"""
import seaborn as sns
import os
import matplotlib.pyplot as plt
from paper_behavior_functions import (figpath, seaborn_style, group_colors,
query_sessions_around_criterion,
institution_map)
# import wrappers etc
from ibl_pipeline import reference, subject, behavior
from dj_tools import plot_psychometric, dj2pandas
# INITIALIZE A FEW THINGS
seaborn_style()
figpath = figpath()
pal = group_colors()
institution_map, col_names = institution_map()
col_names = col_names[:-1]
# ================================= #
# GET DATA FROM TRAINED ANIMALS
# ================================= #
use_sessions, use_days = query_sessions_around_criterion(
criterion='trained', days_from_criterion=[2, 0], as_dataframe=False)
# restrict by list of dicts with uuids for these sessions
b = use_sessions * subject.Subject * subject.SubjectLab * reference.Lab * \
behavior.TrialSet.Trial
# reduce the size of the fetch
b2 = b.proj('institution_short', 'subject_nickname', 'task_protocol',
'trial_stim_contrast_left', 'trial_stim_contrast_right',
'trial_response_choice', 'task_protocol', 'trial_stim_prob_left',
if QUERY is True:
from paper_behavior_functions import query_sessions_around_criterion
from ibl_pipeline import reference, subject, behavior
use_sessions, _ = query_sessions_around_criterion(criterion='biased',
days_from_criterion=[1, 3])
use_sessions = use_sessions & 'task_protocol LIKE "%biased%"' # only get biased sessions
b = (use_sessions * subject.Subject * subject.SubjectLab * reference.Lab
* behavior.TrialSet.Trial)
b2 = b.proj('institution_short', 'subject_nickname', 'task_protocol',
'trial_stim_contrast_left', 'trial_stim_contrast_right', 'trial_response_choice',
'task_protocol', 'trial_stim_prob_left', 'trial_feedback_type',
'trial_response_time', 'trial_stim_on_time', 'time_zone')
bdat = b2.fetch(order_by='institution_short, subject_nickname, session_start_time, trial_id',
format='frame').reset_index()
behav = dj2pandas(bdat)
behav['institution_code'] = behav.institution_short.map(institution_map()[0])
else:
behav = load_csv('Fig4.csv')
biased_fits = pd.DataFrame()
for i, nickname in enumerate(behav['subject_nickname'].unique()):
if np.mod(i+1, 10) == 0:
print('Processing data of subject %d of %d' % (i+1,
len(behav['subject_nickname'].unique())))
# Get lab and timezone
lab = behav.loc[behav['subject_nickname'] == nickname, 'institution_code'].unique()[0]
time_zone = behav.loc[behav['subject_nickname'] == nickname, 'time_zone'].unique()[0]
if (time_zone == 'Europe/Lisbon') or (time_zone == 'Europe/London'):
time_zone_number = 0
elif time_zone == 'America/New_York':
# Query sessions
use_subjects = query_subjects()
ses = (use_subjects * behavior_analysis.SessionTrainingStatus * behavior_analysis.PsychResults
& 'training_status = "in_training" OR training_status = "untrainable"').proj(
'subject_nickname', 'n_trials_stim', 'institution_short').fetch(format='frame')
ses = ses.reset_index()
ses['n_trials'] = [sum(i) for i in ses['n_trials_stim']]
# Construct dataframe
training_time = pd.DataFrame(columns=['sessions'], data=ses.groupby('subject_nickname').size())
training_time['trials'] = ses.groupby('subject_nickname').sum()
training_time['lab'] = ses.groupby('subject_nickname')['institution_short'].apply(list).str[0]
# Change lab name into lab number
training_time['lab_number'] = training_time.lab.map(institution_map()[0])
training_time = training_time.sort_values('lab_number')
# statistics
# Test normality
_, normal = stats.normaltest(training_time['sessions'])
if normal < 0.05:
kruskal = stats.kruskal(*[group['sessions'].values
for name, group in training_time.groupby('lab')])
if kruskal[1] < 0.05: # Proceed to posthocs
posthoc = sp.posthoc_dunn(training_time, val_col='sessions',
group_col='lab_number')
else:
anova = stats.f_oneway(*[group['sessions'].values
for name, group in training_time.groupby('lab')])
if anova[1] < 0.05:
sessions
& 'subject_nickname = "%s"' % nickname).fetch('institution_short')[0]
learned.loc[i, 'perf_easy'] = perf_easy
learned.loc[i, 'reaction_time'] = reaction_time
learned.loc[i, 'threshold'] = fit_result.loc[0, 'threshold']
learned.loc[i, 'bias'] = fit_result.loc[0, 'bias']
learned.loc[i, 'lapse_low'] = fit_result.loc[0, 'lapselow']
learned.loc[i, 'lapse_high'] = fit_result.loc[0, 'lapsehigh']
learned.loc[i, 'n_trials'] = ntrials_perday
learned.loc[i, 'n_sessions'] = nsessions
# Drop mice with faulty RT
learned = learned[learned['reaction_time'].notnull()]
