In [1]:
#from http://www.ons.gov.uk/ons/publications/re-reference-tables.html?edition=tcm%3A77-168405
"http://www.ons.gov.uk/ons/rel/occupational-mortality/occupational-mortality-in-england-and-wales/occupational-mortality/occupational-mortality--men-age-16-64.zip"
Out[1]:
'http://www.ons.gov.uk/ons/rel/occupational-mortality/occupational-mortality-in-england-and-wales/occupational-mortality/occupational-mortality--men-age-16-64.zip'
In [10]:
import requests
from StringIO import StringIO
from numpy import nan as NA
import pandas as pd
import zipfile
import re
%matplotlib inline
import matplotlib.pyplot as plt
import xlrd
In [22]:
url = "http://www.ons.gov.uk/ons/rel/occupational-mortality/occupational-mortality-in-england-and-wales/occupational-mortality/occupational-mortality--men-age-65-74.zip"
r = requests.get(url)
z = zipfile.ZipFile(StringIO(r.content))
notes = pd.read_excel(z.open('Men65_74.xls'), sheetname=1)
df = pd.read_excel(z.open('Men65_74.xls'), sheetname=2)
In [29]:
notes[15:]
Out[29]:
Notes to the Table
Unnamed: 1
15
NaN
Mortality in England and Wales,. 1991-2000, Ap...
16
Occupation
Name of occupation group
17
Observed
Actual number of deaths occurring for that com...
18
Exp_Adj
Expected number of deaths for this combination...
19
NaN
accounted for by this cause, and standardised ...
20
PMR_Adj
Ratio of observed to expected deaths, where ex...
21
Lower_adj
Lower 95 per cent confidence limit for PMR_Adj
22
Upper_Adj
Upper 95 per cent confidence limit for PMR_Adj
23
Exp_Unadj
Expected number of deaths for this combination...
24
NaN
accounted for by this cause, and standardised ...
25
PMR_Unadj
Ratio of observed to expected deaths, where ex...
26
Lower_Unadj
Lower 95 per cent confidence limit for PMR_Unadj
27
Upper_Unadj
Upper 95 per cent confidence limit for PMR_Unadj
In [33]:
df.columns
Out[33]:
Index([ u'diagrp', u'Cause ', u'SOdm', u'Occupation',
u'Observed', u'Exp_Adj', u'PMR_Adj', u'Lower_Adj',
u'Upper_Adj', u'Exp_Unadj', u'PMR_Unadj', u'Lower_Unadj',
u'Upper_Unadj'],
dtype='object')
In [34]:
df.columns = [x.strip() for x in df.columns]
In [63]:
df.Cause.unique()
Out[63]:
array([u'Intestinal infectious diseases', u'Tuberculosis',
u'Zoonotic bacterial diseases', u'Meningococcal infections',
u'Septicaemia', u'Viral hepatitis', u'Sarcoidosis', u'HIV',
u'Cancer of the oral cavity', u'Cancer of the salivary glands',
u'Cancer of the pharynx (specified)', u'Cancer of oesophagus',
u'Cancer of the stomach', u'Cancer of the small intestine',
u'Cancer of the colon', u'Cancer of the rectum',
u'Cancer of the liver', u'Cancer of the gall bladder',
u'Cancer of the pancreas', u'Cancer of the retroperitoneum',
u'Cancer of the peritoneum',
u'Cancer of the nose and nasal sinuses', u'Cancer of the larynx',
u'Cancer of the bronchus', u'Cancer of the pleura',
u'Cancer of the thymus', u'Cancer of other mediastinum',
u'Cancer of bone', u'Cancer of soft tissue', u'Melanoma of skin',
u'Other cancer of skin', u'Cancer of the female breast',
u'Cancer of the male breast',
u'Cancer of the uterus, part unspecified', u'Cancer of the cervix',
u'Cancer of the placenta', u'Cancer of the body of uterus',
u'Cancer of the ovary', u'Cancer of the prostate',
u'Cancer of the testis', u'Cancer of the penis',
u'Cancer of the scrotum', u'Urothelial cancer',
u'Cancer of the kidney (except pelvis)', u'Cancer of the eye',
u'Cancer of the brain', u'Meningeal tumour',
u'Cancer of the thyroid', u'Cancer of the suprarenal',
