def ANOVA_Tukey(variable):
new = diagnoses["Overall"][["diagnosis", variable]]
new = new.astype({variable: 'float64'})
df_pivot = new.pivot(columns="diagnosis", values=variable)
data = [df_pivot[diagnosis].dropna().values for diagnosis in df_pivot]
f_val, p_val = stats.f_oneway(*data)
anova_results = [f_val, p_val]
tukey = pairwise_tukey(data=new, dv=variable, between="diagnosis")
return anova_results, tukey
def tukey_pairwise_ph(tidy_df,
hour_col: str = "Hour",
dep_var: str = "Value",
protocol_col: str = "Protocol"):
"""
:type protocol_col: object
"""
hours = tidy_df[hour_col].unique()
ph_dict = {}
for hour in hours:
print(hour)
hour_df = tidy_df.query("%s == '%s'" % (hour_col, hour))
ph = pg.pairwise_tukey(dv=dep_var, between=protocol_col, data=hour_df)
pg.print_table(ph)
ph_dict[hour] = ph
ph_df = pd.concat(ph_dict)
return ph_df
marker_ph_dict = {}
for marker_label, marker_df in zip(marker_dict.keys(), marker_dict.values()):
print(marker_label)
# run anova
curr_anova_marker = pg.anova(
dv=dep_var,
between=condition_col,
data=marker_df
)
pg.print_table(curr_anova_marker)
curr_ph_marker = pg.pairwise_tukey(
dv=dep_var,
between=condition_col,
data=marker_df
)
pg.print_table(curr_ph_marker)
marker_ph_dict[marker_label] = curr_ph_marker
# save the files
label_test_dir = marker_test_dir / marker_label
if not os.path.exists(label_test_dir):
os.mkdir(label_test_dir)
curr_anova_marker.to_csv(label_test_dir / anova_str)
curr_ph_marker.to_csv(label_test_dir / ph_str)
marker_ph_df = pd.concat(marker_ph_dict)
marker_ph_df.set_index(["A", "B"], append=True, inplace=True)
between='Subject Group')
tdist_ph
dist_Welch.to_csv(
'/Users/labc02/Documents/PDCB_data/Behavior/EPM/Stats/total_dist_Welch_s2.csv'
)
tdist_ph.to_csv(
'/Users/labc02/Documents/PDCB_data/Behavior/EPM/Stats/total_dist_ph_s2.csv'
)
opa_anova = pg.anova(data=epm_s2,
dv='Time in Zone (%) - Open Arms',
between='Subject Group')
opa_anova
opa_anova.to_csv(
'/Users/labc02/Documents/PDCB_data/Behavior/EPM/Stats/opa_anova_s2.csv')
opa_ph = pg.pairwise_tukey(data=epm_s2,
dv='Time in Zone (%) - Open Arms',
between='Subject Group')
opa_ph.to_csv(
'/Users/labc02/Documents/PDCB_data/Behavior/EPM/Stats/opa_ph_s2.csv')
#%%
epms2_fig, epms2_ax = plt.subplots(nrows=1, ncols=3, figsize=(7, 4))
sns.boxplot(x='Subject Group',
y='Entries in Zone - Center',
data=epm_s2,
palette=['forestgreen', 'forestgreen', 'royalblue', 'royalblue'],
showmeans=True,
meanprops={
'marker': '+',
'markeredgecolor': 'k'
},
ax=epms2_ax[0])
def mixed_anova(self,
stat_key,
verbose=True,
group_tukey=True,
day_tukey=True):
'''
:param stat_key:
:return:
'''
ko_sum_stat, ctrl_sum_stat = self.summary_stat_matrices(stat_key)
df = {'ko_ctrl': [], 'day': [], stat_key: [], 'mouse': []}
for m, mouse in enumerate(self.ko_mice):
for day in self.days:
df['ko_ctrl'].append(0)
df['day'].append(day)
df[stat_key].append(ko_sum_stat[m, day])
df['mouse'].append(mouse)
for m, mouse in enumerate(self.ctrl_mice):
for day in self.days:
df['ko_ctrl'].append(1)
df['day'].append(day)
df[stat_key].append(ctrl_sum_stat[m, day])
df['mouse'].append(mouse)
df = pd.DataFrame(df)
results = {}
aov = mixed_anova(data=df,
dv=stat_key,
between='ko_ctrl',
within='day',
subject='mouse')
results['anova'] = aov
if verbose:
print('Mixed design ANOVA results')
print(aov)
if group_tukey:
ko_ctrl_tukey = pairwise_tukey(data=df,
dv=stat_key,
between='ko_ctrl')
results['ko_ctrl_tukey'] = ko_ctrl_tukey
if verbose:
print('PostHoc Tukey: KO vs Ctrl')
print(ko_ctrl_tukey)
if day_tukey:
day_stats = []
print('PostHov Tukey on each day')
for day in self.days:
print('Day %d' % day)
stats = pairwise_tukey(data=df[df['day'] == day],
dv=stat_key,
between='ko_ctrl')
day_stats.append(stats)
if verbose:
print(stats)
results['day_tukey'] = day_stats
return results
#%%
### STATISTICAL TESTS ###
# For subplots D and D we perform a one-way ANOVA to test the null hypothesis that
# two or more groups have the same population mean. Here all the samples are independent
# as coming from different FCGR3A haplotype and tested only in one condition
# !pip install openpyxl
ANOVA_top = anova(
data=data_adcc,
dv='top', # dependent variable
between='FCGR3A') # between-subject identifier
ANOVA_top.to_excel('../stats/ANOVA_top_figure3.xlsx')
ANOVA_top_posthoc = pairwise_tukey(data=data_adcc, dv='top', between='FCGR3A')
ANOVA_top_posthoc.to_excel('../stats/ANOVA_top_posthoc_figure3.xlsx')
ANOVA_ec50 = anova(
data=data_adcc,
dv='EC50', # dependent variable
between='FCGR3A') # between-subject identifier
ANOVA_ec50.to_excel('../stats/ANOVA_ec50_figure3.xlsx')
ANOVA_ec50_posthoc = pairwise_tukey(data=data_adcc,
dv='EC50',
between='FCGR3A')
ANOVA_ec50_posthoc.to_excel('../stats/ANOVA_ec50_posthoc_figure3.xlsx')
#%%
### FUNCTION FOR PLOTING THE STARS ###
# The output from this command provides us with two things. First, it shows us the result of a t-test for each of the dummy variables, which basically tell us whether each of the conditions separately differs from placebo; it appears that Drug 1 does whereas Drug 2 does not. However, keep in mind that if we wanted to interpret these tests, we would need to correct the p-values to account for the fact that we have done multiple hypothesis tests; we will see an example of how to do this in the next chapter. # # Remember that the hypothesis that we started out wanting to test was whether there was any difference between any of the conditions; we refer to this as an *omnibus* hypothesis test, and it is the test that is provided by the F statistic. The F statistic basically tells us whether our model is better than a simple model that just includes an intercept. In this case we see that the F test is highly significant, consistent with our impression that there did seem to be differences between the groups (which in fact we know there were, because we created the data). # %% ols_model = ols(formula='BPsys~ group', data=df) ols_result = ols_model.fit() aov_table = sm.stats.anova_lm(ols_result) aov_table # %% import pingouin as pg pg.anova(data=df, dv='BPsys',between='group', effsize="np2") # %% pg.pairwise_tukey(data=df, dv='BPsys', between='group') # %% [markdown] # ## Learning objectives # # After reading this chapter, you should be able to: # # * Describe the rationale behind the sign test # * Describe how the t-test can be used to compare a single mean to a hypothesized value # * Compare the means for two paired or unpaired groups using a two-sample t-test # # # ## Appendix # # ### The paired t-test as a linear model #
def test_pandas(self):
"""Test pandas method.
"""
# Test the ANOVA (Pandas)
aov = df.anova(dv='Scores', between='Group', detailed=True)
assert aov.equals(
pg.anova(dv='Scores', between='Group', detailed=True, data=df))
aov3_ss1 = df_aov3.anova(dv='Cholesterol',
between=['Sex', 'Drug'],
ss_type=1)
aov3_ss2 = df_aov3.anova(dv='Cholesterol',
between=['Sex', 'Drug'],
ss_type=2)
aov3_ss2_pg = pg.anova(dv='Cholesterol',
between=['Sex', 'Drug'],
data=df_aov3,
ss_type=2)
assert not aov3_ss1.equals(aov3_ss2)
assert aov3_ss2.round(3).equals(aov3_ss2_pg.round(3))
# Test the Welch ANOVA (Pandas)
aov = df.welch_anova(dv='Scores', between='Group')
assert aov.equals(pg.welch_anova(dv='Scores', between='Group',
data=df))
# Test the ANCOVA
aov = df_anc.ancova(dv='Scores', covar='Income',
between='Method').round(3)
assert (aov.equals(
pg.ancova(data=df_anc,
dv='Scores',
covar='Income',
between='Method').round(3)))
# Test the repeated measures ANOVA (Pandas)
aov = df.rm_anova(dv='Scores',
within='Time',
subject='Subject',
detailed=True)
assert (aov.equals(
pg.rm_anova(dv='Scores',
within='Time',
subject='Subject',
detailed=True,
data=df)))
# FDR-corrected post hocs with Hedges'g effect size
ttests = df.pairwise_tests(dv='Scores',
within='Time',
subject='Subject',
padjust='fdr_bh',
effsize='hedges')
assert (ttests.equals(
pg.pairwise_tests(dv='Scores',
within='Time',
subject='Subject',
padjust='fdr_bh',
effsize='hedges',
data=df)))
# Pairwise Tukey
tukey = df.pairwise_tukey(dv='Scores', between='Group')
assert tukey.equals(
pg.pairwise_tukey(data=df, dv='Scores', between='Group'))
# Test two-way mixed ANOVA
aov = df.mixed_anova(dv='Scores',
between='Group',
within='Time',
subject='Subject',
correction=False)
assert (aov.equals(
pg.mixed_anova(dv='Scores',
between='Group',
within='Time',
subject='Subject',
correction=False,
data=df)))
# Test parwise correlations
corrs = data.pairwise_corr(columns=['X', 'M', 'Y'], method='spearman')
corrs2 = pg.pairwise_corr(data=data,
columns=['X', 'M', 'Y'],
method='spearman')
assert corrs['r'].equals(corrs2['r'])
# Test partial correlation
corrs = data.partial_corr(x='X', y='Y', covar='M', method='spearman')
corrs2 = pg.partial_corr(x='X',
y='Y',
covar='M',
method='spearman',
data=data)
assert corrs['r'].equals(corrs2['r'])
# Test partial correlation matrix (compare with the ppcor package)
corrs = data.iloc[:, :5].pcorr().round(3)
np.testing.assert_array_equal(corrs.iloc[0, :].to_numpy(),
[1, 0.392, 0.06, -0.014, -0.149])
# Now compare against Pingouin's own partial_corr function
corrs = data[['X', 'Y', 'M']].pcorr()
corrs2 = data.partial_corr(x='X', y='Y', covar='M')
assert np.isclose(corrs.at['X', 'Y'], corrs2.at['pearson', 'r'])
# Test rcorr (correlation matrix with p-values)
# We compare against Pingouin pairwise_corr function
corrs = df_corr.rcorr(padjust='holm', decimals=4)
corrs2 = df_corr.pairwise_corr(padjust='holm').round(4)
assert corrs.at['Neuroticism', 'Agreeableness'] == '*'
assert (corrs.at['Agreeableness',
'Neuroticism'] == str(corrs2.at[2, 'r']))
corrs = df_corr.rcorr(padjust='holm', stars=False, decimals=4)
assert (corrs.at['Neuroticism',
'Agreeableness'] == str(corrs2.at[2,
'p-corr'].round(4)))
corrs = df_corr.rcorr(upper='n', decimals=5)
corrs2 = df_corr.pairwise_corr().round(5)
assert corrs.at['Extraversion', 'Openness'] == corrs2.at[4, 'n']
assert corrs.at['Openness', 'Extraversion'] == str(corrs2.at[4, 'r'])
# Method = spearman does not work with Python 3.5 on Travis?
# Instead it seems to return the Pearson correlation!
df_corr.rcorr(method='spearman')
df_corr.rcorr()
# Test mediation analysis
med = data.mediation_analysis(x='X', m='M', y='Y', seed=42, n_boot=500)
np.testing.assert_array_equal(med.loc[:, 'coef'].round(4).to_numpy(),
[0.5610, 0.6542, 0.3961, 0.0396, 0.3565])
names = ["No_Vibration", "Symmetric_Vibration", "Asymmetric_Vibration", "Randomized_Asymmetric_Vibration"]
df1.columns = names
df2.columns = names
import scipy.stats as stats
# stats f_oneway functions takes the groups as input and returns F and P-value
# fvalue, pvalue = stats.f_oneway(df1["No_Vibration"], df1["Symmetric_Vibration"], df1["Asymmetric_Vibration"], df1["Randomized_Asymmetric_Vibration"])
fvalue, pvalue = stats.f_oneway(df2["No_Vibration"], df2["Symmetric_Vibration"], df2["Asymmetric_Vibration"], df2["Randomized_Asymmetric_Vibration"])
print(fvalue, pvalue)
# get ANOVA table as R like output
import statsmodels.api as sm
from statsmodels.formula.api import ols
# reshape the d dataframe suitable for statsmodels package
# d_melt = pd.melt(df1.reset_index(), id_vars=['index'], value_vars=names)
d_melt = pd.melt(df2.reset_index(), id_vars=['index'], value_vars=names)
# replace column names
d_melt.columns = ['index', 'Vibration_Modes', 'value']
# Ordinary Least Squares (OLS) model
model = ols('value ~ C(Vibration_Modes)', data=d_melt).fit()
anova_table = sm.stats.anova_lm(model, typ=2)
print(anova_table)
from pingouin import pairwise_tukey
m_comp = pairwise_tukey(data=d_melt, dv='value', between='Vibration_Modes')
print(m_comp)
w, pvalue = stats.shapiro(model.resid)
print(w, pvalue)
print(key)
# tidy data
long_df = df.stack().reset_index()
long_df.columns = stat_colnames
part_df = long_df.query("%s == '%s'" % (time, part))
# do anova
part_rm = pg.rm_anova(dv=dep_var,
within=day,
subject=anim,
data=part_df)
pg.print_table(part_rm)
# do posthoc
ph = pg.pairwise_tukey(dv=dep_var, between=day, data=part_df)
pg.print_table(ph)
ph_part_dict[key] = ph
stage_test_dir = part_dir / key
anova_file = stage_test_dir / "01_anova.csv"
ph_file = stage_test_dir / "02_posthoc.csv"
part_rm.to_csv(anova_file)
ph.to_csv(ph_file)
ph_part_df = pd.concat(ph_part_dict)
ph_total_dict[part] = ph_part_df
ph_total_df = pd.concat(ph_total_dict)
ph_total_df = ph_total_df.reorder_levels([1, 0, 2])
#data_merged.to_csv(r'C:\Users\user\Desktop\FOCUS\behavioral\P_Merged_var.csv', index = None, header=True)
# ANOVA - does correct reaction time differ between blocks?
aov_corr_rt = anova(dv='corr_rt', between='blocks', data=data_merged)
print(aov_corr_rt)
rep_anov_alarm = pg.rm_anova(data=data_merged,
dv='false_alarm',
within='blocks',
subject='participant',
detailed=True)
# follow-up pairwise comparison
pairs_corr_rt = pairwise_tukey(dv='corr_rt',
between='blocks',
data=data_merged)
print(pairs_corr_rt)
#### ANOVA - does false alarms differ between blocks?
aov_alarms = anova(dv='false_alarm', between='blocks', data=data_merged)
print(aov_alarms)
# follow-up pairwise comparison
pairs_alarms = pairwise_tukey(dv='false_alarm',
between='blocks',
data=data_merged)
print(pairs_alarms)
d_melt = pd.melt(data0.reset_index(),
id_vars=['index'],
value_vars=['No_Up', 'Single_Up', 'Double_Up'])
# replace column names
d_melt.columns = ['index', 'treatments', 'value']
# Ordinary Least Squares (OLS) model
model = ols('value ~ C(treatments)', data=d_melt).fit()
anova_table = sm.stats.anova_lm(model, typ=2)
anova_table
# pairwise comparision significance with HSD https://reneshbedre.github.io/blog/anova.html
from pingouin import pairwise_tukey
# perform multiple pairwise comparison (Tukey HSD)
# for unbalanced (unequal sample size) data, pairwise_tukey uses Tukey-Kramer test
print("Pairwise comparison with Tukey HSD")
m_comp = pairwise_tukey(data=d_melt, dv='value', between='treatments')
print(m_comp)
plt.title("Regulation: no change", fontsize=16)
plt.tight_layout()
pdf.savefig(fig)
##### For the runs with changes ###################
sigma_1 = 0.01875
sigma_1_list = sigma_1 * np.array([1 / 2, 2, 2**2, 2**3, 2**4])
mes = ["halved"] + ["times %d" % 2**i for i in (1, 2, 3, 4)]
for i in range(len(sigma_1_list)):
data1 = pd.read_csv("MI_10000traj_shift30_%d.csv" % i)
count_dir = marker_test_dir / "01_count"
mean_dir = marker_test_dir / "02_mean"
hist_dir = marker_test_dir / "03_hist"
for dir in [count_dir, mean_dir, hist_dir]:
if not os.path.exists(dir):
os.mkdir(dir)
curr_count = count_data_dict[curr_label]
curr_mean = mean_data_dict[curr_label]
curr_hist = hist_data_dict[curr_label]
count = count_cols[-1]
count_anova = pg.anova(dv=count, between=condition_col, data=curr_count)
pg.print_table(count_anova)
count_ph = pg.pairwise_tukey(dv=count,
between=condition_col,
data=curr_count)
pg.print_table(count_ph)
count_anova.to_csv(count_dir / anova_str)
count_ph.to_csv(count_dir / ph_str)
count_stats_dict[curr_label] = count_ph
mean = mean_cols[-1]
mean_anova = pg.anova(dv=mean, between=condition_col, data=curr_mean)
pg.print_table(mean_anova)
mean_ph = pg.pairwise_tukey(dv=mean, between=condition_col, data=curr_mean)
pg.print_table(mean_ph)
mean_anova.to_csv(mean_dir / anova_str)
mean_ph.to_csv(mean_dir / ph_str)
mean_stats_dict[curr_label] = mean_ph
(HWK_errors['Block'] == 'D1_2')].item()
d2a = HWK_errors['Error mean'][(HWK_errors['Subject'] == ii) &
(HWK_errors['Block'] == 'D2_1')].item()
d2b = HWK_errors['Error mean'][(HWK_errors['Subject'] == ii) &
(HWK_errors['Block'] == 'D2_2')].item()
d3a = HWK_errors['Error mean'][(HWK_errors['Subject'] == ii) &
(HWK_errors['Block'] == 'D3_1')].item()
index_dict['Acquisition'].append(((d1a - d1b) + (d2a - d2b)) / 2)
index_dict['Retrival'].append(((d1b - d2a) + (d2b - d3a)) / 2)
kesner_index = pd.DataFrame(index_dict)
kesner_index
pg.anova(dv='Acquisition', between=['Genotype', 'Sex'],
data=kesner_index, export_filename='kesneraov_acq')
acq_tk = pg.pairwise_tukey(dv='Acquisition', between='Group', data=kesner_index)
pg.anova(dv='Retrival', between=['Genotype', 'Sex'],
data=kesner_index, export_filename='kesneraov_ret')
acq_tk
# Kesner indexes figure
#%%
kesner_ind = plt.figure(figsize=(9, 5))
plt.subplot(1, 2, 1)
acq_ax = sns.barplot(x='Group', y='Acquisition', data=kesner_index,
ci=68, capsize=.3, palette=['g', 'g', 'b', 'b'])
plt.xticks(range(0, 4), ['Fem_KO', 'Male_KO', 'Fem_WT', 'Male_WT'])
acq_ax.annotate('*', xy=(0.5, .93), xytext=(0.5, .91), xycoords='axes fraction', fontsize=18, ha='center',
va='bottom', fontweight='bold', arrowprops=dict(arrowstyle='-[, widthB=6, lengthB=.1', lw=2, color='black'))
acq_ax.annotate('**', xy=(0.25, .83), xytext=(0.25, .81), xycoords='axes fraction', fontsize=18, ha='center',
va='bottom', fontweight='bold', arrowprops=dict(arrowstyle='-[, widthB=2, lengthB=.1', lw=2, color='black'))
hourly_test_dir = save_test_dir / "hour_prop"
# prop 2 way rm
test_rm = pg.rm_anova2(dv=dep_var,
within=[day_col, hour_col],
subject=anim,
data=long_df)
pg.print_table(test_rm)
# prop post hoc
ph_dict = {}
for hour in hours:
print(hour)
hour_df = long_df.query("%s == '%s'" % (hour_col, hour))
ph = pg.pairwise_tukey(dv=dep_var, between=day_col, data=hour_df)
pg.print_table(ph)
ph_dict[hour] = ph
hourly_ph_df = pd.concat(ph_dict)
hr_anova_file = hourly_test_dir / anova_csv
hr_ps_file = hourly_test_dir / ph_csv
test_rm.to_csv(hr_anova_file)
hourly_ph_df.to_csv(hr_ps_file)
# can't do repeated measures on swe since missing values
swe_test = delta_mean_masked.reset_index()
swe_test = swe_test.iloc[:, [0, 2, 1, 3]].copy()
swe_test.columns = stat_colnames
swa_test_dir = save_test_dir / "SWA"
data2 = mean2 + np.random.randn(N2)*stdev
data3 = mean3 + np.random.randn(N3)*stdev
datacolumn = np.hstack((data1,data2,data3))
# group labels
groups = ['1']*N1 + ['2']*N2 + ['3']*N3
# convert to a pandas dataframe
df = pd.DataFrame({'TheData':datacolumn,'Group':groups})
df
# In[ ]:
pg.anova(data=df,dv='TheData',between='Group')
# In[ ]:
pg.pairwise_tukey(data=df,dv='TheData',between='Group')
# In[ ]:
df.boxplot('TheData',by='Group');