raghavrv

raghavrv

raghavrv

import numpy as np
from sklearn.datasets import make_classification

# Data with features in different scales
n_classes = 2
X_clean, y_clean = make_classification(
    n_samples=500, n_features=2, n_redundant=0,
    scale=(10, 100), random_state=0)

# Add outliers to the data

raghavrv

"""
===============================
Gradient Boosting Classifier CV
===============================

Gradient boosting is an ensembling technique where several weak learners
(regression trees) are combined to yield a powerful single model, in an
iterative fashion.

:class:`sklearn.ensemble.GradientBoostingClassifierCV` enables us to

raghavrv

Question 1

Sequence is defined by -

• A0 = 1
• Ai+1 = Ai + 1 or Ai * 2

Now given An = some number find the smallest n.

def find_smallest_n(An):

raghavrv

# Write a function that takes a list of string and returns the sum of the list items that represents an integer.

def sum_up_int_terms(string):
    sum = 0
    for item in string:
        try:
            sum += int(item)
        except:
            pass
    return sum

raghavrv

import numpy as np

from sklearn.utils.validation import check_random_state
from sklearn.externals import six

from functools import partial


def mcar_mask(X, y=None, proba=0.1, random_state=None):
    """Generate a MCAR mask to uniformly drop values

raghavrv

import numpy as np

from sklearn.utils.validation import check_random_state
from sklearn.externals import six

from functools import partial


def drop_values_mcar(X, y=None, missing_values=np.nan,
                     proba=0.1, random_state=None):

raghavrv

missing_rate : float in range [0, 1), default 0.1
    The absolute fraction of values that must be missing.

    If there are previously existing missing values (say x fraction of
    values were already missing), an additional ``missing_rate - x``
    fraction of values will be dropped further to achieve a total of
    ``missing_rate`` fraction of missing values.

    That is, at the end, the dataset will contain a total of

(X.shape[0] * X.shape[1]) * missing_rate numbers of missing values.

raghavrv

export LANG=en_US.UTF-8

# COMMON CONFS

# Use pgrep with full command path and display the name
alias checktuns="ps x | grep 'ssh -N'"
alias pgrep="ps x | grep "

# Set the scikit path env var
export SCIKIT_LEARN_PATH=~/raghav/code/scikit-learn