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=range(1,13)
for (d,r) in zip(D,R):
self.assertAlmostEqual(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=range(1,13)
for (d,r) in zip(D,R):
self.assertAlmostEqual(d,r)
def test04(self):
# line missing data, no comma after 6
with open('test.csv','wb') as f:
f.write("""
x,y,z
1,5,9
2,6
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['y']) + \
list(self.df['z'])
R=[1,3,4,5,7,8,9,11,12]
for (d,r) in zip(D,R):
self.assertAlmostEqual(d,r)
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 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 = """\
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 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))
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):
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 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 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 test3(self):
"""unequal"""
df=DataFrame()
df[1]=range(10)
df[2]=range(10)
df[3]=range(10)
df[4]=range(9)
self.assertFalse(df._are_col_lengths_equal())
def test2(self):
"""equal non-zero"""
df=DataFrame()
df[1]=range(10)
df[2]=range(10)
df[3]=range(10)
df[4]=range(10)
self.assertTrue(df._are_col_lengths_equal())
def test05(self):
R = """Marginals([('factorials', OrderedDict([('AGE', [u'old', u'old', u'old', u'old', u'old']), ('CONDITION', [u'adjective', u'counting', u'imagery', u'intention', u'rhyming'])])), ('dmu', [11.0, 7.0, 13.4, 12.0, 6.9000000000000004]), ('dN', [10, 10, 10, 10, 10]), ('dsem', [0.78881063774661542, 0.57735026918962573, 1.4236104336041748, 1.1832159566199232, 0.67412494720522276]), ('dlower', [9.4539311500166345, 5.868393472388334, 10.609723550135818, 9.6808967250249509, 5.578715103477764]), ('dupper', [12.546068849983365, 8.131606527611666, 16.190276449864182, 14.319103274975049, 8.2212848965222367])], val='WORDS', factors=['AGE', 'CONDITION'], where='AGE == "old"')"""
df=DataFrame()
df.read_tbl('data/words~ageXcondition.csv')
D = df.marginals('WORDS',
factors=['AGE','CONDITION'],
where='AGE == "old"')
def test3(self):
df=DataFrame()
with self.assertRaises(Exception) as cm:
df.validate({'GROUP' : lambda x: x in ['AA', 'AB', 'LAB']})
self.assertEqual(str(cm.exception),
'table must have data to validate data')
def test02(self):
df = DataFrame()
df.read_tbl('data/words~ageXcondition.csv')
D = repr(df.histogram('WORDS'))
R = "Histogram([('values', [4.0, 14.0, 17.0, 12.0, 15.0, 10.0, 9.0, 5.0, 6.0, 8.0]), \
('bin_edges', [3, 5.0, 7.0, 9.0, 11.0, 13.0, 15.0, 17.0, 19.0, 21.0, 23])], cname='WORDS')"
self.assertEqual(D, R)
def test3(self):
df = DataFrame()
with self.assertRaises(Exception) as cm:
df.sort()
self.assertEqual(str(cm.exception),
'Table must have data to sort data')
def test12(self):
df = DataFrame()
df['DUM'] = range(48) # Shouldn't complain
self.assertEqual(df.keys(), ['DUM'])
df['DUM'] = ['A' for i in range(48)] # Shouldn't complain
self.assertEqual(df.keys(), ['DUM'])
self.assertEqual(df._sqltypesdict['DUM'], 'text')
def test3(self):
df = DataFrame()
with self.assertRaises(Exception) as cm:
df.box_plot('a', output_dir='output')
self.assertEqual(str(cm.exception),
'Table must have data to print data')
def test6(self):
df = DataFrame()
df['a'] = [2, 5]
df['b'] = [2, 3]
with self.assertRaises(KeyError) as cm:
df.box_plot('c', output_dir='output')
self.assertEqual(str(cm.exception), "'c'")
def test4(self):
df = DataFrame()
df['a'] = [2]
df['b'] = [2, 3]
with self.assertRaises(Exception) as cm:
df.sort()
self.assertEqual(str(cm.exception), 'columns have unequal lengths')
def test4(self):
df = DataFrame()
df['a'] = [2]
df['b'] = [2, 3]
with self.assertRaises(Exception) as cm:
df.box_plot('a', output_dir='output')
self.assertEqual(str(cm.exception), 'columns have unequal lengths')
def test5(self):
df = DataFrame()
df['a'] = [2, 5]
df['b'] = [2, 3]
with self.assertRaises(Exception) as cm:
df.sort(42)
self.assertEqual(str(cm.exception), "'int' object is not iterable")
def test5(self):
df = DataFrame()
df['a'] = [2, 5]
df['b'] = [2, 3]
with self.assertRaises(Exception) as cm:
df.box_plot('a', 42, output_dir='output')
self.assertEqual(str(cm.exception), "'int' object is not iterable")
def test0(self):
self.df1 = DataFrame()
self.df1.read_tbl('data/words~ageXcondition.csv')
with self.assertRaises(Exception) as cm:
self.df1.attach('s')
self.assertEqual(str(cm.exception),
'second argument must be a DataFrame')
def test2(self):
## Between-Subjects test
R = """WORDS ~ AGE * CONDITION
TESTS OF BETWEEN-SUBJECTS EFFECTS
Measure: WORDS
Source Type III df MS F Sig. et2_G Obs. SE 95% CI lambda Obs.
SS Power
===============================================================================================================
AGE 240.250 1 240.250 29.936 3.981e-07 0.250 50 0.406 0.796 16.631 0.981
CONDITION 1514.940 4 378.735 47.191 2.530e-21 0.677 20 0.642 1.258 41.948 1.000
AGE * CONDITION 190.300 4 47.575 5.928 2.793e-04 0.209 10 0.908 1.780 2.635 0.207
Error 722.300 90 8.026
===============================================================================================================
Total 2667.790 99
TABLES OF ESTIMATED MARGINAL MEANS
Estimated Marginal Means for AGE
AGE Mean Std. Error 95% Lower Bound 95% Upper Bound
===============================================================
old 10.060 0.567 8.949 11.171
young 13.160 0.818 11.556 14.764
Estimated Marginal Means for CONDITION
CONDITION Mean Std. Error 95% Lower Bound 95% Upper Bound
===================================================================
adjective 12.900 0.791 11.350 14.450
counting 6.750 0.362 6.041 7.459
imagery 15.500 0.933 13.671 17.329
intention 15.650 1.096 13.502 17.798
rhyming 7.250 0.452 6.363 8.137
Estimated Marginal Means for AGE * CONDITION
AGE CONDITION Mean Std. Error 95% Lower Bound 95% Upper Bound
===========================================================================
old adjective 11 0.789 9.454 12.546
old counting 7 0.577 5.868 8.132
old imagery 13.400 1.424 10.610 16.190
old intention 12 1.183 9.681 14.319
old rhyming 6.900 0.674 5.579 8.221
young adjective 14.800 1.104 12.637 16.963
young counting 6.500 0.453 5.611 7.389
young imagery 17.600 0.819 15.994 19.206
young intention 19.300 0.844 17.646 20.954
young rhyming 7.600 0.618 6.388 8.812
"""
df = DataFrame()
