pair = [pair[1],pair[0]]
a = df_sub[pair[0]].values
b = df_sub[pair[1]].values
ps = resample_ttest_2sample(a,b,500,10000)
results['greater'].append(pair[0])
results['lesser'].append(pair[1])
results['ps_mean'].append(ps.mean())
results['ps_std'].append(ps.std())
results['model'].append(model)
results = pd.DataFrame(results)
temp = []
for modle, df_sub in results.groupby('model'):
idx_sort = np.argsort(df_sub['ps_mean'].values)
df_sub = df_sub.iloc[idx_sort,:]
converter = MCPConverter(df_sub['ps_mean'].values)
d = converter.adjust_many()
df_sub['p_corrected'] = d['bonferroni'].values
temp.append(df_sub)
results = pd.concat(temp)
results_pos = results.copy()
results_pos['exp'] = 'pos'
# epx 2
results = dict(greater = [],
lesser = [],
ps_mean = [],
ps_std = [],
model = [],)
df = att[(att['window'] > 0) & (att['window'] < 4)]
for model,df_sub in df.groupby('model'):
###########################################################################
#############################################################################
############################################################################
pos = pd.read_csv(os.path.join(results_dir,'Att_leave_one_sub_out.csv'))
att = pd.read_csv(os.path.join(results_dir,'Att_leave_one_sub_out.csv'))
combimed = []
n_back = 4
df = pos.copy()
df = df[df['window'] <= 4]
temp = []
for model,df_sub in df.groupby('model'):
df_temp = df_sub.sort_values(by='p_val')
converter = MCPConverter(df_temp['p_val'].values)
df_pvals = converter.adjust_many()
df_temp['p_corrected'] = df_pvals['bonferroni'].values
temp.append(df_temp)
df = pd.concat(temp)
df['experiment'] = 'Probability of Success'
combimed.append(df)
df = att.copy()
df = df[df['window'] <= 4]
temp = []
for model,df_sub in df.groupby('model'):
df_temp = df_sub.sort_values(by='p_val')
converter = MCPConverter(df_temp['p_val'].values)
df_pvals = converter.adjust_many()
df_temp['p_corrected'] = df_pvals['bonferroni'].values
corr,
0,
)
print(corr.shape)
t_test_results['experiment'].append(experiment)
t_test_results['comparison'].append(comparison)
t_test_results['p'].append(p)
t_test_results['t'].append(t)
t_test_results['corr_mean'].append(df_sub['correlation'].values.mean())
t_test_results['corr_std'].append(df_sub['correlation'].values.std())
t_test_results = pd.DataFrame(t_test_results)
temp = []
for experiment, df_sub in t_test_results.groupby(['experiment']):
df_sub = df_sub.sort_values(['p'])
ps = df_sub['p'].values
converter = MCPConverter(pvals=ps)
d = converter.adjust_many()
df_sub['p_corrected'] = d['bonferroni'].values
temp.append(df_sub)
t_test_results = pd.concat(temp)
t_test_results = t_test_results[[
'experiment', 'comparison', 'p_corrected', 't', 'corr_mean', 'corr_std',
'p'
]]
df_full = pd.concat([df, df_chance])
df_full['x'] = 0
g = sns.catplot(
x='x',
y='correlation',
if not os.path.exists(figure_dir):
os.mkdir(figure_dir)
n_sub = {'POS': 15, 'ATT': 16}
df_plot = []
for f in working_data:
f = f.replace('\\', '/')
df = pd.read_csv(f)
df = df.iloc[1:, :]
attr = df['Unnamed: 0'].apply(lambda x: x.split('_')[0])
time = df['Unnamed: 0'].apply(lambda x: int(x.split('_')[1]))
df = df.iloc[:, 1:]
df['Attributes'] = attr
df['time'] = time
df['experiment'] = f.split('/')[-1].split('_')[0]
df = df.sort_values(['sign'])
converter = MCPConverter(df['sign'].values)
d = converter.adjust_many()
df['ps_corrected'] = d['bonferroni'].values
df_plot.append(df)
df_plot = pd.concat(df_plot)
df_plot['star'] = df_plot['ps_corrected'].apply(stars)
df_plot['Attributes'] = df_plot['Attributes'].map({
'awareness': 'awareness',
'confidence': 'confidence',
'correct': 'correctness'
})
res = dict(
experiment=[],
time=[],
t=[],
ps = resample_ttest_2sample(df_sub['score'].values,
df_sub_chance['score'].values,
one_tail=False,
n_ps=1000,
n_permutation=10000)
results['model'].append(model)
results['window'].append(window)
results['ps_mean'].append(ps.mean())
results['ps_std'].append(ps.std())
results = pd.DataFrame(results)
temp = []
for model, df_sub in results.groupby('model'):
idx_sort = np.argsort(df_sub['ps_mean'])
for name in results.columns:
df_sub[name] = df_sub[name].values[idx_sort]
convert = MCPConverter(pvals=df_sub['ps_mean'].values)
df_pvals = convert.adjust_many()
df_sub['ps_corrected'] = df_pvals['bonferroni'].values
temp.append(df_sub)
results = pd.concat(temp)
results.sort_values(['model', 'window'
]).to_csv('../results/Pos_ttest_6_features.csv',
index=False)
##########################################################################
id_vars = [
'model',
'score',
'sub',
'window',
]
)
ttest['model'].append(model)
ttest['window'].append(window)
ttest['ps_mean'].append(np.mean(ps))
ttest['ps_std'].append(np.std(ps))
print('{} window {} {:.3f}'.format(model, window, np.mean(ps)))
d = pd.DataFrame(ttest) # transform a dictionary object to data frame
# now it is the p value correction for multiple comparison
# note that the correction is done within each model along the number of windows
# , and we have 3 models
temp = []
for model, d_ in d.groupby('model'): # for each model
idx_sort = np.argsort(d_['ps_mean'].values)
for name in d_.columns:
d_[name] = d_[name].values[idx_sort]
coverter = MCPConverter(d_['ps_mean'].values # numpy array
) # initialize the functional object
df = coverter.adjust_many() # run the method in the object
d_['ps_corrected'] = df[
'bonferroni'].values # here is one of the 4 correction methods
temp.append(d_)
d = pd.concat(temp)
d.to_csv('../results/Pos_ttest_6_features.csv', index=False)
################################################################################
# use success, awareness, and confidence as features
experiment = 'pos'
df = pd.read_csv(os.path.join(working_dir, '../data/PoSdata.csv'))
df = df[df.columns[1:]]
df.columns = [
'participant', 'blocks', 'trials', 'firstgabor', 'success', 'tilted',
'correct', 'RT_correct', 'awareness', 'RT_awareness', 'confidence',
'RT_confidence'