stress_at_work_analysis/exploration/expl_stress_event.py

# -*- coding: utf-8 -*-
# ---
# jupyter:
#   jupytext:
#     formats: ipynb,py:percent
#     text_representation:
#       extension: .py
#       format_name: percent
#       format_version: '1.3'
#       jupytext_version: 1.13.0
#   kernelspec:
#     display_name: straw2analysis
#     language: python
#     name: straw2analysis
# ---

# %%
import os
import sys
import datetime
import math

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 *
from features.esm_JCQ import *
from features.esm_SAM import *

from IPython.core.interactiveshell import InteractiveShell
InteractiveShell.ast_node_interactivity = "all"

# %%
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)


# %% [markdown]
# Investigate stressfulness events
# %%
extracted_ers = df_esm_preprocessed.groupby(["device_id", "esm_session"])['timestamp'].apply(lambda x: math.ceil((x.max() - x.min()) / 1000)).reset_index().rename(columns={'timestamp': 'session_length'}) # questionnaire length
extracted_ers = extracted_ers[extracted_ers["session_length"] <= 15 * 60].reset_index(drop=True) # ensure that the longest duration of the questionnaire answering is 15 min
session_start_timestamp = df_esm_preprocessed.groupby(['device_id', 'esm_session'])['timestamp'].min().to_frame().rename(columns={'timestamp': 'session_start_timestamp'}) # questionnaire start timestamp
session_end_timestamp = df_esm_preprocessed.groupby(['device_id', 'esm_session'])['timestamp'].max().to_frame().rename(columns={'timestamp': 'session_end_timestamp'}) # questionnaire end timestamp
se_time = df_esm_preprocessed[df_esm_preprocessed.questionnaire_id == 90.].set_index(['device_id', 'esm_session'])['esm_user_answer'].to_frame().rename(columns={'esm_user_answer': 'se_time'})
se_duration = df_esm_preprocessed[df_esm_preprocessed.questionnaire_id == 91.].set_index(['device_id', 'esm_session'])['esm_user_answer'].to_frame().rename(columns={'esm_user_answer': 'se_duration'})

# Make se_durations to the appropriate lengths

# Extracted 3 targets that will be transfered in the csv file to the cleaning script. 
df_esm_preprocessed[df_esm_preprocessed.questionnaire_id == 87.].columns
se_stressfulness_event_tg = df_esm_preprocessed[df_esm_preprocessed.questionnaire_id == 87.].set_index(['device_id', 'esm_session'])['esm_user_answer'].to_frame().rename(columns={'esm_user_answer': 'appraisal_stressfulness_event'})

# All relevant features are joined by inner join to remove standalone columns (e.g., stressfulness event target has larger count)
extracted_ers = extracted_ers.join(session_start_timestamp, on=['device_id', 'esm_session'], how='inner') \
                                .join(session_end_timestamp, on=['device_id', 'esm_session'], how='inner') \
                                .join(se_stressfulness_event_tg, on=['device_id', 'esm_session'], how='inner') \
                                .join(se_time, on=['device_id', 'esm_session'], how='left') \
                                .join(se_duration, on=['device_id', 'esm_session'], how='left') \

# Filter-out the sessions that are not useful. Because of the ambiguity this excludes: 
# (1) straw event times that are marked as "0 - I don't remember"
# (2) straw event durations that are marked as "0 - I don't remember" 
extracted_ers = extracted_ers[(~extracted_ers.se_time.astype(str).str.startswith("0 - ")) & (~extracted_ers.se_duration.astype(str).str.startswith("0 - ")) & (~extracted_ers.se_duration.astype(str).str.startswith("Removed "))]
extracted_ers.reset_index(drop=True, inplace=True)

# Add default duration in case if participant answered that no stressful event occured

# Prepare data to fit the data structure in the CSV file ...
# Add the event time as the start of the questionnaire if no stress event occured
extracted_ers['se_time'] = extracted_ers['se_time'].fillna(extracted_ers['session_start_timestamp'])
# Type could be an int (timestamp [ms]) which stays the same, and datetime str which is converted to timestamp in miliseconds 
extracted_ers['event_timestamp'] = extracted_ers['se_time'].apply(lambda x: x if isinstance(x, int) else pd.to_datetime(x).timestamp() * 1000).astype('int64')
extracted_ers['shift_direction'] = -1

""">>>>> begin section (could be optimized) <<<<<"""

# Checks whether the duration is marked with "1 - It's still ongoing" which means that the end of the current questionnaire
# is taken as end time of the segment. Else the user input duration is taken. 
extracted_ers['temp_duration'] = extracted_ers['se_duration']
extracted_ers['se_duration'] = \
    np.where(
        extracted_ers['se_duration'].astype(str).str.startswith("1 - "),
        extracted_ers['session_end_timestamp'] - extracted_ers['event_timestamp'], 
        extracted_ers['se_duration']
    )

# This converts the rows of timestamps in miliseconds and the rows with datetime... to timestamp in seconds.

extracted_ers['se_duration'] = \
    extracted_ers['se_duration'].apply(lambda x: math.ceil(x / 1000) if isinstance(x, int) else abs(pd.to_datetime(x).hour * 60 + pd.to_datetime(x).minute) * 60)

# Check whether min se_duration is at least the same duration as the ioi. Filter-out the rest.

""">>>>> end section <<<<<"""

# %% [markdown]
# Count negative values of duration
print("Count all:", extracted_ers[['se_duration', 'temp_duration', 'session_end_timestamp', 'event_timestamp']].shape[0])
print("Count stressed:", extracted_ers[(~extracted_ers['se_duration'].isna())][['se_duration', 'temp_duration', 'session_end_timestamp', 'event_timestamp']].shape[0])
print("Count negative durations (invalid se_time user input):", extracted_ers[extracted_ers['se_duration'] < 0][['se_duration', 'temp_duration', 'session_end_timestamp', 'event_timestamp']].shape[0])
print("Count 0 durations:", extracted_ers[extracted_ers['se_duration'] == 0][['se_duration', 'temp_duration', 'session_end_timestamp', 'event_timestamp']].shape[0])
extracted_ers[extracted_ers['se_duration'] <= 0][['se_duration', 'temp_duration', 'session_end_timestamp', 'event_timestamp']].shape[0]
extracted_ers[(~extracted_ers['se_duration'].isna()) & (extracted_ers['se_duration'] <= 0)][['se_duration', 'temp_duration', 'session_end_timestamp', 'event_timestamp']]

ax = extracted_ers.hist(column='se_duration', bins='auto', grid=False, figsize=(12,8), color='#86bf91', zorder=2, rwidth=0.9)
hist, bin_edges = np.histogram(extracted_ers['se_duration'].dropna())
hist
bin_edges

extracted_ers = extracted_ers[extracted_ers['se_duration'] >= 0]

# %%
# bins = [-100000000, 0, 0.0000001, 1200, 7200, 100000000] #'neg', 'zero', '<20min', '2h', 'high_pos'  ..... right=False
bins = [-100000000, -0.0000001, 0, 300, 600, 1200, 3600, 7200, 14400, 1000000000] # 'neg', 'zero', '5min', '10min', '20min', '1h', '2h', '4h', 'more'

extracted_ers['bins'], edges = pd.cut(extracted_ers.se_duration, bins=bins, labels=['neg', 'zero', '5min', '10min', '20min', '1h', '2h', '4h', 'more'], retbins=True, right=True) #['low', 'medium', 'high']
sns.displot(
    data=extracted_ers.dropna(),
    x="bins",
    binwidth=0.1,
)

# %% [markdown]
extracted_ers[extracted_ers['session_end_timestamp'] - extracted_ers['event_timestamp'] >= 0]
extracted_ers['se_time'].value_counts()
pd.set_option('display.max_rows', 100)
# Tukaj nas zanima, koliko so oddaljeni časi stresnega dogodka od konca vprašalnika. 
extracted_ers = extracted_ers[~extracted_ers['se_duration'].isna()] # Remove no stress events
extracted_ers['diff_se_time_session_end'] = (extracted_ers['session_end_timestamp'] - extracted_ers['event_timestamp'])

print("Count all:", extracted_ers[['se_duration', 'temp_duration', 'session_start_timestamp', 'event_timestamp']].shape[0])
print("Count negative durations:", extracted_ers[extracted_ers['diff_se_time_session_end'] < 0][['se_duration', 'temp_duration', 'session_start_timestamp', 'event_timestamp']])
print("Count 0 durations:", extracted_ers[extracted_ers['diff_se_time_session_end'] == 0][['se_duration', 'temp_duration', 'session_start_timestamp', 'event_timestamp']].shape[0])

extracted_ers[extracted_ers['diff_se_time_session_end'] < 0]['diff_se_time_session_end']
# extracted_ers = extracted_ers[(extracted_ers['diff_se_time_session_end'] > 0)]
bins2 = [-100000, 0, 300, 600, 1200, 3600, 7200, 14400, 1000000000] # 'zero', '5min', '10min', '20min', '1h', '2h', '4h', 'more'
extracted_ers['bins2'], edges = pd.cut(extracted_ers.diff_se_time_session_end, bins=bins2, labels=['neg_zero', '5min', '10min', '20min', '1h', '2h', '4h', 'more'], retbins=True, right=True) #['low', 'medium', 'high']
extracted_ers['bins2']
sns.displot(
    data=extracted_ers.dropna(),
    x="bins2",
    binwidth=0.1,
)

extracted_ers.shape
extracted_ers.dropna().shape

print()


# %%
extracted_ers['appraisal_stressfulness_event_num'] = extracted_ers['appraisal_stressfulness_event'].str[0].astype(int)
print("duration-target (corr):", extracted_ers['se_duration'].corr(extracted_ers['appraisal_stressfulness_event_num']))

# %%
# Explore groupby participants?