fname = 'data/words~ageXcondition.csv'
df.read_tbl(fname)
aov = Anova()
aov.run(df, 'WORDS', bfactors=['AGE', 'CONDITION'])
self.assertEqual(str(aov), R)
def test0(self):
R = """SUBJECT TIMEOFDAY COURSE MODEL ERROR
============================================
1 T1 C1 M1 10
1 T1 C1 M2 8
1 T1 C1 M3 6
1 T1 C2 M1 9
1 T1 C3 M1 7
1 T1 C3 M2 6
1 T1 C3 M3 3
1 T2 C1 M1 5
1 T2 C1 M2 4
1 T2 C1 M3 3
1 T2 C2 M1 4
1 T2 C2 M2 3
1 T2 C2 M3 3
1 T2 C3 M1 2
1 T2 C3 M2 2
1 T2 C3 M3 1
2 T1 C2 M1 10
2 T1 C2 M2 6
2 T1 C2 M3 4
2 T1 C3 M1 4
2 T1 C3 M2 5
2 T1 C3 M3 2
2 T2 C1 M1 4
2 T2 C1 M2 3
2 T2 C1 M3 3
2 T2 C2 M1 4
2 T2 C2 M2 2
2 T2 C2 M3 2
2 T2 C3 M1 2
2 T2 C3 M2 3
2 T2 C3 M3 2
3 T1 C1 M1 8
3 T1 C1 M2 7
3 T1 C1 M3 4
3 T1 C2 M1 7
3 T1 C2 M3 3
3 T1 C3 M1 3
3 T1 C3 M2 4
3 T1 C3 M3 2
3 T2 C1 M1 4
3 T2 C1 M2 1
3 T2 C1 M3 2
3 T2 C2 M1 3
3 T2 C2 M2 3
3 T2 C2 M3 2
3 T2 C3 M1 1
3 T2 C3 M2 0
3 T2 C3 M3 1 """
df = DataFrame()
df.read_tbl('data/error~subjectXtimeofdayXcourseXmodel_MISSING.csv')
self.assertEqual(str(df), R)
def test4(self):
"""method='full', aggregate=tolist, invalid col"""
R = """\
tolist(id)
member Name=name1, Name=name1, Name=name2, Name=name2,
Year=2010 Year=2011 Year=2010 Year=2011
==================================================================
N [None, None] [1.0, 1.0] [None, None] [None, None]
Y [0.0, 0.0] [None, None] [None, None] [2.0, 2.0] """
df = DataFrame()
df.insert({'id':0,'Name':'name1','Year':2010,'member':'Y','rep':1})
df.insert({'id':1,'Name':'name1','Year':2011,'member':'N','rep':1})
df.insert({'id':2,'Name':'name2','Year':2011,'member':'Y','rep':1})
df.insert({'id':0,'Name':'name1','Year':2010,'member':'Y','rep':2})
df.insert({'id':1,'Name':'name1','Year':2011,'member':'N','rep':2})
df.insert({'id':2,'Name':'name2','Year':2011,'member':'Y','rep':2})
my_pivot = df.pivot('id',rows = ['member'], cols = ['Name','Year'],
aggregate='tolist', method='full')
## print(my_pivot)
self.assertEqual(R,str(my_pivot))
def test3(self):
"""method='full', aggregate=tolist, invalid row"""
R = """\
tolist(id)
Name Year member=N member=Y
==========================================
name1 2010 [None, None] [0.0, 0.0]
name1 2011 [1.0, 1.0] [None, None]
name2 2010 [None, None] [None, None]
name2 2011 [None, None] [2.0, 2.0] """
df = DataFrame()
df.insert({'id':0,'Name':'name1','Year':2010,'member':'Y','rep':1})
df.insert({'id':1,'Name':'name1','Year':2011,'member':'N','rep':1})
df.insert({'id':2,'Name':'name2','Year':2011,'member':'Y','rep':1})
df.insert({'id':0,'Name':'name1','Year':2010,'member':'Y','rep':2})
df.insert({'id':1,'Name':'name1','Year':2011,'member':'N','rep':2})
df.insert({'id':2,'Name':'name2','Year':2011,'member':'Y','rep':2})
my_pivot = df.pivot('id',rows = ['Name','Year'], cols = ['member'],
aggregate='tolist', method='full')
## print(my_pivot)
self.assertEqual(R,str(my_pivot))
def test4(self):
df = DataFrame()
df[1] = range(100)
df[2] = ['bob' for i in range(100)]
df[3] = [i * 1.234232 for i in range(100)]
df[4] = ['bob' for i in range(50)] + range(50)
with self.assertRaises(TypeError) as cm:
df._build_sqlite3_tbl(df.keys()[:2], 42)
self.assertEqual(str(cm.exception), "'int' object is not iterable")
