-
-
Save jef5ez/a9b0650293f343682a58b0f0500f3332 to your computer and use it in GitHub Desktop.
xcessive errors
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
"""In this code block, you must define the function `extract_main_dataset`. | |
`extract_main_dataset` must take no arguments and return a tuple (X, y), where X is a | |
Numpy array with shape (n_samples, n_features) corresponding to the features of your | |
main dataset and y is the Numpy array corresponding to the ground truth labels of each | |
sample. | |
""" | |
import numpy as np | |
import pandas as pd | |
# data available through kaggle https://www.kaggle.com/c/zillow-prize-1/data | |
def extract_main_dataset(): | |
train = pd.read_csv('../data/train_2016.csv') | |
prop = pd.read_csv('../data/properties_2016.csv') | |
for c, dtype in zip(prop.columns, prop.dtypes): | |
if dtype == np.float64: | |
prop[c] = prop[c].astype(np.float32) | |
merged = train.merge(prop, how='left', on='parcelid') | |
x_train = merged.drop(['parcelid', 'logerror', 'transactiondate', 'propertyzoningdesc', 'propertycountylandusecode'], axis=1) | |
y_train = merged['logerror'].values | |
for c in x_train.dtypes[x_train.dtypes == object].index.values: | |
x_train[c] = (x_train[c] == True) | |
return x_train, y_train |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from xgboost import XGBRegressor | |
base_learner = XGBRegressor(seed=8) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
::1 - - [2017-05-30 23:26:29] "POST /ensemble/base-learner-origins/1/verify/?path=/home/joseph/zillow/xcessivModel/xgboost HTTP/1.1" 200 1059 0.149282 | |
::1 - - [2017-05-30 23:28:25] "GET /ensemble/base-learner-origins/1/confirm/?path=/home/joseph/zillow/xcessivModel/xgboost HTTP/1.1" 200 1058 0.182894 | |
::1 - - [2017-05-30 23:29:34] "POST /ensemble/base-learner-origins/1/create-base-learner/?path=/home/joseph/zillow/xcessivModel/xgboost HTTP/1.1" 200 739 0.018246 | |
23:29:34 default: xcessiv.rqtasks.generate_meta_features('/home/joseph/zillow/xcessivModel/xgboost', 1) (96755f8c-5f4a-4520-973d-73edd73e7203) | |
[2017-05-30 23:29:34,749] ERROR in app: Exception on /ensemble/base-learners/ [GET] | |
Traceback (most recent call last): | |
File "/home/joseph/environments/tf-env/lib/python3.5/site-packages/flask/app.py", line 1982, in wsgi_app | |
response = self.full_dispatch_request() | |
File "/home/joseph/environments/tf-env/lib/python3.5/site-packages/flask/app.py", line 1614, in full_dispatch_request | |
rv = self.handle_user_exception(e) | |
File "/home/joseph/environments/tf-env/lib/python3.5/site-packages/flask/app.py", line 1517, in handle_user_exception | |
reraise(exc_type, exc_value, tb) | |
File "/home/joseph/environments/tf-env/lib/python3.5/site-packages/flask/_compat.py", line 33, in reraise | |
raise value | |
File "/home/joseph/environments/tf-env/lib/python3.5/site-packages/flask/app.py", line 1612, in full_dispatch_request | |
rv = self.dispatch_request() | |
File "/home/joseph/environments/tf-env/lib/python3.5/site-packages/flask/app.py", line 1598, in dispatch_request | |
return self.view_functions[rule.endpoint](**req.view_args) | |
File "/home/joseph/environments/tf-env/lib/python3.5/site-packages/xcessiv/views.py", line 414, in get_base_learners | |
return jsonify(map(lambda x: x.serialize, base_learners)) | |
File "/home/joseph/environments/tf-env/lib/python3.5/site-packages/flask/json.py", line 263, in jsonify | |
(dumps(data, indent=indent, separators=separators), '\n'), | |
File "/home/joseph/environments/tf-env/lib/python3.5/site-packages/flask/json.py", line 123, in dumps | |
rv = _json.dumps(obj, **kwargs) | |
File "/usr/lib/python3.5/json/__init__.py", line 237, in dumps | |
**kw).encode(obj) | |
File "/usr/lib/python3.5/json/encoder.py", line 200, in encode | |
chunks = list(chunks) | |
File "/usr/lib/python3.5/json/encoder.py", line 436, in _iterencode | |
o = _default(o) | |
File "/home/joseph/environments/tf-env/lib/python3.5/site-packages/flask/json.py", line 80, in default | |
return _json.JSONEncoder.default(self, o) | |
File "/usr/lib/python3.5/json/encoder.py", line 179, in default | |
raise TypeError(repr(o) + " is not JSON serializable") | |
TypeError: <map object at 0x7fab23a226a0> is not JSON serializable | |
::1 - - [2017-05-30 23:29:34] "GET /ensemble/base-learners/?path=/home/joseph/zillow/xcessivModel/xgboost HTTP/1.1" 500 412 0.004038 | |
/home/joseph/environments/tf-env/lib/python3.5/site-packages/sklearn/cross_validation.py:44: 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 note 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) | |
/home/joseph/environments/tf-env/lib/python3.5/site-packages/xcessiv/rqtasks.py:121: DtypeWarning: Columns (22,32,34,49,55) have mixed types. Specify dtype option on import or set low_memory=False. | |
X, y = extraction.return_train_dataset() | |
23:29:55 default: Job OK (96755f8c-5f4a-4520-973d-73edd73e7203) | |
23:29:55 Result is kept for 500 seconds | |
23:29:55 | |
23:29:55 *** Listening on default... |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment