANAS_summary_participant, x="std", hue="PANAS_subscale", binwidth=1
)