junos
/
stress_at_work_analysis
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Calculate daily means instead of sums.

communication
junos 2021-07-04 13:41:34 +02:00
parent 5362f64941
commit 3bb66e3838
2 changed files with 22 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
exploration/expl_esm_labels.py
View File

@ -44,24 +44,24 @@ df_esm_PANAS = df_esm_preprocessed[
]
df_esm_PANAS_clean = clean_up_esm(df_esm_PANAS)
# %%
df_esm_PANAS_grouped = df_esm_PANAS_clean.groupby(
["participant_id", "date_lj", "questionnaire_id"]
)
# %% [markdown]
# Group by participants, date, and subscale and calculate daily means.
# %%
df_esm_PANAS_daily_sums = (
df_esm_PANAS_grouped.esm_user_answer_numeric.agg("sum")
df_esm_PANAS_daily_means = (
df_esm_PANAS_clean.groupby(
["participant_id", "date_lj", "questionnaire_id"])
.esm_user_answer_numeric.agg("mean")
.reset_index()
.rename(columns={"esm_user_answer_numeric": "esm_numeric_sum"})
.rename(columns={"esm_user_answer_numeric": "esm_numeric_mean"})
)
# %% [markdown]
# Group by participants, date, and subscale and calculate daily sums.
# Next, calculate mean, median, and standard deviation across all days for each participant.
# %%
df_esm_PANAS_summary_participant = (
df_esm_PANAS_daily_sums.groupby(["participant_id", "questionnaire_id"])
df_esm_PANAS_daily_means.groupby(["participant_id", "questionnaire_id"])
.agg(["mean", "median", "std"])
.reset_index(col_level=1)
)
@ -70,19 +70,24 @@ df_esm_PANAS_summary_participant.columns = df_esm_PANAS_summary_participant.colu
)
df_esm_PANAS_summary_participant[
"PANAS_subscale"
] = df_esm_PANAS_daily_sums.questionnaire_id.astype("category").cat.rename_categories(
] = df_esm_PANAS_daily_means.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
data=df_esm_PANAS_summary_participant, x="mean", hue="PANAS_subscale", binwidth=0.2
)
# %%
sns.displot(
data=df_esm_PANAS_summary_participant, x="std", hue="PANAS_subscale", binwidth=1
data=df_esm_PANAS_summary_participant, x="median", hue="PANAS_subscale", binwidth=0.2
)
# %%
sns.displot(
data=df_esm_PANAS_summary_participant, x="std", hue="PANAS_subscale", binwidth=0.05
)
# %%
df_esm_PANAS_summary_participant[df_esm_PANAS_summary_participant["std"] < 0.1]

4
statistical_analysis/adherence.py
View File

@ -242,8 +242,8 @@ df_session_workday[df_session_workday.time_diff_minutes < 30]
# %%
df_esm_preprocessed.loc[
(df_esm_preprocessed.participant_id == 35) & (df_esm_preprocessed.esm_session == 6),
["esm_trigger", "esm_session", "datetime_lj", "esm_instructions"],
(df_esm_preprocessed.participant_id == 35) & (df_esm_preprocessed.esm_session == 7) & (df_esm_preprocessed.device_id == "62a44038-3ccb-401e-a69c-6f22152c54a6"),
["esm_trigger", "esm_session", "datetime_lj", "esm_instructions", "device_id", "_id"],
]
# %%