anna-hope

git clone --bare [email protected]:anna-hope/dotfiles.git $HOME/.cfg
function dotfiles {
   /usr/bin/git --git-dir=$HOME/.cfg/ --work-tree=$HOME $@
}
mkdir -p .dotfiles-backup
dotfiles checkout
if [ $? = 0 ]; then
  echo "Checked out the dotfiles.";
  else
    echo "Backing up pre-existing dot files.";

anna-hope

package main

import (
	"image"
	"image/color"
	"math/rand"
	"time"

	"golang.org/x/tour/pic"
)

anna-hope

package main

import (
	"io"
	"os"
	"strings"
)

type rot13Reader struct {
	r io.Reader

anna-hope

from typing import Union, Dict

import pandas as pd
from torchtext.data import (Field, Example, Iterator, BucketIterator, Dataset)
from tqdm import tqdm


class DataFrameExampleSet:
    def __init__(self, df: pd.DataFrame, fields: Dict[str, Field]):
        self._df = df

anna-hope

# Implementation of Structured Self-Attention mechanism
# from Lin et al. 2017 (https://arxiv.org/pdf/1703.03130.pdf)
# Anton Melnikov

import torch
import torch.nn as nn


class StructuredAttention(nn.Module):
    def __init__(self, *, input_dim: int, hidden_dim: int, attention_hops: int):

anna-hope

import numpy as np

def get_conv_out(dim_in, padding, kernel_size, stride):
    out_dim = (dim_in + 2 * padding - kernel_size) / stride
    out_dim += 1
    return int(np.floor(out_dim))

layers = [(0, 7, 1),
          (0, 3, 3),
          (0, 7, 1),

anna-hope

# Implementation of the Hierarchical Attention Network from Yang et al. 2016
# https://www.cs.cmu.edu/~diyiy/docs/naacl16.pdf
# Anton Melnikov

import torch
from torch import nn
import torch.nn.functional as F


class SequenceClassifierAttention(nn.Module):

anna-hope

# Very Deep Convolutional Network (http://aclweb.org/anthology/E17-1104)
# PyTorch implementation by Anton Melnikov

from typing import Iterable, Tuple

import torch
from torch import nn
import torch.nn.functional as F
from torch.autograd import Variable

anna-hope

# Convolutional block from http://aclweb.org/anthology/E17-1104
# Anton Melnikov

import numpy as np
import torch
from torch import nn

class ConvBlock(nn.Module):
    def __init__(self, in_channels, out_channels, *,
                 kernel_size, stride=1):

anna-hope

import pandas as pd
from torchtext import data
from tqdm import tqdm


def make_examples(df: pd.DataFrame, fields: Dict[str, data.Field]):
    fields = {field_name: (field_name, field)
              for field_name, field in fields.items()}
    for _, row in tqdm(df.iterrows()):
        example = data.Example.fromdict(row, fields)