def sign_barplot(df, val_col, group_col, test="HSD"):
if test == "HSD":
result_df = tukey_hsd(df, val_col, group_col)
if test == "tukey":
result_df = sp.posthoc_tukey(df, val_col, group_col)
if test == "ttest":
result_df = sp.posthoc_ttest(df, val_col, group_col)
if test == "scheffe":
result_df = sp.posthoc_scheffe(df, val_col, group_col)
if test == "dscf":
result_df = sp.posthoc_dscf(df, val_col, group_col)
if test == "conover":
result_df = sp.posthoc_conover(df, val_col, group_col)
#マッピングのプロファイル
fig, ax = plt.subplots(1, 2, figsize=(10, 6))
cmap = ['1', '#fb6a4a', '#08306b', '#4292c6', '#c6dbef']
heatmap_args = {
'cmap': cmap,
'linewidths': 0.25,
'linecolor': '0.5',
'clip_on': False,
'square': True
}
sp.sign_plot(result_df, ax=ax[1], **heatmap_args) #検定結果を描画
sns.barplot(data=df, x=group_col, y=val_col, capsize=0.1,
ax=ax[0]) #使ったデータを描画
plt.show()
def anova_posthoc_tests(benchmark_snapshot_df):
"""Returns p-value tables for various ANOVA posthoc tests.
Results should considered only if ANOVA test rejects null hypothesis.
"""
common_args = {
'a': benchmark_snapshot_df,
'group_col': 'fuzzer',
'val_col': 'edges_covered',
'sort': True
}
p_adjust = 'holm'
posthoc_tests = {}
posthoc_tests['student'] = sp.posthoc_ttest(**common_args,
equal_var=False,
p_adjust=p_adjust)
posthoc_tests['turkey'] = sp.posthoc_tukey(**common_args)
return posthoc_tests
def post_hoc_df(df, Y_col, X_col, posthoc="tukey", alpha=0.05):
"""
Returns a df with pairwise comparisons with reject column calculated according to alpha
TODO: Add more posthoc tests to this function
"""
if posthoc == "Statsmodels_tukey":
comp = multi.MultiComparison(df[Y_col], df['comb'])
results = comp.tukeyhsd(alpha=alpha)
results = pd.DataFrame(data=results._results_table.data[1:],
columns=results._results_table.data[0])
if posthoc == "dunn":
results = scikit_results_munger(
sp.posthoc_dunn(df,
val_col=Y_col,
group_col=X_col,
p_adjust='holm'), alpha)
if posthoc == "tukey":
results = scikit_results_munger(
sp.posthoc_tukey(df, val_col=Y_col, group_col=X_col), alpha)
return results
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:
posthoc = sp.posthoc_tukey(training_time, val_col='sessions',
group_col='lab_number')
# %% PLOT
# Set figure style and color palette
use_palette = [[0.6, 0.6, 0.6]] * len(np.unique(training_time['lab']))
use_palette = use_palette + [[1, 1, 0.2]]
lab_colors = group_colors()
# Add all mice to dataframe seperately for plotting
training_time_no_all = training_time.copy()
training_time_no_all.loc[training_time_no_all.shape[0] + 1, 'lab_number'] = 'All'
training_time_all = training_time.copy()
training_time_all['lab_number'] = 'All'
training_time_all = training_time.append(training_time_all)
print(
levene(all_data["Gaussian"].tolist(), all_data["Hessian"].tolist(),
all_data["Laplacian"].tolist(), all_data["Ilastik"].tolist(),
all_data["MitoSegNet"].tolist(),
all_data["Finetuned\nFiji U-Net"].tolist()))
print(
f_oneway(all_data["Gaussian"].tolist(), all_data["Hessian"].tolist(),
all_data["Laplacian"].tolist(), all_data["Ilastik"].tolist(),
all_data["MitoSegNet"].tolist(),
all_data["Finetuned\nFiji U-Net"].tolist()))
x = all_data
x = x.melt(var_name='groups', value_name='values')
pht = posthoc_tukey(x, val_col='values', group_col='groups')
print(pht)
#pht.to_excel("fod_posthoc.xlsx")
"""
for seg in seg_list:
if seg != "MitoSegNet":
print(seg, cohens_d(all_data[seg], all_data["MitoSegNet"]))
"""
#n = sb.violinplot(data=all_data, color="white", inner=None)#.set(ylabel="Percent of wrongly\nsegmented objects")
n = sb.swarmplot(data=all_data, color="black")
sb.boxplot(data=all_data, color="white", fliersize=0)
n.set_ylabel("Missing objects", fontsize=32)
#n.set_ylabel("Percent of missing objects", fontsize=18)
group[var].values for name, group in test_df.groupby('lab_number')
])
if test[1] < 0.05: # Proceed to posthocs
posthoc = sp.posthoc_dunn(test_df,
val_col=var,
group_col='lab_number')
else:
posthoc = np.nan
else:
test_type = 'anova'
test = stats.f_oneway(*[
group[var].values for name, group in test_df.groupby('lab_number')
])
if test[1] < 0.05:
posthoc = sp.posthoc_tukey(test_df,
val_col=var,
group_col='lab_number')
else:
posthoc = np.nan
posthoc_tests['posthoc_' + str(var)] = posthoc
stats_tests.loc[i, 'variable'] = var
stats_tests.loc[i, 'test_type'] = test_type
stats_tests.loc[i, 'p_value'] = test[1]
# Z-score data
learned_zs = pd.DataFrame()
learned_zs['lab'] = learned['lab']
learned_zs['lab_number'] = learned['lab_number']