u'Cancer of other endocrine organs', u"Non-Hodgkin's lymphoma",
u"Hodgkin's disease", u'Myeloma', u'All leukaemias',
u'Acute lymphatic leukaemia', u'Chronic lymphatic leukaemia',
u'Acute myeloid leukaemia', u'Chronic myeloid leukaemia',
u'Acute monocytic leukaemia', u'Other leukaemia', u'Adrenal tumour',
u'Pituitary tumour', u'Thyrotoxicosis', u'Hypothyroidism',
u'Diabetes', u"Cushing's disease", u"Addison's disease",
u'Amyloidosis', u'Immunodeficiency', u'Haemolytic anaemia',
u'Aplastic anaemia', u'Defibrination syndrome', u'Purpura',
u'Agranulocytosis', u'Dementia', u'Other alcohol-related diseases',
u'Drug dependence', u'Anorexia nervosa',
u'Bacterial and unspecified meningitis', u'Encephalitis',
u'Intracranial/spinal abscess', u"Parkinson's disease",
u'Motor neuron disease', u'Multiple sclerosis', u'Epilepsy',
u'Guillain Barre syndrome', u'Myasthenia',
u'Chronic rheumatic heart disease', u'Hypertensive disease',
u'Ischaemic heart disease', u'Pulmonary embolism and phlebitis',
u'Pulmonary hypertension', u'Cor pulmonale', u'Pericarditis',
u'Endocarditis', u'Acute myocarditis', u'Mitral valve disease',
u'Aortic valve disorders', u'Other cardiomyopathies',
u'Atrial fibrillation', u'Chronic and unspecified myocarditis',
u'Sub-arachnoid haemorrhage', u'Other cerebrovascular disease',
u'Aortic aneurysm', u'Other aneurysm', u'Peripheral valve disease',
u'Arterial embolism and thrombosis', u'Polyarthritis nodosa',
u"Wegener's granulomatosis", u'Arteritis',
u'Portal vein thrombosis', u'Oesophageal varices',
u'Acute upper respiratory infection', u'Acute bronchitis',
u'Viral pneumonia', u'Pneumoccal and unspecified lobar pneumonia',
u'Other bacterial pneumonia', u'Other specified pneumonia',
u'Bronchopneumonia', u'Unspecified pneumonia', u'Influenza',
u'Chronic bronchitis and emphysema', u'Asthma', u'Bronchiectasis',
u"Farmer's lung disease", u"Bird fancier's lung",
u'Other and unspecified allergic pneumonitis',
u"Coal worker's pneumoconiosis", u'Asbestosis', u'Silicosis',
u'Other pneumoconiosis', u'Byssinosis',
u'Respiratory conditions from chemical fumes', u'Pleurisy',
u'Pneumothorax', u'Pulmonary fibrosis', u'Fibrosing alveolitis',
u'Oesophageal disease', u'Gastric ulcer', u'Duodenal ulcer',
u'Peptic ulcer', u'Gastrojejunal ulcer',
u'Non-alcoholic gastritis and duodenitis', u'Appendicitis',
u'Inguinal hernia', u'Other hernia', u"Crohn's disease",
u'Ulcerative colitis', u'Other colitis', u'Volvulus',
u'Diverticular disease', u'Peritonitis', u'Hepatitis',
u'Cirrhosis (not specified as biliary)', u'Biliary cirrhosis',
u'Cholelithiasis and cholecystitis', u'Pancreatitis',
u'Glomerulonephritis', u'Renal failure', u'Urinary infections',
u'Hydronephrosis', u'Renal stones', u'Hyperplasia of prostate',
u'Pelvic inflammatory disease', u'Ovarian cysts',
u'Ectopic pregnancy', u'Complications of pregnancy',
u'Complications of delivery', u'Complications of puerperium',
u'Infections of skin, joints and bones', u'Erythematous conditions',
u'Systemic lupus erythematous', u'Systematic sclerosis',
u'Myositis', u'Rheumatoid arthritis', u'Ankylosing spondylitis',
u'Osteoporosis', u'Railway accidents',
u'Motor vehicle traffic accidents',
u'Off-road motor vehicle traffic accidents',
u'Pedal cycle accidents', u'Animal transport accidents',
u'Water transport accidents', u'Air transport accidents',
u'Other vehicle accidents', u'Accidental poisoning by drugs',
u'Methanol poisoning', u'Poisoning by cleansing agents',
