amueller

amueller

amueller

from github import Github


gh = Github("SECRETKEY")
rep = gh.get_repo("scikit-learn/scikit-learn")
org = gh.get_organization("scikit-learn")
org_members = list(org.get_members())
import datetime
n_commits = {}
limit = datetime.datetime(2017, 1, 1)

amueller

amueller

import cvxpy as cvx

n_students = 130
n_projects = 30
assignment = cvx.Int(rows=n_students, cols=n_projects)

import numpy as np
rng = np.random.RandomState(0)
project_preferences = rng.rand(n_students, n_projects)

amueller

import numpy as np
from numbers import Integral

from sklearn.externals import six
from sklearn.tree.export import _color_brew, _criterion, _tree


def plot_tree(decision_tree, max_depth=None, feature_names=None,
              class_names=None, label='all', filled=False,
              leaves_parallel=False, impurity=True, node_ids=False,

amueller

"""
Benchmarks np.bincount method vs np.mean for feature agglomeration in
../sklearn/cluster/_feature_agglomeration. Use of np.bincount provides
a significant speed up if the pooling function is np.mean.

np.bincount performs better especially as the size of X and n_clusters
increase.
"""
import matplotlib.pyplot as plt
import numpy as np

amueller

class Formatter(object):
    def __init__(self, indent_est='step'):
        self.indent_est = indent_est
        self.types = {}
        self.htchar = ' '
        self.lfchar = '\n'
        self.indent = 0
        self.step = 4
        self.width = 79
        self.set_formater(object, self.__class__.format_object)

amueller

amueller

import numpy as np
import matplotlib.pyplot as plt

class Curve(object):
    def __init__(self, scores, to="B+", std_adjust=0):
        self.to = to
        self.scores = scores
        self.letters = ["A+", "A", "A-", "B+", "B", "B-", "C+", "C", "C-", "D", "F"]
        idx = self.letters.index(to)
        # +3 is because we do D and F manually