Identify unique sessions and assign status.

Use CONSTANT variables for these statuses.

exploration/expl_esm.py

@@ -141,14 +141,14 @@ df_esm_preprocessed.query("participant_id == 31 & esm_session == 77")[
     ["esm_trigger", "esm_instructions", "esm_user_answer"]
 ]
 
-# %%
+# %% tags=[]
 df_esm_2 = df_session_counts[
     df_session_counts["esm_session_count"] == 2
 ].reset_index().merge(df_esm_preprocessed, how="left", on=["participant_id", "device_id", "esm_session"])
-with pd.option_context('display.max_rows', None, 'display.max_columns', None):  # more options can be specified also
+#with pd.option_context('display.max_rows', None, 'display.max_columns', None):  # more options can be specified also
-    display(df_esm_2)
+    #display(df_esm_2)
 
-# %% [markdown]
+# %% [markdown] tags=[]
 # ### Long sessions
 
 # %%
@@ -269,4 +269,39 @@ sns.displot(
     height=8,
 )
 
+# %% [markdown]
+# ### Singleton sessions
+
+# %%
+df_session_counts.count()
+
+# %%
+df_session_counts[(df_session_counts.esm_session_count == 1) & df_session_counts.session_response.isna()]
+
+# %%
+df_session_1 = df_session_counts[(df_session_counts["esm_session_count"] == 1)  & df_session_counts.session_response.isna()]
+df_esm_unique_session = df_session_1.join(
+    df_esm_preprocessed.set_index(["participant_id", "device_id", "esm_session"])
+)
+df_esm_unique_session = df_esm_unique_session["esm_trigger"].rename("session_response")
+
+# %%
+df_session_counts.loc[df_esm_unique_session.index, "session_response"] = df_esm_unique_session
+
+# %%
+df_session_counts.count()
+
+# %%
+df_session_counts.merge()
+
+# %%
+df_esm_78243 = df_esm_preprocessed[df_esm_preprocessed["username"] == "uploader_78243"]
+df_esm_78243 = df_esm_78243.sort_values("_id")[["id","_id","datetime_lj", "esm_status","esm_trigger","esm_instructions","esm_user_answer","esm_session"]]
+
+# %%
+df_esm_78243.columns
+
+# %%
+df_esm_78243.to_csv("example.csv")
+
 # %%

features/esm.py

@@ -9,6 +9,13 @@ from config.models import ESM, Participant
 from setup import db_engine, session
 
 TZ_LJ = timezone("Europe/Ljubljana")
+ESM_STATUS_ANSWERED = 2
+
+GROUP_SESSIONS_BY = ["participant_id", "device_id", "esm_session"]
+
+SESSION_STATUS_UNANSWERED = "ema_unanswered"
+SESSION_STATUS_DAY_FINISHED = "day_finished"
+SESSION_STATUS_COMPLETE = "ema_completed"
 
 
 def get_esm_data(usernames: Collection) -> pd.DataFrame:
@@ -75,17 +82,15 @@ def classify_sessions_adherence(df_esm_preprocessed: pd.DataFrame) -> pd.DataFra
     -------
     some dataframe
     """
-    sessions_grouped = df_esm_preprocessed.groupby(
+    sessions_grouped = df_esm_preprocessed.groupby(GROUP_SESSIONS_BY)
-        ["participant_id", "device_id", "esm_session"]
-    )
 
     df_session_counts = pd.DataFrame(sessions_grouped.count()["id"]).rename(
         columns={"id": "esm_session_count"}
     )
     df_session_counts["session_response"] = np.NaN
 
-    esm_not_answered = sessions_grouped.apply(lambda x: (x.esm_status != 2).any())
+    esm_not_answered = sessions_grouped.apply(lambda x: (x.esm_status != ESM_STATUS_ANSWERED).any())
-    df_session_counts.loc[esm_not_answered, "session_response"] = "esm_unanswered"
+    df_session_counts.loc[esm_not_answered, "session_response"] = SESSION_STATUS_UNANSWERED
 
     non_session = sessions_grouped.apply(
         lambda x: (
@@ -94,12 +99,20 @@ def classify_sessions_adherence(df_esm_preprocessed: pd.DataFrame) -> pd.DataFra
             | (x.esm_user_answer == "DayFinishedSetEvening")  # When would you like to answer the evening EMA?
         ).any()
     )
-    df_session_counts.loc[non_session, "session_response"] = "day_finished"
+    df_session_counts.loc[non_session, "session_response"] = SESSION_STATUS_DAY_FINISHED
+
+    singleton_sessions = (df_session_counts.esm_session_count == 1) & (df_session_counts.session_response.isna())
+    df_session_1 = df_session_counts[singleton_sessions]
+    df_esm_unique_session = df_session_1.join(
+        df_esm_preprocessed.set_index(GROUP_SESSIONS_BY), how="left"
+    )
+    df_esm_unique_session = df_esm_unique_session.assign(session_response=lambda x: x.esm_trigger)["session_response"]
+    df_session_counts.loc[df_esm_unique_session.index, "session_response"] = df_esm_unique_session
 
     finished_sessions = sessions_grouped.apply(
         lambda x: (x.esm_trigger.str.endswith("_last")).any()
     )
-    df_session_counts.loc[finished_sessions, "session_response"] = "esm_finished"
+    df_session_counts.loc[finished_sessions, "session_response"] = SESSION_STATUS_COMPLETE
 
     # TODO Look at evening-evening_last sequence, if everything is caught with finished sessions