Mlawrence95

import feedparser  # via conda install anaconda::feedparser
import yaml
from bs4 import BeautifulSoup

_GOODREADS_RSS_STREAM_URL = "https://www.goodreads.com/review/list_rss/<XXXXXXXXXX>?key=<XXXXXXXXXXXXXX>&shelf=<XXXX>"
# Old yaml lives here. We'll use it to ensure our new dump has unique values.
_EXISTING_YAML_PATH = "docs/_data/books.yml"
_NEW_YAML_PATH = "books.yaml"

Mlawrence95

# checked against python 3.7.3, pandas 0.24.2, s3fs 0.4.2
import tarfile
import io
import s3fs 

import pandas as pd

tar_path      = f"s3://my-bucket/debug.tar.gz"  # path in s3
metadata_path = "debug/metadata.csv"  # path inside of the tar file 

Mlawrence95

import pandas as pd
from hashlib import md5

def text_to_hash(text):
    return md5(text.encode("utf8")).hexdigest()

def add_hash(column_name="document"):
    """ 
    Decorator. Wraps a function that returns a dataframe, must have column_name in columns.
    

Mlawrence95

import matplotlib.pyplot as plt
import soundfile as sf

from pydub import AudioSegment

# we want to convert source, mp3, into dest, a .wav file
source = "./recordings/test.mp3"
dest = "./recordings/test.wav"

# conversion - check!

Mlawrence95

import time

def get_timestamp():
    """
    Print the date in m/d/y format, GMT
    
    >>> get_timestamp()
    '3_31_2020'
    """
    t = time.gmtime()

Mlawrence95

import json
import pickle

def openJSON(path):
    """
    Safely opens json file at 'path'
    """

    with open(path, 'r') as File:
        data = json.load(File)

Mlawrence95

import matplotlib.pyplot as plt

params = {'legend.fontsize': 'x-large',
          'figure.figsize':  (15, 15),
          'axes.labelsize':  'x-large',
          'axes.titlesize':  'x-large',
          'xtick.labelsize': 'x-large',
          'ytick.labelsize': 'x-large'}

plt.rcParams.update(params)

Mlawrence95

import pickle
import dill

dill._dill._reverse_typemap['SliceType']  = slice
dill._dill._reverse_typemap['ObjectType'] = object

Mlawrence95

git clone https://[insert username]:[insert password]@github.com/[insert organisation name]/[insert repo name].git

Mlawrence95

import numpy as np
import pandas as pd

def get_word_counts(document: str) -> pd.DataFrame:
    """
    Turns a document into a dataframe of word, counts
    
    Use preprocessing/lowercasing before this step for best results.
    
    If passing many documents, use document = '\n'.join(iterable_of_documents)