eileen-code4fun

func (v *Value) add(v1 *Value) *Value {
  nv := newValue(v.data+v1.data, nil /* incorrect, should be []*Value{v, v1} */)
  nv.backward = func() {
    v.grad = /* incorrect, should be += */ nv.grad
    v1.grad = /* incorrect, should be += */ nv.grad
  }
  return nv
}

func (v *Value) mul(v1 *Value) *Value {

eileen-code4fun

package main

import "fmt"

type Value struct {
  data, grad float64
  backward   func()
  children   []*Value
}

eileen-code4fun

package main

import "fmt"

func sum(a, b int) int {
  return a + b
}

func main() {
  fmt.Printf("%d\n", sum(1, 2))

eileen-code4fun

class Nl2SqlTranslator(tf.keras.Model):
    def __init__(self, nl_text_processor, sql_text_processor, fixed_embedding, unit=128):
        super().__init__()
        # Natural language
        self.nl_text_processor = nl_text_processor
        self.nl_voba_size = len(nl_text_processor.get_vocabulary())
        self.nl_embedding = tf.keras.layers.Embedding(
            self.nl_voba_size,
            output_dim=unit,
            mask_zero=True)

eileen-code4fun

import names

def populate(in_filename, out_filename):
    out = []
    with open(in_filename) as f:
        for l in f.readlines():
            parts = l.split('|||')
            nli_template = parts[0].strip().split()
            nli = []
            target = []

eileen-code4fun

# wget http://nlp.stanford.edu/data/glove.6B.zip
# unzip glove.6B.zip

import numpy as np
import tensorflow as tf

embeddings_index = {}
with open('glove.6B.100d.txt') as f:
    for line in f:
        word, coefs = line.split(maxsplit=1)

eileen-code4fun

def standardize(text):
    # Split accecented characters.
    text = tf_text.normalize_utf8(text, 'NFKD')
    text = tf.strings.lower(text)
    # Keep space, a to z, and select punctuation.
    text = tf.strings.regex_replace(text, '[^ a-z.?!,¿]', '')
    # Add spaces around punctuation.
    text = tf.strings.regex_replace(text, '[.?!,¿]', r' \0 ')
    # Strip whitespace.
    text = tf.strings.strip(text)

eileen-code4fun

import tensorflow as tf

def split(text):
    parts = tf.strings.split(text, sep='\t')
    return parts[0], parts[1]
  
 dataset = tf.data.TextLineDataset(['spa.txt']).map(split)
eng_dataset = dataset.map(lambda eng, spa : eng)
spa_dataset = dataset.map(lambda eng, spa : spa)

eileen-code4fun

class Spa2EngTranslator(tf.keras.Model):
    def __init__(self, eng_text_processor, spa_text_processor, unit=512):
        pass
            
    def call(self, eng_text, spa_text):
        pass

eileen-code4fun

class Spa2EngTranslator(tf.keras.Model):
    def __init__(self, eng_text_processor, spa_text_processor, unit=512):
        super().__init__()
        # Spanish
        self.spa_text_processor = spa_text_processor
        self.spa_voba_size = len(spa_text_processor.get_vocabulary())
        self.spa_embedding = tf.keras.layers.Embedding(
            self.spa_voba_size,
            output_dim=unit,
            mask_zero=True)