Você está na página 1de 12

In [16]: import numpy as np

import matplotlib.pyplot as plt


import pandas as pd

In [17]: import types


import pandas as pd
from botocore.client import Config
import ibm_boto3
def __iter__(self): return 0

client_1dd3315126b3445ba13ee3de57612bf2 = ibm_boto3.client(service_name='s3',
ibm_api_key_id='HRUzrUczp7wFf7hBHgUwQgEaXwrdJqcNo8r0ijWiimK5',
ibm_auth_endpoint="https://iam.bluemix.net/oidc/token",
config=Config(signature_version='oauth'),
endpoint_url='https://s3.eu-geo.objectstorage.service.networklayer.com')

body = client_1dd3315126b3445ba13ee3de57612bf2.get_object(Bucket='rainfallprediction-don
otdelete-pr-qac5ghq4uqv4bj',Key='final-dataset.csv')['Body']
# add missing __iter__ method, so pandas accepts body as file-like object
if not hasattr(body, "__iter__"): body.__iter__ = types.MethodType( __iter__, body )
df = pd.read_csv(body)
df.head()

Out[17]:
temp temp DP DP humidity SLP visibility
year month day tempavg DPavg ... SLPavg
high low high low high low high

0 2008 1 1 24 21 18 17 15 12 83 ... 1013 1011 5

1 2008 1 2 26 22 19 18 17 16 88 ... 1014 1012 5

2 2008 1 3 25 21 18 16 16 13 88 ... 1014 1006 5

3 2008 1 4 26 23 20 17 16 15 83 ... 1014 1013 5

4 2008 1 5 26 21 17 17 15 14 88 ... 1015 1012 5

5 rows × 23 columns

In [18]: df.head()

Out[18]:
temp temp DP DP humidity SLP visibility
year month day tempavg DPavg ... SLPavg
high low high low high low high

0 2008 1 1 24 21 18 17 15 12 83 ... 1013 1011 5

1 2008 1 2 26 22 19 18 17 16 88 ... 1014 1012 5

2 2008 1 3 25 21 18 16 16 13 88 ... 1014 1006 5

3 2008 1 4 26 23 20 17 16 15 83 ... 1014 1013 5

4 2008 1 5 26 21 17 17 15 14 88 ... 1015 1012 5

5 rows × 23 columns
In [19]: df.drop(["A"],axis=1,inplace=True)
df.drop(["b"],axis=1,inplace=True)
df.drop(["temp high"],axis=1,inplace=True)
df.drop(["temp low"],axis=1,inplace=True)
df.drop(["visibilityavg"],axis=1,inplace=True)
df.drop(["DP high"],axis=1,inplace=True)
df.drop(["DP low"],axis=1,inplace=True)
df.drop(["humidity high"],axis=1,inplace=True)
df.drop(["SLP high"],axis=1,inplace=True)
df.drop(["SLP low"],axis=1,inplace=True)
df.drop(["humidity low"],axis=1,inplace=True)
df.drop(["wind high"],axis=1,inplace=True)
df.drop(["visibility high"],axis=1,inplace=True)
#df.drop(["SLP avg"],axis=1,inplace=True)
#df.drop(["visibility low"],axis=1,inplace=True)

In [55]: df.head()

Out[55]:
year month day tempavg DPavg humidity avg SLPavg visibilitylow windavg Rainfall

0 2008 1 1 21 15 65 1013 1 8 0.0

1 2008 1 2 22 17 76 1014 1 2 0.0

2 2008 1 3 21 16 62 1014 0 10 0.0

3 2008 1 4 23 16 65 1014 4 11 0.0

4 2008 1 5 21 15 67 1015 1 11 0.0

In [21]: df.isnull().any()

Out[21]: year False


month False
day False
tempavg False
DPavg False
humidity avg False
SLPavg False
visibilitylow False
windavg False
Rainfall False
dtype: bool

In [22]: x=df.iloc[:,3:9].values

In [23]: y=df.iloc[:,9].values

In [24]: x

Out[24]: array([[ 21, 15, 65, 1013, 1, 8],


[ 22, 17, 76, 1014, 1, 2],
[ 21, 16, 62, 1014, 0, 10],
...,
[ 23, 16, 66, 1014, 2, 5],
[ 23, 17, 62, 1013, 2, 5],
[ 24, 18, 68, 1012, 3, 2]])
In [25]: y

Out[25]: array([ 0., 0., 0., ..., 0., 0., 0.])

In [26]: from sklearn.model_selection import train_test_split

In [27]: x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=0)

In [28]: x_train

Out[28]: array([[ 28, 26, 90, 1001, 2, 10],


[ 28, 24, 79, 1009, 3, 14],
[ 21, 15, 65, 1014, 4, 5],
...,
[ 29, 26, 83, 1003, 4, 10],
[ 28, 23, 73, 1009, 3, 5],
[ 31, 25, 72, 1001, 5, 6]])

In [29]: y_train

Out[29]: array([ 2.03, 0. , 0. , ..., 3.05, 0.76, 0. ])

In [30]: x_test

Out[30]: array([[ 28, 26, 79, 1003, 3, 8],


[ 26, 24, 93, 1004, 2, 6],
[ 27, 24, 89, 1004, 3, 19],
...,
[ 29, 25, 73, 1005, 3, 11],
[ 31, 26, 77, 1006, 5, 2],
[ 26, 19, 66, 1013, 3, 10]])

In [31]: from sklearn.linear_model import LinearRegression

In [32]: mlr=LinearRegression()

In [33]: mlr.fit(x_train,y_train)

Out[33]: LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)

In [34]: y_pred=mlr.predict(x_test)
In [35]: y_pred
Out[35]: array([ 3.38759607, 6.36666643, 6.23912028, 7.99437554,
-4.12204175, 3.36878279, 0.67930045, 5.32868189,
-0.07123403, 0.98144609, 3.52235072, -0.1249315 ,
3.43030437, 3.87767851, 8.58714519, 3.57169665,
1.78510611, 2.9379245 , 0.77287268, -1.23863666,
-0.30046977, -2.00280891, 0.25002615, 5.22567406,
0.38969298, 2.69733689, 1.94386123, -0.71475882,
1.75564883, 1.24554724, 12.49482796, 3.82350061,
-3.38520785, 3.02021826, 2.5528487 , 9.36405054,
-0.57229348, -0.78703655, 1.766801 , 3.49459723,
1.41172939, -2.03857537, 3.84203478, -0.96390209,
-1.08489785, 1.26429088, 3.47308493, -0.03758404,
1.23495678, 5.01153584, 2.11831085, 2.15966804,
0.51327553, 6.0679404 , 0.4935252 , -1.7170277 ,
2.87408157, 8.58463264, 3.24349776, -0.08043386,
2.21390298, 0.32027489, 1.60563103, 2.42945963,
2.64921808, 2.2821146 , -0.54866465, -0.67225936,
-0.58236355, 2.89958489, 2.79112403, 4.65396102,
6.17623243, 2.76842645, 7.34439653, 1.07312259,
1.30039354, 2.64692283, -0.69461567, -0.45476529,
-3.46053904, -3.76629377, -0.47677361, 1.2277714 ,
1.99473737, 1.0197857 , 8.89958677, 0.90117223,
3.20870155, -1.37845702, -1.41086805, -0.60962283,
1.83110959, 0.43454391, -1.74972622, -0.75896364,
-0.90541068, -0.13853245, 1.59825804, 5.29518877,
1.48581236, 1.26642262, 2.19323356, -1.72847975,
-0.02615596, 1.12206782, 6.40144742, -0.69932558,
0.83919759, 0.44874652, 3.72238851, -0.32317445,
3.68760414, 1.85082034, 2.3643502 , -0.04104266,
1.734635 , 3.99064758, 4.63356757, 0.672562 ,
2.8095803 , -1.27499576, 5.57668244, 3.41706305,
-0.35485959, 5.94668814, 3.01575608, 1.01940683,
1.04510095, 0.07757075, -0.15168028, 4.17061761,
-2.28435113, -1.27322759, 2.75816525, 1.44290429,
0.76129995, 1.4587097 , 3.95326306, -1.47419694,
-0.73492321, 1.81818218, 5.231854 , 0.04604856,
1.72548326, 4.25103099, 3.41155836, 0.53496994,
1.48155232, 8.76713939, 1.01272306, -1.18160488,
-0.68535911, 2.00698402, -0.5618786 , 6.00037973,
1.90874991, 1.28338833, 2.52499665, 0.19580336,
3.91172796, 0.37504229, 0.09749899, 0.97341 ,
2.20173761, -0.04893289, -0.22403027, 1.91928526,
2.55235612, 0.1745984 , 0.93704188, -2.98044232,
4.33570315, -1.11342388, -0.88354701, -2.19865423,
8.59103532, 3.14903419, 3.38791118, -2.31023831,
1.53395303, -2.03976065, -0.14693399, 1.42009806,
2.09462786, -0.18758319, 1.14517044, 8.07963734,
0.79168595, 1.46532986, 2.11739765, 5.06668398,
