forked from tea-lang-org/tea-lang
/
test_integration.py
706 lines (607 loc) · 23.9 KB
/
test_integration.py
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
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
import tea
import os
base_url = 'https://homes.cs.washington.edu/~emjun/tea-lang/datasets/'
uscrime_data_path = None
states_path = None
cats_path = None
cholesterol_path = None
soya_path = None
co2_path = None
exam_path = None
liar_path = None
pbcorr_path = None
spider_path = None
drug_path = None
alcohol_path = None
ecstasy_path = None
goggles_path = None
goggles_dummy_path = None
data_paths = [uscrime_data_path, states_path, cats_path, cholesterol_path, soya_path, co2_path, exam_path, liar_path, pbcorr_path, spider_path, drug_path, alcohol_path, ecstasy_path, goggles_path, goggles_dummy_path]
file_names = ['UScrime.csv', 'statex77.csv', 'catsData.csv', 'cholesterol.csv', 'soya.csv', 'co2.csv', 'exam.csv', 'liar.csv', 'pbcorr.csv','spiderLong_within .csv', 'drug.csv', 'alcohol.csv', 'ecstasy.csv', 'gogglesData.csv', 'gogglesData_dummy.csv']
def test_load_data():
global base_url, data_paths, file_names
global drug_path
for i in range(len(data_paths)):
csv_name = file_names[i]
csv_url = os.path.join(base_url, csv_name)
data_paths[i] = tea.download_data(csv_url, csv_name)
eval_file = 'eval.txt'
def log(expected, result):
global eval_file
file = open(eval_file, "a")
file.write("\nExpected:")
file.write(expected)
file.write("\n")
file.write("Result:")
# import pdb; pdb.set_trace()
file.write(str(result))
file.write('\n--------') # divide tests
# import pdb; pdb.set_trace()
# Example from Kabacoff
# Expected outcome: Pearson correlation
def test_pearson_corr():
states_path = "/Users/emjun/.tea/data/statex77.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'Illiteracy',
'data type' : 'interval',
'categories' : [0, 100]
},
{
'name' : 'Life Exp',
'data type' : 'ratio',
# 'range' : [0,1]
}
]
experimental_design = {
'study type': 'observational study',
'contributor variables': ['Illiteracy', 'Life Exp'],
'outcome variables': ''
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05,
# 'normal distribution': ['Illiteracy', 'Life Exp']
}
tea.data(states_path)
tea.define_variables(variables)
tea.define_study_design(experimental_design) # Allows for using multiple study designs for the same dataset (could lead to phishing but also practical for saving analyses and reusing as many parts of analyses as possible)
tea.assume(assumptions)
results = tea.hypothesize(['Illiteracy', 'Life Exp'], ['Illiteracy ~ Life Exp'])
print("\nfrom Kabacoff")
print("Expected outcome: Pearson")
log('Pearson', str(results))
# Suggests non-parametric
def test_pearson_corr_2():
print("\nfrom Field et al.")
print("Expected outcome: Pearson")
exam_path = "/Users/emjun/.tea/data/exam.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'Exam',
'data type' : 'ratio',
'range' : [0, 100]
},
{
'name' : 'Anxiety',
'data type' : 'interval',
'range' : [0, 100]
},
{
'name' : 'Gender',
'data type' : 'nominal',
'categories' : ['Male', 'Female']
},
{
'name' : 'Revise',
'data type' : 'ratio'
}
]
experimental_design = {
'study type': 'observational study',
'contributor variables': ['Anxiety', 'Gender', 'Revise'],
'outcome variables': 'Exam'
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05,
}
tea.data(exam_path)
tea.define_variables(variables)
tea.define_study_design(experimental_design)
tea.assume(assumptions)
results = tea.hypothesize(['Anxiety', 'Exam'])
log('Pearson', results)
results = tea.hypothesize(['Revise', 'Exam'])
log('Pearson', results)
results = tea.hypothesize(['Anxiety', 'Revise'])
log('Pearson', results)
print("\nfrom Field et al.")
print("Expected outcome: Pearson")
# suggests non parametric
# Anxiety, Exam, and Revise are all not normally distributed. Therefore, Tea picks spearman and kendall
def test_spearman_corr():
liar_path = "/Users/emjun/.tea/data/liar.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'Creativity',
'data type' : 'interval'
},
{
'name' : 'Position',
'data type' : 'ordinal',
'categories' : [6, 5, 4, 3, 2, 1] # ordered from lowest to highest
},
{
'name' : 'Novice',
'data type' : 'nominal',
'categories' : [0, 1]
}
]
experimental_design = {
'study type': 'observational study',
'contributor variables': ['Novice', 'Creativity'],
'outcome variables': 'Position'
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05,
}
tea.data(liar_path)
tea.define_variables(variables)
tea.define_study_design(experimental_design)
tea.assume(assumptions)
results = tea.hypothesize(['Position', 'Creativity'], ['Position:1 > 6']) # TODO: allow for partial orders?
print("\nfrom Field et al.")
print("Expected outcome: Spearman")
log('Spearman', results)
# Returns Spearman
# Same as test for Spearman rho
def test_kendall_tau_corr():
print("\nfrom Field et al.")
print("Expected outcome: Kendall Tau")
liar_path = "/Users/emjun/.tea/data/liar.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'Creativity',
'data type' : 'interval'
},
{
'name' : 'Position',
'data type' : 'ordinal',
'categories' : [6, 5, 4, 3, 2, 1] # ordered from lowest to highest
},
{
'name' : 'Novice',
'data type' : 'nominal',
'categories' : [0, 1]
}
]
experimental_design = {
'study type': 'observational study',
'contributor variables': ['Novice', 'Creativity'],
'outcome variables': 'Position'
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05,
}
tea.data(liar_path)
tea.define_variables(variables)
tea.define_study_design(experimental_design)
tea.assume(assumptions)
results = tea.hypothesize(['Position', 'Creativity'], ['Position:1 > 6', 'Position:1 > 2']) # I think this works!?
print("\nfrom Field et al.")
print("Expected outcome: Kendall Tau")
log("Kendall Tau", results)
# import pdb; pdb.set_trace()
# Returns: Kendall Tau and Pearson
def test_pointbiserial_corr():
print("\nfrom Field et al.")
print("Expected outcome: Pointbiserial")
pbcorr_path = "/Users/emjun/.tea/data/pbcorr.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'time',
'data type' : 'ratio'
},
{
'name' : 'gender',
'data type' : 'nominal',
'categories' : [0, 1] # ordered from lowest to highest
},
{
'name' : 'recode',
'data type' : 'nominal',
'categories' : [0, 1]
}
]
experimental_design = {
'study type': 'observational study',
'contributor variables': ['gender', 'recode'],
'outcome variables': 'time'
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05,
}
tea.data(pbcorr_path)
tea.define_variables(variables)
tea.define_study_design(experimental_design)
tea.assume(assumptions)
tea.hypothesize(['time', 'gender'], ['gender:1 > 0']) # I think this works!?
print("\nfrom Field et al.")
print("Expected outcome: Pointbiserial")
# Results: {'mannwhitney_u': MannwhitneyuResult(statistic=262.0,
# pvalue=0.0058742825311290285), 'kruskall_wallis':
# KruskalResult(statistic=7.629432016171138, pvalue=0.00574233835210006)}
def test_indep_t_test():
print("\nfrom Kabacoff")
print("Expected outcome: Student's t-test")
global uscrime_data_path
uscrime_data_path = "/Users/emjun/.tea/data/UScrime.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'So',
'data type' : 'nominal',
'categories' : ['0', '1']
},
{
'name' : 'Prob',
'data type' : 'ratio',
'range' : [0,1]
}
]
experimental_design = {
'study type': 'observational study',
'contributor variables': 'So',
'outcome variables': 'Prob',
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05,
# 'normal distribution': ['So'],
# 'groups normally distributed': [['So', 'Prob']]
}
tea.data(uscrime_data_path)
tea.define_variables(variables)
tea.define_study_design(experimental_design) # Allows for using multiple study designs for the same dataset (could lead to phishing but also practical for saving analyses and reusing as many parts of analyses as possible)
tea.assume(assumptions)
tea.hypothesize(['So', 'Prob'], ['So:1 > 0']) ## Southern is greater
print("\nfrom Kabacoff")
print("Expected outcome: Student's t-test")
# Results: {'students_t': Ttest_indResult(statistic=-4.202130736875173, pvalue=0.00012364897266532775), 'welchs_t': Ttest_indResult(statistic=-3.8953717090736655, pvalue=0.0006505783178002014), 'mannwhitney_u': MannwhitneyuResult(statistic=81.0, pvalue=0.00018546387565891538), 'f_test': df sum_sq mean_sq F PR(>F)
# C(So) 1.0 0.006702 0.006702 17.657903 0.000124
# Residual 45.0 0.017079 0.000380 NaN NaN, 'kruskall_wallis': KruskalResult(statistic=14.056955645161281, pvalue=0.00017735665596242664), 'factorial_ANOVA': df sum_sq mean_sq F PR(>F)
# C(So) 1.0 0.006702 0.006702 17.657903 0.000124
# Residual 45.0 0.017079 0.000380 NaN NaN}
# tea.hypothesize(['So', 'Prob'], null='So:1 <= So:0', alternative='So:1 > So:0')
# import pdb; pdb.set_trace()
def test_paired_t_test():
print("\nfrom Field et al.")
print("Expected outcome: Paired/Dependent t-test")
global spider_path
spider_path = "/Users/emjun/.tea/data/spiderLong_within.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'Group',
'data type' : 'nominal',
'categories' : ['Picture', 'Real Spider']
},
{
'name' : 'Anxiety',
'data type' : 'ratio'
}
]
experimental_design = {
'study type': 'experiment',
'independent variables': 'Group',
'dependent variables': 'Anxiety',
'within subjects' : 'Group'
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05
}
tea.data(spider_path, key="id")
tea.define_variables(variables)
tea.define_study_design(experimental_design) # Allows for using multiple study designs for the same dataset (could lead to phishing but also practical for saving analyses and reusing as many parts of analyses as possible)
tea.assume(assumptions)
tea.hypothesize(['Group', 'Anxiety'], ['Group:Real Spider > Picture'])
print("\nfrom Field et al.")
print("Expected outcome: Paired/Dependent t-test")
# Results: {'pointbiserial_corr_a': True, 'paired_students_t': Ttest_relResult(statistic=-2.472533427497901, pvalue=0.030981783136040896), 'wilcoxon_signed_rank': WilcoxonResult(statistic=8.0, pvalue=0.045855524379089546), 'rm_one_way_anova': True, 'factorial_ANOVA': df sum_sq mean_sq F PR(>F)
# C(Group) 1.0 294.0 294.0 2.826923 0.106839
# Residual 22.0 2288.0 104.0 NaN NaN}
def test_wilcoxon_signed_rank():
print("\nfrom Field et al.")
print("Expected outcome: Wilcoxon signed rank test")
# global alcohol_path
alcohol_path = "/Users/emjun/.tea/data/alcohol.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'drug',
'data type' : 'nominal',
'categories' : ['Alcohol']
},
{
'name' : 'day',
'data type' : 'nominal',
'categories': ['sundayBDI', 'wedsBDI']
},
{
'name' : 'value',
'data type' : 'ratio'
}
]
experimental_design = {
'study type': 'experiment',
'independent variables': 'day',
'dependent variables': 'value',
'within subjects' : 'day'
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05
}
tea.data(alcohol_path)
tea.define_variables(variables)
tea.define_study_design(experimental_design) # Allows for using multiple study designs for the same dataset (could lead to phishing but also practical for saving analyses and reusing as many parts of analyses as possible)
tea.assume(assumptions)
tea.hypothesize(['day', 'value'], ['day:sundayBDI > wedsBDI'])
print("\nfrom Field et al.")
print("Expected outcome: Wilcoxon signed rank test")
def test_f_test():
print("\nFrom Field et al.")
print("Expected outcome: Oneway ANOVA (F) test")
cholesterol_path = "/Users/emjun/.tea/data/cholesterol.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'trt',
'data type' : 'nominal',
'categories' : ['1time', '2times', '4times', 'drugD', 'drugE']
},
{
'name' : 'response',
'data type' : 'ratio',
# 'categories' : ['Yes', 'No']
}
]
experimental_design = {
'study type': 'experiment',
'independent variables': 'trt',
'dependent variables': 'response',
'between subjects': 'trt'
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05,
}
tea.data(cholesterol_path)
tea.define_variables(variables)
tea.define_study_design(experimental_design) # Allows for using multiple study designs for the same dataset (could lead to phishing but also practical for saving analyses and reusing as many parts of analyses as possible)
tea.assume(assumptions)
tea.hypothesize(['trt', 'response'])
print("\nFrom Field et al.")
print("Expected outcome: Oneway ANOVA (F) test")
def test_kruskall_wallis():
print("\nFrom Field et al.")
print("Expected outcome: Kruskall Wallis")
soya_path = "/Users/emjun/.tea/data/soya.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'Sperm',
'data type' : 'interval'
},
{
'name' : 'Soya',
'data type' : 'ordinal',
'categories': ['No Soya', '1 Soya Meal', '4 Soya Meals', '7 Soya Meals']
}
]
experimental_design = {
'study type': 'experiment',
# 'study type': 'observational study', # shouldn't change anything
'independent variables': 'Soya',
'dependent variables': 'Sperm',
'between subjects': 'Soya'
# 'within subjects': 'Soya' # Correctly does not choose Kruskall Wallis
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05,
}
tea.data(soya_path)
tea.define_variables(variables)
tea.define_study_design(experimental_design) # Allows for using multiple study designs for the same dataset (could lead to phishing but also practical for saving analyses and reusing as many parts of analyses as possible)
tea.assume(assumptions)
tea.hypothesize(['Soya', 'Sperm'])
print("\nFrom Field et al.")
print("Expected outcome: Kruskall Wallis")
def test_rm_one_way_anova():
print("\nFrom Field et al.")
print("Expected outcome: Repeated Measures One Way ANOVA")
co2_path = "/Users/emjun/.tea/data/co2.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'uptake',
'data type' : 'interval'
},
{
'name' : 'Type',
'data type' : 'nominal',
'categories': ['Quebec', 'Mississippi']
},
{
'name' : 'conc',
'data type' : 'ordinal',
'categories': [95, 175, 250, 350, 500, 675, 1000]
}
]
experimental_design = {
'study type': 'experiment',
'independent variables': ['Type', 'conc'],
'dependent variables': 'uptake',
'within subjects': 'conc',
'between subjects': 'Type'
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05,
}
tea.data(co2_path, key="Plant")
tea.define_variables(variables)
tea.define_study_design(experimental_design) # Allows for using multiple study designs for the same dataset (could lead to phishing but also practical for saving analyses and reusing as many parts of analyses as possible)
tea.assume(assumptions)
tea.hypothesize(['uptake', 'conc']) # Picks friedman!
print("\nFrom Field et al.")
print("Expected outcome: Repeated Measures One Way ANOVA")
def test_factorial_anova():
print("\nFrom Field et al.")
print("Expected outcome: Factorial ANOVA")
goggles_path = "/Users/emjun/.tea/data/gogglesData.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'gender',
'data type' : 'nominal',
'categories' : ['Female', 'Male']
},
{
'name' : 'alcohol',
'data type' : 'nominal',
'categories': ['None', '2 Pints', '4 Pints']
},
{
'name' : 'attractiveness',
'data type' : 'interval'
}
]
experimental_design = {
'study type': 'experiment',
'independent variables': ['gender', 'alcohol'],
'dependent variables': 'attractiveness',
'between subjects': ['gender', 'alcohol']
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05,
}
tea.data(goggles_path)
tea.define_variables(variables)
tea.define_study_design(experimental_design) # Allows for using multiple study designs for the same dataset (could lead to phishing but also practical for saving analyses and reusing as many parts of analyses as possible)
tea.assume(assumptions)
tea.hypothesize(['attractiveness', 'gender', 'alcohol'])
# alcohol main effect?
print("\nFrom Field et al.")
print("Expected outcome: Factorial ANOVA")
"""
def test_factorial_anova_2():
print("\nFrom Field et al.")
print("Expected outcome: Factorial ANOVA")
goggles_dummy_path = "/Users/emjun/.tea/data/gogglesData_dummy.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'gender',
'data type' : 'nominal',
'categories' : ['Female', 'Male']
},
{
'name' : 'alcohol',
'data type' : 'nominal',
'categories': ['None', '2 Pints', '4 Pints']
},
{
'name' : 'attractiveness',
'data type' : 'interval'
},
{
'name' : 'dummy',
'data type' : 'nominal',
'categories': [1, 2]
}
]
experimental_design = {
'study type': 'experiment',
'independent variables': ['gender', 'alcohol', 'dummy'],
'dependent variables': 'attractiveness',
# 'within subjects': 'conc',
'between subjects': ['gender', 'alcohol', 'dummy']
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05,
}
tea.data(goggles_dummy_path)
tea.define_variables(variables)
tea.define_study_design(experimental_design) # Allows for using multiple study designs for the same dataset (could lead to phishing but also practical for saving analyses and reusing as many parts of analyses as possible)
tea.assume(assumptions)
tea.hypothesize(['attractiveness', 'gender', 'alcohol', 'dummy'])
print("\nFrom Field et al.")
print("Expected outcome: Factorial ANOVA")
import pdb; pdb.set_trace()
"""
def test_two_way_anova():
co2_path = "/Users/emjun/.tea/data/co2.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'uptake',
'data type' : 'interval'
},
{
'name' : 'Type',
'data type' : 'nominal',
'categories': ['Quebec', 'Mississippi']
},
{
'name' : 'conc',
'data type' : 'ordinal',
'categories': [95, 175, 250, 350, 500, 675, 1000]
}
]
experimental_design = {
'study type': 'experiment',
'independent variables': ['Type', 'conc'],
'dependent variables': 'uptake',
'within subjects': 'conc',
'between subjects': 'Type'
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05,
}
tea.data(co2_path)
tea.define_variables(variables)
tea.define_study_design(experimental_design) # Allows for using multiple study designs for the same dataset (could lead to phishing but also practical for saving analyses and reusing as many parts of analyses as possible)
tea.assume(assumptions)
tea.hypothesize(['uptake', 'conc', 'Type']) # Fails: not all groups are normal
#Type main effect?
print('Supposed to be 2 way ANOVA')
def test_chi_square():
cats_path = "/Users/emjun/.tea/data/catsData.csv"
# Declare and annotate the variables of interest
variables = [
{
'name' : 'Training',
'data type' : 'nominal',
'categories' : ['Food as Reward', 'Affection as Reward']
},
{
'name' : 'Dance',
'data type' : 'nominal',
'categories' : ['Yes', 'No']
}
]
experimental_design = {
'study type': 'observational study',
'contributor variables': 'Training',
'outcome variables': 'Dance'
}
assumptions = {
'Type I (False Positive) Error Rate': 0.05,
}
tea.data(cats_path)
tea.define_variables(variables)
tea.define_study_design(experimental_design) # Allows for using multiple study designs for the same dataset (could lead to phishing but also practical for saving analyses and reusing as many parts of analyses as possible)
tea.assume(assumptions)
tea.hypothesize(['Training', 'Dance'])
print('Chi square')