泰勒·斯威夫特歌词生成器

什么是LSTM递归神经网络?

LSTM递归神经网络的应用

• 语言建模


• 文本分类


• 对话系统


• 自然语言生成

• 从头开始


• 使用名为textgenrnn的Python模块

处理数据集

# Import the dependencies

import numpy as np

import pandas as pd

import sys 

from keras.models import Sequential

from keras.layers import LSTM, Activation, Flatten, Dropout, Dense, Embedding, TimeDistributed, CuDNNLSTM

from keras.callbacks import ModelCheckpoint

from keras.utils import np_utils

#Load the dataset

dataset = pd.read_csv('taylor_swift_lyrics.csv', encoding = "latin1")

dataset.head()

def processFirstLine(lyrics, songID, songName, row):

    lyrics.append(row['lyric'] + '\n')

    songID.append( row['year']*100+ row['track_n'])

    songName.append(row['track_title'])

    return lyrics,songID,songName# define empty lists for the lyrics , songID , songName 

lyrics = []

songID = []

songName = []# songNumber indicates the song number in the dataset

songNumber = 1# i indicates the song number

i = 0

isFirstLine = True# Iterate through every lyrics line and join them together for each song independently 

for index,row in dataset.iterrows():

    if(songNumber == row['track_n']):

        if (isFirstLine):

            lyrics,songID,songName = processFirstLine(lyrics,songID,songName,row)

            isFirstLine = False

        else :

            #if we still in the same song , keep joining the lyrics lines    

            lyrics[i] +=  row['lyric'] + '\n'

    #When it's done joining a song's lyrics lines , go to the next song :    

    else :

        lyrics,songID,songName = processFirstLine(lyrics,songID,songName,row)

        songNumber = row['track_n']

        i+=1

lyrics_data = pd.DataFrame({'songID':songID, 'songName':songName, 'lyrics':lyrics })

# Save Lyrics in .txt file

with open('lyricsText.txt', 'w',encoding="utf-8") as filehandle: 

       for listitem in lyrics:

            filehandle.write('%s\n' % listitem)

歌词预处理

1-将歌词转换为小写：

# Load the dataset and convert it to lowercase :



textFileName = 'lyricsText.txt'



raw_text = open(textFileName, encoding = 'UTF-8').read()



raw_text = raw_text.lower()

2-映射字符：

# Mapping chars to ints :

chars = sorted(list(set(raw_text)))

int_chars = dict((i, c) for i, c in enumerate(chars))

chars_int = dict((i, c) for c, i in enumerate(chars))

n_chars = len(raw_text)

n_vocab = len(chars)



print(‘Total Characters : ‘ , n_chars) # number of all the characters



in lyricsText.txt

print(‘Total Vocab : ‘, n_vocab) # number of unique characters

3-制作样品和标签:

# process the dataset:

seq_len = 100

data_X = []

data_y = []for i in range(0, n_chars - seq_len, 1):

    # Input Sequeance(will be used as samples)

    seq_in  = raw_text[i:i+seq_len]

    # Output sequence (will be used as target)

    seq_out = raw_text[i + seq_len]

    # Store samples in data_X

    data_X.append([chars_int[char] for char in seq_in])

    # Store targets in data_y

    data_y.append(chars_int[seq_out])

n_patterns = len(data_X)

print( 'Total Patterns : ', n_patterns)

4-准备样品和标签：

• 重塑样本


• 使它们正常化


• 一个热编码输出目标

# Reshape X to be suitable to go into LSTM RNN :

X = np.reshape(data_X , (n_patterns, seq_len, 1))

# Normalizing input data :

X = X/ float(n_vocab)

# One hot encode the output targets :

y = np_utils.to_categorical(data_y)