def test2(self):
R = DataFrame([('SUBJECT', [1, 2]), ('TIMEOFDAY', ['T1', 'T1']), ('COURSE', ['C1', 'C2']), ('MODEL', ['M1', 'M1']), ('ERROR', [10, 10])])
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
df.where_update([('ERROR', '=', 10)])
self.assertEqual(repr(df),repr(R))
def test6(self):
R = DataFrame([('SUBJECT', [1, 1, 1, 1, 1, 1, 2, 2, 2, 3, 3, 3, 3, 3, 3]), ('TIMEOFDAY', ['T1', 'T1', 'T1', 'T2', 'T2', 'T2', 'T2', 'T2', 'T2', 'T1', 'T1', 'T1', 'T2', 'T2', 'T2']), ('COURSE', ['C1', 'C1', 'C1', 'C1', 'C1', 'C1', 'C1', 'C1', 'C1', 'C1', 'C1', 'C1', 'C1', 'C1', 'C1']), ('MODEL', ['M1', 'M2', 'M3', 'M1', 'M2', 'M3', 'M1', 'M2', 'M3', 'M1', 'M2', 'M3', 'M1', 'M2', 'M3']), ('ERROR', [10, 8, 6, 5, 4, 3, 4, 3, 3, 8, 7, 4, 4, 1, 2])])
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
df.where_update([('COURSE','=',['C1']),('TIMEOFDAY','in',["T1", "T2"])])
self.assertEqual(repr(df),repr(R))
def test0(self):
R = DataFrame([('SUBJECT', [1, 2]), ('TIMEOFDAY', [u'T1', u'T1']),
('COURSE', [u'C1', u'C2']), ('MODEL', [u'M1', u'M1']),
('ERROR', [10, 10])])
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
df2 = df.where('ERROR = 10')
self.assertEqual(repr(df2), repr(R))
def test1(self):
self.df1 = DataFrame()
self.df2 = DataFrame()
self.df1.read_tbl('data/words~ageXcondition.csv')
self.df2.read_tbl('data/words~ageXcondition.csv')
# add an extra key to df1
self.df1['EXTRA'] = [5 for a in self.df1['AGE']]
with self.assertRaises(Exception) as cm:
self.df1.attach(self.df2)
self.assertEqual(str(cm.exception),
'self and other must have the same columns')
def test00(self):
# skip 4 lines
# DON'T MESS WITH THE SPACING
with open('test.csv', 'wb') as f:
f.write("""
x,y,z
1,5,9
2,6,10
3,7,11
4,8,12""")
self.df = DataFrame()
self.df.read_tbl('data/skiptest.csv', skip=4)
D = list(self.df['x']) + \
list(self.df['y']) + \
list(self.df['z'])
R = list(range(1, 13))
for (d, r) in zip(D, R):
self.assertAlmostEqual(d, r)
def test11(self):
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
D = str(df.descriptives('ERROR'))
R = """\
Descriptive Statistics
ERROR
==========================
count 48.000
mean 3.896
mode 3.000
var 5.797
stdev 2.408
sem 0.348
rms 4.567
min 0.000
Q1 2.000
median 3.000
Q3 5.000
max 10.000
range 10.000
95ci_lower 3.215
95ci_upper 4.577 """
self.assertEqual(D, R)
def test1(self):
R = {
'd': [
np.array([
9, 8, 6, 8, 10, 4, 6, 5, 7, 7, 7, 9, 6, 6, 6, 11, 6, 3, 8,
7, 11, 13, 8, 6, 14, 11, 13, 13, 10, 11, 12, 11, 16, 11, 9,
23, 12, 10, 19, 11, 10, 19, 14, 5, 10, 11, 14, 15, 11, 11
]),
np.array([
8, 6, 4, 6, 7, 6, 5, 7, 9, 7, 10, 7, 8, 10, 4, 7, 10, 6, 7,
7, 14, 11, 18, 14, 13, 22, 17, 16, 12, 11, 20, 16, 16, 15,
18, 16, 20, 22, 14, 19, 21, 19, 17, 15, 22, 16, 22, 22, 18,
21
])
],
'fname':
'output\\box(WORDS~AGE).png',
'maintitle':
'WORDS by AGE',
'xlabels': ['AGE = old', 'AGE = young']
}
df = DataFrame()
df.TESTMODE = True
df.read_tbl('data/words~ageXcondition.csv')
D = df.box_plot('WORDS', ['AGE'], output_dir='output')
self.assertEqual(D['fname'], R['fname'])
self.assertEqual(D['maintitle'], R['maintitle'])
self.assertEqual(D['xlabels'], R['xlabels'])
for d, r in zip(np.array(D['d']).flat, np.array(R['d']).flat):
self.assertAlmostEqual(d, r)
def test1(self):
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY', 'MODEL'], ['COURSE'])
self.assertEqual(repr(eval(repr(pt))), repr(pt))
def test1(self):
df = DataFrame()
with self.assertRaises(Exception) as cm:
df.insert([1, 2, 3, 4])
self.assertEqual(str(cm.exception), 'row must be mappable type')
def test2(self):
## Between-Subjects test
df=DataFrame()
fname='words~ageXcondition.csv'
df.read_tbl(fname)
aov=Anova()
aov.run(df,'WORDS',bfactors=['AGE','CONDITION'])
def test01(self):
df = DataFrame()
df.TESTMODE = True
df.read_tbl('data/iqbrainsize.txt', delimiter='\t')
D = df.scatter_plot('TOTVOL', 'FIQ', output_dir='output')
self.assertEqual(None, D['trend'])
def do_anovas(some_df, variable):
'''
This method takes a dataframe, returns the pyvttbl
anova object for that element
'''
pyv_df = DataFrame()
if variable == 'qp':
pyv_df['qual'] = str_list(some_df['qualification_performance'])
pyv_df['vals'] = int_list(some_df['adj_diffs'])
elif variable == 'ed':
pyv_df['qual'] = str_list(some_df['education_level'])
pyv_df['vals'] = int_list(some_df['adj_diffs'])
elif variable == 'fp':
pyv_df['qual'] = str_list(some_df['fps'])
pyv_df['vals'] = int_list(some_df['adj_diffs'])
else:
return None
anova = pyv_df.anova1way('vals', 'qual')
anova['omega-sq'] = get_w(anova)
return anova
def test1(self):
R = """\
t-Test: One Sample for means
SUPPRESSION
=====================================
Sample Mean 19.541
Hypothesized Pop. Mean 17
Variance 228.326
Observations 384
df 383
t Stat 3.295
alpha 0.050
P(T<=t) one-tail 5.384e-04
t Critical one-tail 1.966
P(T<=t) two-tail 0.001
t Critical two-tail 1.649
P(T<=t) two-tail 0.001
Effect size d 0.168
delta 3.295
Observed power one-tail 0.950
Observed power two-tail 0.908 """
df = DataFrame()
df.read_tbl('data/suppression~subjectXgroupXageXcycleXphase.csv')
D = df.ttest('SUPPRESSION', pop_mean=17.)
self.assertEqual(str(D), R)
def test03(self):
# duplicate labels
with open('test.csv', 'wb') as f:
f.write("""
x,x,x
1,5,9
2,6,10
3,7,11
4,8,12""")
self.df = DataFrame()
with warnings.catch_warnings(record=True) as w:
# Cause all warnings to always be triggered.
warnings.simplefilter("always")
