def test_mood_3d(self):
shape = (10, 5, 6)
np.random.seed(1234)
x1 = np.random.randn(*shape)
x2 = np.random.randn(*shape)
for axis in range(3):
z_vectest, pval_vectest = stats.mood(x1, x2, axis=axis)
# Tests that result for 3-D arrays is equal to that for the
# same calculation on a set of 1-D arrays taken from the
# 3-D array
axes_idx = ([1, 2], [0, 2], [0, 1]) # the two axes != axis
for i in range(shape[axes_idx[axis][0]]):
for j in range(shape[axes_idx[axis][1]]):
if axis == 0:
slice1 = x1[:, i, j]
slice2 = x2[:, i, j]
elif axis == 1:
slice1 = x1[i, :, j]
slice2 = x2[i, :, j]
else:
slice1 = x1[i, j, :]
slice2 = x2[i, j, :]
assert_array_almost_equal([z_vectest[i, j],
pval_vectest[i, j]],
stats.mood(slice1, slice2))
def test_mood_3d(self):
shape = (10, 5, 6)
np.random.seed(1234)
x1 = np.random.randn(*shape)
x2 = np.random.randn(*shape)
for axis in range(3):
z_vectest, pval_vectest = stats.mood(x1, x2, axis=axis)
# Tests that result for 3-D arrays is equal to that for the
# same calculation on a set of 1-D arrays taken from the
# 3-D array
axes_idx = ([1, 2], [0, 2], [0, 1]) # the two axes != axis
for i in range(shape[axes_idx[axis][0]]):
for j in range(shape[axes_idx[axis][1]]):
if axis == 0:
slice1 = x1[:, i, j]
slice2 = x2[:, i, j]
elif axis == 1:
slice1 = x1[i, :, j]
slice2 = x2[i, :, j]
else:
slice1 = x1[i, j, :]
slice2 = x2[i, j, :]
assert_array_almost_equal(
[z_vectest[i, j], pval_vectest[i, j]],
stats.mood(slice1, slice2))
def test_mood_order_of_args(self):
# z should change sign when the order of arguments changes, pvalue
# should not change
np.random.seed(1234)
x1 = np.random.randn(10, 1)
x2 = np.random.randn(15, 1)
z1, p1 = stats.mood(x1, x2)
z2, p2 = stats.mood(x2, x1)
assert_array_almost_equal([z1, p1], [-z2, p2])
def test_mood_order_of_args(self):
# z should change sign when the order of arguments changes, pvalue
# should not change
np.random.seed(1234)
x1 = np.random.randn(10, 1)
x2 = np.random.randn(15, 1)
z1, p1 = stats.mood(x1, x2)
z2, p2 = stats.mood(x2, x1)
assert_array_almost_equal([z1, p1], [-z2, p2])
def test_mood_with_axis_none(self):
#Test with axis = None, compare with results from R
x1 = [
-0.626453810742332, 0.183643324222082, -0.835628612410047,
1.59528080213779, 0.329507771815361, -0.820468384118015,
0.487429052428485, 0.738324705129217, 0.575781351653492,
-0.305388387156356, 1.51178116845085, 0.389843236411431,
-0.621240580541804, -2.2146998871775, 1.12493091814311,
-0.0449336090152309, -0.0161902630989461, 0.943836210685299,
0.821221195098089, 0.593901321217509
]
x2 = [
-0.896914546624981, 0.184849184646742, 1.58784533120882,
-1.13037567424629, -0.0802517565509893, 0.132420284381094,
0.707954729271733, -0.23969802417184, 1.98447393665293,
-0.138787012119665, 0.417650750792556, 0.981752777463662,
-0.392695355503813, -1.03966897694891, 1.78222896030858,
-2.31106908460517, 0.878604580921265, 0.035806718015226,
1.01282869212708, 0.432265154539617, 2.09081920524915,
-1.19992581964387, 1.58963820029007, 1.95465164222325,
0.00493777682814261, -2.45170638784613, 0.477237302613617,
-0.596558168631403, 0.792203270299649, 0.289636710177348
]
x1 = np.array(x1)
x2 = np.array(x2)
x1.shape = (10, 2)
x2.shape = (15, 2)
assert_array_almost_equal(stats.mood(x1, x2, axis=None),
[-1.31716607555, 0.18778296257])
def nonparametric_check_for_d_similarity(df1, df2, alpha=0.01):
common_features = set(df1.columns) & set(df2.columns)
features_stats = []
for col in common_features:
# H0=same central parameter
delta_test, delta_pvalue = stats.mannwhitneyu(df1[col], df2[col])
if delta_pvalue > alpha:
delta = 'Same central parameter'
else:
delta = 'Different central parameter'
# H0=equality of the scale parameters
scale1_test, scale1_pval = stats.ansari(df1[col], df2[col])
if scale1_pval > alpha:
scale1 = 'Same scale AnsariTest'
else:
scale1 = 'Different scale AnsariTest'
# H0=equality of the scale parameters
scale2_test, scale2_pval = stats.mood(df1[col], df2[col])
if scale2_pval > alpha:
scale2 = 'Same scale MoodTest'
else:
scale2 = 'Different scale MoodTest'
features_stats.append([col, delta_pvalue, delta, scale1_pval, scale1, scale2_pval, scale2])
features_stats = pd.DataFrame(features_stats)
features_stats.columns = ['col_name', 'delta_pval', 'delta_status', \
'scale1_pval', 'scale1_status', 'scale2_pval', 'scale2_status']
return features_stats
def test_mood_with_axis_none(self):
#Test with axis = None, compare with results from R
x1 = [-0.626453810742332, 0.183643324222082, -0.835628612410047,
1.59528080213779, 0.329507771815361, -0.820468384118015,
0.487429052428485, 0.738324705129217, 0.575781351653492,
-0.305388387156356, 1.51178116845085, 0.389843236411431,
-0.621240580541804, -2.2146998871775, 1.12493091814311,
-0.0449336090152309, -0.0161902630989461, 0.943836210685299,
0.821221195098089, 0.593901321217509]
x2 = [-0.896914546624981, 0.184849184646742, 1.58784533120882,
-1.13037567424629, -0.0802517565509893, 0.132420284381094,
0.707954729271733, -0.23969802417184, 1.98447393665293,
-0.138787012119665, 0.417650750792556, 0.981752777463662,
-0.392695355503813, -1.03966897694891, 1.78222896030858,
-2.31106908460517, 0.878604580921265, 0.035806718015226,
1.01282869212708, 0.432265154539617, 2.09081920524915,
-1.19992581964387, 1.58963820029007, 1.95465164222325,
0.00493777682814261, -2.45170638784613, 0.477237302613617,
-0.596558168631403, 0.792203270299649, 0.289636710177348]
x1 = np.array(x1)
x2 = np.array(x2)
x1.shape = (10, 2)
x2.shape = (15, 2)
assert_array_almost_equal(stats.mood(x1, x2, axis=None),
[-1.31716607555, 0.18778296257])
def test_mood_2d(self):
# Test if the results of mood test in 2-D case are consistent with the
# R result for the same inputs. Numbers from R mood.test().
ny = 5
np.random.seed(1234)
x1 = np.random.randn(10, ny)
x2 = np.random.randn(15, ny)
z_vectest, pval_vectest = stats.mood(x1, x2)
for j in range(ny):
assert_array_almost_equal([z_vectest[j], pval_vectest[j]], stats.mood(x1[:, j], x2[:, j]))
# inverse order of dimensions
x1 = x1.transpose()
x2 = x2.transpose()
z_vectest, pval_vectest = stats.mood(x1, x2, axis=1)
for i in range(ny):
# check axis handling is self consistent
assert_array_almost_equal([z_vectest[i], pval_vectest[i]], stats.mood(x1[i, :], x2[i, :]))
def test_mood_2d(self):
# Test if the results of mood test in 2-D case are consistent with the
# R result for the same inputs. Numbers from R mood.test().
ny = 5
np.random.seed(1234)
x1 = np.random.randn(10, ny)
x2 = np.random.randn(15, ny)
z_vectest, pval_vectest = stats.mood(x1, x2)
for j in range(ny):
assert_array_almost_equal([z_vectest[j], pval_vectest[j]],
stats.mood(x1[:, j], x2[:, j]))
# inverse order of dimensions
x1 = x1.transpose()
x2 = x2.transpose()
z_vectest, pval_vectest = stats.mood(x1, x2, axis=1)
for i in range(ny):
# check axis handling is self consistent
assert_array_almost_equal([z_vectest[i], pval_vectest[i]],
stats.mood(x1[i, :], x2[i, :]))
def test_significance_tests(normal_obs, normal_obs_control):
treatment = ab.sample(normal_obs)
control = ab.sample(normal_obs_control)
res = treatment.t_test(control, equal_var=True)
res_expected = ttest_ind(normal_obs, normal_obs_control, equal_var=True)
assert res.p_value == res_expected.pvalue
assert res.statistic == res_expected.statistic
res = treatment.t_test(control, equal_var=False)
res_expected = ttest_ind(normal_obs, normal_obs_control, equal_var=False)
assert res.p_value == res_expected.pvalue
assert res.statistic == res_expected.statistic
res = treatment.t_test_1samp(101)
res_expected = ttest_1samp(normal_obs, 101)
assert res.p_value == res_expected.pvalue
assert res.statistic == res_expected.statistic
res = treatment.mann_whitney_u_test(control)
res_expected = mannwhitneyu(normal_obs_control, normal_obs, alternative='two-sided')
assert res.p_value == pytest.approx(res_expected.pvalue, 1e-6)
assert res.u_statistic == res_expected.statistic
res = treatment.shapiro_test()
res_expected = shapiro(normal_obs)
assert res.statistic == res_expected[0]
assert res.p_value == res_expected[1]
res = treatment.median_test(control)
res_expected = median_test(normal_obs, normal_obs_control)
assert res.p_value == res_expected[1]
assert res.statistic == res_expected[0]
assert res.grand_median == res_expected[2]
res = treatment.levene_test(control)
res_expected = levene(normal_obs, normal_obs_control)
assert res.p_value == res_expected.pvalue
assert res.statistic == res_expected.statistic
res = treatment.mood_test(control)
res_expected = mood(normal_obs, normal_obs_control)
assert res.p_value == res_expected[1]
assert res.statistic == res_expected[0]
def vector_hypotheses(a, b):
dict_stat = {}
dict_pval = {}
pea = pearsonr(a, b)
dict_stat["pearsonr"], dict_pval["pearsonr"] = pea[0], pea[1]
ran = ranksums(a, b)
dict_stat["ranksums"], dict_pval["ranksums"] = ran[0], ran[1]
moo = mood(a, b)
dict_stat["mood"], dict_pval["mood"] = moo[0], moo[1]
fli = fligner(a, b)
dict_stat["fligner"], dict_pval["fligner"] = fli[0], fli[1]
ans = ansari(a, b)
dict_stat["ansari"], dict_pval["ansari"] = ans[0], ans[1]
bar = bartlett(a, b)
dict_stat["bartlett"], dict_pval["bartlett"] = bar[0], bar[1]
lev = levene(a, b)
dict_stat["levene"], dict_pval["levene"] = lev[0], lev[1]
man = mannwhitneyu(a, b)
dict_stat["mannwhitneyu"], dict_pval["mannwhitneyu"] = man[0], man[1]
return dict_stat, dict_pval
def stream(data, Test, thresholds):
# start monitoring at time = 20
i = 20
while (i < len(data) + 1):
# increment window to be tested
window = data[:i]
arg, D = Test(window)
# test at ith threshold value or at the last loaded threshold value
if i >len(thresholds):
cp = changedetected(D, thresholds[-1])
else:
cp = changedetected(D, thresholds[i-1])
if cp == True:
change = ''
if Test == Lepage:
# If test is Lepage, test to see what change was detected (either location or shit)
# If the p value from eg mann whitney test is 100 times smaller than that from the mood test, we declare a location shift
# If this is not met, then further investigation is needed (tested on synthetic data and the value of 100 seemed appropiate)
p_val_Mood = mood(window[:arg + 1], window[arg + 1:])[1]
p_val_MW = mannwhitneyu(window[:arg + 1], window[arg + 1:])[1]
if 0.01 * p_val_Mood > p_val_MW:
change = "Location"
elif 0.01 * p_val_MW > p_val_Mood:
change = "Scale"
else:
change = 'Needs further investigation'
else:
pass
# return the location of the cp, index for which is was detected, True (cp was declared), what type of change
return arg + 1, i - 1, True, change
else:
# if no change, increase the window size by 1
i += 1
# return this if no cp is found and no more datapoints to process
return None, None, False, None
def __compute_mood_statistic_ts(self, ts):
statistics = [
stat.mood(ts[t + 1:], ts[:t + 1])[0]
for t in np.arange(len(ts) - 1)
]
return pd.Series(statistics).dropna().reset_index(drop=True)
def mood((x, y)):
return stats.mood(x, y)
def mood_test(obs, obs_control) -> MoodTestResult:
"""
:return: MoodTestResult(statistic, p_value)
"""
res = stats.mood(obs, obs_control)
return MoodTestResult(statistic=res[0], p_value=res[1])
def test_mood(self):
# numbers from R: mood.test in package stats
x1 = np.arange(5)
assert_array_almost_equal(stats.mood(x1, x1**2),
(-1.3830857299399906, 0.16663858066771478), 11)
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import scipy.stats as stats
from scipy.stats import ttest_ind
import statsmodels.stats.api as sms
GE = pd.read_csv('C:/Users/anivia/Desktop/geDJ.txt',
sep="\s+",
header=None,
names=['date', 'open', 'high', 'low', 'close', 'vol'])
SP = pd.read_csv(
'https://www.math.ust.hk/~macwyu/MAFS5110_2018-2019/MAFS5110_2018-2019/Chapter_1/sp500.txt',
sep="\s+")
logreturn_GE = np.diff(np.log(np.array(GE["close"])))
logreturn_sp500 = np.diff(np.log(np.array(SP["close"])))
da2 = pd.concat([pd.DataFrame(logreturn_GE),
pd.DataFrame(logreturn_sp500)],
axis=1)
#da2.columns=['date','open','high','low','close','vol','logreturn_sp500']
#da2.index=da.index[1:]
da2.columns = ["logreturn_GE", "logreturn_sp500"]
da2.boxplot(column=['logreturn_GE', 'logreturn_sp500'])
plt.show()
print(stats.mood(logreturn_sp500, logreturn_GE))
print('H0 can be rejected, the variances are significantly different')
print(ttest_ind(logreturn_sp500, logreturn_GE, equal_var=True))
print('')
cm = sms.CompareMeans(sms.DescrStatsW(logreturn_sp500),
sms.DescrStatsW(logreturn_GE))
print(cm.tconfint_diff())
def main(graph_name):
G = nx.read_gml(graph_name)
G = nx.connected_component_subgraphs(G)[0] # Giant component
list_one_friend_percent_weight_change=[]
list_all=[]
for node in G.nodes():
if G.node[node]['label'] == "40155" :
special=node
for n in G.neighbors(node):
if G.node[n]['time_in_system'] >100:
list_all.append(float(G.node[n]['percentage_weight_change']))
print len(G.neighbors(n))
if len(G.neighbors(n))==1:
list_one_friend_percent_weight_change.append(float(G.node[n]['percentage_weight_change']))
break
print "final number of friendless nodes:", len(list_one_friend_percent_weight_change), "av_percent_wc:",numpy.mean(list_one_friend_percent_weight_change),numpy.std(list_one_friend_percent_weight_change)
print "av_%_wc fo all",len(list_all), "neighbors of 40155:", numpy.mean(list_all), numpy.std(list_all)
#dir=graph_name.split("fr")[0]
dir=graph_name.split("mas")[0]
original_name=graph_name.split("data/")[1]
original_name=original_name.split(".gml")[0]
dir=dir+"roles/"+original_name
time_in_system=100 #minimum amount of time in the sytem for a user to be included in the statistics
iterations=1000 #for boostrap
name00=dir+"bootstrap_statistics_percent_weight_change_one_hops_R6s"+str(time_in_system)+"days_exclude_R6s.dat"
list_R6s=[] # collect the R6 of the system
list_R6s_labels=[]
for node in G.nodes() :
if str(G.node[node]['role']) == "R6" :
list_R6s.append(node)
list_R6s_labels.append(str(G.node[node]['label']))
list_percentage_wc_one_hop=[]
list_one_hoppers=[]
for node in G.nodes():
if (str(G.node[node]['role']) == "R6" ):
for n in G.neighbors(node):
if (str(G.node[n]['role']) != "R6" ):
if int(G.node[n]['time_in_system']) > time_in_system :
if n not in list_one_hoppers:
list_percentage_wc_one_hop.append(float(G.node[n]['percentage_weight_change']))
list_one_hoppers.append(n)
print "all one-hops:",numpy.mean(list_percentage_wc_one_hop),len(list_percentage_wc_one_hop)
file0=open(name00, 'wt')
print >> file0,"Percentage Weight Change for one-hop-from-R6s\n\n\n","original:",numpy.mean(list_percentage_wc_one_hop)," set size:",len(list_percentage_wc_one_hop)
file0.close()
# R6s en friend_graph_all.gml: 40155, 28688, 45784, 41794, 43020, 47063, 39625, 31954, 40324,40666
#R6s en master_adherent_homo.gml: 40155, 41794, 39625, 46487, 31954, 40324, 28688, 45784, 40666
for excluding in list_R6s_labels:
list_percentage_wc_one_hop_excluding_oneR6=[]
list_one_hoppers_excluding_oneR6=[]
for node in G.nodes():
if (str(G.node[node]['role']) == "R6" ) and (str(G.node[node]['label']) != excluding ):
for n in G.neighbors(node):
if (str(G.node[n]['role']) != "R6" ):
if int(G.node[n]['time_in_system']) > time_in_system :
if n not in list_one_hoppers_excluding_oneR6:
list_percentage_wc_one_hop_excluding_oneR6.append(float(G.node[n]['percentage_weight_change']))
list_one_hoppers_excluding_oneR6.append(n)
actual_diff=numpy.mean(list_percentage_wc_one_hop)-numpy.mean(list_percentage_wc_one_hop_excluding_oneR6)
print "\n\ndiff. all one-hops & all but one hub",excluding,":",actual_diff
file0=open(name00, 'at')
print >> file0," excluding",excluding, ":",numpy.mean(list_percentage_wc_one_hop_excluding_oneR6), " (diff:" , actual_diff,") set size:",len(list_percentage_wc_one_hop_excluding_oneR6)
file0.close()
###############################################
# boostrap routine, sampling with replacement:#
###############################################
list_all=[]
for i in list_percentage_wc_one_hop:
list_all.append(i)
for i in list_percentage_wc_one_hop_excluding_oneR6:
list_all.append(i)
list_synth_diff=[]
for iter in range(iterations):
list_synth_one_hop=sample_with_replacement(list_all,len(list_percentage_wc_one_hop))
list_synth_one_hop_excluding_oneR6s=sample_with_replacement(list_all,len(list_percentage_wc_one_hop_excluding_oneR6))
mean1=numpy.mean(list_synth_one_hop)
mean2=numpy.mean(list_synth_one_hop_excluding_oneR6s)
list_synth_diff.append(mean1-mean2)
zscore=(actual_diff-numpy.mean(list_synth_diff))/numpy.std(list_synth_diff)
print "mean_over_synth_realizations (with repl.):",numpy.mean(list_synth_diff),"zscore:",zscore
file0=open(name00, 'at')
print >> file0," z-score (sampling with replacement)",zscore
file0.close()
# boostrap routine, sampling without replacement:
list_synth_diff=[]
for iter in range(iterations):
list_synth_one_hop=random.sample(list_all,len(list_percentage_wc_one_hop))
for i in list_all:
if i not in list_synth_one_hop:
list_synth_one_hop_excluding_oneR6s.append(i)
mean1=numpy.mean(list_synth_one_hop)
mean2=numpy.mean(list_synth_one_hop_excluding_oneR6s)
list_synth_diff.append(mean1-mean2)
zscore=(actual_diff-numpy.mean(list_synth_diff))/numpy.std(list_synth_diff)
print "mean_over_synth_realizations (without repl.):",numpy.mean(list_synth_diff),"zscore:",zscore
# mood test
mood=stats.mood(list_percentage_wc_one_hop,list_percentage_wc_one_hop_excluding_oneR6)
print "mood test:",mood
#t test:
ttest=stats.ttest_ind(list_percentage_wc_one_hop,list_percentage_wc_one_hop_excluding_oneR6, axis=0)
print "t-test:",ttest
#wilcoxon test SET SIZES MUST BE THE SAME
# wilcoxon=stats.wilcoxon(list_percentage_wc_one_hop, list_percentage_wc_one_hop_excluding_oneR6)
#print "wilcoxon test:",wilcoxon
file0=open(name00, 'at')
print >> file0," z-score (sampling without replacement)",zscore,"\n mood-test:",mood#,"\n wilcoxon-test:",wilcoxon,"\n"
file0.close()
file0=open(name00, 'at')
print >> file0,"\n\n(number iterations for the bootstrap:",iterations,")"
file0.close()
def mood((x, y)):
return stats.mood(x, y)
def main(graph_name):
H = nx.read_gml(graph_name)
for node in H.nodes(): # i remove self loops
if node in H.neighbors(node):
if len(H.neighbors(node)) > 1:
H.remove_edge(node, node)
else:
H.remove_node(node)
# for node in H.nodes():
# if H.node[node]['weigh_ins'] <5: #Adherent filter
# H.remove_node(node)
# print node, "is going down"
G = nx.connected_component_subgraphs(H)[0] # Giant component
print "size of the GC:", len(
G.nodes()) #, "after filtering for adherence!!"
#dir=graph_name.split("full_")[0]
#dir=graph_name.split("master")[0]
#dir=graph_name.split("method3_")[0]
#dir=graph_name.split("method3_adh")[0]
dir = graph_name.split("friends")[0]
dir = dir + "roles/"
time_in_system = 50 #minimum amount of time in the sytem for a user to be included in the statistics
#name=graph_name.split('data/')[1]
#name=graph_name.split('method3_50/interim/')[1]
#name=graph_name.split('network_all_users/')[1]
name = graph_name.split('5_points_network_2010/data/')[1]
name = name.split('.gml')[0]
name0 = dir + name + "_overlap_R6s_averages_" + str(
time_in_system) + "days_exclude_R6s.dat"
file0 = open(name0, 'wt')
file0.close()
contador = 0
name12 = dir + name + "_slopes_for_the_fits_average_weight_change.dat"
file = open(name12, 'wt')
file.close()
####for the Isolated Clusters:
list_GC_nodes = []
for n in G.nodes():
list_GC_nodes.append(n)
# print G.node[n]['percentage_weight_change']
# print "# users GC:",len(list_GC_nodes),"total:",len(H.nodes())
list_weight_changes_not_GC = []
for n in H.nodes():
if n not in list_GC_nodes:
#print n,"not in GC"
list_weight_changes_not_GC.append(
float(H.node[n]['percentage_weight_change']))
#print "# users not in GC:",len(list_weight_changes_not_GC)
# who="not_GC"
#Nbins=18
#histograma(list_weight_changes_not_GC,Nbins,dir,name,who)
###########################
list_R6s = [] # collect the R6 of the system
list_R6s_label = []
list_R6s_percent_weight_change = []
for node in G.nodes():
if str(G.node[node]['role']) == "R6":
list_R6s.append(node)
list_R6s_label.append(G.node[node]['label'])
list_R6s_percent_weight_change.append(
float(G.node[node]['percentage_weight_change']))
name00 = dir + name + "R6s_and_top_tens_averages_" + str(
time_in_system) + "days_exclude_R6s.dat"
file0 = open(name00, 'at')
print >> file0, "R6s", numpy.mean(
list_R6s_percent_weight_change), numpy.std(
list_R6s_percent_weight_change)
file0.close()
# print "\n\n R6s:\n"
# for i in list_R6s_label:
# print i
# studying the possible cumulative effect of more than one R6 on the population:
for node in G.nodes():
cont = 0
for n in G.neighbors(node):
if str(G.node[n]['role']) == "R6":
cont += 1
G.node[node]["R6_overlap"] = int(cont)
##### weight change for people not connected to any R6s:####
list_weight_changes_no_neighbors = []
for node in G.nodes():
interseccion = list(set(G.neighbors(node)) & set(list_R6s))
# print node, "intersection:",intersection,len(intersection)
# print "because", list_R6s, "and ",G.neighbors(node)
# raw_input()
if len(interseccion) == 0:
list_weight_changes_no_neighbors.append(
G.node[node]['percentage_weight_change'])
# print len(list_weight_changes_no_neighbors),"no_neighbors"
who = "no_neigbors_R6s"
Nbins = 18
histograma(list_weight_changes_no_neighbors, Nbins, dir, name, who)
# mood test
mood = stats.mood(list_weight_changes_no_neighbors,
list_weight_changes_not_GC)
print "mood test for", who, "against not_GC:", mood
########
# K-S test:
ks = stats.ks_2samp(list_weight_changes_no_neighbors,
list_weight_changes_not_GC)
print "KS test for", who, "against not_GC:", ks
name00 = "ks_results.dat"
file0 = open(dir + name00, 'at')
print >> file0, "KS test for", who, "of", graph_name, "against not_GC:", ks
file0.close()
#############################################
#average percentage weight change as a function of the size of the largest CLIQUE the node belongs to:
absolute_max = 1
for i in G.nodes():
maximo = 1
list2 = nx.cliques_containing_node(G, i)
# print i, list2
for elem in list2:
# print elem,len(elem,)
if len(elem) > maximo:
maximo = len(elem)
# print "\n",maximo
G.node[i]['max_clique_size'] = maximo
if absolute_max < maximo:
absolute_max = maximo
#print absolute_max
lista = list(
nx.find_cliques(G)) # crea una lista de cliques (lista de listas)
max_clique = nx.graph_clique_number(G) #finds out max size clique
num_tot_clique = nx.graph_number_of_cliques(
G) #finds out total number of cliques
# count number of 2, 3, 4, 5, 6 and 7cliques:
num_2cliques = 0
num_3cliques = 0
num_4cliques = 0
num_5cliques = 0
num_6cliques = 0
num_7cliques = 0
num_8cliques = 0
num_9cliques = 0
for element in lista:
if len(element) == 2:
num_2cliques = num_2cliques + 1
elif len(element) == 3:
num_3cliques = num_3cliques + 1
elif len(element) == 4:
num_4cliques = num_4cliques + 1
elif len(element) == 5:
num_5cliques = num_5cliques + 1
elif len(element) == 6:
num_6cliques = num_6cliques + 1
elif len(element) == 7:
num_7cliques = num_7cliques + 1
elif len(element) == 8:
num_8cliques = num_8cliques + 1
elif len(element) == 9:
num_9cliques = num_9cliques + 1
# print " 2: ",num_2cliques, " 3: ",num_3cliques, " 4: ",num_4cliques, " 5: ",num_5cliques, " 6: ",num_6cliques, " 7: ",num_7cliques, " 8: ",num_8cliques, " 9: ",num_9cliques, " max_clique_size:",max_clique, " num_tot_cliques:", num_tot_clique
name33 = dir + name + "_percent_weight_change_vs_largest_clique_size.dat"
file11 = open(name33, 'wt')
file11.close()
list_of_lists_for_bootstrap = []
x_positions_fit = []
y_positions_fit = []
cum_size_set = float(len(G.nodes()))
tot_nodes = []
for clique_size in range(1, max_clique):
clique_size = clique_size + 1
print clique_size
num_users_set = cum_size_set
percent_weight_change_that_clique_size = []
for n in G.nodes():
if G.node[n]['max_clique_size'] == clique_size:
percent_weight_change_that_clique_size.append(
float(G.node[n]['percentage_weight_change']))
tot_nodes.append(float(G.node[n]['percentage_weight_change']))
cum_size_set -= 1.0
file11 = open(name33, 'at')
print >> file11, clique_size, len(
percent_weight_change_that_clique_size), num_users_set / float(
len(G.nodes())), numpy.mean(
percent_weight_change_that_clique_size), numpy.std(
percent_weight_change_that_clique_size)
file11.close()
if len(x_positions_fit) <= 7:
x_positions_fit.append(clique_size)
y_positions_fit.append(
numpy.mean(percent_weight_change_that_clique_size))
list_of_lists_for_bootstrap.append(
percent_weight_change_that_clique_size)
slope, intercept, Corr_coef, p_value, std_err = stats.linregress(
x_positions_fit, y_positions_fit) # least squeares polinomial fit
print "result linear. fit for clique size dependency:"
print "slope:", slope, "intercept:", intercept, "Corr_coef:", Corr_coef, "p_value:", p_value, "std_err:", std_err
name11 = dir + name + "_fits_clique_size.dat"
file11 = open(name11, 'wt')
for i in range(len(x_positions_fit)):
print >> file11, x_positions_fit[
i], intercept + x_positions_fit[i] * slope
print >> file11, "\n\n", "y=", intercept, "+", slope, "*x",
print "Bootstrap for clique size:\n"
mean_slope, standard_dev = bootstrap(x_positions_fit[0],
x_positions_fit[-1],
list_of_lists_for_bootstrap)
zscore = (slope - mean_slope) / standard_dev
print >> file11, "bootstrap:\n", "actual slope:", slope, "mean_slope:", mean_slope, "standard_dev:", standard_dev, "\n zscore:", zscore
print x_positions_fit[0], x_positions_fit[
-1], "actual slope:", slope, "mean_slope:", mean_slope, "standard_dev:", standard_dev, "\n zscore:", zscore
file11.close()
contador += 1
file = open(name12, 'at')
print >> file, contador, mean_slope, standard_dev, "largest_clique_size"
file.close()
#######################################
#####dose effect of the R6s independently########
name11 = dir + name + "_dose_eff_indepently_only_one_R6_" + str(
time_in_system) + "days_exclude_R6s.dat"
file11 = open(name11, 'at')
print >> file11, 0, "average_no_neighbors", "average_no_neighbors", "average_no_neighbors", len(
list_weight_changes_no_neighbors
), numpy.mean(list_weight_changes_no_neighbors), numpy.std(
list_weight_changes_no_neighbors
) # the first line of the file is actually for no_neighbors, the rest, for one_and_only_one
file11.close()
file11 = open(name11, 'wt')
file11.close()
cont = 1
list_all = []
list_all_nodes = []
for R6 in list_R6s:
list_weight_changes = []
for n in G.neighbors(R6):
if (G.node[n]['role'] != "R6") and (G.node[n]["R6_overlap"] == 1):
list_weight_changes.append(
float(G.node[n]['percentage_weight_change']))
if n not in list_all_nodes:
list_all_nodes.append(n)
list_all.append(
float(G.node[n]['percentage_weight_change']))
if len(list_weight_changes) > 0:
file11 = open(name11, 'at')
print >> file11, cont, G.node[R6]['role'], G.node[R6][
'label'], len(
G.neighbors(R6)), len(list_weight_changes), numpy.mean(
list_weight_changes), numpy.std(list_weight_changes)
file11.close()
# print cont,G.node[R6]['role'],G.node[R6]['label'], len(G.neighbors(R6)),len(list_weight_changes),numpy.mean(list_weight_changes),numpy.std(list_weight_changes)
cont = cont + 1
else:
# file11=open(name11, 'at')
#print >> file11,cont,G.node[R6]['role'],G.node[R6]['label'],len(G.neighbors(R6)),len(list_weight_changes)
#file11.close()
# print cont,G.node[R6]['role'],G.node[R6]['label'],len(G.neighbors(R6)),len(list_weight_changes)
cont = cont + 1
who = "one_and_only_one_R6s"
Nbins = 18
histograma(list_all, Nbins, dir, name, who)
####################################
print "\n\n"
list_of_lists_for_bootstrap = []
x_positions_fit = []
y_positions_fit = []
averages_larger5_x = []
averages_larger5_y = []
norm = 0.0
cum_size_set = float(len(G.nodes())) - float(len(list_R6s))
for r in range(len(list_R6s) + 1):
# list_BMI_changes=[]
list_weight_changes = []
list_percentage_weight_changes = []
list_activities = []
num_users_set = cum_size_set
for node in G.nodes():
if int(G.node[node]["R6_overlap"]) == r:
if G.node[node]["role"] == "R6": # i exclude the R6s
pass
else:
if int(G.node[node]['time_in_system']) > time_in_system:
# list_BMI_changes.append(float(G.node[node]['final_BMI'])-float(G.node[node]['initial_BMI']))
list_weight_changes.append(
float(G.node[node]['weight_change']))
list_percentage_weight_changes.append(
float(G.node[node]['percentage_weight_change']))
list_activities.append(
float(G.node[node]['activity']) /
float(G.node[node]['time_in_system']))
cum_size_set -= 1.0
if len(list_percentage_weight_changes) > 0:
# average_BMI_change=numpy.mean(list_BMI_changes)
average_weight_change = numpy.mean(list_weight_changes)
average_percentage_weight_change = numpy.mean(
list_percentage_weight_changes)
average_activity = numpy.mean(list_activities)
#deviation_BMI=numpy.std(list_BMI_changes)
deviation_weight = numpy.std(list_weight_changes)
deviation_percentage_weight = numpy.std(
list_percentage_weight_changes)
deviation_activity = numpy.std(list_activities)
#print out
file0 = open(name0, 'at')
print >> file0, r, len(
list_percentage_weight_changes
), num_users_set / float(
len(G.nodes())
), average_percentage_weight_change, deviation_percentage_weight, average_weight_change, deviation_weight, average_activity, deviation_activity
file0.close()
if r <= 5:
x_positions_fit.append(r)
y_positions_fit.append(average_percentage_weight_change)
list_of_lists_for_bootstrap.append(
list_percentage_weight_changes)
# else:
# aux_x=r*len(list_percentage_weight_changes)
# averages_larger5_x.append(aux_x)
# aux_y=average_percentage_weight_change*len(list_percentage_weight_changes)
# averages_larger5_y.append(aux_y)
#norm+=float(len(list_percentage_weight_changes))
# x_positions_fit.append(numpy.mean(averages_larger5_x)/norm)
# y_positions_fit.append(numpy.mean(averages_larger5_y)/norm)
slope, intercept, Corr_coef, p_value, std_err = stats.linregress(
x_positions_fit, y_positions_fit) # least squeares polinomial fit
print "result linear. fit for dose eff.:"
print "slope:", slope, "intercept:", intercept, "Corr_coef:", Corr_coef, "p_value:", p_value, "std_err:", std_err
name11 = dir + name + "_fits_dose_eff_R6.dat"
file11 = open(name11, 'wt')
for i in range(len(x_positions_fit)):
print >> file11, x_positions_fit[
i], intercept + x_positions_fit[i] * slope
print >> file11, "\n\n", "y=", intercept, "+", slope, "*x",
print "Bootstrap for dose eff. R6s:\n"
mean_slope, standard_dev = bootstrap(x_positions_fit[0],
x_positions_fit[-1],
list_of_lists_for_bootstrap)
zscore = (slope - mean_slope) / standard_dev
print >> file11, "bootstrap:\n", "actual slope:", slope, "mean_slope:", mean_slope, "standard_dev:", standard_dev, "\n zscore:", zscore
print x_positions_fit[0], x_positions_fit[
-1], "actual slope:", slope, "mean_slope:", mean_slope, "standard_dev:", standard_dev, "\n zscore:", zscore
file11.close()
contador += 1
file = open(name12, 'at')
print >> file, contador, mean_slope, standard_dev, "dose_eff"
file.close()
#### averages for every R6's egonetwork:#########
cont = 1
list_all_ = []
list_all_nodes_ = []
for node in list_R6s:
neighbors = G.neighbors(node) #a list of nodes
average_BMI_change = 0.0
list_BMI_changes = []
average_weight_change = 0.0
list_weight_changes = []
average_percentage_weight_change = 0.0
list_percentage_weight_changes = []
average_activity = 0.0 # ojo! sera dividida por el numero de dias!!!!!
list_activities = []
for n in G.neighbors(node):
if int(G.node[n]['time_in_system']) > time_in_system:
# list_BMI_changes.append(float(G.node[n]['final_BMI'])-float(G.node[n]['initial_BMI']))
list_weight_changes.append(float(G.node[n]['weight_change']))
list_percentage_weight_changes.append(
float(G.node[n]['percentage_weight_change']))
list_activities.append(
float(G.node[n]['activity']) /
float(G.node[n]['time_in_system']))
if n not in list_all_nodes_:
list_all_nodes_.append(n)
list_all_.append(
float(G.node[n]['percentage_weight_change']))
#averages
average_weight_change = numpy.mean(list_weight_changes)
# average_BMI_change=numpy.mean(list_BMI_changes)
average_activity = numpy.mean(list_activities)
average_percentage_weight_change = numpy.mean(
list_percentage_weight_changes)
#standard deviation
#deviation_BMI=numpy.std(list_BMI_changes)
deviation_weight = numpy.std(list_weight_changes)
deviation_percentage_weight = numpy.std(list_percentage_weight_changes)
deviation_activity = numpy.std(list_activities)
#print out
name2 = dir + name + "_ego_R6s_average_weight_change_" + str(
time_in_system) + "days.dat"
file2 = open(name2, 'at')
print >> file2, cont, G.node[node]['role'], G.node[node]['label'], len(
G.neighbors(node)), average_weight_change, deviation_weight
file2.close()
name22 = dir + name + "_ego_R6s_average_percentage_weight_change_" + str(
time_in_system) + "days.dat"
file22 = open(name22, 'at')
print >> file22, cont, G.node[node]['role'], G.node[node][
'label'], len(
G.neighbors(node)
), average_percentage_weight_change, deviation_percentage_weight
file22.close()
name3 = dir + name + "_ego_R6s_average_activity_" + str(
time_in_system) + "days.dat"
file3 = open(name3, 'at')
print >> file3, cont, G.node[node]['role'], G.node[node]['label'], len(
G.neighbors(node)), average_activity, deviation_activity
file3.close()
cont = cont + 1
who = "R6s_egonetworks_all"
Nbins = 18
histograma(list_all_, Nbins, dir, name, who)
# print "intersection:",len(set(list_all_)&set(list_all)),len(list_all_),len(list_all)
#############just checking what happens if we remove the 40155 guy
##### percent weight change vs. role:
list_roles = ["R1", "R2", "R3", "R4", "R5", "R6", "R7"]
file = open(dir + name + "_percentage_weight_change_vs_role", 'wt')
cont = 1
for role in list_roles:
list_weight_changes_role = []
for n in G.nodes():
if G.node[n]['role'] == role:
list_weight_changes_role.append(
G.node[n]['percentage_weight_change'])
print >> file, cont, role, len(list_weight_changes_role), numpy.mean(
list_weight_changes_role), numpy.std(list_weight_changes_role)
cont += 1
file.close()
#############################
############## percentage weight change vs k
x_positions_fit = []
y_positions_fit = []
cum_size_set = float(len(G.nodes()))
list_of_lists_for_bootstrap = []
list_k = []
for n in G.nodes():
list_k.append(len(G.neighbors(n)))
max_k = max(list_k)
file = open(dir + name + "_percentage_weight_change_vs_k.dat", 'wt')
max_k = max_k + 1
for k in range(1, max_k):
num_users_set = cum_size_set
list_percent_weight_change_k = []
for n in G.nodes():
if len(G.neighbors(n)) == k:
list_percent_weight_change_k.append(
G.node[n]['percentage_weight_change'])
cum_size_set -= 1.0
if len(list_percent_weight_change_k) > 0:
print >> file, k, len(
list_percent_weight_change_k), num_users_set / float(
len(G.nodes())), numpy.mean(
list_percent_weight_change_k), numpy.std(
list_percent_weight_change_k)
if len(x_positions_fit) <= 7:
x_positions_fit.append(k)
y_positions_fit.append(
numpy.mean(list_percent_weight_change_k))
list_of_lists_for_bootstrap.append(
list_percent_weight_change_k)
slope, intercept, Corr_coef, p_value, std_err = stats.linregress(
x_positions_fit, y_positions_fit) # least squeares polinomial fit
print "result linear. fit for degree dependency:"
print "slope:", slope, "intercept:", intercept, "Corr_coef:", Corr_coef, "p_value:", p_value, "std_err:", std_err
file.close()
name11 = dir + name + "_fits_degree.dat"
file11 = open(name11, 'wt')
for i in range(len(x_positions_fit)):
print >> file11, x_positions_fit[
i], intercept + x_positions_fit[i] * slope
print >> file11, "\n\n", "y=", intercept, "+", slope, "*x",
print "Bootstrap for degree:\n"
mean_slope, standard_dev = bootstrap(x_positions_fit[0],
x_positions_fit[-1],
list_of_lists_for_bootstrap)
zscore = (slope - mean_slope) / standard_dev
print >> file11, "bootstrap:\n", "actual slope:", slope, "mean_slope:", mean_slope, "standard_dev:", standard_dev, "\n zscore:", zscore
print x_positions_fit[0], x_positions_fit[
-1], "actual slope:", slope, "mean_slope:", mean_slope, "standard_dev:", standard_dev, "\n zscore:", zscore
file11.close()
contador += 1
file = open(name12, 'at')
print >> file, contador, mean_slope, standard_dev, "degree"
file.close()
########################################
new_name = graph_name.split(".gml")[0]
new_name = new_name + "_adherent_num_R6s_largest_clique.gml"
nx.write_gml(G, new_name)
def main(graph_name):
H = nx.read_gml(graph_name)
for node in H.nodes(): # i remove self loops
if node in H.neighbors(node):
if len(H.neighbors(node))>1:
H.remove_edge(node,node)
else:
H.remove_node(node)
for node in H.nodes():
if H.node[node]['weigh_ins'] <5: #Adherent filter
H.remove_node(node)
# print node, "is going down"
G= nx.connected_component_subgraphs(H)[0] # Giant component
print "final size of the GC:",len(G.nodes())
#dir=graph_name.split("fr")[0]
#dir=graph_name.split("master")[0]
#dir=graph_name.split("method3_")[0]
dir=graph_name.split("engaged_")[0]
dir=dir+"roles/"
print dir
time_in_system=100 #minimum amount of time in the sytem for a user to be included in the statistics
#name=graph_name.split('data/')[1]
name=graph_name.split('method3/')[1]
print name
name=name.split('.gml')[0]
print name
print dir+name
name0=dir+name+"_overlap_R6s_averages_"+str(time_in_system)+"days_exclude_R6s_clinically_signif.dat"
file0=open(name0, 'wt')
file0.close()
####for the Isolated Clusters:
list_GC_nodes=[]
for n in G.nodes():
list_GC_nodes.append(n)
# print G.node[n]['percentage_weight_change']
# print "# users GC:",len(list_GC_nodes),"total:",len(H.nodes())
list_weight_changes_not_GC=[]
for n in H.nodes():
if n not in list_GC_nodes:
#print n,"not in GC"
list_weight_changes_not_GC.append(float(H.node[n]['percentage_weight_change']))
#print "# users not in GC:",len(list_weight_changes_not_GC)
who="not_GC"
Nbins=18
histograma(list_weight_changes_not_GC,Nbins,dir,name,who)
###########################
list_R6s=[] # collect the R6 of the system
list_R6s_label=[]
list_R6s_percent_weight_change=[]
for node in G.nodes() :
if str(G.node[node]['role']) == "R6" :
list_R6s.append(node)
list_R6s_label.append(G.node[node]['label'])
list_R6s_percent_weight_change.append(float(G.node[node]['percentage_weight_change']))
name00=dir+name+"R6s_and_top_tens_averages_"+str(time_in_system)+"days_exclude_R6s_clinically_signif.dat"
file0=open(name00, 'at')
print >> file0,"R6s",numpy.mean(list_R6s_percent_weight_change),numpy.std(list_R6s_percent_weight_change)
file0.close()
# print "\n\n R6s:\n"
# for i in list_R6s_label:
# print i
# studying the possible cumulative effect of more than one R6 on the population:
for node in G.nodes():
cont=0
for n in G.neighbors(node):
if str(G.node[n]['role']) == "R6" :
cont+=1
G.node[node]["R6_overlap"]=int(cont)
##### weight change for people not connected to any R6s:####
list_weight_changes_no_neighbors=[]
for node in G.nodes():
interseccion=list(set(G.neighbors(node)) & set(list_R6s))
# print node, "intersection:",intersection,len(intersection)
# print "because", list_R6s, "and ",G.neighbors(node)
# raw_input()
if len(interseccion)==0:
list_weight_changes_no_neighbors.append(G.node[node]['percentage_weight_change'])
# print len(list_weight_changes_no_neighbors),"no_neighbors"
who="no_neigbors_R6s"
Nbins=18
histograma(list_weight_changes_no_neighbors,Nbins,dir,name,who)
# mood test
mood=stats.mood(list_weight_changes_no_neighbors,list_weight_changes_not_GC)
print "mood test for",who, "against not_GC:",mood
########
# K-S test:
ks=stats.ks_2samp(list_weight_changes_no_neighbors,list_weight_changes_not_GC)
print "KS test for",who, "against not_GC:",ks
name00="ks_results_clinically_signif.dat"
file0=open(dir+name00, 'at')
print >> file0, "KS test for",who,"of",graph_name, "against not_GC:",ks
file0.close()
#############################################
#average percentage weight change as a function of the size of the largest CLIQUE the node belongs to:
absolute_max=1
for i in G.nodes():
maximo=1
list2=nx.cliques_containing_node(G, i)
# print i, list2
for elem in list2:
# print elem,len(elem,)
if len(elem) > maximo:
maximo=len(elem)
# print "\n",maximo
G.node[i]['max_clique_size']=maximo
if absolute_max < maximo:
absolute_max = maximo
print absolute_max
lista=list(nx.find_cliques(G)) # crea una lista de cliques (lista de listas)
max_clique=nx.graph_clique_number(G) #finds out max size clique
num_tot_clique=nx.graph_number_of_cliques(G) #finds out total number of cliques
# count number of 2, 3, 4, 5, 6 and 7cliques:
num_2cliques=0
num_3cliques=0
num_4cliques=0
num_5cliques=0
num_6cliques=0
num_7cliques=0
num_8cliques=0
num_9cliques=0
for element in lista:
if len(element)==2:
num_2cliques=num_2cliques +1
elif len(element)==3:
num_3cliques=num_3cliques+1
elif len(element)==4:
num_4cliques=num_4cliques+1
elif len(element)==5:
num_5cliques=num_5cliques+1
elif len(element)==6:
num_6cliques=num_6cliques+1
elif len(element)==7:
num_7cliques=num_7cliques+1
elif len(element)==8:
num_8cliques=num_8cliques+1
elif len(element)==9:
num_9cliques=num_9cliques+1
print " 2: ",num_2cliques, " 3: ",num_3cliques, " 4: ",num_4cliques, " 5: ",num_5cliques, " 6: ",num_6cliques, " 7: ",num_7cliques, " 8: ",num_8cliques, " 9: ",num_9cliques, " max_clique_size:",max_clique, " num_tot_cliques:", num_tot_clique
name33=dir+name+"_percent_weight_change_vs_largest_clique_size_clinically_signif.dat"
file11=open(name33, 'wt')
file11.close()
cum_size_set=float(len(G.nodes()))
tot_nodes=[]
for clique_size in range(max_clique):
clique_size=clique_size+1
num_users_clinically_signif=0.0
num_users_set=cum_size_set
percent_weight_change_that_clique_size=[]
for n in G.nodes():
if G.node[n]['max_clique_size']==clique_size:
percent_weight_change_that_clique_size.append(float(G.node[n]['percentage_weight_change']))
tot_nodes.append(float(G.node[n]['percentage_weight_change']))
cum_size_set-=1.0
if G.node [n]['percentage_weight_change']<=-5.0:
num_users_clinically_signif+=1.0
try:
file11=open(name33, 'at')
print >> file11,clique_size,len(percent_weight_change_that_clique_size),num_users_set/float(len(G.nodes())),num_users_clinically_signif/len(percent_weight_change_that_clique_size),numpy.mean(percent_weight_change_that_clique_size),numpy.std(percent_weight_change_that_clique_size)
file11.close()
except ZeroDivisionError:
file11=open(name33, 'at')
print >> file11,clique_size,len(percent_weight_change_that_clique_size),num_users_set/float(len(G.nodes())),0.0 ,numpy.mean(percent_weight_change_that_clique_size),numpy.std(percent_weight_change_that_clique_size)
file11.close()
#######################################
#####dose effect of the R6s independently########
name11=dir+name+"_dose_eff_indepently_only_one_R6_"+str(time_in_system)+"days_exclude_R6s.dat"
file11=open(name11, 'at')
print >> file11,0,"average_no_neighbors","average_no_neighbors","average_no_neighbors",len(list_weight_changes_no_neighbors),numpy.mean(list_weight_changes_no_neighbors),numpy.std(list_weight_changes_no_neighbors) # the first line of the file is actually for no_neighbors, the rest, for one_and_only_one
file11.close()
file11=open(name11, 'wt')
file11.close()
cont=1
list_all=[]
list_all_nodes=[]
for R6 in list_R6s:
list_weight_changes=[]
for n in G.neighbors(R6):
if (G.node[n]['role'] != "R6") and ( G.node[n]["R6_overlap"]==1) :
list_weight_changes.append(float(G.node[n]['percentage_weight_change']))
if n not in list_all_nodes:
list_all_nodes.append(n)
list_all.append(float(G.node[n]['percentage_weight_change']))
if len(list_weight_changes)>0:
file11=open(name11, 'at')
print >> file11,cont,G.node[R6]['role'],G.node[R6]['label'],len(G.neighbors(R6)),len(list_weight_changes),numpy.mean(list_weight_changes),numpy.std(list_weight_changes)
file11.close()
# print cont,G.node[R6]['role'],G.node[R6]['label'], len(G.neighbors(R6)),len(list_weight_changes),numpy.mean(list_weight_changes),numpy.std(list_weight_changes)
cont=cont+1
else:
# file11=open(name11, 'at')
#print >> file11,cont,G.node[R6]['role'],G.node[R6]['label'],len(G.neighbors(R6)),len(list_weight_changes)
#file11.close()
# print cont,G.node[R6]['role'],G.node[R6]['label'],len(G.neighbors(R6)),len(list_weight_changes)
cont=cont+1
who="one_and_only_one_R6s"
Nbins=18
histograma(list_all,Nbins,dir,name,who)
####################################
cum_size_set=float(len(G.nodes()))-float(len(list_R6s))
for r in range(len(list_R6s)+1):
# list_BMI_changes=[]
list_weight_changes=[]
list_percentage_weight_changes=[]
list_activities=[]
num_users_clinically_signif=0.0
num_users_set=cum_size_set
for node in G.nodes():
if int(G.node[node]["R6_overlap"])==r:
if G.node[node]["role"]== "R6": # i exclude the R6s
pass
else:
if int(G.node[node]['time_in_system']) > time_in_system:
# list_BMI_changes.append(float(G.node[node]['final_BMI'])-float(G.node[node]['initial_BMI']))
list_weight_changes.append(float(G.node[node]['weight_change']))
list_percentage_weight_changes.append(float(G.node[node]['percentage_weight_change']))
list_activities.append(float(G.node[node]['activity'])/float(G.node[node]['time_in_system']))
cum_size_set-=1.0
if G.node [node]['percentage_weight_change']<=-5.0:
num_users_clinically_signif+=1.0
if len(list_percentage_weight_changes)>0:
# average_BMI_change=numpy.mean(list_BMI_changes)
average_weight_change=numpy.mean(list_weight_changes)
average_percentage_weight_change=numpy.mean(list_percentage_weight_changes)
average_activity=numpy.mean(list_activities)
#deviation_BMI=numpy.std(list_BMI_changes)
deviation_weight=numpy.std(list_weight_changes)
deviation_percentage_weight=numpy.std(list_percentage_weight_changes)
deviation_activity=numpy.std(list_activities)
#print out
try:
file0=open(name0, 'at')
print >> file0,r,len(list_percentage_weight_changes),num_users_set/float(len(G.nodes())),num_users_clinically_signif/len(list_percentage_weight_changes),average_percentage_weight_change,deviation_percentage_weight,average_weight_change,deviation_weight,average_activity,deviation_activity
file0.close()
except ZeroDivisionError:
file11=open(name33, 'at')
print >> file11,clique_size,len(percent_weight_change_that_clique_size),num_users_set/float(len(G.nodes())),0.0 ,numpy.mean(percent_weight_change_that_clique_size),numpy.std(percent_weight_change_that_clique_size)
file11.close()
#### averages for every R6's egonetwork:#########
cont=1
list_all_=[]
list_all_nodes_=[]
for node in list_R6s:
neighbors=G.neighbors(node)#a list of nodes
average_BMI_change=0.0
list_BMI_changes=[]
average_weight_change=0.0
list_weight_changes=[]
average_percentage_weight_change=0.0
list_percentage_weight_changes=[]
average_activity=0.0 # ojo! sera dividida por el numero de dias!!!!!
list_activities=[]
for n in G.neighbors(node):
if int(G.node[n]['time_in_system']) > time_in_system:
# list_BMI_changes.append(float(G.node[n]['final_BMI'])-float(G.node[n]['initial_BMI']))
list_weight_changes.append(float(G.node[n]['weight_change']))
list_percentage_weight_changes.append(float(G.node[n]['percentage_weight_change']))
list_activities.append(float(G.node[n]['activity'])/float(G.node[n]['time_in_system']))
if n not in list_all_nodes_:
list_all_nodes_.append(n)
list_all_.append(float(G.node[n]['percentage_weight_change']))
#averages
average_weight_change=numpy.mean(list_weight_changes)
# average_BMI_change=numpy.mean(list_BMI_changes)
average_activity=numpy.mean(list_activities)
average_percentage_weight_change=numpy.mean(list_percentage_weight_changes)
#standard deviation
#deviation_BMI=numpy.std(list_BMI_changes)
deviation_weight=numpy.std(list_weight_changes)
deviation_percentage_weight=numpy.std(list_percentage_weight_changes)
deviation_activity=numpy.std(list_activities)
#print out
name2=dir+name+"_ego_R6s_average_weight_change_"+str(time_in_system)+"days.dat"
file2=open(name2, 'at')
print >> file2,cont,G.node[node]['role'],G.node[node]['label'],len(G.neighbors(node)),average_weight_change,deviation_weight
file2.close()
name22=dir+name+"_ego_R6s_average_percentage_weight_change_"+str(time_in_system)+"days.dat"
file22=open(name22, 'at')
print >> file22,cont,G.node[node]['role'],G.node[node]['label'],len(G.neighbors(node)),average_percentage_weight_change,deviation_percentage_weight
file22.close()
name3=dir+name+"_ego_R6s_average_activity_"+str(time_in_system)+"days.dat"
file3=open(name3, 'at')
print >> file3,cont,G.node[node]['role'],G.node[node]['label'],len(G.neighbors(node)),average_activity,deviation_activity
file3.close()
cont=cont+1
who="R6s_egonetworks_all"
Nbins=18
histograma(list_all_,Nbins,dir,name,who)
# print "intersection:",len(set(list_all_)&set(list_all)),len(list_all_),len(list_all)
#############just checking what happens if we remove the 40155 guy
##### percent weight change vs. role:
list_roles=["R1","R2","R3","R4","R5","R6","R7"]
file = open(dir+name+"_percentage_weight_change_vs_role",'wt')
cont=1
for role in list_roles:
list_weight_changes_role=[]
for n in G.nodes():
if G.node[n]['role']==role:
list_weight_changes_role.append(G.node[n]['percentage_weight_change'])
print >> file, cont, role, len(list_weight_changes_role),numpy.mean(list_weight_changes_role),numpy.std(list_weight_changes_role)
cont+=1
file.close()
#############################
############## percentage weight change vs k
cum_size_set=float(len(G.nodes()))
list_k=[]
for n in G.nodes():
list_k.append(len(G.neighbors(n)))
max_k=max(list_k)
file = open(dir+name+"_percentage_weight_change_vs_k_clinically_signif.dat",'wt')
max_k=max_k+1
for k in range(1,max_k):
num_users_clinically_signif=0.0
num_users_set=cum_size_set
list_percent_weight_change_k=[]
for n in G.nodes():
if len(G.neighbors(n))==k:
list_percent_weight_change_k.append(G.node[n]['percentage_weight_change'])
cum_size_set-=1.0
if G.node [n]['percentage_weight_change']<=-5.0:
num_users_clinically_signif+=1.0
if len(list_percent_weight_change_k)>0:
try:
print >> file,k, len(list_percent_weight_change_k),num_users_set/float(len(G.nodes())),num_users_clinically_signif/len(list_percent_weight_change_k),numpy.mean(list_percent_weight_change_k),numpy.std(list_percent_weight_change_k)
except ZeroDivisionError:
file11=open(name33, 'at')
print >> file11,clique_size,len(percent_weight_change_that_clique_size),num_users_set/float(len(G.nodes())),0.0 ,numpy.mean(percent_weight_change_that_clique_size),numpy.std(percent_weight_change_that_clique_size)
file11.close()
file.close()
if p_value > alpha:
print('Same distributions (fail to reject H0)')
else:
print('Different distributions (reject H0)')
stat, p_value = levene(dataset['Open'], dataset['Adj Close'])
print('Levene Test')
print('-' * 40)
print('Statistics=%.3f, p=%.3f' % (stat, p_value))
# interpret
alpha = 0.05
if p_value > alpha:
print('Same distributions (fail to reject H0)')
else:
print('Different distributions (reject H0)')
stat, p_value = mood(dataset['Open'], dataset['Adj Close'])
print('Mood Test')
print('-' * 40)
print('Statistics=%.3f, p=%.3f' % (stat, p_value))
# interpret
alpha = 0.05
if p_value > alpha:
print('Same distributions (fail to reject H0)')
else:
print('Different distributions (reject H0)')
stat, p_value, med, tbl = median_test(dataset['Open'], dataset['Adj Close'],
dataset['Volume'])
print('Mood’s median test')
print('-' * 40)
def custom(a, b):
_, p = stats.mood(a, b)
return p
#==============================================================================
# print("mannwhitneyu")
# data['mannwhitneyu'] = [mannwhitneyu(x, y)[0] for (x, y) in zip(np.nan_to_num(question1_vectors),
# np.nan_to_num(question2_vectors))]
#==============================================================================
print("fligner")
data['fligner'] = [
fligner(x, y)[0] for (x, y) in zip(np.nan_to_num(question1_vectors),
np.nan_to_num(question2_vectors))
]
print("mood")
data['mood'] = [
mood(x, y)[0] for (x, y) in zip(np.nan_to_num(question1_vectors),
np.nan_to_num(question2_vectors))
]
print("ks_2samp")
data['ks_2samp'] = [
ks_2samp(x, y)[0] for (x, y) in zip(np.nan_to_num(question1_vectors),
np.nan_to_num(question2_vectors))
]
print("wilcoxon")
data['wilcoxon'] = [
wilcoxon(x, y)[0] for (x, y) in zip(np.nan_to_num(question1_vectors),
np.nan_to_num(question2_vectors))
]
def main():
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--infile", required=True, help="Tabular file.")
parser.add_argument("-o",
"--outfile",
required=True,
help="Path to the output file.")
parser.add_argument("--sample_one_cols",
help="Input format, like smi, sdf, inchi")
parser.add_argument("--sample_two_cols",
help="Input format, like smi, sdf, inchi")
parser.add_argument(
"--sample_cols",
help="Input format, like smi, sdf, inchi,separate arrays using ;",
)
parser.add_argument("--test_id", help="statistical test method")
parser.add_argument(
"--mwu_use_continuity",
action="store_true",
default=False,
help=
"Whether a continuity correction (1/2.) should be taken into account.",
)
parser.add_argument(
"--equal_var",
action="store_true",
default=False,
help=
"If set perform a standard independent 2 sample test that assumes equal population variances. If not set, perform Welch's t-test, which does not assume equal population variance.",
)
parser.add_argument(
"--reta",
action="store_true",
default=False,
help="Whether or not to return the internally computed a values.",
)
parser.add_argument(
"--fisher",
action="store_true",
default=False,
help="if true then Fisher definition is used",
)
parser.add_argument(
"--bias",
action="store_true",
default=False,
help=
"if false,then the calculations are corrected for statistical bias",
)
parser.add_argument(
"--inclusive1",
action="store_true",
default=False,
help="if false,lower_limit will be ignored",
)
parser.add_argument(
"--inclusive2",
action="store_true",
default=False,
help="if false,higher_limit will be ignored",
)
parser.add_argument(
"--inclusive",
action="store_true",
default=False,
help="if false,limit will be ignored",
)
parser.add_argument(
"--printextras",
action="store_true",
default=False,
help=
"If True, if there are extra points a warning is raised saying how many of those points there are",
)
parser.add_argument(
"--initial_lexsort",
action="store_true",
default="False",
help=
"Whether to use lexsort or quicksort as the sorting method for the initial sort of the inputs.",
)
parser.add_argument(
"--correction",
action="store_true",
default=False,
help="continuity correction ",
)
parser.add_argument(
"--axis",
type=int,
default=0,
help=
"Axis can equal None (ravel array first), or an integer (the axis over which to operate on a and b)",
)
parser.add_argument(
"--n",
type=int,
default=0,
help=
"the number of trials. This is ignored if x gives both the number of successes and failures",
)
parser.add_argument("--b",
type=int,
default=0,
help="The number of bins to use for the histogram")
parser.add_argument("--N",
type=int,
default=0,
help="Score that is compared to the elements in a.")
parser.add_argument("--ddof",
type=int,
default=0,
help="Degrees of freedom correction")
parser.add_argument(
"--score",
type=int,
default=0,
help="Score that is compared to the elements in a.",
)
parser.add_argument("--m", type=float, default=0.0, help="limits")
parser.add_argument("--mf", type=float, default=2.0, help="lower limit")
parser.add_argument("--nf", type=float, default=99.9, help="higher_limit")
parser.add_argument(
"--p",
type=float,
default=0.5,
help=
"The hypothesized probability of success. 0 <= p <= 1. The default value is p = 0.5",
)
parser.add_argument("--alpha", type=float, default=0.9, help="probability")
parser.add_argument(
"--new",
type=float,
default=0.0,
help="Value to put in place of values in a outside of bounds",
)
parser.add_argument(
"--proportiontocut",
type=float,
default=0.0,
help="Proportion (in range 0-1) of total data set to trim of each end.",
)
parser.add_argument(
"--lambda_",
type=float,
default=1.0,
help=
"lambda_ gives the power in the Cressie-Read power divergence statistic",
)
parser.add_argument(
"--imbda",
type=float,
default=0,
help=
"If lmbda is not None, do the transformation for that value.If lmbda is None, find the lambda that maximizes the log-likelihood function and return it as the second output argument.",
)
parser.add_argument(
"--base",
type=float,
default=1.6,
help="The logarithmic base to use, defaults to e",
)
parser.add_argument("--dtype", help="dtype")
parser.add_argument("--med", help="med")
parser.add_argument("--cdf", help="cdf")
parser.add_argument("--zero_method", help="zero_method options")
parser.add_argument("--dist", help="dist options")
parser.add_argument("--ties", help="ties options")
parser.add_argument("--alternative", help="alternative options")
parser.add_argument("--mode", help="mode options")
parser.add_argument("--method", help="method options")
parser.add_argument("--md", help="md options")
parser.add_argument("--center", help="center options")
parser.add_argument("--kind", help="kind options")
parser.add_argument("--tail", help="tail options")
parser.add_argument("--interpolation", help="interpolation options")
parser.add_argument("--statistic", help="statistic options")
args = parser.parse_args()
infile = args.infile
outfile = open(args.outfile, "w+")
test_id = args.test_id
nf = args.nf
mf = args.mf
imbda = args.imbda
inclusive1 = args.inclusive1
inclusive2 = args.inclusive2
sample0 = 0
sample1 = 0
sample2 = 0
if args.sample_cols is not None:
sample0 = 1
barlett_samples = []
for sample in args.sample_cols.split(";"):
barlett_samples.append(map(int, sample.split(",")))
if args.sample_one_cols is not None:
sample1 = 1
sample_one_cols = args.sample_one_cols.split(",")
if args.sample_two_cols is not None:
sample_two_cols = args.sample_two_cols.split(",")
sample2 = 1
for line in open(infile):
sample_one = []
sample_two = []
cols = line.strip().split("\t")
if sample0 == 1:
b_samples = columns_to_values(barlett_samples, line)
if sample1 == 1:
for index in sample_one_cols:
sample_one.append(cols[int(index) - 1])
if sample2 == 1:
for index in sample_two_cols:
sample_two.append(cols[int(index) - 1])
if test_id.strip() == "describe":
size, min_max, mean, uv, bs, bk = stats.describe(
map(float, sample_one))
cols.append(size)
cols.append(min_max)
cols.append(mean)
cols.append(uv)
cols.append(bs)
cols.append(bk)
elif test_id.strip() == "mode":
vals, counts = stats.mode(map(float, sample_one))
cols.append(vals)
cols.append(counts)
elif test_id.strip() == "nanmean":
m = stats.nanmean(map(float, sample_one))
cols.append(m)
elif test_id.strip() == "nanmedian":
m = stats.nanmedian(map(float, sample_one))
cols.append(m)
elif test_id.strip() == "kurtosistest":
z_value, p_value = stats.kurtosistest(map(float, sample_one))
cols.append(z_value)
cols.append(p_value)
elif test_id.strip() == "variation":
ra = stats.variation(map(float, sample_one))
cols.append(ra)
elif test_id.strip() == "itemfreq":
freq = stats.itemfreq(map(float, sample_one))
for list in freq:
elements = ",".join(map(str, list))
cols.append(elements)
elif test_id.strip() == "nanmedian":
m = stats.nanmedian(map(float, sample_one))
cols.append(m)
elif test_id.strip() == "variation":
ra = stats.variation(map(float, sample_one))
cols.append(ra)
elif test_id.strip() == "boxcox_llf":
IIf = stats.boxcox_llf(imbda, map(float, sample_one))
cols.append(IIf)
elif test_id.strip() == "tiecorrect":
fa = stats.tiecorrect(map(float, sample_one))
cols.append(fa)
elif test_id.strip() == "rankdata":
r = stats.rankdata(map(float, sample_one), method=args.md)
cols.append(r)
elif test_id.strip() == "nanstd":
s = stats.nanstd(map(float, sample_one), bias=args.bias)
cols.append(s)
elif test_id.strip() == "anderson":
A2, critical, sig = stats.anderson(map(float, sample_one),
dist=args.dist)
cols.append(A2)
for list in critical:
cols.append(list)
cols.append(",")
for list in sig:
cols.append(list)
elif test_id.strip() == "binom_test":
p_value = stats.binom_test(map(float, sample_one),
n=args.n,
p=args.p)
cols.append(p_value)
elif test_id.strip() == "gmean":
gm = stats.gmean(map(float, sample_one), dtype=args.dtype)
cols.append(gm)
elif test_id.strip() == "hmean":
hm = stats.hmean(map(float, sample_one), dtype=args.dtype)
cols.append(hm)
elif test_id.strip() == "kurtosis":
k = stats.kurtosis(
map(float, sample_one),
axis=args.axis,
fisher=args.fisher,
bias=args.bias,
)
cols.append(k)
elif test_id.strip() == "moment":
n_moment = stats.moment(map(float, sample_one), n=args.n)
cols.append(n_moment)
elif test_id.strip() == "normaltest":
k2, p_value = stats.normaltest(map(float, sample_one))
cols.append(k2)
cols.append(p_value)
elif test_id.strip() == "skew":
skewness = stats.skew(map(float, sample_one), bias=args.bias)
cols.append(skewness)
elif test_id.strip() == "skewtest":
z_value, p_value = stats.skewtest(map(float, sample_one))
cols.append(z_value)
cols.append(p_value)
elif test_id.strip() == "sem":
s = stats.sem(map(float, sample_one), ddof=args.ddof)
cols.append(s)
elif test_id.strip() == "zscore":
z = stats.zscore(map(float, sample_one), ddof=args.ddof)
for list in z:
cols.append(list)
elif test_id.strip() == "signaltonoise":
s2n = stats.signaltonoise(map(float, sample_one), ddof=args.ddof)
cols.append(s2n)
elif test_id.strip() == "percentileofscore":
p = stats.percentileofscore(map(float, sample_one),
score=args.score,
kind=args.kind)
cols.append(p)
elif test_id.strip() == "bayes_mvs":
c_mean, c_var, c_std = stats.bayes_mvs(map(float, sample_one),
alpha=args.alpha)
cols.append(c_mean)
cols.append(c_var)
cols.append(c_std)
elif test_id.strip() == "sigmaclip":
c, c_low, c_up = stats.sigmaclip(map(float, sample_one),
low=args.m,
high=args.n)
cols.append(c)
cols.append(c_low)
cols.append(c_up)
elif test_id.strip() == "kstest":
d, p_value = stats.kstest(
map(float, sample_one),
cdf=args.cdf,
N=args.N,
alternative=args.alternative,
mode=args.mode,
)
cols.append(d)
cols.append(p_value)
elif test_id.strip() == "chi2_contingency":
chi2, p, dof, ex = stats.chi2_contingency(
map(float, sample_one),
correction=args.correction,
lambda_=args.lambda_)
cols.append(chi2)
cols.append(p)
cols.append(dof)
cols.append(ex)
elif test_id.strip() == "tmean":
if nf == 0 and mf == 0:
mean = stats.tmean(map(float, sample_one))
else:
mean = stats.tmean(map(float, sample_one), (mf, nf),
(inclusive1, inclusive2))
cols.append(mean)
elif test_id.strip() == "tmin":
if mf == 0:
min = stats.tmin(map(float, sample_one))
else:
min = stats.tmin(map(float, sample_one),
lowerlimit=mf,
inclusive=args.inclusive)
cols.append(min)
elif test_id.strip() == "tmax":
if nf == 0:
max = stats.tmax(map(float, sample_one))
else:
max = stats.tmax(map(float, sample_one),
upperlimit=nf,
inclusive=args.inclusive)
cols.append(max)
elif test_id.strip() == "tvar":
if nf == 0 and mf == 0:
var = stats.tvar(map(float, sample_one))
else:
var = stats.tvar(map(float, sample_one), (mf, nf),
(inclusive1, inclusive2))
cols.append(var)
elif test_id.strip() == "tstd":
if nf == 0 and mf == 0:
std = stats.tstd(map(float, sample_one))
else:
std = stats.tstd(map(float, sample_one), (mf, nf),
(inclusive1, inclusive2))
cols.append(std)
elif test_id.strip() == "tsem":
if nf == 0 and mf == 0:
s = stats.tsem(map(float, sample_one))
else:
s = stats.tsem(map(float, sample_one), (mf, nf),
(inclusive1, inclusive2))
cols.append(s)
elif test_id.strip() == "scoreatpercentile":
if nf == 0 and mf == 0:
s = stats.scoreatpercentile(
map(float, sample_one),
map(float, sample_two),
interpolation_method=args.interpolation,
)
else:
s = stats.scoreatpercentile(
map(float, sample_one),
map(float, sample_two),
(mf, nf),
interpolation_method=args.interpolation,
)
for list in s:
cols.append(list)
elif test_id.strip() == "relfreq":
if nf == 0 and mf == 0:
rel, low_range, binsize, ex = stats.relfreq(
map(float, sample_one), args.b)
else:
rel, low_range, binsize, ex = stats.relfreq(
map(float, sample_one), args.b, (mf, nf))
for list in rel:
cols.append(list)
cols.append(low_range)
cols.append(binsize)
cols.append(ex)
elif test_id.strip() == "binned_statistic":
if nf == 0 and mf == 0:
st, b_edge, b_n = stats.binned_statistic(
map(float, sample_one),
map(float, sample_two),
statistic=args.statistic,
bins=args.b,
)
else:
st, b_edge, b_n = stats.binned_statistic(
map(float, sample_one),
map(float, sample_two),
statistic=args.statistic,
bins=args.b,
range=(mf, nf),
)
cols.append(st)
cols.append(b_edge)
cols.append(b_n)
elif test_id.strip() == "threshold":
if nf == 0 and mf == 0:
o = stats.threshold(map(float, sample_one), newval=args.new)
else:
o = stats.threshold(map(float, sample_one),
mf,
nf,
newval=args.new)
for list in o:
cols.append(list)
elif test_id.strip() == "trimboth":
o = stats.trimboth(map(float, sample_one),
proportiontocut=args.proportiontocut)
for list in o:
cols.append(list)
elif test_id.strip() == "trim1":
t1 = stats.trim1(
map(float, sample_one),
proportiontocut=args.proportiontocut,
tail=args.tail,
)
for list in t1:
cols.append(list)
elif test_id.strip() == "histogram":
if nf == 0 and mf == 0:
hi, low_range, binsize, ex = stats.histogram(
map(float, sample_one), args.b)
else:
hi, low_range, binsize, ex = stats.histogram(
map(float, sample_one), args.b, (mf, nf))
cols.append(hi)
cols.append(low_range)
cols.append(binsize)
cols.append(ex)
elif test_id.strip() == "cumfreq":
if nf == 0 and mf == 0:
cum, low_range, binsize, ex = stats.cumfreq(
map(float, sample_one), args.b)
else:
cum, low_range, binsize, ex = stats.cumfreq(
map(float, sample_one), args.b, (mf, nf))
cols.append(cum)
cols.append(low_range)
cols.append(binsize)
cols.append(ex)
elif test_id.strip() == "boxcox_normmax":
if nf == 0 and mf == 0:
ma = stats.boxcox_normmax(map(float, sample_one))
else:
ma = stats.boxcox_normmax(map(float, sample_one), (mf, nf),
method=args.method)
cols.append(ma)
elif test_id.strip() == "boxcox":
if imbda == 0:
box, ma, ci = stats.boxcox(map(float, sample_one),
alpha=args.alpha)
cols.append(box)
cols.append(ma)
cols.append(ci)
else:
box = stats.boxcox(map(float, sample_one),
imbda,
alpha=args.alpha)
cols.append(box)
elif test_id.strip() == "histogram2":
h2 = stats.histogram2(map(float, sample_one),
map(float, sample_two))
for list in h2:
cols.append(list)
elif test_id.strip() == "ranksums":
z_statistic, p_value = stats.ranksums(map(float, sample_one),
map(float, sample_two))
cols.append(z_statistic)
cols.append(p_value)
elif test_id.strip() == "ttest_1samp":
t, prob = stats.ttest_1samp(map(float, sample_one),
map(float, sample_two))
for list in t:
cols.append(list)
for list in prob:
cols.append(list)
elif test_id.strip() == "ansari":
AB, p_value = stats.ansari(map(float, sample_one),
map(float, sample_two))
cols.append(AB)
cols.append(p_value)
elif test_id.strip() == "linregress":
slope, intercept, r_value, p_value, stderr = stats.linregress(
map(float, sample_one), map(float, sample_two))
cols.append(slope)
cols.append(intercept)
cols.append(r_value)
cols.append(p_value)
cols.append(stderr)
elif test_id.strip() == "pearsonr":
cor, p_value = stats.pearsonr(map(float, sample_one),
map(float, sample_two))
cols.append(cor)
cols.append(p_value)
elif test_id.strip() == "pointbiserialr":
r, p_value = stats.pointbiserialr(map(float, sample_one),
map(float, sample_two))
cols.append(r)
cols.append(p_value)
elif test_id.strip() == "ks_2samp":
d, p_value = stats.ks_2samp(map(float, sample_one),
map(float, sample_two))
cols.append(d)
cols.append(p_value)
elif test_id.strip() == "mannwhitneyu":
mw_stats_u, p_value = stats.mannwhitneyu(
map(float, sample_one),
map(float, sample_two),
use_continuity=args.mwu_use_continuity,
)
cols.append(mw_stats_u)
cols.append(p_value)
elif test_id.strip() == "zmap":
z = stats.zmap(map(float, sample_one),
map(float, sample_two),
ddof=args.ddof)
for list in z:
cols.append(list)
elif test_id.strip() == "ttest_ind":
mw_stats_u, p_value = stats.ttest_ind(map(float, sample_one),
map(float, sample_two),
equal_var=args.equal_var)
cols.append(mw_stats_u)
cols.append(p_value)
elif test_id.strip() == "ttest_rel":
t, prob = stats.ttest_rel(map(float, sample_one),
map(float, sample_two),
axis=args.axis)
cols.append(t)
cols.append(prob)
elif test_id.strip() == "mood":
z, p_value = stats.mood(map(float, sample_one),
map(float, sample_two),
axis=args.axis)
cols.append(z)
cols.append(p_value)
elif test_id.strip() == "shapiro":
W, p_value, a = stats.shapiro(map(float, sample_one),
map(float, sample_two), args.reta)
cols.append(W)
cols.append(p_value)
for list in a:
cols.append(list)
elif test_id.strip() == "kendalltau":
k, p_value = stats.kendalltau(
map(float, sample_one),
map(float, sample_two),
initial_lexsort=args.initial_lexsort,
)
cols.append(k)
cols.append(p_value)
elif test_id.strip() == "entropy":
s = stats.entropy(map(float, sample_one),
map(float, sample_two),
base=args.base)
cols.append(s)
elif test_id.strip() == "spearmanr":
if sample2 == 1:
rho, p_value = stats.spearmanr(map(float, sample_one),
map(float, sample_two))
else:
rho, p_value = stats.spearmanr(map(float, sample_one))
cols.append(rho)
cols.append(p_value)
elif test_id.strip() == "wilcoxon":
if sample2 == 1:
T, p_value = stats.wilcoxon(
map(float, sample_one),
map(float, sample_two),
zero_method=args.zero_method,
correction=args.correction,
)
else:
T, p_value = stats.wilcoxon(
map(float, sample_one),
zero_method=args.zero_method,
correction=args.correction,
)
cols.append(T)
cols.append(p_value)
elif test_id.strip() == "chisquare":
if sample2 == 1:
rho, p_value = stats.chisquare(map(float, sample_one),
map(float, sample_two),
ddof=args.ddof)
else:
rho, p_value = stats.chisquare(map(float, sample_one),
ddof=args.ddof)
cols.append(rho)
cols.append(p_value)
elif test_id.strip() == "power_divergence":
if sample2 == 1:
stat, p_value = stats.power_divergence(
map(float, sample_one),
map(float, sample_two),
ddof=args.ddof,
lambda_=args.lambda_,
)
else:
stat, p_value = stats.power_divergence(map(float, sample_one),
ddof=args.ddof,
lambda_=args.lambda_)
cols.append(stat)
cols.append(p_value)
elif test_id.strip() == "theilslopes":
if sample2 == 1:
mpe, met, lo, up = stats.theilslopes(map(float, sample_one),
map(float, sample_two),
alpha=args.alpha)
else:
mpe, met, lo, up = stats.theilslopes(map(float, sample_one),
alpha=args.alpha)
cols.append(mpe)
cols.append(met)
cols.append(lo)
cols.append(up)
elif test_id.strip() == "combine_pvalues":
if sample2 == 1:
stat, p_value = stats.combine_pvalues(
map(float, sample_one),
method=args.med,
weights=map(float, sample_two),
)
else:
stat, p_value = stats.combine_pvalues(map(float, sample_one),
method=args.med)
cols.append(stat)
cols.append(p_value)
elif test_id.strip() == "obrientransform":
ob = stats.obrientransform(*b_samples)
for list in ob:
elements = ",".join(map(str, list))
cols.append(elements)
elif test_id.strip() == "f_oneway":
f_value, p_value = stats.f_oneway(*b_samples)
cols.append(f_value)
cols.append(p_value)
elif test_id.strip() == "kruskal":
h, p_value = stats.kruskal(*b_samples)
cols.append(h)
cols.append(p_value)
elif test_id.strip() == "friedmanchisquare":
fr, p_value = stats.friedmanchisquare(*b_samples)
cols.append(fr)
cols.append(p_value)
elif test_id.strip() == "fligner":
xsq, p_value = stats.fligner(center=args.center,
proportiontocut=args.proportiontocut,
*b_samples)
cols.append(xsq)
cols.append(p_value)
elif test_id.strip() == "bartlett":
T, p_value = stats.bartlett(*b_samples)
cols.append(T)
cols.append(p_value)
elif test_id.strip() == "levene":
w, p_value = stats.levene(center=args.center,
proportiontocut=args.proportiontocut,
*b_samples)
cols.append(w)
cols.append(p_value)
elif test_id.strip() == "median_test":
stat, p_value, m, table = stats.median_test(
ties=args.ties,
correction=args.correction,
lambda_=args.lambda_,
*b_samples)
cols.append(stat)
cols.append(p_value)
cols.append(m)
cols.append(table)
for list in table:
elements = ",".join(map(str, list))
cols.append(elements)
outfile.write("%s\n" % "\t".join(map(str, cols)))
outfile.close()
def main():
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--infile", required=True, help="Tabular file.")
parser.add_argument("-o", "--outfile", required=True, help="Path to the output file.")
parser.add_argument("--sample_one_cols", help="Input format, like smi, sdf, inchi")
parser.add_argument("--sample_two_cols", help="Input format, like smi, sdf, inchi")
parser.add_argument("--sample_cols", help="Input format, like smi, sdf, inchi,separate arrays using ;")
parser.add_argument("--test_id", help="statistical test method")
parser.add_argument(
"--mwu_use_continuity",
action="store_true",
default=False,
help="Whether a continuity correction (1/2.) should be taken into account.",
)
parser.add_argument(
"--equal_var",
action="store_true",
default=False,
help="If set perform a standard independent 2 sample test that assumes equal population variances. If not set, perform Welch's t-test, which does not assume equal population variance.",
)
parser.add_argument(
"--reta", action="store_true", default=False, help="Whether or not to return the internally computed a values."
)
parser.add_argument("--fisher", action="store_true", default=False, help="if true then Fisher definition is used")
parser.add_argument(
"--bias",
action="store_true",
default=False,
help="if false,then the calculations are corrected for statistical bias",
)
parser.add_argument("--inclusive1", action="store_true", default=False, help="if false,lower_limit will be ignored")
parser.add_argument(
"--inclusive2", action="store_true", default=False, help="if false,higher_limit will be ignored"
)
parser.add_argument("--inclusive", action="store_true", default=False, help="if false,limit will be ignored")
parser.add_argument(
"--printextras",
action="store_true",
default=False,
help="If True, if there are extra points a warning is raised saying how many of those points there are",
)
parser.add_argument(
"--initial_lexsort",
action="store_true",
default="False",
help="Whether to use lexsort or quicksort as the sorting method for the initial sort of the inputs.",
)
parser.add_argument("--correction", action="store_true", default=False, help="continuity correction ")
parser.add_argument(
"--axis",
type=int,
default=0,
help="Axis can equal None (ravel array first), or an integer (the axis over which to operate on a and b)",
)
parser.add_argument(
"--n",
type=int,
default=0,
help="the number of trials. This is ignored if x gives both the number of successes and failures",
)
parser.add_argument("--b", type=int, default=0, help="The number of bins to use for the histogram")
parser.add_argument("--N", type=int, default=0, help="Score that is compared to the elements in a.")
parser.add_argument("--ddof", type=int, default=0, help="Degrees of freedom correction")
parser.add_argument("--score", type=int, default=0, help="Score that is compared to the elements in a.")
parser.add_argument("--m", type=float, default=0.0, help="limits")
parser.add_argument("--mf", type=float, default=2.0, help="lower limit")
parser.add_argument("--nf", type=float, default=99.9, help="higher_limit")
parser.add_argument(
"--p",
type=float,
default=0.5,
help="The hypothesized probability of success. 0 <= p <= 1. The default value is p = 0.5",
)
parser.add_argument("--alpha", type=float, default=0.9, help="probability")
parser.add_argument("--new", type=float, default=0.0, help="Value to put in place of values in a outside of bounds")
parser.add_argument(
"--proportiontocut",
type=float,
default=0.0,
help="Proportion (in range 0-1) of total data set to trim of each end.",
)
parser.add_argument(
"--lambda_",
type=float,
default=1.0,
help="lambda_ gives the power in the Cressie-Read power divergence statistic",
)
parser.add_argument(
"--imbda",
type=float,
default=0,
help="If lmbda is not None, do the transformation for that value.If lmbda is None, find the lambda that maximizes the log-likelihood function and return it as the second output argument.",
)
parser.add_argument("--base", type=float, default=1.6, help="The logarithmic base to use, defaults to e")
parser.add_argument("--dtype", help="dtype")
parser.add_argument("--med", help="med")
parser.add_argument("--cdf", help="cdf")
parser.add_argument("--zero_method", help="zero_method options")
parser.add_argument("--dist", help="dist options")
parser.add_argument("--ties", help="ties options")
parser.add_argument("--alternative", help="alternative options")
parser.add_argument("--mode", help="mode options")
parser.add_argument("--method", help="method options")
parser.add_argument("--md", help="md options")
parser.add_argument("--center", help="center options")
parser.add_argument("--kind", help="kind options")
parser.add_argument("--tail", help="tail options")
parser.add_argument("--interpolation", help="interpolation options")
parser.add_argument("--statistic", help="statistic options")
args = parser.parse_args()
infile = args.infile
outfile = open(args.outfile, "w+")
test_id = args.test_id
nf = args.nf
mf = args.mf
imbda = args.imbda
inclusive1 = args.inclusive1
inclusive2 = args.inclusive2
sample0 = 0
sample1 = 0
sample2 = 0
if args.sample_cols != None:
sample0 = 1
barlett_samples = []
for sample in args.sample_cols.split(";"):
barlett_samples.append(map(int, sample.split(",")))
if args.sample_one_cols != None:
sample1 = 1
sample_one_cols = args.sample_one_cols.split(",")
if args.sample_two_cols != None:
sample_two_cols = args.sample_two_cols.split(",")
sample2 = 1
for line in open(infile):
sample_one = []
sample_two = []
cols = line.strip().split("\t")
if sample0 == 1:
b_samples = columns_to_values(barlett_samples, line)
if sample1 == 1:
for index in sample_one_cols:
sample_one.append(cols[int(index) - 1])
if sample2 == 1:
for index in sample_two_cols:
sample_two.append(cols[int(index) - 1])
if test_id.strip() == "describe":
size, min_max, mean, uv, bs, bk = stats.describe(map(float, sample_one))
cols.append(size)
cols.append(min_max)
cols.append(mean)
cols.append(uv)
cols.append(bs)
cols.append(bk)
elif test_id.strip() == "mode":
vals, counts = stats.mode(map(float, sample_one))
cols.append(vals)
cols.append(counts)
elif test_id.strip() == "nanmean":
m = stats.nanmean(map(float, sample_one))
cols.append(m)
elif test_id.strip() == "nanmedian":
m = stats.nanmedian(map(float, sample_one))
cols.append(m)
elif test_id.strip() == "kurtosistest":
z_value, p_value = stats.kurtosistest(map(float, sample_one))
cols.append(z_value)
cols.append(p_value)
elif test_id.strip() == "variation":
ra = stats.variation(map(float, sample_one))
cols.append(ra)
elif test_id.strip() == "itemfreq":
freq = stats.itemfreq(map(float, sample_one))
for list in freq:
elements = ",".join(map(str, list))
cols.append(elements)
elif test_id.strip() == "nanmedian":
m = stats.nanmedian(map(float, sample_one))
cols.append(m)
elif test_id.strip() == "variation":
ra = stats.variation(map(float, sample_one))
cols.append(ra)
elif test_id.strip() == "boxcox_llf":
IIf = stats.boxcox_llf(imbda, map(float, sample_one))
cols.append(IIf)
elif test_id.strip() == "tiecorrect":
fa = stats.tiecorrect(map(float, sample_one))
cols.append(fa)
elif test_id.strip() == "rankdata":
r = stats.rankdata(map(float, sample_one), method=args.md)
cols.append(r)
elif test_id.strip() == "nanstd":
s = stats.nanstd(map(float, sample_one), bias=args.bias)
cols.append(s)
elif test_id.strip() == "anderson":
A2, critical, sig = stats.anderson(map(float, sample_one), dist=args.dist)
cols.append(A2)
for list in critical:
cols.append(list)
cols.append(",")
for list in sig:
cols.append(list)
elif test_id.strip() == "binom_test":
p_value = stats.binom_test(map(float, sample_one), n=args.n, p=args.p)