4.68128448, 1.32616232, -1.33460051, -3.28067665,
-0.37561348, 2.85152356, 1.39436173, 1.44647507,
1.34636064, 1.77463413, 4.48385817, 2.4394453 ,
0.50254356, 3.34244875, -1.13939271, 6.42993193,
2.87226838, 0.02293078, -0.77209275, 3.45957153,
0.48247894, -0.91362455, 2.50276434, 0.07934243,
-0.80974929, 6.49742341, -0.78829999, 2.87023013,
0.03162201, 0.92089482, 2.8665968 , 1.63372266,
2.86318077, 1.09479282, -1.40752435, 0.21236373,
1.08786976, 0.0912049 , 2.64143336, 3.75724176,
1.51935953, -0.32620925, 1.3743753 , -0.42673534,
1.22334567, 7.64313471, -0.30782561, 8.76079376,
0.13221729, 2.13980907, 2.47530825, -0.42600631,
1.93245419, -1.85455375, 1.58068748, -2.01841098,
1.15403092, 6.13082825, 4.54151228, 0.84258382,
-0.25187918, 1.96723519, 2.90020527, 8.90085327,
1.44882066, 3.55651476, -0.30722715, 1.23316752,
0.97115202, 1.62220147, 3.82063777, 1.47152732,
5.55752475, 3.1392816 , 5.20543747, 1.88738828,
1.98324586, -1.63392819, 1.03402464, 2.55953054,
2.62046441, 2.22608057, 4.07233847, 0.7563003 ,
-1.34938287, -0.47424697, -0.08864465, -2.27425368,
1.20499254, 1.29438369, 1.12629379, 1.99486673,
-0.1181683 , 0.21098525, 5.76458643, 1.11814911,
-0.84631723, 5.32994545, -0.03090232, 10.22681019,
-0.23797602, 1.2654371 , 1.93644216, -4.60969911,
10.1634998 , -1.85410064, -1.47264606, 5.00207056,
-1.3422097 , 4.06667003, -3.91953956, 2.70046267,
0.15180419, 0.73270466, 3.55701092, -0.90077311,
1.90734069, -1.96949982, 1.40480633, 0.55134613,
-2.02901346, 4.8698351 , 1.08279082, 3.04111988,
7.91532349, 6.96554236, 2.09615982, 3.71609762,
0.66830509, 3.11679792, 1.24956794, 7.57268927,
1.80844488, 1.9732669 , -0.36694956, 9.35515053,
2.27611884, 2.21984358, -0.55144302, 1.22903804,
2.97379415, -2.05043233, 1.87017428, 0.03199065,
1.35176564, 3.79499493, 1.18030792, 7.60459533,
0.97015434, 1.21729643, 3.45929599, 2.27585338,
-2.88218047, 2.6780705 , -0.172603 , 0.23103428,
3.63587536, 2.49318722, -0.42701951, -0.64974938,
2.53479771, 0.94427335, -0.56573004, 0.50946662,
3.39906021, -0.30507461, 2.11038121, 3.16428877,
3.42245603, 8.89443864, 0.51643776, -0.60902122,
-1.33054931, 12.85106896, 3.48253813, 1.66822248,
0.70187775, 1.3382191 , 1.12501507, 1.33767487,
1.7988157 , -1.45464323, 5.13623137, -2.56323339,
0.72531846, -1.27913725, 3.43905934, 2.0790561 ,
-3.22958867, 5.34845645, 0.91614852, 3.97658954,
0.52733344, 5.14799721, 6.20669389, 6.01506546,
-0.49407515, 1.85189341, 2.26617313, 5.12466172,
2.80416009, 0.33758852, -1.25496784, -1.70507731,
1.6227789 , 1.53907705, 0.42876318, 2.40307047,
-2.23434216, 1.55396567, 0.48381475, 2.08867819,
2.20390216, 4.00386467, 3.59734269, 0.69808955,
9.16037522, 0.15023542, 3.33010547, 0.39068746,
-0.19696405, 3.45482523, -1.37828814, -2.65652452,
2.65377663, 2.46302201, 1.5335019 , 3.63241994,
-2.68164704, -4.18557928, -0.8084464 , -0.16749119,
0.43273585, 4.52801766, 3.39171653, -0.93455046,
-0.4318593 , 4.01397419, 0.83859593, 1.99013253,
7.93658869, 0.5788264 , 2.76335953, 1.39458259,
4.25851262, -1.65315163, 1.11224804, -0.6434695 ,
0.10870621, 1.75397687, -1.47087784, -1.17994856,
1.25136698, 2.68435237, 2.26037511, 9.64171112,
5.79950881, 0.60043287, 2.71860203, 0.57458827,
1.15207821, -0.18696631, 0.17039667, 1.21818226,
-2.01961744, 1.04878933, 1.1652382 , 1.70261365,
2.01420347, 3.66444128, 1.11034335, 2.59723442,
2.87990488, 2.02040639, 8.65378044, 0.80348786,
1.28019836, 0.14322481, -1.40501506, 1.6633378 ,
2.7664495 , 1.53247455, 9.71323545, 2.79331282,
2.4201601 , 4.88903224, 4.32485588, 3.37570586,
1.55977577, 1.82057072, 0.76569632, -0.33866474,
-1.42024304, 5.4347249 , 2.56036478, 1.47249757,
-0.83395561, 3.22090024, -2.06158136, 9.78471489,
0.6933432 , 3.58245593, 1.88795312, 3.37230554,
4.26851344, 2.0849354 , 1.58383449, 5.61793964,
5.36226299, 2.16788198, -2.59723169, 2.47667808,
0.74028962, 3.99085835, 2.27371307, 0.26117831,
7.45498907, 5.3941296 , 3.86423742, 1.82424358,
0.66341415, 0.78841814, 1.60933781, 6.76255312,
-1.73467684, 0.377219 , 4.73880915, -2.63368428,
-0.55501924, 1.51900923, 0.08300318, 2.54718727,
3.24691173, 5.44111542, -1.36770081, 1.71502932,
-3.33630565, 5.72047862, 1.11220851, -2.89050656,
3.61818113, -0.49273626, 6.20747659, 0.48868542,
-0.21743091, 1.57783685, 5.69946478, 3.99209218,
1.52445367, 3.92718231, 3.8277207 , 7.66273682,
2.29026121, 4.77661636, 4.54669441, 5.75183142,
-2.28230493, -0.54912673, 2.68971554, 0.38201344,
-0.80740064, -1.44723931, 3.97452826, 0.7321601 ,
2.36283519, -0.10159592, -2.1742511 , 3.92755997,
0.22621873, 1.39607322, 0.22521842, 1.92057613,
4.91439284, -1.16264701, 6.82767477, -1.20275798,
2.35854509, 7.21158364, 1.83311033, 2.49566024,
3.38990334, -0.20870567, 1.06486927, 0.55909991,
-1.19011832, -2.0153641 , -1.78145432, 5.73216005,
5.63885014, 5.08269466, 3.7551233 , 1.61565608,
3.52598405, 0.87064151, 1.00159826, 4.67221216,
4.28177662, 2.74163225, -1.18497915, 0.64740347,
3.0589507 , -0.24924936, -2.71828173, 3.72286894,
1.2525336 , 4.91836865, 0.06778485, -0.82060207,
3.77468589, 2.86454089, 2.61202348, -2.08453921,
7.02740165, -0.93635852, 1.27515567, 0.50223515,
1.24181729, 3.95228059, 3.75223272, -1.14006991,
2.40631398, -1.64328132, -3.13896375, -1.6213422 ,
2.31726111, 3.96702777, -0.73826371, 2.47799318,
3.4201378 , 0.63680099, 0.06726766, 2.12131328,
1.3423606 , 2.30596034, -0.92546285, 6.54020091,
0.48925928, 4.60911003, 4.11199632, 2.06053288,
1.77532026, -0.52046437, 4.31164443, -1.75249557,
2.08288919, 0.6458886 , 0.75037172, 4.42767253,
1.10085972, 2.21557152, 0.93711114, 1.50651108,
-0.39221679, 3.04097523, 0.02542811, 1.03141867,
1.2214289 , 3.27759612, 1.2654371 , 0.87992895,
1.21992312, 4.69847738, -0.67148568, 4.06037286,
0.68453662, -1.45194927, 4.89601234, 0.08756844,
3.11041942, 2.14301318, -0.03632253, 2.19743023,
1.17824337, 8.19676012, 2.8297599 , 6.07190406,
1.40959872, 6.65997769, 4.11696681, 5.46018869,
2.44816625, 2.12695762, 3.0996875 , 1.27280106,
-1.72669586, 7.28612868, 5.95864487, 4.62929551,
3.05444562, 2.47705574, 1.94015088, 2.67871116,
3.20194231, 3.75092356, 2.28062391, 1.86527112,
-0.58544131, 2.91229174, -2.01793369, 4.38562406,
-0.82595002, -1.75900458, 1.11389221, -1.08901524,
2.39856226, -2.03138999, 2.4701449 , 0.5230402 ,
-1.57117331, 8.18854619, 0.83168509, 0.10357911,
3.05151946, 2.19809213, -0.20989997, 4.30526004,
-1.02437401, 6.65989328, -1.2508986 , 1.33260795,
-1.6388192 , -0.80322821, -0.67338135, 6.07465155,
4.51357539, 1.27147432, 4.46946757, 2.54306874,
-0.10148371, -0.51950608])
In [36]: mlr.intercept_

Out[36]: 316.19992552911049

In [37]: mlr.coef_

Out[37]: array([ 0.23450242, -0.25308268, 0.16938077, -0.32275087, -1.11311252,


0.10989131])

In [38]: from sklearn.metrics import r2_score

In [39]: r2_score(y_test,y_pred)

Out[39]: 0.1163989252024541

In [40]: df.corr()

Out[40]:
humidity
year month day tempavg DPavg SLPavg visibilitylow
avg

year 1.000000 0.005107 -0.001671 0.036119 0.053910 -0.022888 0.078634 -0.235686

month 0.005107 1.000000 0.017125 0.151150 0.269709 0.327681 -0.122125 0.137833

day -0.001671 0.017125 1.000000 -0.017227 0.003328 0.030402 0.002659 -0.004495

tempavg 0.036119 0.151150 -0.017227 1.000000 0.859614 0.349759 -0.667711 0.593018

DPavg 0.053910 0.269709 0.003328 0.859614 1.000000 0.743077 -0.754915 0.496900

humidity
-0.022888 0.327681 0.030402 0.349759 0.743077 1.000000 -0.584092 0.149500
avg

SLPavg 0.078634 -0.122125 0.002659 -0.667711 -0.754915 -0.584092 1.000000 -0.487170

visibilitylow -0.235686 0.137833 -0.004495 0.593018 0.496900 0.149500 -0.487170 1.000000

windavg -0.043954 -0.217196 0.009739 0.250798 0.242420 0.151820 -0.407696 0.258366

Rainfall 0.151531 0.023572 0.004873 0.058020 0.150611 0.239933 -0.190219 -0.102174

In [41]: import seaborn as sns


In [42]: sns.heatmap(df.corr(),annot=True)

Out[42]: <matplotlib.axes._subplots.AxesSubplot at 0x7fccfc045208>


In [43]: !pip install watson-machine-learning-client --upgrade

Requirement already up-to-date: watson-machine-learning-client in /opt/conda/envs/DSX-P


ython35/lib/python3.5/site-packages (1.0.365)
Requirement not upgraded as not directly required: lomond in /opt/conda/envs/DSX-Python
35/lib/python3.5/site-packages (from watson-machine-learning-client) (0.1.13)
Requirement not upgraded as not directly required: tabulate in /opt/conda/envs/DSX-Pyth
on35/lib/python3.5/site-packages (from watson-machine-learning-client) (0.8.2)
Requirement not upgraded as not directly required: ibm-cos-sdk in /opt/conda/envs/DSX-P
ython35/lib/python3.5/site-packages (from watson-machine-learning-client) (2.0.1)
Requirement not upgraded as not directly required: pandas in /opt/conda/envs/DSX-Python
35/lib/python3.5/site-packages (from watson-machine-learning-client) (0.21.0)
Requirement not upgraded as not directly required: requests in /opt/conda/envs/DSX-Pyth
on35/lib/python3.5/site-packages (from watson-machine-learning-client) (2.18.4)
Requirement not upgraded as not directly required: urllib3 in /opt/conda/envs/DSX-Pytho
n35/lib/python3.5/site-packages (from watson-machine-learning-client) (1.22)
Requirement not upgraded as not directly required: certifi in /opt/conda/envs/DSX-Pytho
n35/lib/python3.5/site-packages (from watson-machine-learning-client) (2019.3.9)
Requirement not upgraded as not directly required: tqdm in /opt/conda/envs/DSX-Python3
5/lib/python3.5/site-packages (from watson-machine-learning-client) (4.19.5)
Requirement not upgraded as not directly required: six>=1.10.0 in /opt/conda/envs/DSX-P
ython35/lib/python3.5/site-packages (from lomond->watson-machine-learning-client) (1.1
1.0)
Requirement not upgraded as not directly required: ibm-cos-sdk-core==2.*,>=2.0.0 in /op
t/conda/envs/DSX-Python35/lib/python3.5/site-packages (from ibm-cos-sdk->watson-machine
-learning-client) (2.0.1)
Requirement not upgraded as not directly required: ibm-cos-sdk-s3transfer==2.*,>=2.0.0
in /opt/conda/envs/DSX-Python35/lib/python3.5/site-packages (from ibm-cos-sdk->watson-m
achine-learning-client) (2.0.1)
Requirement not upgraded as not directly required: python-dateutil>=2 in /opt/conda/env
s/DSX-Python35/lib/python3.5/site-packages (from pandas->watson-machine-learning-clien
t) (2.6.1)
Requirement not upgraded as not directly required: pytz>=2011k in /opt/conda/envs/DSX-P
ython35/lib/python3.5/site-packages (from pandas->watson-machine-learning-client) (201
8.3)
Requirement not upgraded as not directly required: numpy>=1.9.0 in /opt/conda/envs/DSX-
Python35/lib/python3.5/site-packages (from pandas->watson-machine-learning-client) (1.1
3.3)
Requirement not upgraded as not directly required: chardet<3.1.0,>=3.0.2 in /opt/conda/
envs/DSX-Python35/lib/python3.5/site-packages (from requests->watson-machine-learning-c
lient) (3.0.4)
Requirement not upgraded as not directly required: idna<2.7,>=2.5 in /opt/conda/envs/DS
X-Python35/lib/python3.5/site-packages (from requests->watson-machine-learning-client)
(2.6)
Requirement not upgraded as not directly required: jmespath<1.0.0,>=0.7.1 in /opt/cond
a/envs/DSX-Python35/lib/python3.5/site-packages (from ibm-cos-sdk-core==2.*,>=2.0.0->ib
m-cos-sdk->watson-machine-learning-client) (0.9.3)
Requirement not upgraded as not directly required: docutils>=0.10 in /opt/conda/envs/DS
X-Python35/lib/python3.5/site-packages (from ibm-cos-sdk-core==2.*,>=2.0.0->ibm-cos-sdk
->watson-machine-learning-client) (0.14)
tensorflow 1.3.0 requires tensorflow-tensorboard<0.2.0,>=0.1.0, which is not installed.
In [44]: from watson_machine_learning_client import WatsonMachineLearningAPIClient

