def test_post_hoc():
np.random.seed(1)
df = pd.read_csv(os.path.join(get_resource_path(), "sample_data.csv"))
model = Lmer("DV ~ IV1*IV3*DV_l + (IV1|Group)", data=df, family="gaussian")
model.fit(
factors={"IV3": ["0.5", "1.0", "1.5"], "DV_l": ["0", "1"]}, summarize=False
)
marginal, contrasts = model.post_hoc(marginal_vars="IV3", p_adjust="dunnet")
assert marginal.shape[0] == 3
assert contrasts.shape[0] == 3
marginal, contrasts = model.post_hoc(marginal_vars=["IV3", "DV_l"])
assert marginal.shape[0] == 6
assert contrasts.shape[0] == 15
def test_post_hoc():
np.random.seed(1)
df = pd.read_csv(os.path.join(get_resource_path(), 'sample_data.csv'))
model = Lmer('DV ~ IV1*IV3*DV_l + (IV1|Group)', data=df, family='gaussian')
model.fit(factors={
'IV3': ['0.5', '1.0', '1.5'],
'DV_l': ['0', '1']
},
summarize=False)
marginal, contrasts = model.post_hoc(marginal_vars='IV3',
p_adjust='dunnet')
assert marginal.shape[0] == 3
assert contrasts.shape[0] == 3
marginal, contrasts = model.post_hoc(marginal_vars=['IV3', 'DV_l'])
assert marginal.shape[0] == 6
assert contrasts.shape[0] == 15
},
ordered=True,
summarize=False,
)
# Get ANOVA table
# We can ignore the note in the output because
# we manually specified polynomial contrasts
print(model.anova())
################################################################################
# Example 1
# ~~~~~~~~~
# Compare each level of IV3 to each other level of IV3, *within* each level of IV4. Use default Tukey HSD p-values.
# Compute post-hoc tests
marginal_estimates, comparisons = model.post_hoc(marginal_vars="IV3",
grouping_vars="IV4")
# "Cell" means of the ANOVA
print(marginal_estimates)
################################################################################
# Pairwise comparisons
print(comparisons)
################################################################################
# Example 2
# ~~~~~~~~~
# Compare each unique IV3,IV4 "cell mean" to every other IV3,IV4 "cell mean" and used FDR correction for multiple comparisons:
# Compute post-hoc tests
#x0 = curve[:15].mean()
curve = curve/x0 - 1
y_df = y_df.append(pd.DataFrame({'metric_type':metric_type, 'fb_type': fb_type, 'subj_id': 's'+str(subj_id), 'channel': ch, 'k': np.linspace(0, 1, 30), 'env': curve+0.0001, 'band': band}), ignore_index=True)
from pymer4.models import Lm, Lmer
from pymer4.utils import get_resource_path
for b, band in enumerate(['alpha', 'beta', 'theta']):
for c, ch in enumerate(CHANNELS):
for m, metric_type in enumerate(['magnitude', 'n_spindles', 'duration', 'amplitude']):
data = y_df.query('metric_type=="{}" & channel=="{}" & band=="{}"'.format(metric_type, ch, band))
model = Lmer('env ~ k:fb_type + (1 |subj_id)', data=data, )
model.fit(factors={'fb_type': ['FB0', 'FB250', 'FB500', 'FBMock']})
a = model.post_hoc('k', 'fb_type')[1]
a['channel'] = ch
a['metric_type'] = metric_type
a['band'] = band
a['P-val-full'] = stats.t.sf(a['T-stat'], 9)
if c==0 and m==0 and b==0:
all_stats_df = a.copy()
else:
all_stats_df = all_stats_df.append(a, ignore_index=True)
print(ch, metric_type)
from mne.stats import fdr_correction
data = np.zeros((3, 6, 4, 32))
data_t = np.zeros((3, 6, 4, 32))
stats_df['k'] = stats_df['block_number'].apply(lambda x: unique_blocks.index(x))
stats_df['subj_id_str'] = 's' + stats_df['subj_id'].astype('str')
stats_df = stats_df.query('k < 15')
import seaborn as sns
sns.catplot('fb_type', 'metric', kind='box', col='metric_type', sharey='col',
data=stats_df.query('threshold_factor==2.75').groupby(['subj_id', 'fb_type', 'metric_type']).mean().reset_index())
stats_df = pd.read_pickle('release/data/{}.pkl'.format('channels1_bands1_splitedTrue_thresholds17'))
stats_df = stats_df.query('block_number==4 | block_number==36')
stats_df['block_name'] = stats_df['block_number'].apply(lambda x: 0 if x ==4 else 1)
stats_df['subj_id_str'] = 's' + stats_df['subj_id'].astype('str')
sns.catplot('block_name', 'metric', 'fb_type', kind='point', col='metric_type', sharey='col', data=stats_df.query('threshold_factor==2.75'), dodge=True)
from pymer4.models import Lm, Lmer
metric_type = 'duration'
threshold_factor = 2.75
data = stats_df.query('metric_type=="{}" & threshold_factor=={}'.format(metric_type, threshold_factor)).copy()
print(len(data))
data = data.replace([np.inf, -np.inf], np.nan)
data.loc[:, 'metric'] = data['metric'].fillna(data['metric'].min()).values
model = Lmer('metric ~ block_name:fb_type + (1 |subj_id_str)', data=data)
model.fit(factors={'fb_type': ['FB0', 'FB250', 'FB500', 'FBMock']})
model.post_hoc('block_name', 'fb_type')
'magnitude', 'n_spindles', 'amplitude', 'duration'
]:
data = stats_df.query(
'metric_type=="{}" & threshold_factor=={}'.format(
metric_type, threshold_factor)).copy()
if LOG and metric_type in ['magnitude', 'amplitude']:
model = Lmer('log(metric) ~ k:fb_type + (1 |subj_id_str)',
data=data)
else:
model = Lmer('metric ~ k:fb_type + (1 |subj_id_str)',
data=data)
model.fit(factors={'fb_type': ['FB0', 'FB250', 'FB500', 'FBMock']},
ordered=True,
summarize=False)
print('***', metric_type)
res = model.post_hoc('fb_type')[1][['Contrast', 'T-stat']]
res['Stat'] = res['T-stat']
res['P-value'] = stats.t.sf(res['T-stat'], 9)
res['metric_type'] = metric_type
res['threshold_factor'] = threshold_factor
t_stat_df = t_stat_df.append(res, ignore_index=True)
else:
contrasts = [
'FB0 - FBMock', 'FB250 - FBMock', 'FB500 - FBMock', 'FB0 - FB500',
'FB250 - FB500', 'FB0 - FB250'
]
for threshold_factor in stats_df.threshold_factor.unique():
for metric_type in [
'magnitude', 'n_spindles', 'amplitude', 'duration'
]:
