def calc_bonuses(data):
bonus_experiments = [
'angling_risk_task_always_sunny', 'two_stage_decision',
'columbia_card_task_hot', 'columbia_card_task_cold',
'hierarchical_rule', 'kirby', 'discount_titrate', 'bickel_titrator'
]
bonuses = []
for row in data.iterrows():
if row[1]['experiment_exp_id'] in bonus_experiments:
try:
df = extract_row(row[1], clean=False)
except TypeError:
bonuses.append(np.nan)
continue
bonus = df.iloc[-1].get('performance_var', 'error')
if pd.isnull(bonus):
bonus = df.iloc[-5].get('performance_var', 'error')
if not isinstance(bonus, (int, float)):
bonus = json.loads(bonus)['amount']
bonuses.append(bonus)
else:
bonuses.append(np.nan)
data.loc[:, 'bonus'] = bonuses
data.loc[:, 'bonus_zscore'] = data['bonus']
means = data.groupby('experiment_exp_id').bonus.mean()
std = data.groupby('experiment_exp_id').bonus.std()
for exp in bonus_experiments:
data.loc[data.experiment_exp_id == exp,
'bonus_zscore'] = (data[data.experiment_exp_id == exp].bonus -
means[exp]) / std[exp]
def calc_bonuses(data):
bonus_experiments = ['angling_risk_task_always_sunny', 'two_stage_decision',
'columbia_card_task_hot', 'columbia_card_task_cold', 'hierarchical_rule',
'kirby','discount_titrate','bickel_titrator']
bonuses = []
for row in data.iterrows():
if row[1]['experiment_exp_id'] in bonus_experiments:
try:
df = extract_row(row[1], clean = False)
except TypeError:
bonuses.append(np.nan)
continue
bonus = df.iloc[-1].get('performance_var','error')
if pd.isnull(bonus):
bonus = df.iloc[-5].get('performance_var','error')
if not isinstance(bonus,(int,float)):
bonus = json.loads(bonus)['amount']
bonuses.append(bonus)
else:
bonuses.append(np.nan)
data.loc[:,'bonus'] = bonuses
data.loc[:,'bonus_zscore'] = data['bonus']
means = data.groupby('experiment_exp_id').bonus.mean()
std = data.groupby('experiment_exp_id').bonus.std()
for exp in bonus_experiments:
data.loc[data.experiment_exp_id == exp,'bonus_zscore'] = (data[data.experiment_exp_id == exp].bonus-means[exp])/std[exp]
def calc_time_taken(data):
'''Selects a worker (or workers) from results object and sorts based on experiment and time of experiment completion
'''
instruction_lengths = []
exp_lengths = []
for i, row in data.iterrows():
if row['experiment_template'] == 'jspsych':
exp_data = extract_row(row, clean=False)
#ensure there is a time elapsed variable
assert 'time_elapsed' in exp_data.iloc[-1].keys(), \
'"time_elapsed" not found for at least one dataset in these results'
#sum time taken on instruction trials
instruction_length = exp_data[
(exp_data.trial_id == 'instruction') |
(exp_data.trial_id == 'instructions')]['rt'].sum()
#Set the length of the experiment to the time elapsed on the last
#jsPsych trial
experiment_length = exp_data.iloc[-1]['time_elapsed']
instruction_lengths.append(instruction_length / 1000.0)
exp_lengths.append(experiment_length / 1000.0)
else:
instruction_lengths.append(numpy.nan)
exp_lengths.append(numpy.nan)
data.loc[:, 'total_time'] = exp_lengths
data.loc[:, 'instruct_time'] = instruction_lengths
data.loc[:, 'ontask_time'] = data['total_time'] - data['instruct_time']
print('Finished calculating time taken')
def calc_time_taken(data):
'''Selects a worker (or workers) from results object and sorts based on experiment and time of experiment completion
'''
instruction_lengths = []
exp_lengths = []
for row in data.iterrows():
if row[1]['experiment_template'] == 'jspsych':
try:
exp_data = extract_row(row[1],clean = False)
except TypeError:
exp_lengths.append(numpy.nan)
instruction_lengths.append(numpy.nan)
continue
#ensure there is a time elapsed variable
assert 'time_elapsed' in exp_data.iloc[-1].keys(), \
'"time_elapsed" not found for at least one dataset in these results'
#sum time taken on instruction trials
instruction_length = exp_data[(exp_data.trial_id == 'instruction') | (exp_data.trial_id == 'instructions')]['rt'].sum()
#Set the length of the experiment to the time elapsed on the last
#jsPsych trial
experiment_length = exp_data.iloc[-1]['time_elapsed']
instruction_lengths.append(instruction_length/1000.0)
exp_lengths.append(experiment_length/1000.0)
else:
instruction_lengths.append(numpy.nan)
exp_lengths.append(numpy.nan)
data.loc[:,'total_time'] = exp_lengths
data.loc[:,'instruct_time'] = instruction_lengths
data.loc[:,'ontask_time'] = data['total_time'] - data['instruct_time']
print('Finished calculating time taken')
def get_post_task_responses(data):
question_responses = [numpy.nan] * len(data)
for i, row in data.iterrows():
if row['experiment_template'] == 'jspsych':
row_data = extract_row(row, clean=False)
if row_data.iloc[-2].get('trial_id') =='post task questions' and \
'responses' in row_data.iloc[-2].keys():
question_responses[i] = (row_data.iloc[-2]['responses'])
data.loc[:, 'post_task_responses'] = question_responses
print('Finished extracting post task responses')
def get_credit(data):
credit_array = []
for i,row in data.iterrows():
if row['experiment_template'] in 'jspsych':
df = extract_row(row, clean = False)
credit_var = df.iloc[-1].get('credit_var',np.nan)
if credit_var != None:
credit_array.append(float(credit_var))
else:
credit_array.append(np.nan)
else:
credit_array.append(np.nan)
data.loc[:,'credit'] = credit_array
def get_credit(data):
credit_array = []
for i, row in data.iterrows():
if row['experiment_template'] in 'jspsych':
df = extract_row(row, clean=False)
credit_var = df.iloc[-1].get('credit_var', np.nan)
if credit_var != None:
credit_array.append(float(credit_var))
else:
credit_array.append(np.nan)
else:
credit_array.append(np.nan)
data.loc[:, 'credit'] = credit_array
def get_post_task_responses(data):
question_responses = [numpy.nan] * len(data)
for i,row in zip(range(0, len(data)),data.iterrows()):
if row[1]['experiment_template'] == 'jspsych':
try:
row_data = extract_row(row[1],clean = False)
except TypeError:
continue
if row_data.iloc[-2].get('trial_id') =='post task questions' and \
'responses' in row_data.iloc[-2].keys():
question_responses[i]= (row_data.iloc[-2]['responses'])
data.loc[:,'post_task_responses'] = question_responses
print('Finished extracting post task responses')
def get_post_task_responses(data):
question_responses = [numpy.nan] * len(data)
for i,row in zip(range(0, len(data)),data.iterrows()):
if row[1]['experiment_template'] == 'jspsych':
try:
row_data = extract_row(row[1],clean = False)
except TypeError:
continue
if row_data.iloc[-2].get('trial_id') =='post task questions' and \
'responses' in row_data.iloc[-2].keys():
question_responses[i]= (row_data.iloc[-2]['responses'])
data.loc[:,'post_task_responses'] = question_responses
print('Finished extracting post task responses')