learned_zs['Performance'] = stats.zscore(learned['perf_easy'])
learned_zs['Threshold'] = stats.zscore(learned['threshold'])
group[var].values for name, group in learned.groupby('lab_number')
])
if test[1] < 0.05: # Proceed to posthocs
posthoc = sp.posthoc_dunn(learned,
val_col=var,
group_col='lab_number')
else:
posthoc = np.nan
else:
test_type = 'anova'
test = stats.f_oneway(*[
group[var].values for name, group in learned.groupby('lab_number')
])
if test[1] < 0.05:
posthoc = sp.posthoc_tukey(learned,
val_col=var,
group_col='lab_number')
else:
posthoc = np.nan
posthoc_tests['posthoc_' + str(var)] = posthoc
stats_tests.loc[i, 'variable'] = var
stats_tests.loc[i, 'test_type'] = test_type
stats_tests.loc[i, 'p_value'] = test[1]
if (stats.normaltest(learned['n_trials'])[1] < 0.05
or stats.normaltest(learned['reaction_time'])[1] < 0.05):
test_type = 'spearman'
correlation_coef, correlation_p = stats.spearmanr(learned['reaction_time'],
learned['n_trials'])
if (stats.normaltest(learned['n_trials'])[1] > 0.05
_, normal = stats.normaltest(test_fits[var])
if normal < 0.05:
test_type = 'kruskal'
test = stats.kruskal(
*[group[var].values for name, group in test_fits.groupby('lab')])
if test[1] < 0.05: # Proceed to posthocs
posthoc = sp.posthoc_dunn(test_fits, val_col=var, group_col='lab')
else:
posthoc = np.nan
else:
test_type = 'anova'
test = stats.f_oneway(
*[group[var].values for name, group in test_fits.groupby('lab')])
if test[1] < 0.05:
posthoc = sp.posthoc_tukey(test_fits, val_col=var, group_col='lab')
else:
posthoc = np.nan
posthoc_tests['posthoc_' + str(var)] = posthoc
stats_tests.loc[i, 'variable'] = var
stats_tests.loc[i, 'test_type'] = test_type
stats_tests.loc[i, 'p_value'] = test[1]
# Correct for multiple tests
stats_tests['p_value'] = multipletests(stats_tests['p_value'])[1]
# %% Prepare for plotting
# Sort by lab number
biased_fits = biased_fits.sort_values('lab')
_, normal = stats.normaltest(biased_fits[var])
if normal < 0.05:
test_type = 'kruskal'
test = stats.kruskal(*[group[var].values
for name, group in biased_fits.groupby('lab')])
if test[1] < 0.05: # Proceed to posthocs
posthoc = sp.posthoc_dunn(biased_fits, val_col=var, group_col='lab')
else:
posthoc = np.nan
else:
test_type = 'anova'
test = stats.f_oneway(*[group[var].values
for name, group in biased_fits.groupby('lab')])
if test[1] < 0.05:
posthoc = sp.posthoc_tukey(biased_fits, val_col=var, group_col='lab')
else:
posthoc = np.nan
posthoc_tests['posthoc_'+str(var)] = posthoc
stats_tests.loc[i, 'variable'] = var
stats_tests.loc[i, 'test_type'] = test_type
stats_tests.loc[i, 'p_value'] = test[1]
# Correct for multiple tests
stats_tests['p_value'] = multipletests(stats_tests['p_value'])[1]
# Test between left/right blocks
for i, var in enumerate(['threshold', 'lapselow', 'lapsehigh', 'bias']):
stats_tests.loc[stats_tests.shape[0] + 1, 'variable'] = '%s_blocks' % var
stats_tests.loc[stats_tests.shape[0], 'test_type'] = 'wilcoxon'
all_data["Laplacian"].tolist(), all_data["Ilastik"].tolist(),
all_data["MitoSegNet"].tolist(),
all_data["Finetuned\nFiji U-Net"].tolist()))
x = [
all_data["Gaussian"].tolist(), all_data["Hessian"].tolist(),
all_data["Laplacian"].tolist(), all_data["Ilastik"].tolist(),
all_data["MitoSegNet"].tolist(),
all_data["Finetuned\nFiji U-Net"].tolist()
]
#print(posthoc_tukey(x))
x = all_data
x = x.melt(var_name='groups', value_name='values')
print(posthoc_tukey(x, val_col='values', group_col='groups'))
print("\n")
print(np.average(all_data["Gaussian"]))
print(np.average(all_data["Hessian"]))
print(np.average(all_data["Laplacian"]))
print(np.average(all_data["Ilastik"]))
print(np.average(all_data["MitoSegNet"]))
print(np.average(all_data["Finetuned\nFiji U-Net"]))
print("\n")
#print(kruskal(all_data["Gaussian"].tolist(), all_data["Hessian"].tolist(), all_data["Laplacian"].tolist(),
# all_data["Ilastik"].tolist(), all_data["MitoSegNet"].tolist(), all_data["Finetuned\nFiji U-Net"].tolist()))
co.summary() # ### another library for post-hoc tests # #### # https://scikit-posthocs.readthedocs.io/en/latest/posthocs_api/ # In[27]: import scikit_posthocs as sk_ph # In[28]: sk_ph.posthoc_tukey_hsd(df['libido'], df['dose']) # In[29]: sk_ph.posthoc_tukey(df, val_col='libido', group_col='dose') # ## Robust Post-hoc test # In[30]: sk_ph.posthoc_wilcoxon(df, val_col='libido', group_col='dose') # #### # from above table it seems that groups (1,3) and (2,3) are significant. # # In[31]: anova_table # In[32]: