#| include: false
! [ -e /content ] && pip install -Uqq fastbook
import fastbook
fastbook.setup_book()

#| include: false
from fastbook import *

from fastai.text.all import *
path = untar_data(URLs.HUMAN_NUMBERS)

#| include: false
Path.BASE_PATH = path

path.ls()

lines = L()
with open(path/'train.txt') as f: lines += L(*f.readlines())
with open(path/'valid.txt') as f: lines += L(*f.readlines())
lines

text = ' . '.join([l.strip() for l in lines])
text[:100]

tokens = text.split(' ')
tokens[:10]

vocab = L(*tokens).unique()
vocab

word2idx = {w:i for i,w in enumerate(vocab)}
nums = L(word2idx[i] for i in tokens)
nums

L((tokens[i:i+3], tokens[i+3]) for i in range(0,len(tokens)-4,3))

seqs = L((tensor(nums[i:i+3]), nums[i+3]) for i in range(0,len(nums)-4,3))
seqs

bs = 64
cut = int(len(seqs) * 0.8)
dls = DataLoaders.from_dsets(seqs[:cut], seqs[cut:], bs=64, shuffle=False)

class LMModel1(Module):
    def __init__(self, vocab_sz, n_hidden):
        self.i_h = nn.Embedding(vocab_sz, n_hidden)  
        self.h_h = nn.Linear(n_hidden, n_hidden)     
        self.h_o = nn.Linear(n_hidden,vocab_sz)
        
    def forward(self, x):
        h = F.relu(self.h_h(self.i_h(x[:,0])))
        h = h + self.i_h(x[:,1])
        h = F.relu(self.h_h(h))
        h = h + self.i_h(x[:,2])
        h = F.relu(self.h_h(h))
        return self.h_o(h)

learn = Learner(dls, LMModel1(len(vocab), 64), loss_func=F.cross_entropy, 
                metrics=accuracy)
learn.fit_one_cycle(4, 1e-3)

n,counts = 0,torch.zeros(len(vocab))
for x,y in dls.valid:
    n += y.shape[0]
    for i in range_of(vocab): counts[i] += (y==i).long().sum()
idx = torch.argmax(counts)
idx, vocab[idx.item()], counts[idx].item()/n

class LMModel2(Module):
    def __init__(self, vocab_sz, n_hidden):
        self.i_h = nn.Embedding(vocab_sz, n_hidden)  
        self.h_h = nn.Linear(n_hidden, n_hidden)     
        self.h_o = nn.Linear(n_hidden,vocab_sz)
        
    def forward(self, x):
        h = 0
        for i in range(3):
            h = h + self.i_h(x[:,i])
            h = F.relu(self.h_h(h))
        return self.h_o(h)

learn = Learner(dls, LMModel2(len(vocab), 64), loss_func=F.cross_entropy, 
                metrics=accuracy)
learn.fit_one_cycle(4, 1e-3)

class LMModel3(Module):
    def __init__(self, vocab_sz, n_hidden):
        self.i_h = nn.Embedding(vocab_sz, n_hidden)  
        self.h_h = nn.Linear(n_hidden, n_hidden)     
        self.h_o = nn.Linear(n_hidden,vocab_sz)
        self.h = 0
        
    def forward(self, x):
        for i in range(3):
            self.h = self.h + self.i_h(x[:,i])
            self.h = F.relu(self.h_h(self.h))
        out = self.h_o(self.h)
        self.h = self.h.detach()
        return out
    
    def reset(self): self.h = 0

m = len(seqs)//bs
m,bs,len(seqs)

def group_chunks(ds, bs):
    m = len(ds) // bs
    new_ds = L()
    for i in range(m): new_ds += L(ds[i + m*j] for j in range(bs))
    return new_ds

cut = int(len(seqs) * 0.8)
dls = DataLoaders.from_dsets(
    group_chunks(seqs[:cut], bs), 
    group_chunks(seqs[cut:], bs), 
    bs=bs, drop_last=True, shuffle=False)

learn = Learner(dls, LMModel3(len(vocab), 64), loss_func=F.cross_entropy,
                metrics=accuracy, cbs=ModelResetter)
learn.fit_one_cycle(10, 3e-3)

sl = 16
seqs = L((tensor(nums[i:i+sl]), tensor(nums[i+1:i+sl+1]))
         for i in range(0,len(nums)-sl-1,sl))
cut = int(len(seqs) * 0.8)
dls = DataLoaders.from_dsets(group_chunks(seqs[:cut], bs),
                             group_chunks(seqs[cut:], bs),
                             bs=bs, drop_last=True, shuffle=False)

[L(vocab[o] for o in s) for s in seqs[0]]

class LMModel4(Module):
    def __init__(self, vocab_sz, n_hidden):
        self.i_h = nn.Embedding(vocab_sz, n_hidden)  
        self.h_h = nn.Linear(n_hidden, n_hidden)     
        self.h_o = nn.Linear(n_hidden,vocab_sz)
        self.h = 0
        
    def forward(self, x):
        outs = []
        for i in range(sl):
            self.h = self.h + self.i_h(x[:,i])
            self.h = F.relu(self.h_h(self.h))
            outs.append(self.h_o(self.h))
        self.h = self.h.detach()
        return torch.stack(outs, dim=1)
    
    def reset(self): self.h = 0

def loss_func(inp, targ):
    return F.cross_entropy(inp.view(-1, len(vocab)), targ.view(-1))

learn = Learner(dls, LMModel4(len(vocab), 64), loss_func=loss_func,
                metrics=accuracy, cbs=ModelResetter)
learn.fit_one_cycle(15, 3e-3)

class LMModel5(Module):
    def __init__(self, vocab_sz, n_hidden, n_layers):
        self.i_h = nn.Embedding(vocab_sz, n_hidden)
        self.rnn = nn.RNN(n_hidden, n_hidden, n_layers, batch_first=True)
        self.h_o = nn.Linear(n_hidden, vocab_sz)
        self.h = torch.zeros(n_layers, bs, n_hidden)
        
    def forward(self, x):
        res,h = self.rnn(self.i_h(x), self.h)
        self.h = h.detach()
        return self.h_o(res)
    
    def reset(self): self.h.zero_()

learn = Learner(dls, LMModel5(len(vocab), 64, 2), 
                loss_func=CrossEntropyLossFlat(), 
                metrics=accuracy, cbs=ModelResetter)
learn.fit_one_cycle(15, 3e-3)

class LSTMCell(Module):
    def __init__(self, ni, nh):
        self.forget_gate = nn.Linear(ni + nh, nh)
        self.input_gate  = nn.Linear(ni + nh, nh)
        self.cell_gate   = nn.Linear(ni + nh, nh)
        self.output_gate = nn.Linear(ni + nh, nh)

    def forward(self, input, state):
        h,c = state
        h = torch.cat([h, input], dim=1)
        forget = torch.sigmoid(self.forget_gate(h))
        c = c * forget
        inp = torch.sigmoid(self.input_gate(h))
        cell = torch.tanh(self.cell_gate(h))
        c = c + inp * cell
        out = torch.sigmoid(self.output_gate(h))
        h = out * torch.tanh(c)
        return h, (h,c)

class LSTMCell(Module):
    def __init__(self, ni, nh):
        self.ih = nn.Linear(ni,4*nh)
        self.hh = nn.Linear(nh,4*nh)

    def forward(self, input, state):
        h,c = state
        # One big multiplication for all the gates is better than 4 smaller ones
        gates = (self.ih(input) + self.hh(h)).chunk(4, 1)
        ingate,forgetgate,outgate = map(torch.sigmoid, gates[:3])
        cellgate = gates[3].tanh()

        c = (forgetgate*c) + (ingate*cellgate)
        h = outgate * c.tanh()
        return h, (h,c)

t = torch.arange(0,10); t

t.chunk(2)

class LMModel6(Module):
    def __init__(self, vocab_sz, n_hidden, n_layers):
        self.i_h = nn.Embedding(vocab_sz, n_hidden)
        self.rnn = nn.LSTM(n_hidden, n_hidden, n_layers, batch_first=True)
        self.h_o = nn.Linear(n_hidden, vocab_sz)
        self.h = [torch.zeros(n_layers, bs, n_hidden) for _ in range(2)]
        
    def forward(self, x):
        res,h = self.rnn(self.i_h(x), self.h)
        self.h = [h_.detach() for h_ in h]
        return self.h_o(res)
    
    def reset(self): 
        for h in self.h: h.zero_()

learn = Learner(dls, LMModel6(len(vocab), 64, 2), 
                loss_func=CrossEntropyLossFlat(), 
                metrics=accuracy, cbs=ModelResetter)
learn.fit_one_cycle(15, 1e-2)

class Dropout(Module):
    def __init__(self, p): self.p = p
    def forward(self, x):
        if not self.training: return x
        mask = x.new(*x.shape).bernoulli_(1-p)
        return x * mask.div_(1-p)

class LMModel7(Module):
    def __init__(self, vocab_sz, n_hidden, n_layers, p):
        self.i_h = nn.Embedding(vocab_sz, n_hidden)
        self.rnn = nn.LSTM(n_hidden, n_hidden, n_layers, batch_first=True)
        self.drop = nn.Dropout(p)
        self.h_o = nn.Linear(n_hidden, vocab_sz)
        self.h_o.weight = self.i_h.weight
        self.h = [torch.zeros(n_layers, bs, n_hidden) for _ in range(2)]
        
    def forward(self, x):
        raw,h = self.rnn(self.i_h(x), self.h)
        out = self.drop(raw)
        self.h = [h_.detach() for h_ in h]
        return self.h_o(out),raw,out
    
    def reset(self): 
        for h in self.h: h.zero_()

learn = Learner(dls, LMModel7(len(vocab), 64, 2, 0.5),
                loss_func=CrossEntropyLossFlat(), metrics=accuracy,
                cbs=[ModelResetter, RNNRegularizer(alpha=2, beta=1)])

learn = TextLearner(dls, LMModel7(len(vocab), 64, 2, 0.4),
                    loss_func=CrossEntropyLossFlat(), metrics=accuracy)

learn.fit_one_cycle(15, 1e-2, wd=0.1)