# Trigger a warning.
self.df.read_tbl('test.csv', skip=1, labels=True)
assert issubclass(w[-1].category, RuntimeWarning)
D = list(self.df['x']) + \
list(self.df['x_2'])+ \
list(self.df['x_3'])
R = list(range(1, 13))
for (d, r) in zip(D, R):
self.assertAlmostEqual(d, r)
def test2(self):
R = """Chi-Square: Single Factor
SUMMARY
1 2 3 4 5
=====================================================
Observed 7 20 23 9 0
Expected 11.800 11.800 11.800 11.800 11.800
CHI-SQUARE TESTS
Value df P
=============================================
Pearson Chi-Square 30.746 4 3.450e-06
Likelihood Ratio nan nan nan
Observations 59 """
df = DataFrame()
df.read_tbl('chi_test.csv')
X = df.chisquare1way('RESULT', {
1: 11.8,
2: 11.8,
3: 11.8,
4: 11.8,
5: 11.8
})
self.assertEqual(str(X), R)
def test4(self):
"""method='full', aggregate=count, invalid row"""
R = """\
count(id)
member Name=name1, Name=name1, Name=name2, Name=name2, Total
Year=2010 Year=2011 Year=2010 Year=2011
======================================================================
N 0 1 -- 0 1
Y 1 0 -- 1 2
======================================================================
Total 1 1 -- 1 3 """
df = DataFrame()
df.insert({'id': 0, 'Name': 'name1', 'Year': 2010, 'member': 'Y'})
df.insert({'id': 1, 'Name': 'name1', 'Year': 2011, 'member': 'N'})
df.insert({'id': 2, 'Name': 'name2', 'Year': 2011, 'member': 'Y'})
my_pivot = df.pivot('id',
rows=['member'],
cols=['Name', 'Year'],
aggregate='count',
method='full')
self.assertEqual(R, str(my_pivot))
def test1(self):
df = DataFrame()
fname = 'error~subjectXtimeofdayXcourseXmodel.csv'
df.read_tbl(fname)
aov = df.anova('ERROR', wfactors=['TIMEOFDAY', 'COURSE',
'MODEL']) #,transform='windsor05')
aov.output2html(fname[:-4] + 'RESULTS.htm')
def test3(self):
"""method='full', aggregate=count, invalid row"""
R = """\
count(id)
Name Year member=N member=Y Total
==========================================
name1 2010 0 1 1
name1 2011 1 0 1
name2 2010 -- -- --
name2 2011 0 1 1
==========================================
Total 1 2 3 """
df = DataFrame()
df.insert({'id': 0, 'Name': 'name1', 'Year': 2010, 'member': 'Y'})
df.insert({'id': 1, 'Name': 'name1', 'Year': 2011, 'member': 'N'})
df.insert({'id': 2, 'Name': 'name2', 'Year': 2011, 'member': 'Y'})
my_pivot = df.pivot('id',
rows=['Name', 'Year'],
cols=['member'],
aggregate='count',
method='full')
self.assertEqual(R, str(my_pivot))
def test1(self):
R="""Bivariate Correlations
A B C
======================================================
A spearman 1 0.958 -0.924
Sig (2-tailed) . 9.699e-12 2.259e-09
N 21 21 21
------------------------------------------------------
B spearman 0.958 1 -0.890
Sig (2-tailed) 9.699e-12 . 0.000
N 21 21 21
------------------------------------------------------
C spearman -0.924 -0.890 1
Sig (2-tailed) 2.259e-09 0.000 .
N 21 21 21
Larzelere and Mulaik Significance Testing
Pair i Correlation P alpha/(k-i+1) Sig.
============================================================
A vs. B 1 0.958 9.699e-12 0.017 **
A vs. C 2 0.924 2.259e-09 0.025 **
B vs. C 3 0.890 6.850e-08 0.050 ** """
df=DataFrame()
df['A']=[24,61,59,46,43,44,52,43,58,67,62,57,71,49,54,43,53,57,49,56,33]
df['B']=[42.93472681237495, 78.87307334936268, 75.37292628918023, 65.49076317291956, 55.55965179772366, 56.777730638998236, 62.19451880792437, 54.73710611356715, 72.10021832823149, 85.94377749485642, 78.2087578930983, 72.01681829338037, 84.27889316830063, 60.20516982367225, 65.6276497088971, 62.36549856901088, 69.18772114281175, 67.00548667483324, 59.042687027269466, 71.99214593063917, 45.00831155783992]