/opt/conda/envs/DSX-Python35/lib/python3.5/site-packages/sklearn/cross_validation.py:4
1: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model
_selection module into which all the refactored classes and functions are moved. Also n
ote that the interface of the new CV iterators are different from that of this module.
This module will be removed in 0.20.
"This module will be removed in 0.20.", DeprecationWarning)
2019-05-23 09:43:11,507 - watson_machine_learning_client.metanames - WARNING - 'AUTHOR_
EMAIL' meta prop is deprecated. It will be ignored.

In [45]: wml_credentials = {
"username": "cf43da35-0ce4-4edb-a106-02fc4fb042b8",
"password": "5c83964d-5dda-4f53-ab1f-40ac25f3ac0a",
"instance_id": "90f9eaf2-9a60-4712-b10d-23315d3a042c",
"url" : "https://eu-gb.ml.cloud.ibm.com"
}

In [46]: client = WatsonMachineLearningAPIClient(wml_credentials)

In [47]: model_props = {client.repository.ModelMetaNames.AUTHOR_NAME: "BALAJI",client.repository.


ModelMetaNames.AUTHOR_EMAIL: "balajigullapalli246@gmail.com",client.repository.ModelMeta
Names.NAME: "final project"}

In [48]: model = client.repository.store_model(mlr,meta_props=model_props)

In [49]: client.repository.list_models()

------------------------------------ ------------- ------------------------ --------


---------
GUID NAME CREATED FRAMEWOR
K
3bb6d31f-e18c-4bd6-b2c4-72d02bff5ce9 final project 2019-05-23T09:43:11.768Z scikit-l
earn-0.19
7a43d714-bc8b-4b08-8e30-fec4cbd80b36 final project 2019-05-23T05:05:27.799Z scikit-l
earn-0.19
879e3a4f-f4d9-4536-860d-bd659227998d keras model 2019-05-18T06:37:12.696Z tensorfl
ow-1.5
e1bf7fcd-5c24-4782-b857-25df9579427e model1 2019-05-18T05:14:42.991Z wml-1.2
b3970b8e-2ac9-4c06-bbd9-0057c3302d2e MLR model 2019-05-14T07:19:10.074Z scikit-l
earn-0.19
------------------------------------ ------------- ------------------------ --------
---------

In [50]: published_model_uid =client.repository.get_model_uid(model)

In [51]: published_model_uid

Out[51]: '3bb6d31f-e18c-4bd6-b2c4-72d02bff5ce9'
In [52]: deployment = client.deployments.create(published_model_uid,name="final project")

#######################################################################################

Synchronous deployment creation for uid: '3bb6d31f-e18c-4bd6-b2c4-72d02bff5ce9' started

#######################################################################################

INITIALIZING
DEPLOY_SUCCESS

---------------------------------------------------------------------------------------
---------
Successfully finished deployment creation, deployment_uid='ff138a13-247f-41ae-a0b8-202c
bfd1d7e7'
---------------------------------------------------------------------------------------
---------

In [53]: scoring_endpoint = client.deployments.get_scoring_url(deployment)

In [54]: scoring_endpoint

Out[54]: 'https://eu-gb.ml.cloud.ibm.com/v3/wml_instances/90f9eaf2-9a60-4712-b10d-23315d3a042c/d
eployments/ff138a13-247f-41ae-a0b8-202cbfd1d7e7/online'

Você também pode gostar