# Change lab name into lab number
learned['lab_number'] = learned.lab.map(institution_map()[0])
learned = learned.sort_values('lab_number')
# Convert to float
learned[[
'perf_easy', 'reaction_time', 'threshold', 'n_sessions', 'bias',
'lapse_low', 'lapse_high'
]] = learned[[
'perf_easy', 'reaction_time', 'threshold', 'n_sessions', 'bias',
'lapse_low', 'lapse_high'
]].astype(float)
# Add all mice to dataframe seperately for plotting
learned_2 = learned.copy()
learned_2['lab'] = 'All'
learned_2['lab_number'] = 'All'
group_colors, figpath, query_subjects,
FIGURE_WIDTH, FIGURE_HEIGHT)
from ibl_pipeline.analyses import behavior as behavior_analysis
# Settings
fig_path = figpath()
bin_centers = np.arange(3, 40, 3)
bin_size = 5
seaborn_style()
# Load in data
use_subjects = query_subjects()
behav = (use_subjects *
behavior_analysis.BehavioralSummaryByDate).fetch(format='frame')
behav['lab'] = behav['institution_short']
behav['lab_number'] = behav.lab.map(institution_map()[0])
# Get variability over days
mean_days = pd.DataFrame(columns=bin_centers,
index=np.unique(behav['lab_number']))
std_days = pd.DataFrame(columns=bin_centers,
index=np.unique(behav['lab_number']))
for i, day in enumerate(bin_centers):
this_behav = behav[(behav['training_day'] > day - np.floor(bin_size / 2))
&
(behav['training_day'] < day + np.floor(bin_size / 2))]
mean_days[day] = this_behav.groupby(
'lab_number').mean()['performance_easy']
std_days[day] = this_behav.groupby('lab_number').std()['performance_easy']
# Plot output
& 'task_protocol LIKE "%biased%"').fetch('KEY')
ses = ((use_sessions & 'task_protocol LIKE "%biased%"') * subject.Subject *
subject.SubjectLab * reference.Lab *
(behavior.TrialSet.Trial & session_keys))
ses = ses.proj(
'institution_short', 'subject_nickname', 'task_protocol',
'trial_stim_contrast_left', 'trial_stim_contrast_right',
'trial_response_choice', 'task_protocol', 'trial_stim_prob_left',
'trial_feedback_type', 'trial_response_time', 'trial_stim_on_time',
'time_zone').fetch(
order_by=
'institution_short, subject_nickname,session_start_time, trial_id',
format='frame').reset_index()
behav = dj2pandas(ses)
behav['institution_code'] = behav.institution_short.map(
institution_map()[0])
else:
behav = load_csv('Fig4.csv')
biased_fits = pd.DataFrame()
for i, nickname in enumerate(behav['subject_nickname'].unique()):
if np.mod(i + 1, 10) == 0:
print('Processing data of subject %d of %d' %
(i + 1, len(behav['subject_nickname'].unique())))
# Get lab and timezone
lab = behav.loc[behav['subject_nickname'] == nickname,
'institution_code'].unique()[0]
time_zone = behav.loc[behav['subject_nickname'] == nickname,
'time_zone'].unique()[0]
Guido Meijer
Jul 1, 2020
"""
from os import mkdir
from os.path import join, isdir
import pandas as pd
from paper_behavior_functions import (query_subjects,
query_sessions_around_criterion,
institution_map, CUTOFF_DATE)
from ibl_pipeline.analyses import behavior as behavioral_analyses
from ibl_pipeline import reference, subject, behavior, acquisition
from dj_tools import dj2pandas
# Get map of lab number to institute
institution_map, _ = institution_map()
# create data directory if it doesn't exist yet
if not isdir('data'):
mkdir('data')
# Create list of subjects used
subjects = query_subjects(as_dataframe=True)
subjects.to_csv(join('data', 'subjects.csv'))
# %%=============================== #
# FIGURE 2
# ================================= #
print('Starting figure 2..')
# Query list of subjects to use
def decoding(data, labels, clf):
kf = LeaveOneOut()
y_pred = np.empty(len(labels), dtype='<U5')
for train_index, test_index in kf.split(data):
clf.fit(data[train_index], labels[train_index])
y_pred[test_index] = clf.predict(data[test_index])
f1 = f1_score(labels, y_pred, average='micro')
cm = confusion_matrix(labels, y_pred)
return f1, cm
# %% Query sessions
if QUERY is True:
behav = query_session_around_performance()
behav['institution_code'] = behav.institution_short.map(institution_map()[0])
else:
behav = load_csv('Fig3.csv')
# Create dataframe with behavioral metrics of all mice
learned = pd.DataFrame(columns=['mouse', 'lab', 'perf_easy', 'n_trials',
'threshold', 'bias', 'reaction_time',
'lapse_low', 'lapse_high', 'time_zone', 'UTC'])
for i, nickname in enumerate(behav['subject_nickname'].unique()):
if np.mod(i+1, 10) == 0:
print('Processing data of subject %d of %d' % (i+1,
len(behav['subject_nickname'].unique())))
# Get the trials of the sessions around criterion for this subject
trials = behav[behav['subject_nickname'] == nickname]