cols.append(p_value)
elif test_id.strip() == "gmean":
gm = stats.gmean(map(float, sample_one), dtype=args.dtype)
cols.append(gm)
elif test_id.strip() == "hmean":
hm = stats.hmean(map(float, sample_one), dtype=args.dtype)
cols.append(hm)
elif test_id.strip() == "kurtosis":
k = stats.kurtosis(map(float, sample_one), axis=args.axis, fisher=args.fisher, bias=args.bias)
cols.append(k)
elif test_id.strip() == "moment":
n_moment = stats.moment(map(float, sample_one), n=args.n)
cols.append(n_moment)
elif test_id.strip() == "normaltest":
k2, p_value = stats.normaltest(map(float, sample_one))
cols.append(k2)
cols.append(p_value)
elif test_id.strip() == "skew":
skewness = stats.skew(map(float, sample_one), bias=args.bias)
cols.append(skewness)
elif test_id.strip() == "skewtest":
z_value, p_value = stats.skewtest(map(float, sample_one))
cols.append(z_value)
cols.append(p_value)
elif test_id.strip() == "sem":
s = stats.sem(map(float, sample_one), ddof=args.ddof)
cols.append(s)
elif test_id.strip() == "zscore":
z = stats.zscore(map(float, sample_one), ddof=args.ddof)
for list in z:
cols.append(list)
elif test_id.strip() == "signaltonoise":
s2n = stats.signaltonoise(map(float, sample_one), ddof=args.ddof)
cols.append(s2n)
elif test_id.strip() == "percentileofscore":
p = stats.percentileofscore(map(float, sample_one), score=args.score, kind=args.kind)
cols.append(p)
elif test_id.strip() == "bayes_mvs":
c_mean, c_var, c_std = stats.bayes_mvs(map(float, sample_one), alpha=args.alpha)
cols.append(c_mean)
cols.append(c_var)
cols.append(c_std)
elif test_id.strip() == "sigmaclip":
c, c_low, c_up = stats.sigmaclip(map(float, sample_one), low=args.m, high=args.n)
cols.append(c)
cols.append(c_low)
cols.append(c_up)
elif test_id.strip() == "kstest":
d, p_value = stats.kstest(
map(float, sample_one), cdf=args.cdf, N=args.N, alternative=args.alternative, mode=args.mode
)
cols.append(d)
cols.append(p_value)
elif test_id.strip() == "chi2_contingency":
chi2, p, dof, ex = stats.chi2_contingency(
map(float, sample_one), correction=args.correction, lambda_=args.lambda_
)
cols.append(chi2)
cols.append(p)
cols.append(dof)
cols.append(ex)
elif test_id.strip() == "tmean":
if nf is 0 and mf is 0:
mean = stats.tmean(map(float, sample_one))
else:
mean = stats.tmean(map(float, sample_one), (mf, nf), (inclusive1, inclusive2))
cols.append(mean)
elif test_id.strip() == "tmin":
if mf is 0:
min = stats.tmin(map(float, sample_one))
else:
min = stats.tmin(map(float, sample_one), lowerlimit=mf, inclusive=args.inclusive)
cols.append(min)
elif test_id.strip() == "tmax":
if nf is 0:
max = stats.tmax(map(float, sample_one))
else:
max = stats.tmax(map(float, sample_one), upperlimit=nf, inclusive=args.inclusive)
cols.append(max)
elif test_id.strip() == "tvar":
if nf is 0 and mf is 0:
var = stats.tvar(map(float, sample_one))
else:
var = stats.tvar(map(float, sample_one), (mf, nf), (inclusive1, inclusive2))
cols.append(var)
elif test_id.strip() == "tstd":
if nf is 0 and mf is 0:
std = stats.tstd(map(float, sample_one))
else:
std = stats.tstd(map(float, sample_one), (mf, nf), (inclusive1, inclusive2))
cols.append(std)
elif test_id.strip() == "tsem":
if nf is 0 and mf is 0:
s = stats.tsem(map(float, sample_one))
else:
s = stats.tsem(map(float, sample_one), (mf, nf), (inclusive1, inclusive2))
cols.append(s)
elif test_id.strip() == "scoreatpercentile":
if nf is 0 and mf is 0:
s = stats.scoreatpercentile(
map(float, sample_one), map(float, sample_two), interpolation_method=args.interpolation
)
else:
s = stats.scoreatpercentile(
map(float, sample_one), map(float, sample_two), (mf, nf), interpolation_method=args.interpolation
)
for list in s:
cols.append(list)
elif test_id.strip() == "relfreq":
if nf is 0 and mf is 0:
rel, low_range, binsize, ex = stats.relfreq(map(float, sample_one), args.b)
else:
rel, low_range, binsize, ex = stats.relfreq(map(float, sample_one), args.b, (mf, nf))
for list in rel:
cols.append(list)
cols.append(low_range)
cols.append(binsize)
cols.append(ex)
elif test_id.strip() == "binned_statistic":
if nf is 0 and mf is 0:
st, b_edge, b_n = stats.binned_statistic(
map(float, sample_one), map(float, sample_two), statistic=args.statistic, bins=args.b
)
else:
st, b_edge, b_n = stats.binned_statistic(
map(float, sample_one),
map(float, sample_two),
statistic=args.statistic,
bins=args.b,
range=(mf, nf),
)
cols.append(st)
cols.append(b_edge)
cols.append(b_n)
elif test_id.strip() == "threshold":
if nf is 0 and mf is 0:
o = stats.threshold(map(float, sample_one), newval=args.new)
else:
o = stats.threshold(map(float, sample_one), mf, nf, newval=args.new)
for list in o:
cols.append(list)
elif test_id.strip() == "trimboth":
o = stats.trimboth(map(float, sample_one), proportiontocut=args.proportiontocut)
for list in o:
cols.append(list)
elif test_id.strip() == "trim1":
t1 = stats.trim1(map(float, sample_one), proportiontocut=args.proportiontocut, tail=args.tail)
for list in t1:
cols.append(list)
elif test_id.strip() == "histogram":
if nf is 0 and mf is 0:
hi, low_range, binsize, ex = stats.histogram(map(float, sample_one), args.b)
else:
hi, low_range, binsize, ex = stats.histogram(map(float, sample_one), args.b, (mf, nf))
cols.append(hi)
cols.append(low_range)
cols.append(binsize)
cols.append(ex)
elif test_id.strip() == "cumfreq":
if nf is 0 and mf is 0:
cum, low_range, binsize, ex = stats.cumfreq(map(float, sample_one), args.b)
else:
cum, low_range, binsize, ex = stats.cumfreq(map(float, sample_one), args.b, (mf, nf))
cols.append(cum)
cols.append(low_range)
cols.append(binsize)
cols.append(ex)
elif test_id.strip() == "boxcox_normmax":
if nf is 0 and mf is 0:
ma = stats.boxcox_normmax(map(float, sample_one))
else:
ma = stats.boxcox_normmax(map(float, sample_one), (mf, nf), method=args.method)
cols.append(ma)
elif test_id.strip() == "boxcox":
if imbda is 0:
box, ma, ci = stats.boxcox(map(float, sample_one), alpha=args.alpha)
cols.append(box)
cols.append(ma)
cols.append(ci)
else:
box = stats.boxcox(map(float, sample_one), imbda, alpha=args.alpha)
cols.append(box)
elif test_id.strip() == "histogram2":
h2 = stats.histogram2(map(float, sample_one), map(float, sample_two))
for list in h2:
cols.append(list)
elif test_id.strip() == "ranksums":
z_statistic, p_value = stats.ranksums(map(float, sample_one), map(float, sample_two))
cols.append(z_statistic)
cols.append(p_value)
elif test_id.strip() == "ttest_1samp":
t, prob = stats.ttest_1samp(map(float, sample_one), map(float, sample_two))
for list in t:
cols.append(list)
for list in prob:
cols.append(list)
elif test_id.strip() == "ansari":
AB, p_value = stats.ansari(map(float, sample_one), map(float, sample_two))
cols.append(AB)
cols.append(p_value)
elif test_id.strip() == "linregress":
slope, intercept, r_value, p_value, stderr = stats.linregress(
map(float, sample_one), map(float, sample_two)
)
cols.append(slope)
cols.append(intercept)
cols.append(r_value)
cols.append(p_value)
cols.append(stderr)
elif test_id.strip() == "pearsonr":
cor, p_value = stats.pearsonr(map(float, sample_one), map(float, sample_two))
cols.append(cor)
cols.append(p_value)
elif test_id.strip() == "pointbiserialr":
r, p_value = stats.pointbiserialr(map(float, sample_one), map(float, sample_two))
cols.append(r)
cols.append(p_value)
elif test_id.strip() == "ks_2samp":
d, p_value = stats.ks_2samp(map(float, sample_one), map(float, sample_two))
cols.append(d)
cols.append(p_value)
elif test_id.strip() == "mannwhitneyu":
mw_stats_u, p_value = stats.mannwhitneyu(
map(float, sample_one), map(float, sample_two), use_continuity=args.mwu_use_continuity
)
cols.append(mw_stats_u)
cols.append(p_value)
elif test_id.strip() == "zmap":
z = stats.zmap(map(float, sample_one), map(float, sample_two), ddof=args.ddof)
for list in z:
cols.append(list)
elif test_id.strip() == "ttest_ind":
mw_stats_u, p_value = stats.ttest_ind(
map(float, sample_one), map(float, sample_two), equal_var=args.equal_var
)
cols.append(mw_stats_u)
cols.append(p_value)
elif test_id.strip() == "ttest_rel":
t, prob = stats.ttest_rel(map(float, sample_one), map(float, sample_two), axis=args.axis)
cols.append(t)
cols.append(prob)
elif test_id.strip() == "mood":
z, p_value = stats.mood(map(float, sample_one), map(float, sample_two), axis=args.axis)
cols.append(z)
cols.append(p_value)
elif test_id.strip() == "shapiro":
W, p_value, a = stats.shapiro(map(float, sample_one), map(float, sample_two), args.reta)
cols.append(W)
cols.append(p_value)
for list in a:
cols.append(list)
elif test_id.strip() == "kendalltau":
k, p_value = stats.kendalltau(
map(float, sample_one), map(float, sample_two), initial_lexsort=args.initial_lexsort
)
cols.append(k)
cols.append(p_value)
elif test_id.strip() == "entropy":
s = stats.entropy(map(float, sample_one), map(float, sample_two), base=args.base)
cols.append(s)
elif test_id.strip() == "spearmanr":
if sample2 == 1:
rho, p_value = stats.spearmanr(map(float, sample_one), map(float, sample_two))
else:
rho, p_value = stats.spearmanr(map(float, sample_one))
cols.append(rho)
cols.append(p_value)
elif test_id.strip() == "wilcoxon":
if sample2 == 1:
T, p_value = stats.wilcoxon(
map(float, sample_one),
map(float, sample_two),
zero_method=args.zero_method,
correction=args.correction,
)
else:
T, p_value = stats.wilcoxon(
map(float, sample_one), zero_method=args.zero_method, correction=args.correction
)
cols.append(T)
cols.append(p_value)
elif test_id.strip() == "chisquare":
if sample2 == 1:
rho, p_value = stats.chisquare(map(float, sample_one), map(float, sample_two), ddof=args.ddof)
else:
rho, p_value = stats.chisquare(map(float, sample_one), ddof=args.ddof)
cols.append(rho)
cols.append(p_value)
elif test_id.strip() == "power_divergence":
if sample2 == 1:
stat, p_value = stats.power_divergence(
map(float, sample_one), map(float, sample_two), ddof=args.ddof, lambda_=args.lambda_
)
else:
stat, p_value = stats.power_divergence(map(float, sample_one), ddof=args.ddof, lambda_=args.lambda_)
cols.append(stat)
cols.append(p_value)
elif test_id.strip() == "theilslopes":
if sample2 == 1:
mpe, met, lo, up = stats.theilslopes(map(float, sample_one), map(float, sample_two), alpha=args.alpha)
else:
mpe, met, lo, up = stats.theilslopes(map(float, sample_one), alpha=args.alpha)
cols.append(mpe)
cols.append(met)
cols.append(lo)
cols.append(up)
elif test_id.strip() == "combine_pvalues":
if sample2 == 1:
stat, p_value = stats.combine_pvalues(
map(float, sample_one), method=args.med, weights=map(float, sample_two)
)
else:
stat, p_value = stats.combine_pvalues(map(float, sample_one), method=args.med)
cols.append(stat)
cols.append(p_value)
elif test_id.strip() == "obrientransform":
ob = stats.obrientransform(*b_samples)
for list in ob:
elements = ",".join(map(str, list))
cols.append(elements)
elif test_id.strip() == "f_oneway":
f_value, p_value = stats.f_oneway(*b_samples)
cols.append(f_value)
cols.append(p_value)
elif test_id.strip() == "kruskal":
h, p_value = stats.kruskal(*b_samples)
cols.append(h)
cols.append(p_value)
elif test_id.strip() == "friedmanchisquare":
fr, p_value = stats.friedmanchisquare(*b_samples)
cols.append(fr)
cols.append(p_value)
elif test_id.strip() == "fligner":
xsq, p_value = stats.fligner(center=args.center, proportiontocut=args.proportiontocut, *b_samples)
cols.append(xsq)
cols.append(p_value)
elif test_id.strip() == "bartlett":
T, p_value = stats.bartlett(*b_samples)
cols.append(T)
cols.append(p_value)
elif test_id.strip() == "levene":
w, p_value = stats.levene(center=args.center, proportiontocut=args.proportiontocut, *b_samples)
cols.append(w)
cols.append(p_value)
elif test_id.strip() == "median_test":
stat, p_value, m, table = stats.median_test(
ties=args.ties, correction=args.correction, lambda_=args.lambda_, *b_samples
)
cols.append(stat)
cols.append(p_value)
cols.append(m)
cols.append(table)
for list in table:
elements = ",".join(map(str, list))
cols.append(elements)
outfile.write("%s\n" % "\t".join(map(str, cols)))
outfile.close()
def test_mood():
# numbers from R: mood.test in package stats
x1 = np.arange(5)
assert_array_almost_equal(stats.mood(x1, x1**2),
(-1.3830857299399906, 0.16663858066771478), 11)
def test_moodTest_zResult(self):
data_1 = np.random.randint(0, 100, 1000)
data_2 = np.random.normal(0, 100, 1000)
z1, p1 = mood_test(data_1, data_2)
z2, p2 = mood(data_1, data_2)
assert pytest.approx(z2) == z1