df['C']=[-53.05540625388731, -96.33996451998567, -92.32465861908086, -70.90536432779966, -55.953777697739255, -74.12814626217357, -75.89188834814621, -64.24093256012688, -89.62208010083313, -87.41075066046812, -80.40932820298143, -77.99906284144805, -95.31607277596169, -61.672429800914486, -85.26088499198657, -63.4402296673869, -74.84950736563589, -85.00433219746624, -71.5901436929124, -76.43243666219388, -48.01082320924727]
cor=df.correlation(['A','B','C'],coefficient='spearman')
self.assertEqual(str(cor),R)
def test2(self):
df=DataFrame()
with self.assertRaises(TypeError) as cm:
df['DUM']=42
self.assertEqual(str(cm.exception),
"'int' object is not iterable")
def test5(self):
from pyvttbl import DataFrame
from collections import namedtuple
import sys
import time
## N = 2560;
N = 10
ROW = namedtuple('ROW', ['A', 'B'])
dt = DataFrame()
start = time.clock()
## interval = 5
## print('insert\tsecs\tt/i\tt/i*2')
## for i in range(N) :
## dt.insert( ROW(i, i*i)._asdict() )
## if i>0 and i % interval == 0 :
## now = time.clock()
## delta = now-start
## print('%d\t%f\t%f\t%f' %(i, delta, delta/i, delta/(float(i)*i)))
## interval *=2
##
## print(dt)
dt['A'] = range(2560)
dt['B'] = [i * i for i in xrange(2560)]
now = time.clock()
print(now - start)
def test_kn(self):
df = DataFrame()
df.read_tbl('data/example.csv')
y = [23]*len(df['X'])
df['X'] = y
self.assertEqual(df.keys(), ['CASE', 'TIME', 'CONDITION', 'X'])
def setUp(self):
D = {
'SUBJECT': [
1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18,
19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34,
35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50,
51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66,
67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82,
83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98,
99, 100
],
'AGE':
'old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,old,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young,young'
.split(','),
'CONDITION':
'counting,counting,counting,counting,counting,counting,counting,counting,counting,counting,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,intention,intention,intention,intention,intention,intention,intention,intention,intention,intention,counting,counting,counting,counting,counting,counting,counting,counting,counting,counting,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,rhyming,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,adjective,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,imagery,intention,intention,intention,intention,intention,intention,intention,intention,intention,intention'
.split(','),
'WORDS': [
9, 8, 6, 8, 10, 4, 6, 5, 7, 7, 7, 9, 6, 6, 6, 11, 6, 3, 8, 7,
11, 13, 8, 6, 14, 11, 13, 13, 10, 11, 12, 11, 16, 11, 9, 23,
12, 10, 19, 11, 10, 19, 14, 5, 10, 11, 14, 15, 11, 11, 8, 6, 4,
6, 7, 6, 5, 7, 9, 7, 10, 7, 8, 10, 4, 7, 10, 6, 7, 7, 14, 11,
18, 14, 13, 22, 17, 16, 12, 11, 20, 16, 16, 15, 18, 16, 20, 22,
14, 19, 21, 19, 17, 15, 22, 16, 22, 22, 18, 21
],
}
self.df = DataFrame()
self.df.read_tbl('data/words~ageXcondition.csv')
def test0(self):
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
pt = df.pivot('ERROR', ['TIMEOFDAY'], ['COURSE'])
self.assertAlmostEqual(3.22222222222, pt[1, 0], 5)
def test0(self):
R = {
'd': [
9.0, 8.0, 6.0, 8.0, 10.0, 4.0, 6.0, 5.0, 7.0, 7.0, 7.0, 9.0,
6.0, 6.0, 6.0, 11.0, 6.0, 3.0, 8.0, 7.0, 11.0, 13.0, 8.0, 6.0,
14.0, 11.0, 13.0, 13.0, 10.0, 11.0, 12.0, 11.0, 16.0, 11.0,
9.0, 23.0, 12.0, 10.0, 19.0, 11.0, 10.0, 19.0, 14.0, 5.0, 10.0,
11.0, 14.0, 15.0, 11.0, 11.0, 8.0, 6.0, 4.0, 6.0, 7.0, 6.0,
5.0, 7.0, 9.0, 7.0, 10.0, 7.0, 8.0, 10.0, 4.0, 7.0, 10.0, 6.0,
7.0, 7.0, 14.0, 11.0, 18.0, 14.0, 13.0, 22.0, 17.0, 16.0, 12.0,
11.0, 20.0, 16.0, 16.0, 15.0, 18.0, 16.0, 20.0, 22.0, 14.0,
19.0, 21.0, 19.0, 17.0, 15.0, 22.0, 16.0, 22.0, 22.0, 18.0,
21.0
],
'fname':
'output\\box(WORDS).png',
'maintitle':
'WORDS',
'val':
'WORDS'
}
df = DataFrame()
df.TESTMODE = True
df.read_tbl('data/words~ageXcondition.csv')
D = df.box_plot('WORDS', output_dir='output')
self.assertEqual(D['fname'], R['fname'])
self.assertEqual(D['maintitle'], R['maintitle'])
self.assertEqual(D['val'], R['val'])
for d, r in zip(np.array(D['d']).flat, np.array(R['d']).flat):
self.assertAlmostEqual(d, r)
def test2(self):
R = {
'A': [
-8.0, -7.0, -3.0, -2.0, -1.0, 1.0, 2.0, 3.0, 4.0, 9.0, -10.0,
-9.0, -6.0, -5.0, -4.0, 0.0, 5.0, 6.0, 7.0, 8.0
],
'B': [
1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 2.0, 2.0,
2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0
]
}
a = [
4, 8, 1, 5, -7, -5, 9, 7, -8, -10, -1, -4, 3, 0., -2, 6, 2, -9, -3,
-6
]
b = [1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2]
df = DataFrame()
for A, B in zip(a, b):
df.insert({'A': A, 'B': B})
df.sort(['B', 'A'])
for d, r in zip(df['A'], R['A']):
self.assertAlmostEqual(d, r)
for d, r in zip(df['B'], R['B']):
self.assertAlmostEqual(d, r)
def test1(self):
R = Descriptives([('count', 48.0),
('mean', 3.8958333333333335),
('mode', 3.0),
('var', 5.797429078014184),
('stdev', 2.4077850979716158),
('sem', 0.34753384361617046),
('rms', 4.566636252940086),
('min', 0.0),
('Q1', 2.0),
('median', 3.0),
('Q3', 5.0),
('max', 10.0),
('range', 10.0),
('95ci_lower', 3.2146669998456394),
('95ci_upper', 4.5769996668210275)],
cname='ERROR')
df=DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
D=df.descriptives('ERROR')
for k in list(D.keys()):
self.assertAlmostEqual(D[k],R[k])
def test1(self):
R = """\
Chi-Square: Single Factor
SUMMARY
1 2 3 4
============================================
Observed 7 20 23 9
Expected 14.750 14.750 14.750 14.750
CHI-SQUARE TESTS
Value df P
========================================
Pearson Chi-Square 12.797 3 0.005
Likelihood Ratio 13.288 3 0.004
Observations 59
POST-HOC POWER
Measure
==============================
Effect size w 0.466
Non-centrality lambda 12.797
Critical Chi-Square 7.815
Power 0.865 """
df = DataFrame()
df.read_tbl('data/chi_test.csv')
X = df.chisquare1way('RESULT')
self.assertEqual(str(X), R)
def test01(self):
"""repr test"""
R = Descriptives([('count', 100.0),
('mean', 11.61),
('mode', 11.0),
('var', 26.947373737373752),
('stdev', 5.191085988246944),
('sem', 0.5191085988246944),
('rms', 12.707084638106414),
('min', 3.0),
('Q1', 7.0),
('median', 11.0),
('Q3', 15.5),
('max', 23.0),
('range', 20.0),
('95ci_lower', 10.592547146303598),
('95ci_upper', 12.6274528536964)],
cname='WORDS')
df = DataFrame()
df.read_tbl('data/words~ageXcondition.csv')
D = eval(repr(df.descriptives('WORDS')))
for k in list(D.keys()):
self.assertAlmostEqual(D[k],R[k])
def test07(self):
# labels have spaces
with open('test.csv', 'wb') as f:
f.write("""
y 1, y 2 , y 3
1,5,9
2,6,
3,7,11
4,8,12""")
self.df = DataFrame()
self.df.read_tbl('test.csv', skip=1, labels=True)
print((self.df))
for z in self.df['y 3']:
print((type(z)))
D = list(self.df['y 1']) + \
list(self.df['y 2']) + \
list(self.df['y 3'])
R = [1, 2, 3, 4, 5, 6, 7, 8, 9, np.ma.core.MaskedConstant(), 11, 12]
for (d, r) in zip(D, R):
self.assertEqual(str(d), str(r))
