import numpy as np
import pingouin as pg
import seaborn as sns
from statsmodels.stats.multicomp import pairwise_tukeyhsd
import csv
df = pd.read_csv("Datos.csv", index_col=None,usecols=[1,2,3,4,8],dtype={'generador': 'category',
'algoritmo_flujo': 'category','vertices': 'category','aristas': 'category', 'mediana': np.float64} )
logX = np.log1p(df['mediana'])
df = df.assign(mediana_log=logX.values)
df.drop(['mediana'], axis= 1, inplace= True)
factores=["vertices","generador","aristas","algoritmo_flujo"]
plt.figure(figsize=(8, 6))
for i in factores:
print(rp.summary_cont(df['mediana_log'].groupby(df[i])))
anova = pg.anova (dv='mediana_log', between=i, data=df, detailed=True)
pg._export_table (anova,("ANOVA"+i+".csv"))
ax=sns.boxplot(x=df["mediana_log"], y=df[i], data=df, palette="Set1")
plt.savefig("boxplot_"+ i+".png", bbox_inches='tight')
plt.savefig("boxplot_" + i + ".eps", bbox_inches='tight')
tukey = pairwise_tukeyhsd(endog = df["mediana_log"], groups= df[i], alpha=0.05)
tukey.plot_simultaneous(xlabel='Time', ylabel=i)
plt.vlines(x=49.57,ymin=-0.5,ymax=4.5, color="red")
plt.savefig("simultaneous_tukey"+ i+".png", bbox_inches='tight')
plt.savefig("simultaneous_tukey" + i + ".eps", bbox_inches='tight')
print(tukey.summary())
t_csv = open("Tukey"+i+".csv", 'w')
with t_csv:
writer = csv.writer(t_csv)
writer.writerows(tukey.summary())
plt.show()
df.drop(['Mediana'], axis=1, inplace=True)
factores = [
"Grado", "CoefAg", "CentCer", "CentCag", "Excentricidad", "PageRag"
]
plt.figure(figsize=(8, 6))
for i in factores:
print(rp.summary_cont(df['FlujoMax'].groupby(df[i])))
anova = pg.anova(
dv='FlujoMax',
between=i,
data=df,
detailed=True,
)
pg._export_table(anova, ("ANOVAsFlujoMax" + i + ".csv"))
ax = sns.boxplot(x=df["FlujoMax"], y=df[i], data=df, palette="cubehelix")
plt.savefig("boxplot_FlujoMax" + i + ".eps", bbox_inches='tight')
tukey = pairwise_tukeyhsd(endog=df["FlujoMax"], groups=df[i], alpha=0.05)
tukey.plot_simultaneous(xlabel='Flujo Maximo', ylabel=i)
plt.savefig("simultaneous_tukey" + i + ".eps", bbox_inches='tight')
print(tukey.summary())
t_csv = open("TukeyFlujoMax" + i + ".csv", 'w')
with t_csv:
writer = csv.writer(t_csv)
writer.writerows(tukey.summary())
def friedman(dv=None, within=None, subject=None, data=None,
export_filename=None):
"""Friedman test for repeated measurements.
Parameters
----------
dv : string
Name of column containing the dependant variable.
within : string
Name of column containing the within-subject factor.
subject : string
Name of column containing the subject identifier.
data : pandas DataFrame
DataFrame
export_filename : string
Filename (without extension) for the output file.
If None, do not export the table.
By default, the file will be created in the current python console
directory. To change that, specify the filename with full path.
Returns
-------
stats : DataFrame
Test summary ::
'Q' : The Friedman Q statistic, corrected for ties
'p-unc' : Uncorrected p-value
'dof' : degrees of freedom
Notes
-----
The Friedman test is used for one-way repeated measures ANOVA by ranks.
Data are expected to be in long-format.
Note that if the dataset contains one or more other within subject
factors, an automatic collapsing to the mean is applied on the dependant
variable (same behavior as the ezANOVA R package). As such, results can
differ from those of JASP. If you can, always double-check the results.
Due to the assumption that the test statistic has a chi squared
distribution, the p-value is only reliable for n > 10 and more than 6
repeated measurements.
NaN values are automatically removed.
Examples
--------
Compute the Friedman test for repeated measurements.
>>> from pingouin import friedman, read_dataset
>>> df = read_dataset('rm_anova')
>>> friedman(dv='DesireToKill', within='Disgustingness',
... subject='Subject', data=df)
Source ddof1 Q p-unc
Friedman Disgustingness 1 9.228 0.002384
"""
# Check data
_check_dataframe(dv=dv, within=within, data=data, subject=subject,
effects='within')
# Collapse to the mean
data = data.groupby([subject, within]).mean().reset_index()
# Remove NaN
if data[dv].isnull().any():
data = remove_rm_na(dv=dv, within=within, subject=subject,
data=data[[subject, within, dv]])
# Extract number of groups and total sample size
grp = data.groupby(within)[dv]
rm = list(data[within].unique())
k = len(rm)
X = np.array([grp.get_group(r).values for r in rm]).T
n = X.shape[0]
# Rank per subject
ranked = np.zeros(X.shape)
for i in range(n):
ranked[i] = scipy.stats.rankdata(X[i, :])
ssbn = (ranked.sum(axis=0)**2).sum()
# Compute the test statistic
Q = (12 / (n * k * (k + 1))) * ssbn - 3 * n * (k + 1)
# Correct for ties
ties = 0
for i in range(n):
replist, repnum = scipy.stats.find_repeats(X[i])
for t in repnum:
ties += t * (t * t - 1)
c = 1 - ties / float(k * (k * k - 1) * n)
Q /= c
# Approximate the p-value
ddof1 = k - 1
p_unc = scipy.stats.chi2.sf(Q, ddof1)
# Create output dataframe
stats = pd.DataFrame({'Source': within,
'ddof1': ddof1,
'Q': np.round(Q, 3),
'p-unc': p_unc,
}, index=['Friedman'])
col_order = ['Source', 'ddof1', 'Q', 'p-unc']
stats = stats.reindex(columns=col_order)
stats.dropna(how='all', axis=1, inplace=True)
# Export to .csv
if export_filename is not None:
_export_table(stats, export_filename)
return stats
def cochran(dv=None, within=None, subject=None, data=None,
export_filename=None):
"""Cochran Q test. Special case of the Friedman test when the dependant
variable is binary.
Parameters
----------
dv : string
Name of column containing the binary dependant variable.
within : string
Name of column containing the within-subject factor.
subject : string
Name of column containing the subject identifier.
data : pandas DataFrame
DataFrame
export_filename : string
Filename (without extension) for the output file.
If None, do not export the table.
By default, the file will be created in the current python console
directory. To change that, specify the filename with full path.
Returns
-------
stats : DataFrame
Test summary ::
'Q' : The Cochran Q statistic
'p-unc' : Uncorrected p-value
'dof' : degrees of freedom
Notes
-----
The Cochran Q Test is a non-parametric test for ANOVA with repeated
measures where the dependent variable is binary.
Data are expected to be in long-format. NaN are automatically removed
from the data.
The Q statistics is defined as:
.. math:: Q = \\frac{(r-1)(r\\sum_j^rx_j^2-N^2)}{rN-\\sum_i^nx_i^2}
where :math:`N` is the total sum of all observations, :math:`j=1,...,r`
where :math:`r` is the number of repeated measures, :math:`i=1,...,n` where
:math:`n` is the number of observations per condition.
The p-value is then approximated using a chi-square distribution with
:math:`r-1` degrees of freedom:
.. math:: Q \\sim \\chi^2(r-1)
References
----------
.. [1] Cochran, W.G., 1950. The comparison of percentages in matched
samples. Biometrika 37, 256–266.
https://doi.org/10.1093/biomet/37.3-4.256
Examples
--------
Compute the Cochran Q test for repeated measurements.
>>> from pingouin import cochran, read_dataset
>>> df = read_dataset('cochran')
>>> cochran(dv='Energetic', within='Time', subject='Subject', data=df)
Source dof Q p-unc
cochran Time 2 6.706 0.034981
"""
# Check data
_check_dataframe(dv=dv, within=within, data=data, subject=subject,
effects='within')
# Remove NaN
if data[dv].isnull().any():
data = remove_rm_na(dv=dv, within=within, subject=subject,
data=data[[subject, within, dv]])
# Groupby and extract size
grp = data.groupby(within)[dv]
grp_s = data.groupby(subject)[dv]
k = data[within].nunique()
dof = k - 1
# n = grp.count().unique()[0]
# Q statistic and p-value
q = (dof * (k * np.sum(grp.sum()**2) - grp.sum().sum()**2)) / \
(k * grp.sum().sum() - np.sum(grp_s.sum()**2))
p_unc = scipy.stats.chi2.sf(q, dof)
# Create output dataframe
stats = pd.DataFrame({'Source': within,
'dof': dof,
'Q': np.round(q, 3),
'p-unc': p_unc,
}, index=['cochran'])
# Export to .csv
if export_filename is not None:
_export_table(stats, export_filename)
return stats
def kruskal(dv=None, between=None, data=None, detailed=False,
export_filename=None):
"""Kruskal-Wallis H-test for independent samples.
Parameters
----------
dv : string
Name of column containing the dependant variable.
between : string
Name of column containing the between factor.
data : pandas DataFrame
DataFrame
export_filename : string
Filename (without extension) for the output file.
If None, do not export the table.
By default, the file will be created in the current python console
directory. To change that, specify the filename with full path.
Returns
-------
stats : DataFrame
Test summary ::
'H' : The Kruskal-Wallis H statistic, corrected for ties
'p-unc' : Uncorrected p-value
'dof' : degrees of freedom
Notes
-----
The Kruskal-Wallis H-test tests the null hypothesis that the population
median of all of the groups are equal. It is a non-parametric version of
ANOVA. The test works on 2 or more independent samples, which may have
different sizes.
Due to the assumption that H has a chi square distribution, the number of
samples in each group must not be too small. A typical rule is that each
sample must have at least 5 measurements.
NaN values are automatically removed.
Examples
--------
Compute the Kruskal-Wallis H-test for independent samples.
>>> from pingouin import kruskal, read_dataset
>>> df = read_dataset('anova')
>>> kruskal(dv='Pain threshold', between='Hair color', data=df)
Source ddof1 H p-unc
Kruskal Hair color 3 10.589 0.014172
"""
# Check data
_check_dataframe(dv=dv, between=between, data=data,
effects='between')
# Remove NaN values
data = data.dropna()
# Reset index (avoid duplicate axis error)
data = data.reset_index(drop=True)
# Extract number of groups and total sample size
groups = list(data[between].unique())
n_groups = len(groups)
n = data[dv].size
# Rank data, dealing with ties appropriately
data['rank'] = scipy.stats.rankdata(data[dv])
# Find the total of rank per groups
grp = data.groupby(between)['rank']
sum_rk_grp = grp.sum().values
n_per_grp = grp.count().values
# Calculate chi-square statistic (H)
H = (12 / (n * (n + 1)) * np.sum(sum_rk_grp**2 / n_per_grp)) - 3 * (n + 1)
# Correct for ties
H /= scipy.stats.tiecorrect(data['rank'].values)
# Calculate DOF and p-value
ddof1 = n_groups - 1
p_unc = scipy.stats.chi2.sf(H, ddof1)
# Create output dataframe
stats = pd.DataFrame({'Source': between,
'ddof1': ddof1,
'H': np.round(H, 3),
'p-unc': p_unc,
}, index=['Kruskal'])
col_order = ['Source', 'ddof1', 'H', 'p-unc']
stats = stats.reindex(columns=col_order)
stats.dropna(how='all', axis=1, inplace=True)
# Export to .csv
if export_filename is not None:
_export_table(stats, export_filename)
return stats