u'Poisoning by solvents', u'Pesticide poisoning',
u'Poisoning by corrosive and caustics', u'Other poisoning',
u'Poisoning by gas and other domestic fuels',
u'Poisoning by liquefied petroleum gas',
u'Poisoning by motor vehicle exhaust',
u'Poisoning by carbon monoxide from other sources',
u'Poisoning by other gases', u'Fall on stairs',
u'Fall from ladder or scaffolding', u'Fall from building',
u'Fall into hole', u'Other fall', u'Slipping and tripping',
u'Fracture unspecified', u'Fall unspecified', u'Injured by fire',
u'Heat injury', u'Cold injury',
u'Injury by high or low air pressure',
u'Injury by animals and plants', u'Injury by lightning',
u'Non-recreational drowning', u'Injury by falling object',
u'Injury by being caught between objects', u'Injury by machinery',
u'Injury by cutting and piercing instruments or',
u'Injury by explosion of pressure vessel', u'Injury by firearms',
u'Injury by explosive material', u'Injury by hot substances',
u'Injury by electric current', u'Overexertion', u'Other accidents',
u'Suicide', u'Homicide',
u'Injury undetermined as accidental or purposef', u'War',
u'Unspecified Group'], dtype=object)
In [83]:
df[((df['Cause'] == 'Pulmonary fibrosis') | (df['Cause'] == 'Fibrosing alveolitis')) & (df['Observed'] > 5)].sort('PMR_Adj', ascending=False)
Out[83]:
diagrp
Cause
SOdm
Occupation
Observed
Exp_Adj
PMR_Adj
Lower_Adj
Upper_Adj
Exp_Unadj
PMR_Unadj
Lower_Unadj
Upper_Unadj
24550
138
Pulmonary fibrosis
123
Machine Tool Setter Operators
6
2.463433
243.56250
89.38338
530.13410
2.435855
246.32010
90.39538
536.13630
24699
139
Fibrosing alveolitis
84
Ceramics casters
8
3.410907
234.54170
101.25750
462.14100
3.398858
235.37320
101.61650
463.77930
24436
138
Pulmonary fibrosis
2
Accountants and Financial Managers
11
5.179028
212.39510
106.02760
380.03270
6.008953
183.06020
91.38364
327.54460
24599
138
Pulmonary fibrosis
182
Bus & Coach Drivers
11
5.688039
193.38830
96.53942
346.02440
5.085345
216.30780
107.98090
387.03380
24690
139
Fibrosing alveolitis
75
Chemical workers
15
8.144490
184.17360
103.08070
303.76610
7.703251
194.72300
108.98520
321.16570
24621
139
Fibrosing alveolitis
6
Sales Managers etc.
30
16.380030
183.14990
123.57060
261.45810
15.161290
197.87230
133.50380
282.47530
24671
139
Fibrosing alveolitis
56
Roundsmen/women & Van Salespersons
6
3.437844
174.52800
64.04886
379.87470
3.420561
175.40980
64.37249
381.79410
24601
138
Pulmonary fibrosis
184
Other motor drivers
11
6.404210
171.76200
85.74360
307.32910
5.784600
190.16010
94.92790
340.24820
24573
138
Pulmonary fibrosis
149
Welding Trades
8
4.880501
163.91760
70.76733
322.98320
4.435566
180.36030
77.86605
355.38190
24676
139
Fibrosing alveolitis
61
Hospital Porters and Ward Orderlies
12
7.469115
160.66160
83.01653
280.64370
7.065194
169.84670
87.76263
296.68820
24657
139
Fibrosing alveolitis
42
Butchers
9
5.610746
160.40650
73.34853
304.50140
5.582460
161.21920
73.72018
306.04430
24669
139
Fibrosing alveolitis
54
Postal Workers, Mail Sorters
18
11.560610
155.70120
92.27804
246.07530
10.909750
164.99010
97.78320
260.75580
24474
138
Pulmonary fibrosis
40
Managers in Transport, Mining and Energy Indus...
7
4.852604
144.25240
57.99772
297.21570
5.250402
133.32310
53.60352
274.69710
24533
138
Pulmonary fibrosis
104
Carpenters & Joiners
16
11.269040
141.98190
81.15510
230.56980
10.189130
157.03000
89.75642
255.00700
24740
139
Fibrosing alveolitis
133
Motor Mechanics, Auto Engineers (including roa...
19
13.425520
141.52150
85.20490
221.00370
13.295340
142.90730
86.03919
223.16770
24750
139
Fibrosing alveolitis
145
Sheet Metal Workers
6
4.245677
141.32020
51.86216
307.59520
4.229693
141.85430
52.05815
308.75760
24568
138
Pulmonary fibrosis
144
Plumbers, Heating & Ventilating Engineers & Re...
11
7.816734
140.72370
70.24928
251.79310
7.031103
156.44770
78.09869
279.92760
24487
138
Pulmonary fibrosis
53
Office Workers and Cashiers
29
21.662120
133.87420
89.65788
192.26550
22.215400
130.54010
87.42493
187.47710
24655
139
Fibrosing alveolitis
40
Managers in Transport, Mining and Energy Indus...
18
13.725140
131.14620
77.72527
207.26790
12.691940
141.82230
84.05253
224.14060
24795
139
Fibrosing alveolitis
198
Other Labourers
71
54.282220
130.79790
102.15430
164.98370
66.089290
107.43040
83.90406
135.50880
24607
138
Pulmonary fibrosis
190
Storekeepers & warehousemen/women
13
10.032320
129.58120
68.99699
221.58780
11.063340
117.50520
62.56699
200.93750
24780
139
Fibrosing alveolitis
182
Bus & Coach Drivers
16
12.491670
128.08540
73.21200
208.00260
12.421800
128.80580
73.62378
209.17260
24653
139
Fibrosing alveolitis
38
Production and maintenance managers
29
22.824100
127.05870
85.09339
182.47730
21.181210
136.91380
91.69353
196.63090
24645
139
Fibrosing alveolitis
30
Other Professional Engineers
18
14.221410
126.56970
75.01294
200.03500
17.432650
103.25450
61.19495
163.18690
24754
139
Fibrosing alveolitis
149
Welding Trades
13
10.548860
123.23600
65.61845
210.73740
10.446600
124.44240
66.26080
212.80040
24478
138
Pulmonary fibrosis
44
Retailers and Dealers
9
7.315822
123.02100
56.25342
233.53220
7.485923
120.22570
54.97519
228.22570
24654
139
Fibrosing alveolitis
39
Managers in Construction
8
6.541175
122.30220
52.80091
240.98420
6.163199
129.80270
56.03908
255.76330
24748
139
Fibrosing alveolitis
143
Electrical Engineers (not professional)
7
5.783771
121.02830
48.66029
249.36500
5.738286
121.98770
49.04601
251.34160
24765
139
Fibrosing alveolitis
167
Plasterers
6
5.041742
119.00650
43.67340
259.02760
4.986297
120.32980
44.15902
261.90780
24786
139
Fibrosing alveolitis
188
Fork Lift & Mechanical Truck Drivers
10
8.465798
118.12240
56.64439
217.23170
8.390629
119.18060
57.15186
219.17790
...
...
...
...
...
...
...
...
...
...
...
...
...
...
24707
139
Fibrosing alveolitis
97
Printers
8
8.550961
93.55673
40.39078
184.34420
8.505954
94.05177
40.60450
185.31960
24782
139
Fibrosing alveolitis
184
Other motor drivers
13
14.022930
92.70530
49.36200
158.52890
13.887610
93.60864
49.84300
160.07370
24551
138
Pulmonary fibrosis
124
Machine Tool Operatives (including CNC machine...
9
9.763569
92.17941
42.15057
174.98520
10.842050
83.01017
37.95778
157.57910
24767
139
Fibrosing alveolitis
169
Builders, Building Contractors
20
21.827090
91.62926
55.96944
141.51410
21.646060
92.39558
56.43753
142.69760
24639
139
Fibrosing alveolitis
24
Literary and Artistic Occupations
14
15.320120
91.38309
49.95979
153.32510
14.447160
96.90488
52.97859
162.58980
24562
138
Pulmonary fibrosis
137
Electricians, Electrical Maintenance Fitters
8
8.773247
91.18630
39.36741
179.67350
7.927672
100.91230
43.56638
198.83770
24672
139
Fibrosing alveolitis
57
Sales Representatives
14
15.476830
90.45781
49.45393
151.77270
15.730200
89.00079
48.65737
149.32810
24763
139
Fibrosing alveolitis
164
Packers, Sorters and Testers
12
13.290970
90.28685
46.65272
157.71310
12.762600
94.02474
48.58415
164.24240
24443
138
Pulmonary fibrosis
9
Other Administrators
19
21.138670
89.88268
54.11505
140.36320
22.751370
83.51147
50.27917
130.41370
24749
139
Fibrosing alveolitis
144
Plumbers, Heating & Ventilating Engineers & Re...
