def alpha_analysis(alpha, idx_onsets):
# get the alpha power for each bin
dict_alpha = {}
dict_alpha['silence'] = alpha[idx_onsets['silence']]
dict_alpha['low density'] = alpha[idx_onsets['low density']]
dict_alpha['medium density'] = alpha[idx_onsets['medium density']]
dict_alpha['high density'] = alpha[idx_onsets['high density']]
# boxplot
fig, ax = subplots()
ax.boxplot(dict_alpha.values())
ax.set_xticklabels(dict_alpha.keys())
title("Distribution of alpha's power for four rythms")
# savefig('results_44100/alpha_power_perf3')
show()
# kruskal_test
print('Alpha Kruskal Test\n', kruskal_test(dict_alpha['silence'], dict_alpha['low density'], dict_alpha['medium density'], dict_alpha['high density']))
# post hoc t test
a = [dict_alpha['silence'], dict_alpha['low density'], dict_alpha['medium density'], dict_alpha['high density']]
print('Alpha Posthoc t-test\n', posthoc_ttest(a))
pass
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
res = sm.stats.anova_lm(model, typ=2)
res.to_csv(tracker, mode="a")
tracker.write("\nPost-hoc Tukey Tests\n")
mc = statsmodels.stats.multicomp.MultiComparison(df['total_score'], df['year'])
mc_results = mc.tukeyhsd()
tracker.write(str(mc_results))
mc = statsmodels.stats.multicomp.MultiComparison(df['total_score'],
df['is_kashmir'])
mc_results = mc.tukeyhsd()
tracker.write(str(mc_results))
df['kashyear'] = df["is_kashmir"].astype(str) + df['year'].astype(str)
tracker.write("\nPost Hoc Student t-yTesting\n")
sp.posthoc_ttest(df, val_col='total_score',
group_col='kashyear').to_csv(tracker, mode="a")
#HYPOTHESIS 2 Kashmir conflict to Kashmir non conflict
tracker.write(
"\n\n\n\nHYPOTHESIS 2: Kashmir-related headlines will have more negative sentiment scores on average in conflict periods than Kashmir-related headlines in non-conflict periods\r\n"
)
rp.summary_cont(df.groupby(['is_kashmir',
'conflict'])['total_score']).to_csv(tracker,
mode="a")
levene = stats.levene(
df['total_score'][(df['conflict'] == "Standoff")
& (df['is_kashmir'] == True)],
df['total_score'][(df['conflict'] == "Mumbai")
& (df['is_kashmir'] == True)],
omega_1 = list(CSI.w1) + list(SSI.w1) + list(SSD.w1)
model = (['CSI'] * 50) + (['SSI'] * 50) + (['SSD'] * 50)
data = pd.DataFrame({'model': model, 'omega_0': omega_0, 'omega_1': omega_1})
# check if any of the means is significantly different from the rest
lm = ols('omega_0 ~ model', data=data).fit()
table = sm.stats.anova_lm(lm)
print(table)
# post-hoc test to see if CSI mean is significantly higher
print('omega_0')
print(
sp.posthoc_ttest(data,
val_col='omega_0',
group_col='model',
p_adjust='bonferroni'))
print('\nomega_1')
print(
sp.posthoc_ttest(data,
val_col='omega_1',
group_col='model',
p_adjust='bonferroni'))
#%% Load number of amino acids per site
CSI, SSI, SSD = num_aa_per_site(protein)
one = list(CSI[:, 0]) + list(SSI[:, 0]) + list(SSD[:, 0])
five = list(np.sum(CSI[:, 4:], axis=1)) + list(np.sum(
SSI[:, 4:], axis=1)) + list(np.sum(SSD[:, 4:], axis=1))
def calculate_p_values_groups(self, measure, merged_df, figures_dir, affix, plot=True):
merged_df = merged_df[merged_df[measure].notnull()]
p_values = sp.posthoc_ttest(merged_df, val_col=measure, group_col="group")
if plot:
p_values.to_csv(figures_dir + "/p_values_" +affix+ ".csv")
return p_values
#print(curr_engine_and_device)
#print(total_runtimes.shape)
#print(total_runtimes)
# test if data is normal
res_normal = np.zeros((len(total_runtimes)), dtype=np.float32)
for i in range(len(total_runtimes)):
res_normal[i] = np.round(shapiro(total_runtimes[i])[1], 4)
print(res_normal)
print(multipletests(res_normal, method="fdr_bh")[1])
df = pd.DataFrame(total_runtimes, curr_engine_and_device)
# test significance between total runtime between IEs (assuming normal)
res = np.round(sp.posthoc_ttest(total_runtimes, p_adjust="fdr_by"), 4)
print(total_runtimes.shape)
print(curr_engine_and_device)
# Use Tukey's method for multiple testing instead (works well with groups of the same number of samples)
print(total_runtimes.flatten().dtype)
tmp = np.repeat(range(len(curr_engine_and_device)), 10)
print(tmp.dtype)
#tukey = pairwise_tukeyhsd(total_runtimes.flatten(), groups=tmp, alpha=0.05)
#print(df)
#print(res)
#print(tukey)
'''
import statsmodels.api as sa
import statsmodels.formula.api as sfa
import scikit_posthocs as sp
import numpy as np
import pandas as pd
df = sa.datasets.get_rdataset('iris').data
print(df.head())
ttest = sp.posthoc_ttest(df,
val_col='Sepal.Width',
group_col='Species',
p_adjust='holm')
tukey = sp.posthoc_tukey_hsd()
import scikit_posthocs as sp
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
import pandas as pd
import statsmodels.api as sm
data = pd.read_table(
"https://www.krigolsonteaching.com/uploads/4/3/8/4/43848243/sampleanovadata2.txt",
header=None)
data.columns = ['Subject', 'Group', 'rt']
#Groupings
G1 = data[data['Group'] == 1]['rt']
G2 = data[data['Group'] == 2]['rt']
G3 = data[data['Group'] == 3]['rt']
G4 = data[data['Group'] == 4]['rt']
#anova
A1 = stats.f_oneway(G1, G2, G3, G4)
#Post-Hoc analysis
tt = sp.posthoc_ttest(A1)
Tuk = sp.posthoc_tukey_hsd('rt', 'Group', alpha=0.04)
#Princple component anlysis
#Support Vector Machine learning
#K-means cluster learning
