CamDavidsonPilon

import py4j
from pyspark.sql.functions import monotonically_increasing_id

# very important to cache this.
df = df.select(monotonically_increasing_id().alias("index"), "*")\
       .cache()
MAX = 34359738368

def mod_binary_search(round, previous_winner, dataset):
    # round starts at 0, previous_winner starts at 0

CamDavidsonPilon

# FFN to model game outcome
import pandas as pd
from keras.layers import Dense
from keras.models import Sequential
import numpy as np


if __name__ == "__main__":
    import sqlite3
    with sqlite3.connect("data/heroes.db") as conn:

CamDavidsonPilon

from collections import deque

def sequence():
    queue = deque([3,3,3,2])

    yield queue.popleft()

    while True:
        value = queue.popleft()
        queue.extend([3] * value + [2])

CamDavidsonPilon

"""
C6 = sum of heads on the 60% coin after N flips
C5 = sum of heads on the 50% coin after N flips


P(C6 > C5 | N flips) >= 0.95 # solve for smallest N

C6 ~ Binomial(N, 0.6)
C5 ~ Binomial(N, 0.5)

CamDavidsonPilon

%pyplot

x = np.arange(32)
A = [5, 10, 14, 20, 24, 27]
B = [3, 4, 6, 7, 8]
C = [2, 12, 22]

plt.scatter(A, 3*np.ones_like(A), c='k', marker='X', lw=0.5)
plt.scatter(B, 2*np.ones_like(B), c='k', marker='X', lw=0.5)
plt.scatter(C, 1*np.ones_like(C), c='k', marker='X', lw=0.5)

CamDavidsonPilon

Economists jobs on the Shopify Decision Science Team

Hi there,

At Shopify, we empower 500,000+ entrepreneurs all over the world. We’re looking for hard-working, passionate people to help us make commerce better. On the Shopify Decision Science team, it's our job to understand and measure the company using a statistical lens. We strongly feel that economists make a big impact here. Below are some jobs open for economists:

Finance Analytics Team

Shopify can be seen as a country, with 500,000+ citizens (I suppose that makes us the government). With this perspective, we can ask questions like what is the wealth inequality in Shopify, how are our population cohorts evolving over time, how much should we "tax" citizens, what is the predicted birth rate of the country, and so on. This team works closely with the CFO and Finance team and sees their results reported publically.

CamDavidsonPilon

import numpy as np
from numpy.linalg import matrix_power
from matplotlib import pyplot as plt
import seaborn as sns

SIZE = 100
M = np.zeros((SIZE, SIZE))

# encoding rolls of die
for y in xrange(SIZE):

CamDavidsonPilon

import numpy as np
from numpy.linalg import matrix_power
from matplotlib import pyplot as plt
import seaborn as sns

SIZE = 100
M = np.zeros((SIZE, SIZE))

# encoding rolls of die
for y in xrange(SIZE):

CamDavidsonPilon

def concordance_index(event_times, predicted_scores, event_observed=None):
    """
    Calculates the concordance index (C-index) between two series
    of event times. The first is the real survival times from
    the experimental data, and the other is the predicted survival
    times from a model of some kind.

    The concordance index is a value between 0 and 1 where,
    0.5 is the expected result from random predictions,
    1.0 is perfect concordance and,

CamDavidsonPilon

def falling_factorial(k, n):
    product = 1
    counter = k
    while counter > n:
        product *= counter
        counter -= 1
    return product

f = lambda k: 2 * falling_factorial(k, k-100) - k**100