15
16.948800
88.50185
49.53389
145.97020
16.884000
88.84151
49.72400
146.53050
24794
139
Fibrosing alveolitis
197
Other Transport and Machine Operatives
10
11.327610
88.27988
42.33374
162.35030
10.812370
92.48667
44.35106
170.08670
24625
139
Fibrosing alveolitis
10
Teachers in Higher Education
6
6.847532
87.62281
32.15611
190.71840
7.340598
81.73721
29.99619
177.90790
24662
139
Fibrosing alveolitis
47
Farmers
33
37.872480
87.13451
59.97944
122.36930
35.539190
92.85523
63.91732
130.40340
24651
139
Fibrosing alveolitis
36
Seafarers
7
8.035377
87.11476
35.02511
179.49000
7.521931
93.06120
37.41592
191.74200
24781
139
Fibrosing alveolitis
183
Lorry drivers
57
65.937490
86.44550
65.47292
112.00020
65.653760
86.81909
65.75587
112.48420
24673
139
Fibrosing alveolitis
58
Security Workers
22
25.546590
86.11716
53.96923
130.38260
24.252620
90.71184
56.84870
137.33900
24558
138
Pulmonary fibrosis
132
Production fitters
14
16.745920
83.60246
45.70606
140.27060
15.050520
93.02007
50.85474
156.07170
24675
139
Fibrosing alveolitis
60
Other Service Personnel
26
31.171400
83.40980
54.48617
122.21460
33.570930
77.44796
50.59169
113.47910
24656
139
Fibrosing alveolitis
41
General and office managers
12
14.441440
83.09418
42.93615
145.14890
13.350890
89.88168
46.44336
157.00530
24591
138
Pulmonary fibrosis
174
Other Construction Workers
10
12.229760
81.76777
39.21092
150.37420
11.863920
84.28921
40.42004
155.01120
24788
139
Fibrosing alveolitis
190
Storekeepers & warehousemen/women
22
27.678890
79.48296
49.81161
120.33830
26.313930
83.60590
52.39544
126.58050
24492
138
Pulmonary fibrosis
58
Security Workers
7
8.904111
78.61537
31.60787
161.97800
10.017060
69.88079
28.09607
143.98140
24481
138
Pulmonary fibrosis
47
Farmers
10
13.614370
73.45179
35.22307
135.08080
14.992530
66.69990
31.98527
122.66380
24586
138
Pulmonary fibrosis
169
Builders, Building Contractors
7
10.030310
69.78848
28.05895
143.79120
9.096371
76.95376
30.93981
158.55440
24759
139
Fibrosing alveolitis
160
Painters & Decorators
16
22.951030
69.71365
39.84745
113.21060
22.862360
69.98404
40.00200
113.64970
24617
139
Fibrosing alveolitis
2
Accountants and Financial Managers
9
13.532080
66.50863
30.41218
126.25410
14.194400
63.40527
28.99312
120.36290
24661
139
Fibrosing alveolitis
46
Caterers
6
9.096940
65.95625
24.20484
143.55930
8.996549
66.69224
24.47494
145.16120
24659
139
Fibrosing alveolitis
44
Retailers and Dealers
10
17.314950
57.75357
27.69515
106.21110
17.075470
58.56356
28.08357
107.70070
24772
139
Fibrosing alveolitis
174
Other Construction Workers
13
25.219410
51.54760
27.44712
88.14799
28.082690
46.29186
24.64864
79.16051
24626
139
Fibrosing alveolitis
11
School Teachers
6
13.054130
45.96245
16.86745
100.04110
12.090690
49.62497
18.21154
108.01290
83 rows × 13 columns
In [78]:
df[(df['Cause'] == 'Fibrosising alveolitis') & (df['Observed'] > 5)].sort('PMR_Adj', ascending=False)
Out[78]:
diagrp
Cause
SOdm
Occupation
Observed
Exp_Adj
PMR_Adj
Lower_Adj
Upper_Adj
Exp_Unadj
PMR_Unadj
Lower_Unadj
Upper_Unadj
In [ ]:
Content source: drcjar/pa-research
Similar notebooks: