pmbaumgartner

pmbaumgartner

#!/bin/sh

# use this to get predictions on a test.csv located in BERT_DATA_DIR

export OUTCOME={classification_task_name}
export NOTEBOOK=/notebooks # don't change me

docker run --runtime=nvidia -it --rm \
  -v $(pwd):$NOTEBOOK/ \
  -e "BERT_BASE_DIR=$NOTEBOOK/uncased_L-12_H-768_A-12" \

pmbaumgartner

from contextlib import closing
from io import StringIO
from time import time

import pandas as pd
from django.core.management.base import BaseCommand
from django.db import transaction
from faker import Faker

from core.models import Thing

pmbaumgartner

import streamlit as st
from vega_datasets import data


@st.cache
def load_data():
    return data.birdstrikes()


cols = {

pmbaumgartner

import streamlit as st
from vega_datasets import data
from time import time
import pandas as pd


@st.cache
def load_data():
    return pd.concat((data.airports() for _ in range(100)))

pmbaumgartner

import altair as alt
import streamlit as st
from vega_datasets import data

cars = data.cars()

quantitative_variables = [
    "Miles_per_Gallon",
    "Cylinders",
    "Displacement",

pmbaumgartner

from time import time

import altair as alt
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import streamlit as st


def mpl_scatter(dataset, x, y):

pmbaumgartner

# ⛔️ BAD EXAMPLE: PRE-REFACTOR
## app.py
import streamlit as st
import pandas as pd

data = pd.read_csv("data.csv")  # no function → no cache, requires pandas import: 👎,👎
sample = data.head(100)  # not input into streamlit object: 👎
described_sample = sample.describe()  # input into streamlit object: ✅
st.write(described_sample)

pmbaumgartner

Packing Conda Environments

You must be using conda for this approach. You will need conda installed on the Source machine and the Target machine. The Source machine must have an internet connection, the Target does not. The OS in both environments must match; no going from macOS to Win10 for example.

1. (Source) Install conda-pack in your base python environment.

conda install -c conda-forge conda-pack

pmbaumgartner

import numpy as np
import numba


@numba.njit()
def tsss(vec1, vec2):
    euclidean_distance = np.linalg.norm(vec1 - vec2)
    cosine_distance = np.dot(vec1, vec2.T) / (
        np.linalg.norm(vec1) * np.linalg.norm(vec2)
    )