Joel Nothman jnothman

## get-pr-modified-lines.sh
#!/bin/bash

# requires curl, jq, python

# set these variables
repo=scikit-learn/scikit-learn
remote=upstream
token=  # GitHub personal access token goes here

list_open_prs() {

## memoryfit.py
from sklearn.externals import joblib
from sklearn.linear_model import LogisticRegression
from sklearn.feature_selection import RFE
from sklearn.model_selection import GridSearchCV
from sklearn.datasets import make_classification


memory = joblib.Memory('/tmp')


## bench_working_memory.csv

          
            elapsed
            n_features
            n_samples_Y
            working_memory

            
              0
              37.13675403594971
              1000
              100
              1

            
              1
              36.132298946380615
              1000
              100
              1

            
              2
              38.42840266227722
              1000
              100
              1

            
              3
              37.29706525802612
              1000
              1000
              1

            
              4
              34.58624744415283
              1000
              1000
              1

            
              5
              36.96818971633911
              1000
              1000
              1

            
              6
              38.077014684677124
              1000
              5000
              1

            
              7
              36.49429655075073
              1000
              5000
              1

            
              8
              39.22079372406006
              1000
              5000
              1

## bench_working_memory.csv

          
            elapsed
            n_features
            n_samples
            working_memory

            
              0
              259.7408814430237
              100
              40000
              1

            
              1
              263.6345293521881
              100
              40000
              1

            
              2
              263.4755172729492
              100
              40000
              1

            
              3
              32.214531898498535
              100
              20000
              1

            
              4
              32.38340449333191
              100
              20000
              1

            
              5
              32.6368203163147
              100
              20000
              1

            
              6
              4.7826080322265625
              100
              10000
              1

            
              7
              4.722550392150879
              100
              10000
              1

            
              8
              4.735676050186157
              100
              10000
              1

## plotview.py
from django.views import View
from django.http import HttpResponse

MIMETYPES = {
    'ps': 'application/postscript',
    'eps': 'application/postscript',
    'pdf': 'application/pdf',
    'svg': 'image/svg+xml',
    'png': 'image/png',
    'jpeg': 'image/jpeg',

## auspoliticians-wikidata.rq
SELECT
?subj
?subjLabel
?prop
?position
?positionLabel
?start
?end
?district
?districtLabel

## deprecdict.py
import warnings
from sklearn.utils.testing import assert_warns_message, assert_no_warnings


class DeprecationDict(dict):
    """A dict which raises a warning when some keys are looked up

    Note, this does not raise a warning for __contains__ and iteration.

    It also will raise a warning even after the key has been manually set by

## check_multilabel_output_shapes.py
import warnings
import sklearn
warnings.simplefilter('ignore')
from sklearn import *

X, y = datasets.make_multilabel_classification()
for clf in [tree.DecisionTreeClassifier(),
            neighbors.KNeighborsClassifier(),
            neural_network.MLPClassifier(),
            multioutput.MultiOutputClassifier(linear_model.LogisticRegression()),

## check_multilabel_output_shapes.py
import warnings
import sklearn
warnings.simplefilter('ignore')
from sklearn import *

X, y = datasets.make_multilabel_classification()
for clf in [tree.DecisionTreeClassifier(),
            neighbors.KNeighborsClassifier(),
            neural_network.MLPClassifier(),
            multioutput.MultiOutputClassifier(linear_model.LogisticRegression()),

## pandasvectorizer.py
from sklearn.feature_extraction import DictVectorizer

class PandasVectorizer(DictVectorizer):
    def fit(self, x, y=None):
        return super(PandasVectorizer, self).fit(x.to_dict('records'))

    def fit_transform(self, x, y=None):
        return super(PandasVectorizer, self).fit_transform(x.to_dict('records'))

    def transform(self, x):
	#!/bin/bash

	# requires curl, jq, python

	# set these variables
	repo=scikit-learn/scikit-learn
	remote=upstream
	token= # GitHub personal access token goes here

	list_open_prs() {
	from sklearn.externals import joblib
	from sklearn.linear_model import LogisticRegression
	from sklearn.feature_selection import RFE
	from sklearn.model_selection import GridSearchCV
	from sklearn.datasets import make_classification


	memory = joblib.Memory('/tmp')
	elapsed	n_features	n_samples_Y	working_memory
0	37.13675403594971	1000	100	1
1	36.132298946380615	1000	100	1
2	38.42840266227722	1000	100	1
3	37.29706525802612	1000	1000	1
4	34.58624744415283	1000	1000	1
5	36.96818971633911	1000	1000	1
6	38.077014684677124	1000	5000	1
7	36.49429655075073	1000	5000	1
8	39.22079372406006	1000	5000	1
	elapsed	n_features	n_samples	working_memory
0	259.7408814430237	100	40000	1
1	263.6345293521881	100	40000	1
2	263.4755172729492	100	40000	1
3	32.214531898498535	100	20000	1
4	32.38340449333191	100	20000	1
5	32.6368203163147	100	20000	1
6	4.7826080322265625	100	10000	1
7	4.722550392150879	100	10000	1
8	4.735676050186157	100	10000	1
	from django.views import View
	from django.http import HttpResponse

	MIMETYPES = {
	'ps': 'application/postscript',
	'eps': 'application/postscript',
	'pdf': 'application/pdf',
	'svg': 'image/svg+xml',
	'png': 'image/png',
	'jpeg': 'image/jpeg',
	SELECT
	?subj
	?subjLabel
	?prop
	?position
	?positionLabel
	?start
	?end
	?district
	?districtLabel
	import warnings
	from sklearn.utils.testing import assert_warns_message, assert_no_warnings


	class DeprecationDict(dict):
	"""A dict which raises a warning when some keys are looked up

	Note, this does not raise a warning for __contains__ and iteration.

	It also will raise a warning even after the key has been manually set by
	import warnings
	import sklearn
	warnings.simplefilter('ignore')
	from sklearn import *

	X, y = datasets.make_multilabel_classification()
	for clf in [tree.DecisionTreeClassifier(),
	neighbors.KNeighborsClassifier(),
	neural_network.MLPClassifier(),
	multioutput.MultiOutputClassifier(linear_model.LogisticRegression()),
	from sklearn.feature_extraction import DictVectorizer

	class PandasVectorizer(DictVectorizer):
	def fit(self, x, y=None):
	return super(PandasVectorizer, self).fit(x.to_dict('records'))

	def fit_transform(self, x, y=None):
	return super(PandasVectorizer, self).fit_transform(x.to_dict('records'))

	def transform(self, x):