pavlov99

// Based on following links:
// http://andrew.hedges.name/experiments/haversine/
// http://www.movable-type.co.uk/scripts/latlong.html
df
  .withColumn("a", pow(sin(toRadians($"destination_latitude" - $"origin_latitude") / 2), 2) + cos(toRadians($"origin_latitude")) * cos(toRadians($"destination_latitude")) * pow(sin(toRadians($"destination_longitude" - $"origin_longitude") / 2), 2))
  .withColumn("distance", atan2(sqrt($"a"), sqrt(-$"a" + 1)) * 2 * 6371)

>>>
+--------------+-------------------+-------------+----------------+---------------+----------------+--------------------+---------------------+--------------------+------------------+
|origin_airport|destination_airport|  origin_city|destination_city|origin_latitude|origin_longitude|destination_latitude|destination_longitude|                   a|          distance|

pavlov99

function deque_init(d) {d["+"] = d["-"] = 0}
function deque_is_empty(d) {return d["+"] == d["-"]}
function deque_push_back(d, val) {d[d["+"]++] = val}
function deque_push_front(d, val) {d[--d["-"]] = val}
function deque_back(d) {return d[d["+"] - 1]}
function deque_front(d) {return d[d["-"]]}
function deque_pop_back(d) {if(deque_is_empty(d)) {return NULL} else {i = --d["+"]; x = d[i]; delete d[i]; return x}} 
function deque_pop_front(d) {if(deque_is_empty(d)) {return NULL} else {i = d["-"]++; x = d[i]; delete d[i]; return x}} 
function deque_print(d){x="["; for (i=d["-"]; i<d["+"] - 1; i++) x = x d[i]", "; print x d[d["+"] - 1]"]; size: "d["+"] - d["-"] " [" d["-"] ", " d["+"] ")"}

pavlov99

Keybase proof

I hereby claim:

• I am pavlov99 on github.
• I am p99 (https://keybase.io/p99) on keybase.
• I have a public key whose fingerprint is 247B E451 E71C 8AAD 6AF2 7842 5849 1A6C A92B 0F59

To claim this, I am signing this object:

pavlov99

$ ansible-galaxy info YourUser.RoleName | grep -E 'id: [0-9]' | awk {'print $2'}

pavlov99

class Choices(object):

    """ Choices."""

    def __init__(self, *choices):
        self._choices = []
        self._choice_dict = {}

        for choice in choices:
            if isinstance(choice, (list, tuple)):

pavlov99

model = xgb.Booster(model_file='your.model')
model.feature_names = xgtrain.feature_names  # Note: xgtrain is your train file with features.
model.feature_types = xgtrain.feature_types

# Number of trees in the model
num_trees = len(model.get_dump())

# dump all of the trees to tree folder
for tree_index in range(num_trees):
    dot = xgb.to_graphviz(model, num_trees=tree_index)

pavlov99

// NOTE: add minimum and maximum values to thresholds
val thresholds: Array[Double] = Array(Double.MinValue, 0.0) ++ (((0.0 until 50.0 by 10).toArray ++ Array(Double.MaxValue)).map(_.toDouble))

// Convert DataFrame to RDD and calculate histogram values
val _tmpHist = df
    .select($"column" cast "double")
    .rdd.map(r => r.getDouble(0))
    .histogram(thresholds)

// Result DataFrame contains `from`, `to` range and the `value`.

pavlov99

from functools import reduce

def crossjoin(*dfs, **kwargs):
    """Calculate a cartesian product of given dataframes.
    
    Subsequently join each dataframe using a temporary constant key and then remove it.
    Also set a MultiIndex - cartesian product of the indices of the input dataframes.
    See: https://github.com/pydata/pandas/issues/5401

    Args:

pavlov99

OIFS=$IFS;
IFS=",";

# fill in your details here
dbname=DBNAME
user=USERNAME
pass=PASSWORD
host=HOSTNAME:PORT

# first get all collections in the database

pavlov99

# Install madge (https://github.com/pahen/madge) and graphviz first
madge --dot --layout neato --include-npm src/ | dot -Tpng > dependencies.png