kristiewirth

from numpy import mean, quantile
from scipy.stats import beta

################# Parameters #################
control_successes = 10
control_failures = 20
treatment_successes = 40
treatment_failures = 23
##############################################

kristiewirth

# Navigating quickly to commonly used directories (change to your own)
export CDPATH=.:~:/Users/kristiewirth/Documents:/Users/kristiewirth/Documents/work

# Changing command line beginning to just be directory and $
export PS1="\W/ $ "

# Expanding bash completion
if [ -f /etc/bash_completion ]; then
    . /etc/bash_completion
elif [ -f /opt/local/etc/profile.d/bash_completion.sh ]; then

kristiewirth

import os
import pandas as pd
import json

# Update these for your use case
folder = 'FOLDER'
csv_filename = 'CSV_FILENAME'

concated_df = pd.DataFrame()

kristiewirth

import datto as dt
import pandas as pd
import spacy
from featurestore import FeatureStore
from sklearn.ensemble import RandomForestClassifier
from sklearn.feature_extraction.text import ENGLISH_STOP_WORDS, TfidfVectorizer
from sklearn.metrics import (
    accuracy_score,
    mean_squared_error,
    median_absolute_error,

kristiewirth

import re

import numpy as np
from langdetect import detect
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import linear_kernel
from toolz.functoolz import pipe

def find_non_sentences(sentences: list, nlp):
    non_sentences = []

kristiewirth

####
# Source: some commands from https://medium.com/@waxzce/keeping-macos-clean-this-is-my-osx-brew-update-cli-command-6c8f12dc1731
# Run: $ `bash update-all-the-things.sh`
####

# Update command line tools
softwareupdate --all --install --force

# Clean up brew
brew update && brew upgrade && brew cleanup -s

kristiewirth

# Interstate must be a unique prime number
interstate = 227
percent_in_control = 0.5
identity_id = 4545136090

assignment_number = identity_id % interstate

lane_divider = interstate * percent_in_control
if assignment_number > lane_divider:
  condition = 'treatment'

kristiewirth

WITH birth_events AS
 (SELECT identity_id, MIN(timestamp) AS first_timestamp
 FROM fact_experiment_birth_events
 -- Experiment name chosen
 WHERE experiment_name LIKE '%experiment-1%'
 GROUP BY identity_id),

death_events AS
 (SELECT identity_id, MIN(timestamp) AS first_timestamp
 -- Table with chosen metric

kristiewirth

from flask import Flask, jsonify, request
import pandas as pd

# Intialize app
app = Flask(__name__)

# Need the liveness & readiness routes in order to pass Kubernetes checks
@app.route('/liveness')
def liveness():
    return "alive"

kristiewirth

FROM python:3.6

COPY /requirements.txt /app/requirements.txt
COPY /src/app.py /app/src/app.py

WORKDIR /app/src

RUN pip install -r /app/requirements.txt

ENTRYPOINT ["python", "app.py"]