mapmeld

from allennlp.predictors import Predictor
from transformers.tokenization_gpt2 import GPT2Tokenizer
from transformers import pipeline

class HuggingFacePredictor(Predictor):
    def __init__(self) -> None:
        self.tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
        self.model = pipeline('question-answering')

    def predict(self, passage='', question=''):

mapmeld

from allennlp.predictors.predictor import Predictor
predictor = Predictor.from_path("https://storage.googleapis.com/allennlp-public-models/bidaf-elmo-model-2018.11.30-charpad.tar.gz")

qas = open("simplified-nq-test.jsonl").read().split("\n")
for qa in qas:
  rep = json.loads(qa)
  best = rep['long_answer_candidates'][0]
  print(rep['question_text'])
  print('AllenNLP: ')
  print(predictor.predict(

mapmeld

from sys import argv
import json

# pip install fiona shapely shapely-geojson
import fiona
from shapely.geometry import shape
from shapely_geojson import dumps

if len(argv) < 2:
    print('usage: gen_map.py "New Mexico" > output.geojson')

mapmeld

The number of awesome ML projects is limitless, but:

This lists project ideas which I grouped together as awesome and seemingly achievable:

Open-ended Datasets

• Twitter disinformation datasets https://about.twitter.com/en_us/values/elections-integrity.html#data
• DuoLingo language development - https://research.duolingo.com/
• YouTube reccomendations https://github.com/markledwich2/YouTubeNetworks
• fake news dataset https://github.com/jgolbeck/fakenews
• https://factordaily.com/indigenous-datasets-from-india/ - do MNIST in different languages

mapmeld

import pandas as pd
for lang in ['ar', 'en', 'ru', 'ja', 'tr', 'fa']:
    mentionsum = {}
    for doc in range(1, 10): # ends at 9
        print(doc)
        df = pd.read_csv("saudi_arabia_112019_tweets_csv_hashed_" + str(doc) + ".csv")
        rows = df[df['tweet_language'] == lang][['user_mentions']].values.tolist()
        df = None # clear memory
        for row in rows:
            mentions = row[0].replace('[','').replace(']','').replace('\'','').split(', ')

mapmeld

import pandas as pd
dflangsum = None
for doc in range(1, 10): # ends at 9
    df = pd.read_csv("saudi_arabia_112019_tweets_csv_hashed_" + str(doc) + ".csv")
    langcount =  df[df['is_retweet'] == False].groupby(['tweet_language']).count()['tweetid']
    if dflangsum is not None:
        dflangsum += langcount
    else:
        dflangsum = langcount
    df = None # memory

mapmeld

"""
# BASH dependencies
apt-get install python-opencv ffmpeg
pip install keras numpy shap matplotlib pillow

rm ./drive/My\ Drive/mlin/training/*/*.jpg
rm ./drive/My\ Drive/mlin/validation/*/*.jpg

"""
# native imports

mapmeld

# set config.json for LJSpeech
%%writefile config.json
{
        "run_name": "mozilla-tacotron-tagent-bn",
        "run_description": "Xhosa",
    
        "audio":{
            // Audio processing parameters
            "num_mels": 80,         // size of the mel spec frame. 
            "num_freq": 1201,       // number of stft frequency levels. Size of the linear spectogram frame.

mapmeld

const fs = require('fs');

const en = JSON.parse(fs.readFileSync('en.json'));
const fa = JSON.parse(fs.readFileSync('fa.json'));

let terms = Object.keys(en);
let missing = {};

terms.forEach((term) => {
  if (!fa[term]) {

mapmeld

text_src = item['text']
del item['text']
words = wordpunct_tokenize(text_src)
sentence_vecs = []
for w in range(0, len(words)):
    word = words[w]
    if word in ar_model:
        word_vec = ar_model[word]
    else:
        word_vec = ar_model['the']