Export figures and add additional linear regression analyses.

communication
junos 2021-06-14 17:09:45 +02:00
parent b1dd27d516
commit 767548b562
2 changed files with 77 additions and 24 deletions

View File

@ -89,6 +89,6 @@ baseline_inactive = baseline_inactive.assign(
baseline_inactive["age"].describe() baseline_inactive["age"].describe()
# %% # %%
3710/365.25 3618 / 365.25
# %% # %%

View File

@ -51,25 +51,6 @@ baseline_inactive = baseline[
baseline["Gebruikersnaam"].isin(participants_inactive_usernames) baseline["Gebruikersnaam"].isin(participants_inactive_usernames)
] ]
# %%
df_esm_inactive = get_esm_data(participants_inactive_usernames)
# %%
df_esm_preprocessed = preprocess_esm(df_esm_inactive)
df_session_counts_time = classify_sessions_by_completion_time(df_esm_preprocessed)
# %%
tbl_session_outcomes = df_session_counts_time.reset_index()[
"session_response"
].value_counts()
# %%
print("All sessions:", len(df_session_counts_time))
print("-------------------------------------")
print(tbl_session_outcomes)
print("-------------------------------------")
print(tbl_session_outcomes / len(df_session_counts_time))
# %% # %%
VARIABLES_TO_TRANSLATE = { VARIABLES_TO_TRANSLATE = {
"Gebruikersnaam": "username", "Gebruikersnaam": "username",
@ -83,9 +64,37 @@ baseline_inactive = baseline_inactive.assign(
age=lambda x: (now - x.date_of_birth).dt.days / 365.25245, age=lambda x: (now - x.date_of_birth).dt.days / 365.25245,
) )
# %%
df_esm_inactive = get_esm_data(participants_inactive_usernames)
# %% [markdown]
# # Classify EMA sessions
# %%
df_esm_preprocessed = preprocess_esm(df_esm_inactive)
df_session_counts_time = classify_sessions_by_completion_time(df_esm_preprocessed)
# %% [markdown]
# Sessions are now classified according to the type of a session (a true questionnaire or simple single questions) and users response.
# %% # %%
df_session_counts_time df_session_counts_time
# %%
tbl_session_outcomes = df_session_counts_time.reset_index()[
"session_response"
].value_counts()
# %%
print("All sessions:", len(df_session_counts_time))
print("-------------------------------------")
print(tbl_session_outcomes)
print("-------------------------------------")
print(tbl_session_outcomes / len(df_session_counts_time))
# %% [markdown]
# ## Consider only true EMA sessions
# %% # %%
df_session_finished = df_session_counts_time[ df_session_finished = df_session_counts_time[
df_session_counts_time["session_response"] == SESSION_STATUS_COMPLETE df_session_counts_time["session_response"] == SESSION_STATUS_COMPLETE
@ -117,6 +126,9 @@ df_adherence
# %% # %%
df_adherence.describe() df_adherence.describe()
# %%
df_adherence[["gender", "startlanguage"]].value_counts()
# %% # %%
sns.displot(df_adherence["finished_sessions"], binwidth=5, height=5) sns.displot(df_adherence["finished_sessions"], binwidth=5, height=5)
@ -209,7 +221,9 @@ df_session_workday = df_session_workday.assign(
) )
# %% # %%
sns.displot(df_session_workday["time_diff_minutes"], binwidth=5, height=5) g1 = sns.displot(df_session_workday["time_diff_minutes"], binwidth=5, height=5)
g1.set_axis_labels("Time difference [min]", "Session count")
# g1.savefig("WorkdayEMAtimeDiff.pdf")
# %% [markdown] # %% [markdown]
# There are some sessions that are really close together. By design, none should be closer than 30 min. Let's take a look at those. # There are some sessions that are really close together. By design, none should be closer than 30 min. Let's take a look at those.
@ -246,6 +260,11 @@ df_session_workday = df_session_workday[df_session_workday.time_diff_minutes > 2
# %% # %%
df_session_workday.describe() df_session_workday.describe()
# %%
df_session_workday[df_session_workday["time_diff_minutes"] < 120].shape[
0
] / df_session_workday.shape[0]
# %% [markdown] # %% [markdown]
# These statistics look reasonable. # These statistics look reasonable.
@ -253,13 +272,27 @@ df_session_workday.describe()
# ### Differences between participants # ### Differences between participants
# %% # %%
df_mean_daytime_interval = df_session_workday.groupby("participant_id").mean() df_mean_daytime_interval = df_session_workday.groupby("participant_id").median()
# %% # %%
df_mean_daytime_interval.describe() df_mean_daytime_interval.describe()
# %% # %%
sns.displot(df_mean_daytime_interval.time_diff_minutes, binwidth=5, height=5) g2 = sns.displot(df_mean_daytime_interval.time_diff_minutes, binwidth=5, height=5)
g2.set_axis_labels("Median time difference [min]", "Participant count")
# g2.savefig("WorkdayEMAtimeDiffMedianParticip.pdf")
# %%
df_adherence = df_adherence.merge(
df_mean_daytime_interval, how="left", left_on="participant_id", right_index=True
)
# %%
lr_ols_time_diff_median = smf.ols(
"time_diff_minutes ~ C(gender) + C(startlanguage) + age", data=df_adherence
)
ls_result_time_diff_median = lr_ols_time_diff_median.fit()
ls_result_time_diff_median.summary()
# %% # %%
df_count_daytime_per_participant = df_session_workday.groupby( df_count_daytime_per_participant = df_session_workday.groupby(
@ -288,6 +321,9 @@ s_evening_completed = df_session_counts_time_completed.groupby(
# %% # %%
df_session_counts_time_completed df_session_counts_time_completed
# %%
s_evening_completed.sum()
# %% # %%
s_evening_completed_ratio = ( s_evening_completed_ratio = (
s_evening_completed.groupby("participant_id").sum() s_evening_completed.groupby("participant_id").sum()
@ -298,6 +334,23 @@ s_evening_completed_ratio = (
s_evening_completed_ratio.describe() s_evening_completed_ratio.describe()
# %% # %%
sns.displot(s_evening_completed_ratio - 0.001, binwidth=0.1, height=5) g3 = sns.displot(s_evening_completed_ratio - 0.001, binwidth=0.05, height=5)
g3.set_axis_labels("Ratio of days with the evening EMA filled out", "Participant count")
# g3.savefig("EveningEMAratioParticip.pdf")
# %%
df_adherence = df_adherence.merge(
s_evening_completed_ratio.rename("evening_EMA_ratio"),
how="left",
left_on="participant_id",
right_index=True,
)
# %%
lr_ols_evening_ratio = smf.ols(
"evening_EMA_ratio ~ C(gender) + C(startlanguage) + age", data=df_adherence
)
ls_result_evening_ratio = lr_ols_evening_ratio.fit()
ls_result_evening_ratio.summary()
# %% # %%