In [6]:
%pylab inline
import pandas as pd
from soln.dataset import get_augmented_train_and_test_set
pd.set_option('display.max_columns', None)
Populating the interactive namespace from numpy and matplotlib
In [3]:
aug_train_set, aug_test_set = get_augmented_train_and_test_set()
In [7]:
taids = [
('TA-00875', 100),
('TA-10796', 250),
('TA-10918', 100),
('TA-10919', 100),
('TA-10956', 250),
('TA-17565', 100),
('TA-18894', 250),
('TA-19109', 100),
('TA-19344', 100),
('TA-19867', 1), # weird one, different supplier
('TA-20766', 250), # the one that our predictor thinks is similar
]
df = aug_train_set
subset = pd.DataFrame()
for taid, quantity in taids:
subset = subset.append(df[(df.tube_assembly_id == taid) & (df.quantity == quantity)])
subset
Out[7]:
tube_assembly_id
supplier
quote_date
annual_usage
min_order_quantity
bracket_pricing
quantity
log_cost
material_id
diameter
wall_thickness
length
num_bends
bend_radius
end_a_1x
end_a_2x
end_x_1x
end_x_2x
end_a
end_x
num_boss
num_bracket
num_other
specs
components
quote_age
adj_quantity
adj_bracketing
bracketing_pattern
dev_fold
1538
TA-00875
S-0066
2013-06-30
0
0
True
100
1.032593
SP-0019
6.35
0.71
31
2
19.05
False
False
False
False
EF-008
EF-008
0
0
0
[]
[C-1312, C-1312]
41453
100
True
(1, 2, 5, 10, 25, 50, 100, 250)
7
16556
TA-10796
S-0066
2013-09-01
0
0
True
250
1.032593
SP-0029
19.05
1.65
87
4
38.10
False
False
False
True
NONE
NONE
0
0
0
[]
[]
41516
250
True
(1, 2, 5, 10, 25, 50, 100, 250)
6
16901
TA-10918
S-0066
2013-08-01
0
0
True
100
1.032593
SP-0035
9.52
1.24
25
2
19.05
False
False
False
False
EF-018
EF-018
0
0
0
[]
[C-1243, C-1243, C-1244, C-1244]
41485
100
True
(1, 2, 5, 10, 25, 50, 100, 250)
2
16909
TA-10919
S-0066
2013-08-01
0
0
True
100
1.032593
SP-0035
9.52
1.24
25
2
19.05
False
False
False
False
EF-018
EF-018
0
0
0
[]
[C-1243, C-1243, C-1244, C-1244]
41485
100
True
(1, 2, 5, 10, 25, 50, 100, 250)
3
17050
TA-10956
S-0066
2013-03-31
0
0
True
250
1.032593
SP-0019
12.70
0.89
36
3
38.10
False
False
False
False
NONE
EF-008
0
0
0
[]
[C-1229]
41362
250
True
(1, 2, 5, 10, 25, 50, 100, 250)
2
22993
TA-17565
S-0066
2013-06-01
0
0
True
100
1.032593
SP-0039
6.35
0.71
31
2
19.05
False
False
False
False
EF-008
EF-008
0
0
0
[]
[C-1312, C-1312]
41424
100
True
(1, 2, 5, 10, 25, 50, 100, 250)
9
24364
TA-18894
S-0066
2013-06-01
0
0
True
250
1.032593
SP-0039
6.35
0.71
31
2
25.40
False
False
False
False
EF-008
EF-008
0
0
0
[]
[C-1845, C-1845, C-1846, C-1846]
41424
250
True
(1, 2, 5, 10, 25, 50, 100, 250)
6
25000
TA-19109
S-0066
2013-07-21
0
0
True
100
1.032593
SP-0019
6.35
0.71
23
3
19.05
False
False
False
False
EF-008
EF-008
0
0
0
[]
[C-1312, C-1312]
41474
100
True
(1, 2, 5, 10, 25, 50, 100, 250)
4
25651
TA-19344
S-0066
2013-08-11
0
0
True
100
1.032593
SP-0035
6.35
0.89
26
2
19.05
False
False
False
False
EF-018
EF-018
0
0
0
[]
[C-1845, C-1845, C-1846, C-1846]
41495
100
True
(1, 2, 5, 10, 25, 50, 100, 250)
8
26620
TA-19867
S-0062
2005-05-09
2311
1
False
1
1.032593
SP-0028
25.40
1.65
45
1
50.80
False
False
False
True
EF-009
EF-017
0
0
0
[SP-0016, SP-0058, SP-0080]
[]
38479
1
False
()
7
29135
TA-20766
S-0066
2013-11-02
1
0
True
250
2.979539
SP-0029
12.70
0.89
34
3
25.40
False
False
False
True
EF-017
EF-003
0
0
0
[]
[C-1475, C-1476]
41578
250
True
(1, 2, 5, 10, 25, 50, 100, 250)
0
In [ ]:
Content source: arorahardeep/kaggle-caterpillar
Similar notebooks: